JP6166883B2 - Predicted defect analysis - Google Patents

Description

Related Patents This application is a continuation-in-part of pending US Application No. 12 / 538,995, entitled “Methods and Apparatus to Predicate Process Quality in a Process Control System” filed on August 11, 2009. And the contents of which are expressly incorporated herein by reference.

  The present disclosure relates generally to process control systems, and more specifically to methods and apparatus for predicting process quality in a process control system.

  Process control systems, such as those used in chemical, petroleum, or other processes, typically are connected to at least one host or operator workstation and via an analog, digital, or combined analog / digital bus. One or more process controllers and an input / output (I / O) device that are communicatively coupled to one or more field devices. For example, field devices, which may be valves, valve positioners, switches, and transmitters (eg, temperature, pressure, and flow sensors) can be used in processes such as opening or closing valves and measuring process control parameters. Implement process control functions. The process controller receives signals indicating process measurements made by the field device, processes this information to implement control routines, and controls the operation of the process on a bus or other communication line. A control signal to be transmitted to the field device is generated. In this way, the process controller can use field devices over buses and / or other communication links to execute and coordinate control strategies.

  Process information from field devices and controllers allows operators to view the current state of the process (eg, via a graphical user interface), evaluate the process, modify process behavior (eg, via visual object diagrams) One or more applications (ie, software routines, programs, etc.) that are executed by an operator workstation (eg, a processor-based system) to allow a desired function related to the process to be performed. Can be made available. Many process control systems also include one or more application stations (eg, workstations). Typically, these application stations are personal computers, laptops, or communicatively coupled to controllers, operator workstations, and other systems within the process control system via a local area network (LAN). Implemented using equivalents. Each application station may include a graphical user interface that displays process control information, including process variable values, quality parameter values associated with the process, process defect detection information, and / or process state information.

  Typically, the display of process information in a graphical user interface is limited to displaying the value of each process variable associated with the process. Furthermore, some process control systems can characterize relationships between some process variables to determine quality metrics associated with the process. However, if the resulting product of the process does not meet predefined quality control metrics, the process and / or process variables can be analyzed after completion of the resulting product batch, process, and / or assembly. Only. Improvements can be implemented to improve subsequent product manufacturing and / or processing as a result of displaying process and / or quality variables after completion of the process and / or batch. However, these improvements cannot correct finished products that are out of current standards.

  Exemplary methods, apparatus, and systems for correlating candidate factors with predicted defects in a process control system are described. Exemplary methods include process control information (eg, one or more values associated with one or more measured variables or parameters, or other process control information) corresponding to the process being controlled in the process control system. Can be included. An example method may include predicting a defect based on received process control information. For example, a defect can be predicted when the predicted quality of the process exceeds a first threshold, and the predicted quality of the process is determined based on the process control information. In another example, a defect can be predicted when the variation in the received value of a particular measured variable passes a second threshold. An exemplary method includes determining a set of candidate factors (eg, calculations based on measured variables, parameters, and / or values of variables or parameters) that may contribute to the predicted defects and predicted Displaying a correlation between the defect and at least one candidate factor from the set may further be included.

  An exemplary apparatus for correlating factors contributing to a predicted defect in a process control system can include a computing device in communication connection with a batch data receiver. The batch data receiver can be communicatively coupled to the process control system to receive process control information corresponding to a process being controlled in the process control system, such as a value corresponding to a measured variable or parameter. Can be configured. The computing device can include a processor and memory that stores instructions that are executable by the processor to predict defects corresponding to process control information received by the batch data receiver. be able to. A defect can be predicted, for example, when a variation in the value of a particular measured variable passes a corresponding threshold and / or when the predicted quality of the process passes a corresponding threshold. The computer-executable instructions are further configured to determine a set of candidate factors that may contribute to the predicted defect and between the predicted defect to be displayed on the user interface and the at least one candidate factor. It may be feasible to represent a correlation between the two.

  An exemplary system for correlating factors that contribute to predicted defects in a process control system can include a batch data receiver and a processor in communication with the batch data receiver. The batch data receiver can be configured to receive process control information corresponding to a process, and the process control information can include one or more values associated with a particular measured variable or parameter. . The processor can be configured to execute computer-executable instructions so as to present an indication of the correlation between a predicted defect corresponding to the process and a specific measured variable or parameter The predicted defect can be determined based on at least a portion of the process control information received by the batch data receiver. The display can be presented on a user interface, and the display can include a first section corresponding to the predicted defect and a second section corresponding to a particular measured variable or parameter. . The first and second sections of the display can be time aligned.

1 is a block diagram illustrating an example process control system that includes an example operations management system. FIG. Fig. 4 represents a data structure for an exemplary batch including process variables and quality variables. Fig. 4 represents a data structure for an exemplary batch including process variables and respective quality variables. FIG. 2 is a functional diagram of the exemplary operation management system of FIG. 1. FIG. 2 is a diagram representing charts and / or graphs generated by the operations management system of FIG. 1 that can be displayed to determine defects in the process control system. 2 illustrates a user interface displaying an example process overview of the example process control system of FIG. FIG. 7 illustrates the user interface of FIG. 6 displaying an exemplary process variation graph including unexplained and described variation graphs for the exemplary batch process of FIG. FIG. 8 illustrates the user interface of FIG. 7 displaying an exemplary process variation graph including a summary contribution faceplate. FIG. FIG. 7 illustrates the user interface of FIG. 6 displaying an exemplary contribution graph including unexplained and described process variations for variables associated with the process control system of FIG. FIG. 10 shows the user interface of FIG. 6 displaying a variable trend graph for the media flow variable of FIGS. 8 and 9. FIG. FIG. 7 illustrates the user interface of FIG. 6 displaying a quality prediction graph for the example batch of FIG. FIG. 10 illustrates the user interface of FIG. 6 displaying an exemplary microchart at a first time, including sparklines and bar charts, for some of the variables of FIG. FIG. 7 illustrates the user interface of FIG. 6 displaying the exemplary microchart of FIG. 12 at a selected second time. FIG. 14 illustrates the user interface of FIG. 6 displaying an exemplary sparkline for the Mixer Temp process variable of FIGS. FIG. 14 illustrates the user interface of FIG. 6 displaying an exemplary sparkline for the Mixer Temp process variable of FIGS. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. Exemplary methods that can be used to implement the exemplary operational management system, exemplary user interface, exemplary analysis processor, process model generator, and / or display manager of FIGS. 1 and / or 4. It is a flowchart of. FIG. 6 is a block diagram of an example processor system that can be used to implement the example methods and apparatus described herein. Fig. 4 illustrates an exemplary display of a display corresponding to a predicted defect that can be presented on a user interface. Fig. 4 illustrates an exemplary display of a display corresponding to a predicted defect that can be presented on a user interface. 2 is a flowchart of an exemplary method for correlating candidate factors with predicted defects in a process control system.

  Among the components, exemplary methods and apparatus that include software and / or firmware running on hardware are described below, but these examples are illustrative only and should not be considered limiting Please note that. For example, any or all of the hardware, software, and firmware components may be embodied only in hardware, only in software, or in any combination of hardware and software. Conceivable. Accordingly, although exemplary methods and apparatus are described below, those skilled in the art will readily appreciate that the examples provided are not the only way to implement such methods and apparatuses.

  Currently, process control systems provide analysis and / or statistical analysis of process control information. However, these systems implement offline tools to determine the cause of process control defects and potential corrective actions that can affect the quality of the resulting product. These offline tools may include process research, experimental research, business research, troubleshooting, process improvement analysis, and / or six sigma analysis. While these tools can correct the process of subsequent products, the tools cannot correct and / or correct process quality when a defect occurs. For this reason, these off-line tools are dependent on the process control status and may produce products with quality problems until the process can be corrected.

  The example methods and apparatus described herein can be used within a process control system to provide in-process defect detection, analysis, and / or correction information so that an operator can Allows process deficiencies to be corrected while occurring or ongoing. That is, process correction can be implemented in response to a predicted defect, when the defect occurs, or immediately after the defect occurs. The example methods and apparatus described herein may be used to predict and / or correct process defects to improve the process quality of batch and / or continuous processes. Additionally or alternatively, the exemplary methods and apparatus are for correcting product quality by predicting product quality, correcting corresponding process defects, and / or correcting detected process defects. May be used.

  The exemplary operations management system (OMS) described herein manages the analysis, organization, and display of process control information generated by the process control system. An exemplary OMS provides process control information to a workstation that has authority to access the information. The process control system can include any type of batch processing system, continuous processing system, automation system, and / or manufacturing system.

  Process control information is generated by field devices in the process control system, for example, process environment measurements (eg, temperature, concentration, or pressure sensing), field device measurements (eg, pump speed, valve position, or line speed). ), Process status measurements, and / or process throughput measurements. The process control information can be received by the controller as output variable data (eg, a value associated with a variable from which the field device originates). The controller can then transfer such variable data to the OMS for analysis and statistical processing based on the process model.

  The exemplary OMS described herein utilizes descriptive modeling, predictive modeling, and / or optimization to generate feedback regarding the status and / or quality of the process control system. In addition, the OMS predicts, detects, identifies, and / or diagnoses process operational defects and predicts the impact of any defects on quality variables associated with the quality of the resulting product. Defects may include process quality defects that are multivariate and / or statistical combinations of outputs from one or more field devices that exceed a threshold. Further, the defect may include output from one or more field devices that exceed their respective thresholds. Moreover, the exemplary OMS manages access and control to process control data via a graphical user interface. This user interface may be used to alert the process control operator of the occurrence of any process control defect. Further, the user interface can guide the operator through the analysis process to determine the source of process defects and to predict the impact of process defect corrective actions on the resulting product quality. The user interface can be accessed by any process control operator with access to information, including process operators that may access the user interface remotely from the Internet. The OMS can provide process information to the process control operator when the process is occurring, thereby allowing the operator to make adjustments to the process to correct any deficiencies. By correcting defects during the process, the operator can maintain the quality of the resulting product and subsequent products.

  An exemplary OMS can display detection, analysis, corrective action, and quality prediction information in one or more charts and / or graphs (eg, graphics) within a graphical user interface. For example, the process summary chart can display the status of one or more processes being monitored. From this overview chart, the operator can select a process variation graph that shows any described (eg, modeled) and / or unexplained (eg, unmodeled) variation within the process. . The operator can select a point in the process variation graph that shows the unexplained variation and the contribution of the explained variation to each process variable and / or quality variable associated with the overall process variation. An exemplary OMS can determine contributions between process variables and / or quality variables based on modeling and / or analysis of the process control system.

  Within the contribution chart, the operator can identify one or more variables contributing to the process defect. In addition, the operator can select one or more variables and display a variable trend graph that compares the value associated with each variable in the process with the past average and / or standard deviation of the variables in the previous process. can do. The operator can then access the process quality prediction graph to determine if the defect significantly affects the resulting quality of the product obtained from the process. If the quality was not significantly affected, the operator can use variable trend information to make appropriate adjustments to the process to correct any defects.

  In an alternative implementation, the operator can display a microchart showing various defects associated with each of the process variables and / or quality variables. Further, the microchart can include a sparkline displaying summary information of past values for each process variable and / or quality variable in the process. Moreover, the microchart can include a timeline that displays previous and / or current defects and / or deviations. The operator may scroll to a time on the timeline to display the variable contribution, process value, and / or quality variable for that selected time. Further, the microchart may show predicted and calculated quality variables and / or overall quality variables at a selected time. The operator may select any one of the variables and view the variable trend graph for that variable, or alternatively, access the process quality prediction graph. Thus, by providing multivariate analytical data and / or predictive data in easily readable linked charts and / or graphs (eg, graphics), the exemplary described herein The method and apparatus allows a process control operator to address process control defects relatively quickly before they affect the quality of the product from which the process control defects are obtained.

  The exemplary methods and apparatus described herein refer to exemplary microcharts, sparklines, integrated graphs, summary charts, process variation graphs, process quality prediction graphs, and / or variable trend graphs, Microcharts, sparklines, integrated graphs, summary charts, process variation graphs, process quality prediction graphs, and / or variable trend graphs substantially indicate the same types of process control information and / or relationships between process control information It may be implemented using graphics in any manner. Further, the exemplary OMS generates an exemplary microchart, sparkline, integrated graph, summary chart, process variation graph, process quality prediction graph, and / or variable trend graph, but any other process control controller , Servers, workstations, and / or components may generate microcharts, sparklines, integrated graphs, summary charts, process variation graphs, process quality prediction graphs, and / or variable trend graphs.

  FIG. 1 is a block diagram illustrating an example process control environment 100 that includes an example operations management system (OMS) 102. In another example, OMS 102 may be known as a process monitoring and quality prediction system (PMS). The exemplary OMS 102 is located in a plant 104 that includes a process control system 106. The example plant 104 may include any type of manufacturing facility, process facility, automation facility, and / or any other type of process control structure or system. In some examples, the plant 104 may include multiple facilities located at different locations. Further, although the exemplary plant 104 shows a process control system 106, the plant 104 may include additional process control systems.

  The exemplary process control system 106 is communicatively coupled to the controller 108 via the data bus 110. The process control system 106 can include any number of field devices (eg, input and / or output devices). A field device can include any type of process control component that can receive input, generate output, and / or control a process. For example, field devices may include input devices such as valves, pumps, fans, heaters, coolers, and / or mixers to control the process. In addition, the field device may include an output device such as a thermometer, pressure gauge, concentration meter, liquid level meter, flow meter, and / or vapor sensor to measure a portion of the process. The input device can receive instructions from the controller 108 to execute specified commands and cause changes to the process. In addition, the output device measures process data, environmental data, and / or input device data, and transmits the measured data to the controller 108 as process control information. This process control information may include the value of a variable (eg, a measured process variable and / or a measured quality variable) corresponding to the measured output from each field device.

  In the illustrated example of FIG. 1, the exemplary controller 108 can communicate with field devices in the process control system 106 via the data bus 110. This data bus 110 may be coupled to intermediate communication components within the process control system 106. These communication components can include a field connection box to communicatively couple field devices in the command area to the data bus 110. In addition, the communication component can include a marshalling cabinet to organize communication paths to the field devices and / or field junction boxes. Moreover, the communication component can include an I / O card to receive data from the field device and convert the data into a communication medium that can be received by the example controller 108. . In addition, these I / O cards can convert data from the controller 108 into a data format that can be processed by the corresponding field device. In one example, the data bus 110 may be implemented using the Fieldbus protocol or other types of wired and / or wireless communication protocols (eg, Profibus protocol, HART protocol, etc.).

  The example controller 108 of FIG. 1 manages one or more control routines to manage field devices in the process control system 106. Control routines can include process monitoring applications, alert management applications, process trends and / or history applications, batch processing and / or campaign management applications, statistical applications, streaming video applications, advanced control applications, and the like. In addition, the controller 108 forwards process control information to the exemplary OMS 102. The control routine can ensure that the process control system 106 produces a specified quantity of the desired product within a predetermined quality threshold. For example, the process control system 106 may be configured as a batch system that produces products at the end of the batch. In other examples, the process control system 106 may include a continuous process manufacturing system that continuously manufactures products.

  Process control information from the controller 108 may include values corresponding to measured process variables and / or measured quality variables originating from within field devices in the process control system 106. In other examples, the OMS 102 can parse values in the process control information into corresponding variables. The measured process variable may be associated with process control information originating from a field device that measures some of the process and / or characteristics of the field device. The measured quality variable may be associated with process control information relating to measuring a characteristic of the process associated with at least a portion of the finished product.

  For example, the process control system 106 may include a chemical reaction in a tank that produces a concentration of chemical in the liquid. In this example, the chemical concentration in the liquid may be a quality variable. Liquid temperature and liquid flow rate into the tank may be process variables. The exemplary OMS 102 may determine, via process control modeling and / or monitoring, that the concentration of liquid in the tank is based on the liquid temperature in the tank and the liquid flow rate into the tank. Thus, not only the concentration is a quality variable, but the liquid flow rate and the liquid temperature contribute or influence the quality of the concentration. That is, the measured process variable contributes or affects the quality of the measured quality variable. The OMS 102 can use statistical processing to determine the amount of impact and / or contribution each process variable has on the quality variable.

  Further, the exemplary OMS 102 can model and / or determine a relationship between measured process variables and / or measured quality variables associated with the process control system 106. These relationships between measured process variables and / or measured quality variables may result in one or more calculated quality variables. The calculated quality variable may be a multivariate and / or linear algebraic combination of one or more measured process variables, measured quality variables, and / or other calculated quality variables. Moreover, the OMS 102 can determine an overall quality variable from a combination of measured process variables, measured quality variables, and / or calculated quality variables. The overall quality variable may correspond to an overall process quality decision and / or may correspond to the predicted quality of the resulting product of the process.

  The exemplary OMS 102 of FIG. 1 includes an analysis processor 114. The example analysis processor 114 utilizes descriptive modeling, predictive modeling, and / or optimization to generate feedback regarding the status and / or quality of the process control system 106. The analysis processor 114 detects, identifies, and / or diagnoses process operation defects and predicts the impact of any defects on quality variables and / or overall quality variables associated with the resulting product quality of the process control system 106. May be. Moreover, the analysis processor 114 may monitor the quality of the process by statistically and / or logically combining the quality and / or process variables with an overall quality variable associated with the overall quality of the process. The analysis processor 114 may then compare the values calculated for the overall quality variable and / or values associated with other quality variables to respective threshold values. These thresholds may be based on predefined quality limits of the overall quality variable at different times within the process. For example, if the overall quality variable associated with the process exceeds a threshold over a period of time, the predicted final quality of the resulting product may not meet the quality criteria associated with the final product.

  When the overall quality variable and / or any other quality variable deviates from the respective threshold, the analysis processor 114 is described in the process summary chart and / or the process variation graph as described and / or associated with the overall quality variable. A defect indicator may be generated that exhibits unexplained variation (or variance) and / or a variable that generated the process defect. The example analysis processor 114 may provide a process quality graph (eg, integration) that allows an operator to display current and / or past values of measured process variables, measured quality variables, and / or calculated quality variables. The analysis is managed to determine the cause of one or more process defects by providing the capability to generate graphs, microcharts, process variation graphs, variable trend graphs, graphics, etc.). Moreover, the analysis processor 114 generates these graphs while the process is in operation, and continuously updates and / or multivariate analyzes associated with each of the graphs as additional process control information is received by the OMS 102. Or recalculate.

  The analysis processor 114 can generate a contribution graph by calculating the overall quality variable that triggers the defect or the contribution of the process variable and / or the quality variable to the quality variable. The contributions of process variables and / or quality variables may be displayed as explained variations and / or unexplained variations of each variable as a contribution to the overall quality variable associated with the defect and / or the variation associated with the quality variable. .

  Moreover, the exemplary analysis processor 114 generates a variable trend graph for any of the selected process variables and / or quality variables that may have a variation that is greater than a defined threshold. Can do. The variable trend graph may show a value associated with a variable within a time of the process compared to the value of the variable during a similar time of the previous process. By generating a contribution graph and / or a variable trend graph, the analysis process 114 may also identify possible corrections to the process to adjust the detected defects. The variable trend graph may assist the operator in determining the cause of the process defect by providing an overlay of a historical plot that includes the variation (eg, standard deviation) associated with the current value.

  If implemented, the analysis processor 114 may generate a quality prediction graph to determine the corrective impact on the overall quality of the process. If the correction maintains or improves the overall quality within the specified threshold, the analysis processor 114 may instruct the OMS 102 to implement the correction. Alternatively, the analysis processor 114 may send instructions to the controller 108 to implement process correction.

  Further, once the exemplary analysis processor 114 determines the defects associated with the overall quality variable and / or any other quality variable, it can generate a microchart. The microchart may include values of process variables and / or quality variables at specified times (eg, times associated with process defects) compared to an average value and / or standard deviation for each of the variables. Further, the microchart may include a sparkline that indicates a previous value associated with each of the process variables and / or quality variables. From the microchart, the exemplary analysis processor 114 determines that the operator has determined and / or selected one or more corrective actions for the process and / or that the overall quality variable is within specified limits. It may be possible to determine whether to improve the process as expected.

  The exemplary OMS 102 manages access and control of process control data, including process variation graphs, contribution graphs, variable trend graphs, quality prediction graphs, and / or microcharts via an online data processor 116. Further, the online data processor 116 provides access for the process control operator to view the process control data, change and / or modify the process control data, and / or generate instructions for field devices within the process control system 106. provide.

  The example plant 104 of FIG. 1 includes a router 120 and a local workstation 122 that are communicatively coupled to an online data processor 116 via a local area network (LAN) 124. Moreover, the example router 120 may communicatively couple any other workstation (not shown) in the plant 104 to the LAN 124 and / or the online data processor 116. The router 120 may be communicatively coupled to other workstations via wireless and / or wired connections. Router 120 may include any type of wireless and / or wired router as an access hub to LAN 124 and / or online data processor 116.

  LAN 124 may be implemented using any desired communication medium and protocol. For example, the LAN 124 may be based on a hardwired or wireless Ethernet communication scheme. However, any other suitable communication medium and protocol may be used. In addition, a single LAN is shown, but in two or more LANs and workstations 122 to provide redundant communication paths between the workstation 122 and each similar workstation (not shown). Appropriate communication hardware may be used.

  LAN 124 is also communicatively coupled to firewall 128. The firewall 128 determines whether communication from the remote workstations 130 and / or 132 into the plant 104 is permitted based on one or more rules. The exemplary remote workstations 130 and 132 can provide access to resources in the plant 104 to operators that are not in the plant 104. Remote workstations 130 and 132 are communicatively coupled to firewall 128 via wide area network (WAN) 134.

  The exemplary workstations 122, 130, and / or 132 may be configured to view, change, and / or correct one or more processes within the process control system 106. For example, the workstations 122, 130 and / or 132 may include a user interface 136 that formats and / or displays process control information generated by the OMS 102. For example, the user interface 136 may receive data from the OMS 102 for generating generated graphs and / or charts, or alternatively, process control graphs and / or charts. Upon receipt of the graph and / or chart data at each workstation 122, 130, and / or 132, the user interface 136 may generate a display of the graph and / or chart 138 that is relatively easy for the operator to understand. Can do. The example of FIG. 1 shows a workstation 132 with a user interface 136. However, workstations 122 and / or 130 may include a user interface 136.

  The example user interface 136 can alert the process control operator to the occurrence of any process control defects in the process control system 106 and / or any other process control system in the plant 104. Further, the user interface 136 can guide the operator through the analysis process to determine the source of process defects and to predict the effect of process defects on the quality of the resulting product. The user interface 136 can provide process control statistics to the operator as the process occurs, thereby allowing the operator to make any adjustments to the process to correct any defects. To do. By correcting defects during the process, the operator can maintain the quality of the resulting product.

  The example user interface 136 may display detection, analysis, corrective action, and quality prediction information via the example OMS 102. For example, the user interface 136 may display a process summary chart, process variation graph, microchart, contribution graph, variable trend graph, and / or quality prediction graph (eg, graph 138). Viewing these graphs 138, the operator can select additional graphs 138 to view multivariate and / or statistical process information to determine the cause of process defects. In addition, the user interface 136 can display possible corrective actions for process defects. User interface 136 may then allow the operator to select one or more corrective actions. Upon selecting a correction, the user interface 136 can transmit the correction to the OMS 102, which then sends an instruction to the controller 108 to make the appropriate correction within the process control system 106.

  The exemplary workstations 122, 130, and / or 132 of FIG. 1 can include any computing device, including personal computers, laptops, servers, controllers, personal digital assistants (PDAs), microcomputers, and the like. . Workstations 122, 130 and / or 132 may be implemented using any suitable computer system or processing system (eg, processor system P10 of FIG. 18). For example, the workstations 122, 130 and / or 132 can be implemented using a single processor personal computer, a single or multiprocessor workstation, and the like.

  An exemplary process control environment 100 is provided to illustrate certain systems in which the exemplary methods and apparatus described in detail below may be advantageously employed. However, the exemplary methods and apparatus described herein may be other systems that are more or less complex than the exemplary process control environment 100 and / or process control system 106 shown in FIG. 1, if desired. And / or may be advantageously employed in systems used in connection with process control operations, enterprise management operations, communication operations, and the like.

  FIG. 2 depicts an exemplary batch (eg, batch # 1) data structure 200 that includes measured variables 202 and calculated quality variables 204. The example data structure 200 may also include an overall quality variable (not shown). Batch processing is a type of product manufacturing in which a relatively large number of products and / or parts of products are made in parallel at one or more locations that are routinely controlled. A routine can include one or more process phases, each phase including one or more operations, and each operation including one or more phases. In other examples, the process control system may utilize continuous processing to produce a product. Continuous processing is similar to assembly line manufacturing where each process and / or operation sequentially performs a single function on a single (or few) product at a time. The methods and apparatus described herein refer to a batch process, but any type of process may be implemented.

  Exemplary measured variables 202 include measurement process variables and / or measurement quality variables. For example, the variable P1 may correspond to a liquid flow rate (eg, a process variable) and the variable P2 may correspond to a liquid concentration (eg, a quality variable). The measured variable 202 is shown in relation to the batch process “Batch # 1”. The batch process occurs during the time indicated along the Z axis (eg, time). In addition, the batch process of FIG. 2 includes eight measured variables. However, in other examples, the batch process may include fewer or more measured variables.

  FIG. 2 shows that each measured variable 202 is involved only for a predetermined time during the batch process. For example, the variable P1 is involved from the start of the batch to the midpoint of the entire batch. Thus, when the variable P1 is related to the liquid flow rate, the liquid in the batch process may only flow from the start of the batch to the midpoint of the batch. From this point on, the batch may not use the liquid flow rate, so the variable P1 is not involved in the batch process beyond this point. In contrast, the variable P4 is involved in the entire batch process.

  An exemplary calculated quality variable 204 is associated with the entire batch process. The calculated quality variable 204 may be a multivariate, statistical, and / or algebraic relationship between the measured variable 202 and / or other quality variables 204. For example, the quality variable Q1 204 may correspond to the composition quality of a product obtained from a batch process. The composition quality Q1 may be a quality variable because it may not be directly measurable in the process control system 106. Alternatively, the composition quality Q1 may be modeled and / or determined from a multivariate combination of measured variables 202 P1, P3, P4 and P7. Thus, if the composition quality Q1 exceeds a defined threshold, any one and / or combination of measured variables P1, P3, P4 and / or P7 may be a contributing factor to the variable. .

  FIG. 3 depicts an exemplary batch data structure 300 that includes process variables 302 and respective quality variables 304. A batch (eg, batch 1-7) indicates that the batch process includes stages (eg, stages 1-4) that are performed sequentially. For example, stage 1 may correspond to the synthesis and mixing of chemicals in a batch, while stage 2 corresponds to the firing of those mixed chemicals in a batch. These stages may be further subdivided into operations, phases, and / or levels. In addition, the calculated quality variable 306 corresponds to the measured variable 302 of each batch.

  The example of FIG. 3 shows that each batch may have a different elapsed time, and the start and end of each stage varies from batch to batch. For example, batch 2 completes in a shorter time than batch 1, while batches 3 and 4 complete in a longer time than batch 1. Further, batch 1 requires longer time to complete stage 1 than batch 2. However, the elapsed time involved in each variable (not shown) may be proportional to the length of time of the corresponding stage. Thus, the indefinite time to batch and / or stage completion may be resolved by the measured variable 302 in each batch. Since the length of time of the measured variable is proportional, a comparison may be made between the measured variable values between batches. For example, the value of the measured variable P1 at 50% of the entire stage 1 of batch 1 should have substantially the same value as the value of the variable P1 at 50% of the entire stage 1 of batch 2-7. .

  FIG. 4 is a functional diagram of the exemplary operations management system (OMS) 102 of FIG. The exemplary OMS processes the process control information from the controller 108 of FIG. 1, determines the model involved in variables associated with the process control system 106, calculates quality variables from the process control information, Determine if each threshold is exceeded, generate display information for the user interface, and / or manage access to process control information. Further, although the exemplary OMS 102 of FIG. 4 includes functional blocks configured to perform the process, the OMS 102 may combine functional blocks or include additional functional blocks. In some examples, OMS 102 may be associated with a single process control system (eg, process control system 106), while in other examples, OMS 102 processes data from multiple process control systems. There is a case. Further, although the OMS 102 is described as processing and managing batch data, the OMS 102 may be capable of processing and / or managing data associated with continuous, automated, and / or manufacturing processes. .

  In order to receive and process data from the controller 108, the exemplary OMS 102 includes a batch data receiver 402. The exemplary batch data receiver 402 receives process control information from the controller 108 via the communication path 404. The exemplary communication path 404 can include any type of wired and / or wireless communication path. The process control information can include output data from field devices in the process control system 106. This output data may be received by the batch data receiver 402 as a value corresponding to the measured process variable and / or quality variable originating from the field device. In another example, the process control data may be received as a data file that includes values corresponding to field device outputs. In these examples, the batch data receiver 402 can determine the corresponding measured variable corresponding to the value by annotating the originating field device. Moreover, the batch data receiver 402 receives process control information from the controller 108 at periodic intervals simultaneously with the controller 108 receiving process control information and / or by requesting process control information from the controller 108. can do.

  Upon receipt of the process control information, the exemplary batch data receiver 402 of FIG. 4 organizes values from the field device by corresponding variable and / or time by which data was generated by the field device. The batch data receiver 402 may organize values by stage, operation, process, batch number, and / or event within the process control system 106. For example, the batch data receiver 402 may organize values by batch ID (eg, batch # 7), batch stage (eg, stage 2), batch operation within the stage (eg, heating), and the like. Once the values corresponding to the measured variables are organized, the batch data receiver 402 stores the organized information in the batch data database 406. Further, the exemplary batch data receiver 402 may access stored batch data and / or transmit batch data to the analysis processor 114. The batch data database 406 may be implemented by an electrically erasable and programmable read only memory (EEPROM), random access memory (RAM), read only memory (ROM), and / or any other type of memory. Can do.

  The example analysis processor 114 manages calculations, modeling, and / or defect determination associated with the process control system 106. The analysis processor 114 includes an analysis process modeler 408 to calculate a value associated with the calculated variable from a value associated with the measured variable. The analysis process modeler 408 determines the relationship between the measured process variable and / or the measured quality variable and / or the relationship between the measured variable and the calculated and / or global variable. A model of the process control system 106 is used to make the determination. The analysis process modeler 408 processes the model with the measured values, including values associated with the measured variables in the process model, and / or as the output of the model as a calculated quality variable and / or overall quality. By calculating the value associated with the variable, the value of the calculated and / or overall quality variable is calculated. In other examples, the measured data is multivariate, optimized, geometric, and / or algebraic to extract values and / or generalizations that may be associated with calculated and / or overall quality variables. Sometimes it is organized in a graphics space that uses projection.

  In an exemplary graph that utilizes variability, the exemplary analysis process modeler 408 includes values associated with current batch data (eg, measured variables, calculated variables, and / or global variables) Variations in the current batch data may be calculated by comparing values associated with specific target values for the batch and / or current batch data. Variation calculation may include applying T2 and / or Q statistical tests to the measured variable and / or the value associated with the calculated variable. For example, the T2 statistic may be used to determine the explained variation of the process control variable, while the Q statistic is used to determine the tolerance of outliers associated with the variable corresponding to the unexplained variation. May be used.

  Further, the example analysis process modeler 408 may determine the contribution of the measured variable using the variables associated with the measured variable, the calculated variable, and / or the overall quality variable. Analysis process modeler 408 may determine the contribution of the measured variable based on the process model of process control system 106. Based on these models, the analysis process modeler 408 may apply the measured variable values to the model, process the model, and / or identify the contributing factors for each variable.

  Moreover, the analysis process modeler 408 may use values associated with measured variables, calculated variables, and / or global variables to predict process quality after corrective implementation. The analysis process modeler 408 may predict quality by reviewing current process variables and using a prediction model that considers correction and / or quality of past batches with similar data characteristics. Further, the analysis process modeler 408 may calculate a statistical confidence range of the predicted quality that may indicate the possible quality of the resulting product, for example, with 95% confidence.

  The example analysis process modeler 408 of FIG. 4 calculates overall and / or calculated variables, determines variable contributions, and predicts process quality as process control information is received from the controller 108. And / or variation statistics may be calculated. In another example, the analysis process modeler 408 calculates global variables and / or calculated variables for a predefined period upon request from the process control operator, determines variable contributions, and determines process quality. Predictions and / or variability statistics may be calculated. In addition, the analysis process modeler 408 calculates global and / or calculated variables when the corresponding graph is utilized and / or requested by a process control operator viewing the process control information in the user interface. Contributions may be determined, process quality may be predicted, and / or variation statistics may be calculated. For example, the analysis process modeler 408 may predict process quality only when the process control operator chooses to view the quality prediction graph. Alternatively, the analysis process modeler 408 may display the overall and / or calculated variables, variable contributions, predicted process quality, and / or variability statistics to other functions within the OMS 102 for display to the process control operator. You may provide the block. In addition, the analysis process modeler 708 allows the user to associate the overall and / or calculated quality variables, variable contributions, predicted process quality, and / or variability statistics with the process control operator accessing the process control information. It may be transmitted to an interface (eg, user interface 136).

  The example analysis processor 114 of FIG. 4 determines the evaluation process modeler 410 to determine whether the calculated quality values, process variations, variable contributions, and / or predicted process quality values exceed respective predefined thresholds. including. The example evaluation process modeler 410 may receive thresholds from a model associated with the process control system 106. Alternatively, the evaluation process modeler 410 may receive a threshold value from a process control operator. These thresholds may be based on maximum and / or minimum criteria and / or values that ensure that the product of process control system 106 meets quality standards.

  The example evaluation process modeler 410 may also generate a defect indicator if the measured variable, calculated variable, and / or global variable value exceeds a threshold. Further, the evaluation process modeler 410 may generate a defect indicator if the variation associated with the measured variable, the calculated variable, and / or the global variable exceeds a threshold. After generating the defect indicator, the evaluation process modeler 410 may transmit the defect indicator to another functional block in the OMS 102 and / or a user interface in the workstation accessing process control data regarding the defect. Further, the evaluation process modeler 410 may predict process defects based on trends in measured and / or calculated variable values and / or variations associated with these variables. For example, the evaluation process modeler 410 may determine that a process defect may occur based on a long-term increase in the value of the measured variable. If the evaluation process modeler 410 determines that a process defect may occur, the evaluation process modeler 410 can generate a predicted defect indicator.

  Further, the evaluation process modeler 410 can determine whether the quality prediction calculation from the analysis process modeler 408 exceeds or falls outside the quality limit. Moreover, the evaluation process modeler 410 can determine whether any of the predicted quality confidence ranges exceed a corresponding quality threshold or otherwise fail to satisfy. If any quality range exceeds the quality threshold, the evaluation process modeler 410 can send a predictive defect indicator. The predictive defect indicator can inform the process control operator that the corrective action will not bring the process within quality control thresholds or limits. As a result of the predictive defect indicator, the process control operator saves time and / or restarts the process by terminating the process because the resulting product may not meet quality standards, criteria, and / or thresholds Can be determined.

  The example evaluation process modeler 410 of FIG. 4 allows any variable value, variation, and / or quality prediction to exceed or meet a threshold as each instance of the OMS 102 receives process control data from the controller 108. You can determine if it fails. Alternatively, the evaluation process modeler 410 may determine whether any variable values, variations, and / or quality predictions exceed a threshold during a predefined period and / or upon request from a process control operator.

  To determine the process model of process control system 106, the example OMS 102 of FIG. 4 includes a process model generator 412. The example process model generator 412 determines the model utilized by the analysis process modeler 408, the analysis processor 114, and / or the evaluation process modeler 410. The model may include a relationship between measured variables, quality variables and / or overall process quality, measured variables, quality variables and / or overall process quality thresholds, and / or measured variables, quality variables and / or A graphical display type of the overall process quality can be defined.

  The example process model generator 412 receives a list of field devices in the process control system 106, inputs and / or outputs associated with each field device, field device placement, and / or field device interconnections. The process model can be constructed and / or determined. Further, the process model generator 412 can utilize past process relationships between several field devices to predict relationships between field devices and / or field device outputs. These relationships may also be determined by utilizing multivariate statistical methodologies to analyze data from field devices and determine relationships and / or contributions based on interconnections between field devices. . Multivariate analysis can include discriminant analysis, principal component analysis, projection to latent structure analysis, and / or multivariate process control analysis. In addition to multivariate analysis, the process model generator 412 can be used for exploratory data analysis, control and functional analysis, regression analysis, correlation analysis, analysis of variance (eg, ANOVA), reproducibility analysis, regeneration analysis, and / or time series. Analysis can be used.

  Past relationships, multivariate analysis, and / or statistical analysis are used by the process model generator 412 to determine thresholds for each of measured variables, calculated variables, predicted quality values, variability, etc. May be. The threshold may also be an experiment, design prototyping, failure impact analysis design, pre-production process control system prototyping, process control operator calculations, and / or any other that can accurately predict and / or calculate process quality. It may be determined through the method.

  In addition, the process model generator 412 analyzes the functional diagrams, algorithms, routines, and / or any other type of command structure that define the control and / or operation of the process control system 106 to provide a variable between variables. The relationship can be determined. The process control operator can also define relationships between variables based on experiments and / or calculations performed outside of the process model generator 412. Moreover, the process model generator 412 can determine the conditions for applying the corrective action to correct the process defect by analyzing past batch data including the effects of the defect and the corrective action. Further, corrective action may be determined by linking the input to the field device to a measured variable that may be the cause of the defect. For example, if it is determined that the flow rate is the cause of the defect, the process model generator 412 can determine that the flow rate may be adjusted by a valve and / or pump. In this way, changing the input to the valve and / or pump can be determined to be a corrective action for an abnormal flow rate. Alternatively, the process model generator 412 may receive corrective action from the process control operator.

  In addition, the process model generator 412 uses any multivariate and / or statistical method to determine the relationship between measured and / or calculated variables using the overall process quality. be able to. The process model generator 412 may also use any multivariate and / or statistical method to determine a model that predicts process quality based on corrections to the process control system 106. The quality prediction model may be based on applying corrective actions to past data using projection analysis based on past batches containing similar data features. The process model generator 412 can also use multivariate and / or statistical methods to determine a model that predicts whether any variable exceeds a threshold based on past batch data trends.

  Moreover, the process model generator 412 determines unmeasured disturbances through application of measured process disturbances and / or Q statistics (eg, square prediction error (SPE)) quantified through application of Hotelling's T2 statistics. By doing so, the variation and / or contribution of the measured variable to the quality variable from the modeled data can be determined. Further, the models determined by the process model generator 412 may be non-matching, with individual normally matching batches that may be grouped within a specific range of values and / or outside the group range. By batch, values associated with measured variables can be grouped.

  In addition to determining a model for the relationship between measured variables and / or calculated variables, the example process model generator 412 determines a graph type based on the modeled relationship type. Graph types may generally be created by a process control operator that determines the appearance, data display, data type, and / or interface options for each graph. The exemplary process model generator 412 may then automatically enter the data types corresponding to each type of graph. For example, the process model generator 412 may measure measured variables displayed in a microchart, process variation data and / or corresponding variables displayed in a process variation graph, and measured variables displayed in a contribution graph. And / or calculated variables and contribution relationships.

  The example process model generator 412 of FIG. 4 may store models, relationships, and / or thresholds in the process model database 416. The process model database 416 is accessed via the communication path 418 by the process control operator to view, change, and / or add information to any of the models, relationships, and / or thresholds. May be. The communication path 418 may be any type of wired and / or wireless communication path. Process model database 416 may be implemented by EEPROM, RAM, ROM, and / or any other type of memory.

  The example process model generator 412 may provide models, relationships, and / or thresholds to the analysis process modeler 408 and / or the evaluation process modeler 410 upon request from an operator. Alternatively, the analysis process modeler 408 and / or the evaluation process modeler 410 may access models, relationships, and / or thresholds stored in the process model database 416 via the process model generator 412 as needed. can do. Further, the process model generator 412 can update each model, relationship, and / or threshold at the same time that process control information is received by the OMS 102.

  To manage the display of variable values within the user interface, the exemplary OMS 102 of FIG. 4 includes a display manager 420. The example display manager 420 receives from the analysis processor 114 measured variable values, calculated variable values, calculated variations, calculated contributions, thresholds, graph type information, and / or defect indicators. After receiving the information, the display manager 420 organizes the information by graph type for display in the user interface. For example, when a workstation (eg, workstation 130 of FIG. 1) accesses OMS 102 using a web application, exemplary display manager 420 displays one or more graphs in the user interface.

  Display manager 420 can display a graph by combining the graph information generated from analysis process modeler 408 and / or analysis processor 114 using a user interface application. For example, the display manager 420 may be a Silverlight ™, Adobe Flash ™, Hypertext Markup Language (HTML) 5 to provide a web server framework to process control operators, technicians, and / or administrators. Or the generated graph may be inserted into a rich internet application (RIA) built using any other similar plug-in based rich internet application technology. The display manager 420 enables interactive browser-based applications that do not require the deployment of specialized process control software other than any workstation that includes Silverlight and / or Flash plug-ins. The display manager 420 allows direct manipulation of data in the graph from the workstation without the workstation needing continuous access to the OMS 102. Direct manipulation of the graph can include visual feedback of points on the curve, panning and / or scaling of the graph, and / or display of the related graph. Alternatively, in examples where a special application is required to view the graph, the display manager 420 may provide that application with data associated with the generated graph.

  The exemplary OMS 102 includes a session controller 422 to manage which process control operators access which process control data. In some examples, the session controller 422 may be combined with the display manager 420 as a web server. The example session controller 422 initiates a new session for each process control operator that accesses the data and / or graphs generated by the analysis processor 114. By creating a new session for each operator, the session controller 422 ensures that only process control data relating to the process accessed by the operator is transmitted to the operator. For example, four different operators may access OMS 102 to view data associated with four different processes. In addition, the session controller 422 may manage sessions when two or more operators view process data and / or graphs associated with the same process.

  In addition, the session controller 422 may track data displayed in the user interface on the workstation. In this manner, when the workstation loses connection with the OMS 102, the session controller 422 stores the last location of the workstation for use when the workstation can be reconnected. Furthermore, the session controller 422 can manage the transmission of information to the user interface. For example, when an operator opens a session, the session controller 422 may transmit a summary chart and / or any process variation graph to the workstation. The session controller 422 may then transmit any contribution graph, variable trend graph, and / or microchart.

  In order to manage communication of process control information to the workstation, the exemplary OMS 102 of FIG. 4 includes an online data processor 116. The exemplary online data processor 116 may resolve in-plant communications and / or web browser communications in a single protocol for communicating with the session controller 422, display manager 420, and / or analysis processor 114. . In addition, the online data processor 116 provides security and / or user authentication functions to ensure that only registered workstations and / or process control operators may access process control data and associated graphs. May be included.

  To communicate with workstations within the plant 104, the exemplary OMS 102 includes an in-plant access server 424. The in-plant access server 424 may include components and / or connection functions for coupling to the LAN 124 of FIG. Further, the in-plant access server 424 may include encryption and / or any other data transmission security to ensure that the transmitted data is not likely to be viewed by unauthorized individuals. it can. The in-plant access server 424 is accessed by any workstation, laptop, personal digital assistant (PDA), smartphone, and / or any other device capable of displaying process control data and associated graphs. May be.

  To communicate with workstations outside the plant 104, the exemplary OMS 102 includes a web access server 428. Web access server 428 may include components and / or connectivity functions for coupling to WAN 134 of FIG. Further, the web access server 428 may include encryption and / or any other data transmission security to ensure that the data transmitted is not likely to be viewed by unauthorized individuals.

  Although an exemplary manner of implementing OMS 102 is depicted in FIG. 4, one or more of the interfaces, data structures, elements, processes, and / or devices shown in FIG. 4 may be in any other manner. It may be combined, split, rearranged, omitted, eliminated, and / or implemented. For example, the exemplary batch data receiver 402, exemplary analysis processor 114, exemplary analysis process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, illustrated in FIG. The exemplary display manager 420, exemplary session controller 422, exemplary online data processor 116, exemplary in-plant access server 424, and / or exemplary web access server 428 may include, for example, one or more computing devices. It may be implemented individually and / or in any combination using machine-accessible or readable instructions executed by a device and / or computing platform (eg, exemplary processing platform P10 of FIG. 18). .

  Moreover, exemplary batch data receiver 402, exemplary analysis processor 114, exemplary analysis process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, exemplary display manager 420 The exemplary session controller 422, the exemplary online data processor 116, the exemplary in-plant access server 424, the exemplary web access server 428, and / or more generally, the OMS 102 includes hardware, software, It may be implemented by firmware and / or any combination of hardware, software, and / or firmware. Thus, for example, exemplary batch data receiver 402, exemplary analysis processor 114, exemplary analysis process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, exemplary display Any of manager 420, exemplary session controller 422, exemplary online data processor 116, exemplary in-plant access server 424, exemplary web access server 428, and / or more generally, OMS 102. Or may be implemented by one or more circuits, programmable processors, application specific integrated circuits (ASICs), programmable logic devices (PLDs), and / or field programmable logic devices (FPLDs), and the like.

  FIG. 5 is a diagram 500 representing charts and / or graphs 502-512 generated by OMS 102 of FIGS. 1 and / or 4 that may be displayed to determine defects in process control system 106. . FIG. 500 illustrates how much from the initial detection of a process defect to the process control operator determining the cause of the defect and then determining whether the corrective action for the defect may improve the overall process quality. Shows how easy it is to navigate logically with relative ease. The diagram 500 shows two possible flows for determining defects and / or predicting process quality due to defect correction. However, other charts, graphs, diagrams, and / or data may be displayed. A description of each of the charts and / or graphs 502-512 is provided with reference to FIGS.

  Process summary chart 502 shows status or one or more process control systems (eg, process control system 106). An overview chart 502 may be displayed when a process control operator first opens a user interface on a workstation and selects a process control environment and / or plant. If OMS 102 detects a defect and / or process defect prediction, OMS 102 may indicate the defect in summary chart 502.

  Viewing the defect indicator in the overview chart 502, the process control operator can select the indicator to open the process variation graph 504. Alternatively, the operator may select an indicator to open the microchart 508. The process variation graph 504 can show the variation associated with the indicated defect. For example, if a process defect is associated with the overall process quality, the process variation graph 504 may display the explained variation and / or the unexplained variation associated with the overall process quality. Alternatively, if the defect is associated with a measured and / or calculated variable, the process variation graph 504 may display the explained variation and / or unexplained variation associated with the measured and / or calculated variable. Good. Moreover, the process variation graph 504 may display the latest and past values of variables and / or process quality associated with the defect compared to an average value, a standard deviation of values, and / or a threshold value. The process variation graph 504 may also show a bar chart that includes contributions to measured variables and / or calculated variable variations.

  When viewing the process variation graph 504, the process control operator may select one point on the graph corresponding to a certain time. When one point is selected, a contribution graph 506 may be displayed. The contribution graph 506 shows variables that contribute to process and / or variable variations. The operator may use the contribution graph 506 to determine which variables contribute to the identified defects. Thus, the contribution graph 506 shows potential causes of detected defects. In addition, the process control operator may change the time within the process and view the value of the variable at the selected time. Further, the contribution graph 506 may display a defect recommendation corrective action. The operator may select any of the variables listed in the contribution chart 504 to view the current batch process variable history in the variable trend graph 510.

  Alternatively, the microchart 508 may be displayed when the operator selects a point on the process variation graph 504. The example microchart 508 shows values associated with measured and / or calculated variables based on a selected time. The operator may use the measured variables and / or against the batch process history to determine when one or more variables have exceeded a threshold and / or standard deviation, when, and / or to what extent. Or the microchart 508 can be used to verify the value of the calculated variable. The microchart 508 may also include a sparkline that shows a history of measured values and / or calculated values. The operator may select any of the spark lines to view a more detailed description of the selected spark line. In addition, the microchart 508 may include a timeline that indicates the time at which the process defect occurred. The operator may select an arrow in the timeline and scroll and / or select a time in the timeline to display the measured and / or calculated variable values corresponding to that time. Good. The operator may select any one of the displayed variables to open the variable trend graph 510. Alternatively or additionally, the operator may open the quality prediction graph 512 to display the predicted process quality based on the implemented corrective action of the one or more corrective actions.

  The example variable trend graph 510 displays variable values over the duration of the batch process. In some examples, the variable trend graph 510 may display variable values across batch process stages and / or operations, depending on the degree of resolution selected by the operator. The example variable trend graph 510 may show a history of variables selected during a batch process compared to the average and / or standard deviation of previous batch processes. The variable trend graph 510 may also display the threshold of the selected variable and / or the calculated standard deviation. The operator may use the variable trend graph 510 to view the history of variables during the batch process. After viewing the variable trend graph 510, the operator may select the quality prediction graph 512.

  The example quality prediction graph 512 shows the predicted quality of the process based on the implementation of one or more corrective actions. The operator may use the quality prediction graph 512 to determine if the corrective action improves the process quality sufficiently to continue execution of the process. If it is predicted that the process quality will not improve and / or if the process quality is already significantly out of tolerance, the operator may decide to abort the process. In addition, if the selected corrective actions are not expected to improve the process, the operator may select additional corrective actions to determine if one or more corrective actions can improve the quality of the process. May be. If the corrective action is predicted to improve the process quality to within acceptable tolerances, the operator may select within the quality prediction graph 512 to transmit the corrective action to the OMS 102 and / or the controller 108.

  The quality prediction graph 512 may also indicate the overall quality variable associated with the defect and / or the predicted variation of the measured and / or calculated variable. Moreover, the quality prediction graph 512 can show the predicted quality of the process, as well as current and / or past variations in process quality. After visually recognizing the quality prediction graph 512, the operator may return to the overview chart 502. Further, after viewing any of the graphs 504-510, the operator may return to the overview chart 502 and / or open any of the other graphs 504-512. Moreover, the graphs and / or charts 502-512 may be updated with the latest variable values and / or quality predictions as the OMS 102 receives and / or processes process control information.

  6 illustrates a user interface 136 that displays the example process summary chart 502 of FIG. 5 associated with the example process control system 106 of FIG. The overview chart 502 may be used to provide an overview of multiple processes in a plant (eg, plant 104) where two or more batches may be active at the same time. The overview chart 502 is organized by process area and includes the status of a first process area (eg, process area 1) and a second process area (eg, process area 2). The first process area may correspond to the process control system 106. Each process area may be used to alert the process control operator when a defect is detected and / or when the end of the batch quality predictor is outside a specified threshold, and / or Contains information associated with a batch of

  The exemplary summary chart 502 includes batch information for batches 12359-12369. However, only batch information for batch 12369 is shown. Exemplary summary chart 502 includes a batch identification number (eg, batch ID), a batch stage (eg, stage), a stage state (eg, state), a predicted quality value (eg, prediction), and / or Includes a field for defect status (eg, defect). The predicted quality value may correspond to a predicted variation in the overall quality variable associated with the quality of the resulting product. The defect field may indicate whether a defect has been detected and / or if a defect is predicted. The defect field may also display the time at which the defect occurred and / or any other process information about the defect (eg, a measured variable and / or a calculated variable that caused the defect). In addition, the defect field may include an icon 604 to alert the operator of the defect using graphics.

  The operator may also view additional information about the defect by selecting icon 604, defect field text (eg, true), batch number, and / or any other text in the field associated with batch 12369. Good. Alternatively, the operator can view additional information associated with the defect by selecting a forward arrow (not shown) and / or a graph tab (not shown) that may be located in the overview chart 502. May be. In addition, the operator may alert other process control operators and / or administrators of detected defects by selecting text and / or icons 604 associated with the defects.

  FIG. 7 shows the user interface 136 of FIG. 6 displaying the example process variation graph 504 of FIG. . The process variation graph 504 may be displayed by clicking on the batch 12369 information in the overview chart 502 of FIG.

  The example process variation graph 504 shows the statistics calculated for the batch 12369 for the time associated with the process period (eg, T1-T4). The process control operator may select a time period to include batches, stages, operations, and / or time periods before and after the detected defect. The example of FIG. 7 shows process quality variation. However, other process variation graphs may show variations associated with measured variables, calculated variables, and / or overall quality variables. Further, instead of showing the variation of the variable, the process variation graph may show the value of the variable over the process period.

  The illustrated variation graph 710 shows a variation curve 712 of the illustrated variation value for the process period. Similarly, the unexplained variation graph 720 shows an unexplained variation value variation curve 722 for the process period. Point selections 714 and 724 show the points on the respective variation graphs 710 and 720 selected by the operator. For example, in FIG. 7, point selection 724 indicates that the operator has selected the maximum point of variation that is not explained. Alternatively, selecting a defect in the overview chart 502 may open a process variation graph 504 with point selections 714 and / or 724 displayed on the maximum point of variation. The threshold line 726 includes a limit of 1.0. A defect may be indicated when the unexplained variation curve 722 exceeds the threshold line 726. For example, the defect shown in summary chart 502 may be associated with an unexplained variation curve 722 of the overall quality of the batch that exceeds the threshold of 1.0 at 12:38:26 pm just before T3. Time indicator line 728 refers to a time in the period associated with the time corresponding to point selection 714 and / or 724.

  In addition, the process variation graph 504 includes a navigation arrow, a time corresponding to the time of point selection 714 and / or 724 (eg, 12:38:26 pm), batch identification number, material being processed by the batch, batch Includes a process information faceplate 730 that includes the equipment currently in use, the stage of the batch, and the status of the batch. Further, the faceplate 730 includes the explained and unexplained variability values at each point selection 714 and / or 724. The operator may move the point selections 714 and / or 724 along the respective curves 712 and 722 to see the corresponding variation values within the faceplate 730.

  The operator may select one or more of the arrows to navigate between the graphs and / or charts 502-512 of FIG. For example, the contribution graph 506 may be displayed by clicking a forward arrow (eg, an arrow above “Afternoon”), or a summary chart 502 may be displayed by clicking the up and / or back arrows. May be. Further, the operator may navigate between the graphs 504-512 by selecting the corresponding tab located at the top of the process variation graph 504. For example, the operator may view a microchart (eg, microchart 508) by selecting a microchart tab. Further, the operator may navigate to contribution graph 506 and / or microchart 508 by selecting a point on curves 712 and / or 722 (eg, point selection 714 and / or 724). Moreover, the time associated with the selected point on curves 722 and / or 724 may be transferred to contribution graph 506 and / or microchart 508.

  FIG. 8 shows the user interface 136 of FIG. 7 displaying an exemplary process variation graph 504 that includes a summary contribution faceplate 802. Process variation graph 504 includes a variation graph 710 described, a variation graph 720 not described, variation curves 712 and 722, and a process information faceplate 730 similar to FIG. The summary contribution faceplate 802 includes a contribution graph that includes variables that contribute to the explained and / or unexplained fluctuations. The contribution graph bar chart shows the value of the variable compared to the extent to which the variable contributes to the explained and / or unexplained portion of the overall quality variation. Further, the contribution graph shows values associated with the contribution amount and / or variation amount of the variable.

  For example, the “medium flow” variable may be a measured process variable that contributes most to unexplained variations. Unexplained contributions may be indicated by a solid black bar portion, and described contributions may be indicated by a shaded bar portion. Further, the value of the “media flow rate” variable may indicate that the “media flow rate” threshold is 2.33 gallons (gal) / second (sec) below. Alternatively, 2.33 may indicate a statistical confidence value and / or a statistical contribution value of the “medium flow” variable for the overall process quality variation. The contribution of each variable may be modeled and / or calculated by the OMS 102 of FIG. 1 and / or FIG.

  The operator may select one of the curves 712 and / or 722. When the operator selects a point on the curve, the contribution information in the summary contribution faceplate 802 may change to reflect the contribution to the variation of each variable at the selected time. For example, if the point at time T2 is selected, the “medium flow rate” may show a lower explained contribution and / or an unexplained contribution value due to a lower overall process quality variation at time T2. . Further, similar to FIG. 7, the operator opens the contribution graph 506 and / or the microchart 508 by selecting a forward arrow, tab, and / or summary contribution faceplate 802 in the process information faceplate 730. You may choose.

  9 shows the user of FIG. 6 displaying the exemplary contribution graph 506 of FIG. 5 including unexplained process variations and / or described process variations of variables associated with the process control system 106 of FIG. An interface 136 is shown. The exemplary contribution graph 506 displays the illustrated variation (eg, a black bar or bar portion) and unexplained variation (eg, a shaded bar or bar portion) for each variable that contributes to the overall process quality variation. A bar chart 910 is included. In other examples, the bar chart may be shown in different colors and / or shapes. In addition, variables (eg, media flow rate, mixer temperature, water temperature, etc.) are organized for each variable that has the largest contribution to the overall process variation displayed at the top. In other examples, the variables may be organized according to process control operator preferences.

  Variables in the bar chart 910 include numerical values associated with variable variations. For example, a value of −2.33 associated with the “medium flow” variable may indicate that the liquid is flowing 2.33 gal / sec slower than the average value or threshold. Alternatively, a value of −2.33 may indicate the statistical contribution that the “medium flow” variable contributes to the variation in the overall process quality variation of FIGS. The contribution amount of the variables in the bar chart 910 may be determined by the OMS 102 of FIG.

  The explained and unexplained variability of each variable is superimposed or shown together to provide a clear graphical display to the process control operator. The explained variation of each variable may be calculated by the OMS 102 by utilizing model variation T2 statistics. Unexplained variation of each variable may be calculated by OMS 102 by utilizing a Q statistical test. In other examples, the bar chart 910 may display the value of the variable at the selected time, the mean value of the variable, and / or the standard deviation of each of the variables.

  The exemplary contribution graph 506 includes a process information faceplate 920 that displays process information, the process time of the variation displayed for each variable, and the explained and unexplained variation values of the selected variable. For example, in FIG. 9, the process information faceplate 920 indicates that at 12:38:26, the “Media Flow” variable has a variation of 0.26 with respect to the overall process variation displayed in FIGS. 2.89 with unexplained contributions. Contribution graph 506 may indicate a variable variation at 12:38:26 pm based on the time received from process variation graph 504. Alternatively, the operator may change the process time by selecting any one of the arrows to advance or return the time. When the time is changed, the bar chart 910 may display a variable fluctuation value corresponding to the selected time.

  In addition, the contribution graph 506 includes a recommended action faceplate 930. The recommended action faceplate 930 may display process correction recommendations to correct detected process defects (eg, detected defects in FIG. 6). For example, the recommended action faceplate 930 recommends correcting the defect by increasing the media flow rate by 1.85 gal / sec with the field device FIC3. The FIC 3 may correspond to a valve or pump in the process control system 106 that can change the media flow rate. Further, the recommended action faceplate 930 includes a recommendation to inspect the flow meter FIT3. By inspecting the flow meter FIT3, the operator may determine whether the flow meter is outputting an accurate media flow value. The recommended action displayed in the faceplate 930 may be determined by past analysis of similar process control systems with similar defects. Further, the recommended action may be determined by the OMS 102 based on the modeling of the process control system 106.

  The operator may view the history of each value of the variable by selecting the desired variable in the bar chart 910. When a variable is selected, a variable trend graph 510 showing the history of the selected variable is displayed. Alternatively, the operator may select a variable, then select the “Variable Trends” tab, and / or select the forward arrow on the process information faceplate 920. In addition, the operator can select one or more of the recommended actions in the recommended action faceplate 930 to view the predicted quality when one or more corrective actions are implemented, thereby predicting the quality. A graph 512 may be displayed.

  FIG. 10 shows the user interface 136 of FIG. 6 displaying the variable trend graph 510 of FIG. 5 for the “medium flow” variable of FIGS. The variable trend graph 510 may be used by a process control operator to compare the process variable trend during the current batch process to the trend of the variable in the previous batch process that ended with products within the quality threshold. Anomalous deviations in variables from past batches may be the source of defects and / or deviations detected within the overall quality variable and / or overall process quality variation. The variable trend graph 510 shows the extent to which the value associated with the current batch of variables has deviated from the previous batch. A plurality of variable trend graphs 510 may be opened by an operator to display a historical trend of a plurality of variables. The example variable trend graph 510 may display a history of the values of any measured variables, calculated quality variables, and / or overall process quality variables.

  The exemplary variable trend graph 510 includes a current variable curve 1002 that includes a selected point 1004. The latest variable curve 1002 shows the values of variables during the process period (for example, T1 to T4). The time period may be adjusted by the operator to include only stages, actions, and / or times before and after defect detection. The latest variable curve 1002 shows that the media flow started in a batch process before time T2 and showed a flow rate of 1.7-2.4 gal / sec through time T3 to about the middle. By time T4, the media flow of batch process 12369 had stopped.

  The variable trend graph 510 includes a variable average 1006, an upper limit standard deviation 1008, and a lower limit standard deviation 1010 corresponding to the “medium flow rate” values of past processes. Further, the variable trend graph 510 may include a calculated average, a calculated standard deviation, and / or a threshold of the media flow rate. By displaying the variable mean 1006 and standard deviations 1008 and 1010, the exemplary variable trend graph 510 allows the operator to change the variable trend to the previous trend for the same variable in different batches that produced acceptable products. Allows comparison. The variable average 1006 and / or standard deviations 1008 and 1010 may be determined by the OMS 102 of FIG.

  The variable average 1006 may be the determined average value of the “media flow” variable for the past batch, and the standard deviations 1008 and 1010 may be determined from the standard deviation of the “media flow” variable for the past batch. Good. The variable trend graph 510 of FIG. 10 shows that the latest variable curve 1002 is approximately 2.0 gal / sec below the variable average 1006 and approximately 1.6 gal / sec below the lower standard deviation.

  Moreover, the variable trend graph 510 may include a process information faceplate and / or a recommended action faceplate. The operator can select one point on the variable curve 1002 (eg, selection point 1004), by selecting the “Forecast” tab, and / or by selecting a corrective action in the recommended action faceplate. The quality prediction graph 512 may be accessed. Alternatively, the operator may return to the contribution graph 506 by selecting the “Contribution” tab and / or by closing the variable trend graph 510.

  FIG. 11 shows the user interface 136 of FIG. 6 displaying the quality prediction graph 512 of FIG. 5 for an exemplary batch 12369. The example quality prediction graph 512 shows the possible corrective effect on the defects on the process variation (eg, the process variation shown in the process variation graph 504 of FIG. 7). The quality prediction graph 512 may indicate the predicted quality of the product resulting from the process and / or the predicted quality associated with the end of the batch process 12369. In addition, the quality prediction graph 512 may indicate the predicted quality of the batch process after implementing corrective actions to correct the detected defects. The operator may use the quality prediction graph 512 to determine whether corrective action is sufficient to bring the process quality within a defined threshold. If the quality prediction graph 512 indicates that the corrective action is not sufficient to produce a quality product, the operator may select another corrective action and / or decide to end the process. Good.

  Moreover, the quality prediction graph 512 may correspond to the overall quality variable. In other examples, the quality prediction graph 512 may show predicted values of measured variables and / or calculated variables after implementing corrective actions. The example quality prediction graph 512 of FIG. 11 includes a quality prediction curve 1102 for the complete period (eg, T1-T7) of the batch process 12369. The example prediction curve 1102 may be represented as a statistical process quality calculation that may be normalized. Statistical process quality calculations and / or models of statistical process quality calculations may be generated by the exemplary OMS 102 of FIG.

  The exemplary quality prediction graph 512 also includes a time marker line 1104 that indicates the current time and / or progress through the batch process. Further, the time marker line 1104 may represent the time at which the quality prediction graph 512 calculates the impact of applying corrective action to the batch process. Moreover, the quality prediction graph 512 includes a confidence limit 1108 that represents the calculated confidence range of the predicted quality. For example, the confidence limit 1108 may indicate with 95% confidence that the actual quality of the batch process is within the confidence limit 1108. That is, there is a 95% probability that the quality of the batch process is somewhere between the confidence limits 1108. The exemplary confidence limit 1108 is wide at the start of the batch process 12369 because the process quality may be more uncertain at the start of the process. Then, as the batch process progresses, the quality of the process may be more certain, as indicated by the narrowing of the confidence limit 1108 at time T7.

  In addition, the quality prediction graph 512 of FIG. 11 includes a threshold (eg, specification) limit 1110 and a target limit 1111. The threshold limit 1110 may indicate the maximum value that the quality prediction curve 1102 may have with a batch process that is considered acceptable quality. The target limit 1111 may indicate an ideal value of the quality prediction curve 1102 in order to produce an acceptable quality product.

  The exemplary quality prediction graph 512 also includes navigation arrows, batch process information, predicted numerical values of selected points on the batch process quality curve 1102, and confidence limits 1108 associated with the selected points on the curve 1102. A process information faceplate 1112 is also included. The selected point on the predicted quality curve 1102 may be represented by a black circle at time T7. In addition, the quality prediction graph 512 includes a recommended action faceplate 1114 that includes selectable corrective actions. In the example of FIG. 11, the corrective action to increase the flow rate of FIC3 by 1.85 gal / sec was selected and the quality prediction graph 512 indicates that the corrective action has been applied to the prediction of batch process quality. In other examples, the recommended action faceplate 1114 may include additional corrective actions and / or may include functionality that allows an operator to enter corrective actions.

  If the process control operator determines that the applied corrective action corrects the detected defect, the process control operator may correct the process control system 106 of FIG. 1 by selecting the action in the recommended action faceplate 1114. Measures may apply. Alternatively, the operator may select and apply corrective actions via the user interface 136 and / or other functions included in the quality prediction graph.

  FIG. 12 shows the user interface 136 of FIG. 6 displaying the exemplary microchart 508 of FIG. 5 at a first time. The exemplary microchart shows a timeline 1202 showing batch process time 1204 and current progress 1206 through batch process time 1204. In addition, timeline 1202 includes detected defects 1208-1214 and plot time position arrow 1216. Process time 1204 corresponds to the time to complete a batch process (eg, batch process 12369). Current progress 1206 shows the status of the batch process relative to process time 1204. For example, in FIG. 12, the current progress is approximately two-thirds of the total process time 1204. In other examples, the process time 1204 may correspond to a stage time, an operating time, and / or a time specified by an operator.

  The detected defects 1208-1214 correspond to defects detected in the process control system 106 of FIG. The period of detected defects 1208-1214 can be indicated by the width of the bars of detected defects 1208-1214. Furthermore, the density of the detected defects 1208 to 1214 may correspond to the type of defect. For example, defects 1208 and 1210 may correspond to batch process operating conditions (eg, quality variables) that exceed a threshold. Defect 1212 may correspond to a defect associated with measurement, control loop operation, and / or a field device (eg, a measured variable). Defect 1214 may correspond to a combination of defects and measurements corresponding to operating conditions, control loop operations, and / or defects corresponding to field devices. In other examples, detected defects 1208-1214 may be represented by color-coded bars, by shape, and / or by icons.

  The timeline 1202 includes a plot time position arrow 1216 to allow an operator to select a time in the batch process and view the variable value information. The variable value information may be displayed in the bar chart 1218 and / or in the spark lines 1220-1226. A microchart 508 in FIG. 12 shows a plot time position arrow 1216 positioned at the first time, and the variable value shown in the bar chart 1218 corresponds to the first period. Furthermore, the progress of the spark lines 1220-1226 is shown throughout the first period. In addition, the variable includes the name of the variable and the numeric value of the variable at the first time. For example, the first variable “medium flow rate” includes a spark line 1220 indicating a history of the value of the “medium flow rate” variable during the batch process, a value 2.8 gal / sec at a first time, and 2.8 gal. It includes a bar chart 1218 that is normalized to show how per second is relative to the average value of the “medium flow” variable.

  The exemplary microchart 508 shows the latest variable values (eg, via bar chart 1218) and variable value history (eg, sparklines 1220-120) for each of the variables that may contribute to batch process variation. (Via 1226) to the process control operator. Thus, the exemplary microchart 508 combines the functions of the contribution graph 506 and the variable trend graph 510.

  The exemplary microchart 508 normalizes and / or rescals each variable's mean and / or standard deviation so that the variables can be displayed within the common average and / or common standard deviation of the bar chart 1218. May be. The bars in the bar chart 1218 may change color to indicate when one or more variables exceed the standard deviation but do not cause a process defect. Furthermore, the bars in the bar chart 1218 may change color to indicate that one or more variables exceed the standard deviation and are responsible for process defects. In addition, the bars in the bar chart 1218 may be shaded to show the statistical history of each variable. For example, similar to the average and standard deviation of the previous batch in the variable trend chart 510 of FIG. 10, the bars in the bar chart 1218 are shaded to show the average and / or standard deviation of the previous batch for each variable. May be attached. In addition, the operator may select any one of the variables in the bar chart 1218 to view the selected variable in the variable trend graph 510.

  Exemplary sparklines 1220-1226 show a history of previous values for the current batch for each of the variables. Sparklines 1220-126 may be plotted along the average value of each variable and / or shown as the absolute value of the variable. In addition, the sparkline may include an indicator that indicates when the value of the variable exceeds a threshold during the process. The process control operator may view detailed information of the spark lines 1220-1226 by selecting the desired spark lines 1220-1226.

  FIG. 13 shows the user interface 136 of FIG. 6 displaying the example microchart 508 of FIG. 12 for a selected second time. In the example of FIG. 13, the plot time position arrow 1216 has moved to the second time on the latest progress 1206 of the batch process time 1204. Plot time position arrow 1216 is positioned at the time of occurrence of defect 1214. For this reason, the bar chart 1218 shows a variable value associated with the second time, and the variable shows a numerical value (for example, a medium flow rate of 3.3 gal / second) associated with the second time. Furthermore, the spark lines 1220 to 1226 indicate previous values of each variable up to the second time. In other examples, the sparklines 1220-1226 may include previous values for each variable up to the current time of the batch process, but may indicate a second time indicator. The example of FIG. 13 shows that the defect 1214 may contribute to the media flow rate where the media flow rate exceeds the standard deviation indicated by the bar chart 1218. Further, the bars in the bar chart 1218 associated with the media flow rate may change color and / or tint to indicate that the variable is a contributing factor to the defect 1214.

  14A and 14B show the user interface 136 of FIG. 6 displaying an exemplary sparkline 1220 of the “mixer temperature” process variable of FIGS. Sparkline graphs 1400 and / or 1420 may be generated and / or displayed within user interface 136 by selection of sparkline 1220 of FIGS. 12 and / or 13. The exemplary sparkline graphs 1400 and 1420 of FIGS. 14A and 14B show two different configurations for displaying previous variable values for a batch process. However, other sparkline graphs may be configured differently to display previous variable values for the batch process.

  The exemplary sparkline graph 1400 of FIG. 14A includes a sparkline “mixer temperature” sparkline 1220 for batch process times T1-T4. Spark line 1220 is shown along an absolute scale of temperature. For example, at T1, the “mixer temperature” is 40 ° C., and at T4, the “mixer temperature” is 180 ° C. Thus, as shown, the spark line 1220 increases with temperature.

  Further, the sparkline graph 1400 includes deviation indicators 1404 and 1406. The length of the deviation indicators 1404 and 1406 corresponds to the time of the variable value exceeding the threshold. The height of the deviation indicators 1404 and 1406 from the sparkline may indicate how much the variable value exceeds the threshold. A deviation indicator 1404 located above the spark line 1220 may indicate that the variable value exceeds the upper standard deviation limit, and a deviation indicator 1406 located below the spark line 1220 indicates that the variable value is below the lower standard deviation limit. Can be shown to exceed. Further, deviation indicators 1404 and 1406 may be colored to indicate the severity of deviation, the amount of deviation, and / or the type of deviation.

  The exemplary sparkline graph 1420 of FIG. 14B includes a sparkline “mixer temperature” sparkline 1220 for batch process times T1-T4. Sparklines 1220 are shown along the mean and standard deviation scale. For example, the sparkline graph 1420 shows the variable value of the sparkline 1220 compared to the average value calculated for “mixer temperature” during the batch process at times T1-T4. Further, the sparkline graph 1420 includes a deviation indicator 1424. Deviation indicator 1424 does not correspond to deviation indicators 1404 and 1406 shown in sparkline graph 1400 of FIG. 4A. The example deviation indicator 1424 provides the operator with a visual indication that a portion of the sparkline 1220 exceeds a standard deviation (eg, a threshold). Deviation indicator 1424 may be visually indicated by a dashed line, bold line, line color, shape, and / or icon.

  In some embodiments, two or more charts or graphs 502-512 may be displayed on a user interface to correlate candidate factors that may or may contribute to predicted process defects. May be presented at the same time. Candidate factors may include, for example, process parameters or process variables in embodiments. In embodiments, the candidate factor may include one or more calculations based on one or more process parameters or variables. In some cases, the candidate factor may include one or more calculations based on the values of one or more measured parameters or variables over time. For example, candidate factors include a displacement or change in the mean value of one or more measured parameters or variables, a transition or change in the standard deviation of one or more parameter values, or a change or change in the variation frequency of the parameter values. There is a case. Other candidate factors may be possible. In general, the candidate factors may correspond to a model of the process in which defects are predicted.

  In an embodiment, simultaneously displayed charts or graphs 502-512 may be temporally aligned so that the user can quickly analyze candidate factors, identify the most prominent contributing factors to the defect, and corresponding causes May be presented in a split view to allow effective actions to be taken to isolate and correct critical situations.

  For example, as previously described with reference to the process overview chart 502 of FIG. 6, the predicted defect may be determined based on the process control information, and may include an icon 604 or other selectable user control (not shown). ) Or the like. Upon selection of icon 604 or other selectable user control, a display corresponding to the predicted defect may be presented on the user interface.

  FIG. 19 shows an exemplary display of display 1800 that may be presented on the user interface upon selection of predicted defect 604. Display 1800 may include a section 1802 (eg, first section 1802) corresponding to predicted defect 604. In an embodiment, the first section 1802 may include one or more curves 1805, 1808 displayed over a time interval or period 1810. The first curve 1805 may correspond to an unexplained variation in the measured value of a particular process variable or parameter for a time interval or period 1810. In embodiments, the first curve 1805 may be similar or identical to the unexplained variation curve 722 of the process variation graph 504 of FIG. The second curve 1808 may correspond to the predicted process quality over a time interval or period 1810. In an embodiment, the second curve 1808 may be similar or identical to the prediction curve 1102 of the quality prediction graph 512 of FIG. Both curves 1805 and 1808 are shown in FIG. 19 as being presented simultaneously in section 1802, but in some embodiments, only curve 1805 or only curve 1808 may be presented in section 1802 or display 1800. . In some embodiments, more than one unexplained variation curve 1805 may be displayed in the first section 1802 or display 1800.

  Section 1802 may also include a threshold 1812. In the example shown in FIG. 19, a single threshold value 1812 corresponding to a non-explained variation curve 1805 is displayed, but in other embodiments an additional threshold value (not shown) corresponding to the predicted process quality curve 1808. And / or additional thresholds (also not shown) corresponding to any respective additional unexplained variation curves may be displayed in addition to or as an alternative to section 1802 of display 1800. In general, section 1802 of display 1800 may include any or all of the information that may be presented in process variation graph 504 of FIG. 7 and / or presented in quality prediction graph 512 of FIG. Any or all of the possible information may be included. Moreover, the information from FIGS. 7 and / or 11 may be presented in the first section 1802 of the display 1800 in a manner similar to that shown in FIGS. 7 and 11, or the information may be any desired Or it may be presented in an appropriate format.

  Display 1800 may be a split display having multiple sections that are presented simultaneously on the user interface. For example, in addition to the first section 1802, the display 1800 may include a second section 1820 that presents candidate factor information. In an embodiment, the second section 1820 includes a set of valid candidate factors (e.g., one or more process parameters, process variables, one or more) that may have a contributing impact on the predicted defect 604. Calculation based on the values of process parameters or process variables, and / or other candidate factors) 1822 indicators. Section 1820 may include a value for each respective contribution 1825 of factor 1822 to predicted defect 604, and a value for each variation (eg, explained variation and / or unexplained variation) 1828 of factor 1822. May be included. In an embodiment, the set of candidate factors 1822 may be based on a set of process variables or parameters corresponding to the process model created by the process model generator 412 and stored in the process model database 416.

  The embodiment of the second section 1820 shown in FIG. 19 illustrates contributing factor information 1822, 1825, 1828 that is presented in an alphanumeric chart format. The chart may be sorted based on parameter or calculation name 1822, predicted defect contribution 1825, and / or deviation amount 1828.

  In some embodiments, instead of the chart format, some or all of the candidate factor information 1822, 1825, 1828 may be in graph format or the bar chart format 910 shown in FIG. 9 or the summary faceplate format 802 of FIG. Etc., may be presented in some other desired format. In general, the second section 1820 of the split display 1800 may include any or all of the information that may be included in the contribution graph 506 of FIG. 9 or the summary faceplate 802 of FIG. It may be presented in any desired or appropriate format.

  Each indicator of each candidate factor 1822 may be manually selected by a user or operator in embodiments to be more detailed or magnified in the third section 1840 on the display 1800. Each indicator of each candidate factor 1822 may be automatically selected for more detailed or enlarged display within the third section 1840 in embodiments. For example, a parameter, variable, or calculation included in the second section 1820 may be automatically selected to display details when it has a maximum deviation 1828 of a set of candidate factors 1822. In another example, a parameter, variable, or calculation included in the second section 1820 may be automatically selected when it has a maximum contribution 1825 of a set of candidate factors 1822. In yet another example, a particular measured variable or a particular calculation from set 1822 may be identified as a default factor that is automatically displayed in third section 1840.

  Selecting one of the candidate factors 1822 may present information corresponding to the selected candidate factor in the third section 1840 of the display 1800. In the situation illustrated in FIG. 19, for example, the parameter “simple_process / mixer_press” (reference 1822a) has been selected in the second section 1820, as indicated by the highlight. Accordingly, parameter or variable curves 1842, 1845 corresponding to “simple_process / mixer_pres” are presented in the third section 1840. The first curve 1842 may indicate a measured value of the selected parameter 1822a. In an embodiment, the first curve 1842 may correspond to the measured variable curve 1002 of the variable trend graph 510 of FIG. The second curve 1845 may correspond to an optimal prediction or mean variable curve associated with acceptable process quality. In embodiments, the second curve 1845 may be similar or the same as the curve 1006 of FIG. In some embodiments, other curves corresponding to the selected parameter or variable (not shown in FIG. 19) may also be presented in the third section 1840 of the display 1800. For example, upper and lower standard deviation curves corresponding to expected variable curve 1845 (such as deviation curves 1008 and 1010 of variable trend graph 510 of FIG. 10) may be presented in third section 1840. In general, the third section 1840 of the display 1800 may include any or all of the information that may be presented in the variable trend graph 510 of FIG. 10, and the included information is shown in FIG. It may be presented in a form or in any desired or appropriate form.

  In an embodiment of display 1800, first section 1802 and third section 1840 of display 1800 may be aligned over displayed time interval 1810. That is, the time scale of the displayed time interval 1810 may be common to both the first section 1802 and the third section 1840. In an embodiment, display 1800 may include one or more common indicators 1850, 1852, and 1855, each of which may extend to both sections 1802 and 1840 of display 1800. Thus, the common indicators 1850, 1852, 1855 may be common time indicators. In the example of FIG. 19, common indicator 1850 indicates a time instance during the displayed time interval 1852 where the batch process is moving from the “fill” stage to the “heating” stage, and the common indicator 1852 indicates that the batch process is The different time instances during the displayed time interval 1810 are shown moving from the “heating” stage to the “displacement” stage. The common indicator 1855 may not correspond to a particular stage of the process, but instead may correspond to any desired time instance contained within the displayed time interval 1810. In an embodiment, the common indicator 1855 may be movable along a common time axis 1810. For example, the operator or user may move the common indicator 1855 to the desired time case. In some embodiments, more than one movable indicator 1855 may be included on the display 1800.

  Split display 1800, simultaneous and time aligned presentation of information corresponding to predictive defect 604 in first section 1802 and information corresponding to valid contributor 1822a in third section 1840, and common time indicator 1850, 1852, 1855 may allow the operator to quickly and easily analyze and correlate the impact of valid contributor 1822a on the predicted defect 604. A movable common indicator 1855 enables a correlated and temporally synchronized display of candidate factor 1842 behavior, desired behavior of candidate factor 1845, any unexplained variation 1805, and predicted process quality 1808. Also good.

  Moreover, in some embodiments, the operator can adjust the displayed time interval 1810 of the display 1800 to further facilitate defect analysis. During the first manual adjustment for one of the sections 1802, 1840, or for the displayed time interval 1810, the other sections may be automatic so that the correlation between sections 1802 and 1840 may be maintained. May be adjusted. For example, an operator may indicate that the displayed time interval 1810 transitions to an earlier or later time interval, and the time axis of sections 1802 and 1840 are automatically transitioned based on the operator's indicator. May be. Alternatively or additionally, the operator may enlarge or reduce a particular section. For example, if the operator zooms in on the first section 1802 of the display 1800, the displayed time interval 1810 will show a shorter time interval (and thus more granular details) across the first section 1802. It may be changed. Since the first section 1802 and the third section 1840 share a common time scale, the displayed time interval of the third section 1840 will be the modified displayed time interval of the first section 1802. Corresponding and may be automatically changed to match. Similarly, if the operator zooms out on the third section 1840, the displayed time interval 1810 is changed to show a longer time interval (ie, less granular details) across the third section 1840. May be. Accordingly, the displayed time interval of the first section 1802 may be automatically adjusted to correspond to and match the changed displayed time interval of the third section 1840.

  To further assist in easy defect analysis, in an embodiment, a different parameter or variable 1822 other than the currently presented parameter 1822a may be selected from the second section 1820 to be presented on the display 1800. Good. In embodiments, the operator may manually select different parameters or variables. For example, the operator may manually select different candidate factors from the set 1822, and at the time of manual selection, instead of the variable information corresponding to the factor 1822a displayed previously, the variable information corresponding to the parameter selected by the operator May be displayed in the third section 1840.

  In embodiments, different parameters or variables may be automatically selected. For example, the operator may move the common time indicator 1855 to a different time case, and different parameters or variables other than the variable 1822a (whose trend information is currently presented in the third section 1840) May have a higher contribution to the predicted defect 604. Accordingly, variable trend information corresponding to different parameters or variables may be automatically presented in section 1840 instead of variable trend information corresponding to previously presented variable 1822a. The variable trend information for different parameters or variables is common in the embodiment with the predicted defect information in the first section 1802 such that the first section 1820 and the third section 1840 maintain a common time scale. It may be presented consistently.

  In some embodiments, the variable trend information for different candidate factors may be presented simultaneously with the variable trend information for the currently displayed candidate factors. FIG. 20 shows such an example. In FIG. 20, the second parameter or variable 1822b (“simple_process / mixer_conc”) is selected in addition to the first parameter or variable 1822a. In response to selection of candidate factor 1822b, an additional section 1860 that is responsive to additional factor 1822b is presented on display 1800. Additional section 1860 may share a common time alignment and common time scale with both first section 1802 and third section 1840. Additional section 1860 may include variable trend information corresponding to candidate factor 1822b in a manner similar to that described above with respect to third section 1840. In the particular example depicted in FIG. 20, an additional section 1860 of display 1800 includes the latest variable curve 1862 corresponding to the measured variable value of “simple_process / mixer_conc”, the optimal, average or expected of “simple_process / mixer_conc”. Variable curve 1865 and corresponding deviation curves 1868 and 1870 are included.

  Note that any number of candidate factors (eg, process variables, process parameters, calculations, and / or other candidate factors) 1822 may be selected from second section 1820 for presentation in display 1800. I want. For example, 1, 2, 3, or more than four candidate factors may be selected from the second section 1820, and each additional section corresponding to the selected additional candidate factors is included on the display 1800. Also good. Each additional section may include variable trend information corresponding to each particular additional candidate factor, and each additional section includes a first section corresponding to the predicted defect 604 over the displayed time interval 1810. It may be consistent with 1802. Further, any common time indicator 1850, 1852, 1855 may extend to the entire display section of display 1800 that shares a common time alignment.

  If the number of additional sections displayed is limited by the physical dimensions of the user interface, in an embodiment, the user or operator may change the dimensions of one or more sections of display 1800 as desired. . Additionally or alternatively, the user or operator may provide a given number of variables or parameters and their corresponding additional sections for display in the first display of display 1800, and one or more subsequent displays of display 1800. Another given number of other variables or parameters and their corresponding additional sections may be selected for display. Typically, each different display of display 1800 may include a first section 1802 corresponding to a predicted defect 604, but that is not required.

  Moreover, in embodiments, a user or operator may select a particular section of display 1800 that is deleted from display 1800 (eg, section 1840 or section 1860). For example, if the operator analyzes a section displaying the parameter A variable trend information and then determines that the parameter A is not of interest to the operator, the operator displays a variable trend information section corresponding to the parameter A 1800. May be deleted from The section corresponding to parameter A may be deleted; however, parameter A may continue to be associated with the predicted defect 640 and / or the process in which the defect 640 is predicted to occur, so The indicator of A may continue to be maintained in the set of variables 1822 displayed in the second section 1820.

  FIG. 20 represents another exemplary function that may allow an operator or user to easily analyze and correlate candidate factors that may contribute to the predicted defect 604. . In the case illustrated by FIG. 20, the operator has selected a specific time case represented on sections 1802, 1840, 1860 by points 1872, 1875 and 1878, respectively. The operator indicated point 1872 by, for example, selecting point 1872, hovering over point 1872, or otherwise showing point 1872. In response to the operator indicator at point 1872, a window 1880 (eg, a pop-up window, a drop-down window, etc.) may be displayed in the corresponding section 1802. Window 1880 provides more detailed information (eg, one or more details) corresponding to the indicated point 1872, such as process information, batch name, recipe name, time stamp, and / or any other desired detail information. May be presented. In an embodiment, the detailed information displayed in the window 1880 includes at least a portion of the information included in the process information faceplate 730 of FIG. 7 and / or at least of the information included in the process information faceplate 1112 of FIG. Some may be included.

  In a similar manner, the operator may include points contained within the second section 1840 by selecting point 1875, hovering over point 1875, and / or otherwise indicating point 1875. 1875 may be indicated. In response to the indicator at point 1875, a window 1882 (eg, a pop-up window, a drop-down window, etc.) may be displayed in the corresponding section 1840. Window 1882 may include a measured value of a corresponding variable for a particular time case, a predicted value of the corresponding variable for a particular time case, a standard deviation of the corresponding variable for a particular time case, and / or any other More detailed information (eg, one or more details) corresponding to the variable or parameter corresponding to the indicated point 1875 may be presented, such as desired detailed information.

  In an embodiment, instead of displaying detailed information 1880, 1882, when the operator clearly or explicitly indicates a particular point 1872, 1875, respectively, it responds to an explicit indicator of the relevant point corresponding to the same particular time case. Detailed information may be displayed. For example, the operator may select point 1875 clearly or explicitly, and a window 1880 corresponding to point 1872 may be automatically presented on display 1800 upon explicit selection of point 1875.

  FIGS. 15, 16A-16F, FIGS. 17A-17B and FIG. 21 illustrate the exemplary OMS 102, exemplary controller 108, exemplary user interface 136, exemplary batch data receiver of FIGS. 402, exemplary analysis processor 114, exemplary analysis process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, exemplary display manager 420, exemplary session controller 422, exemplary FIG. 6 is a flow diagram of an example method that may be performed to implement an exemplary online data processor 116, an example web access server 428, and / or an example in-plant access server 424. The example methods of FIGS. 15, 16A-16F, FIGS. 17A-17B and / or FIG. 21 may be performed by a processor, controller, and / or any other suitable processing device. For example, the exemplary methods of FIGS. 15, 16A-16F, FIGS. 17A-17B and / or FIG. 21 include flash memory, CD, DVD, floppy disk, ROM, RAM, programmable ROM (PROM), electrical program Program code and / or in the form of a readable ROM (EPROM), an electrically erasable PROM (EEPROM), an optical storage disk, an optical storage device, a magnetic storage disk, a magnetic storage device, and / or a method or data structure Any tangible, such as a processor, a general purpose or special purpose computer, or any other medium accessible to the processor that may be used to carry or store instructions Recorded on non-transitory computer-readable storage medium Which may be embodied in a code instructions (e.g. example processor platform P10 is discussed below in connection with FIG. 18). Combinations of the above are also included within the tangible non-transitory computer readable storage medium.

  The methods include, for example, instructions and / or data that cause a processor, general purpose computer, special purpose computer, or special purpose processing machine to implement one or more specific methods. Alternatively, some or all of the exemplary methods of FIGS. 15, 16A-16F, 17A-17B, and / or FIG. 21 may include ASIC, PLD, FPLD, discrete logic, hardware, firmware, etc. It may be implemented using any combination.

  Also, some or all of the exemplary methods of FIGS. 15, 16A-16F, 17A-17B, and / or FIG. 21 may instead use any of the techniques described above, using manual operation. Any combination of these may be implemented, for example, any combination of firmware, software, discrete logic and / or hardware. Moreover, numerous other ways of implementing the exemplary operations of FIGS. 15, 16A-16F, 17A-17B, and / or 21 may be employed. For example, the order of execution of the blocks may be changed and / or one or more of the described blocks may be changed, eliminated, subdivided, or combined. Further, any or all of the exemplary methods of FIGS. 15, 16A-16F, FIGS. 17A-17B, and / or FIG. 21 may be performed by, for example, individual processing threads, processors, devices, individual logic, circuits, etc. It may be executed sequentially and / or in parallel.

  The example method 1500 of FIG. 15 models the relationship between measured variables, calculated variables, and / or overall quality variables based on features of the process control system. The plurality of exemplary methods 1500 may be performed in parallel or sequentially to model a portion of a process control system and / or to model other process control systems.

  The example method 1500 of FIG. 15 begins by identifying a field device in the process control system (block 1502). The example method 1500 can identify a field device by an identification serial number, a process control identification number, and / or any other identification method. The example method 1500 then identifies input to the field device (block 1504). Next, the example method 1500 identifies outputs from field devices and identifies measurement processes and / or quality variables associated with each output (block 1506).

  The example method 1500 continues by determining a quality variable calculated from the measured process variables and / or quality variables (block 1508). The example method 1500 then determines an overall quality variable for the process based on the measured and / or calculated variables (block 1510). The example method 1500 then calculates a relationship (eg, a contribution relationship) between the measured variable, the calculated variable, and / or the overall quality variable (block 1512). The relationship may be determined and / or modeled by the process model generator 412 of FIG. 4 using any multivariate analysis, statistical analysis, algebra analysis, process control history analysis, and / or optimization method. .

  The example method 1500 of FIG. 15 then determines a threshold value for each of the variables (block 1514). The example method 1500 may be any multivariate, statistical analysis discussed with reference to the process model generator 412 of FIG. 4 to determine variables calculated from measured variables and / or overall quality variables. Algebraic analysis, historical process analysis, and / or optimization methods and / or calculations may be used. Further, the exemplary method 1500 may include any multivariate analysis, statistical analysis, discussed with reference to the process model generator 412 of FIG. 4 to determine the relationship between the variables and their respective thresholds. Algebraic analysis, historical process analysis, and / or optimization methods and / or calculations may be used. After determining the thresholds, the exemplary method 1500 stores the variables, sources of values for each variable (eg, field devices), relationships between the variables, and / or threshold values for each variable in the process model database 414 of FIG. (Block 1516). Further, the example method 1500 determines a prediction model from the process control system and stores the prediction model in the database 414. Once the process control variables, thresholds, and / or relationships are stored, exemplary method 1500 ends.

  The example method 1600 of FIGS. 16A-16F generates and / or manages navigation between process control graphs and / or charts (eg, the graphs and / or charts 502-514 of FIGS. 5-14B). The example methods 1600 may be performed in parallel or sequentially to generate and / or navigate charts and / or graphs. Further, multiple example methods 1600 may be implemented for each session initiated by a process control operator. The example method 1600 begins when a process control operator opens a session and selects a process control environment, plant, and / or process control system. In addition, the example method 1600 may begin by displaying a summary chart (eg, the summary chart 502 of FIG. 6).

  The example method 1600 of FIG. 16A begins by receiving process control information from a controller (eg, the controller 108 of FIG. 1) (block 1602). Further, the example method 1600 may accumulate received process control information from previously received process control information associated with the same batch and / or process. The example method 1600 then determines a value associated with the measured value from the received process control information (block 1604). The example method 1600 then calculates a value that is calculated from a value associated with the measured variable and / or a value that is associated with the overall quality variable (block 1606). The example method 1600 stores values associated with the variables in the batch data database 416 (block 1608). The value may be stored by batch number and / or by stage within the batch based on the time when the value was generated by the field device (eg, using a timestamp).

  The example method 1600 continues by determining whether any of the values associated with the variable exceed a respective threshold (block 1610). If the one or more values exceed the respective thresholds, the example method 1600 indicates a process control defect corresponding to the one or more values exceeding the respective thresholds (block 1612). The example method 1600 then determines whether a graph selection has been received (block 1614). The selection of the graph may be performed by a process control operator. Further, if one or more values do not exceed their respective thresholds (block 1610), the example method 1610 determines whether a graph selection has been received (block 1614).

  If a graph selection has not been received, the example method 1600 continues to receive process control information (block 1602). However, if a graph selection is received, the example method 1600 may select a selected graph type (eg, microchart, sparkline, contribution graph, variable trend graph, process variation graph, and / or quality prediction). Graph) is determined (block 1614). Further, the example method 1600 may continue to receive process control information and / or include in the batch data the variable values received when the operator selects and views the graph.

  The example method 1600 continues on FIG. 16B when a process variation graph selection is received. The example method 1600 generates a display of a process variation graph that includes explained and / or unexplained variations associated with the selected variable (block 1616). Selected variables may include overall quality variables, measured variables, and / or calculated variables, and may correspond to defects detected by exemplary method 1600. Alternatively, the process variation graph may include a history of values and corresponding threshold values associated with the selected variable. The example method 1600 then displays the values for the explained and / or unexplained variations of the selected time and / or the latest received process control information (block 1618). For example, if the operator selects a defect from the overview chart, the exemplary method 1600 may display the explained variation value and / or the unexplained variation value associated with the time the defect was detected.

  The example method 1600 then determines whether a time selection on the process variation graph has been received (block 1620). The selection of the time may correspond to the operator selecting one point on the variation plot that corresponds to a certain process time. If example method 1600 receives a time selection, example method 1600 displays unexplained variation values and / or explained variation values associated with the selected time (block 1622). The example method 1600 then determines if a selection has been received to view the variable contribution to the variation (block 1624). Also, if a time selection on the process variation graph has not been received (block 1620), the example method 1600 determines if a selection has been received to view the variable contribution to the variation (block 1624).

  If no selection is received to view the variable contribution to the variation, the example method 1600 may determine whether the operator intends to continue analyzing the batch data (block 1626). For example, after viewing the process variation graph, the operator may determine that the process is acceptable and may wish to return to the overview chart display. If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue the batch analysis (block 1626), the operator may end the process and the example method 1600 ends.

  However, if a selection is received to view the variable contribution to the variation (block 1624) and the contribution is selected to be viewed in the microchart, the example method 1600 is shown in FIG. Continue by generating a microchart display that includes and / or quality variables (block 1628). The microchart may also display calculated quality variables. Further, the microchart may be displayed by the example method 1600 upon receiving a microchart selection (block 1614). The example method 1600 displays variable values in the microchart based on a time selection by an operator (block 1630). For example, the time selection may be the time associated with the process defect if the operator selects the process defect in the overview chart, and / or unexplained variation and / or explained variation in the process variation graph It may be the time selected for visually recognizing. When displaying the microchart, the example method 1600 determines if another time selection has been received (block 1632). Time selection may be done in the microchart by sliding the arrow along the timeline to the desired time of the process. Alternatively, the time selection may be made by selecting a point on the sparkline associated with a variable in the microchart.

  When the exemplary method receives a time selection, the exemplary method 1600 accesses values from the batch data database 416 corresponding to the selected time for each of the variables displayed in the microchart. (Block 1634). Alternatively, the value may already be included in the generated microchart. If the value is already included in the microchart (eg, a flash plug-in application), the example method 1600 updates the display of the microchart to show the value associated with the selected time.

  The example method 1600 then displays the values in a bar chart and / or sparkline associated with each of the displayed variables (block 1636). Next, the example method 1600 determines if a selection associated with at least one of the variables is received (block 1638). Further, if example method 1600 does not receive a time selection (block 1632), example method 1600 determines whether a selection associated with at least one of the sparklines of the variable has been received (block 1638). ).

  If the example method 1600 receives a selection of a variable in the sparkline, the example method 1600 of FIG. 16D generates a detailed display of the selected sparkline for the selected variable (block 1646). The example method 1600 may also generate a sparkline by receiving a graph selection from an operator (block 1614). The sparkline may start at the time from the start of the batch and end at the time associated with the latest batch data. Alternatively, the sparkline may indicate a period specified by the operator (eg, stage, action, specified times before and after the occurrence of a defect, etc.). The example method 1600 may then indicate any deviations and / or defects in any value in the sparkline that may exceed an associated threshold (block 1648).

  Next, the example method 1600 determines if a selection of points on the displayed sparkline has been received (block 1650). If a point has not been selected, the example method 1600 may determine whether the operator intends to continue analyzing the batch data (block 1652). If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue the batch analysis (block 1652), the operator can end the process and the example method 1600 ends. However, if the example method 1600 of FIG. 16D receives a selection of a point on the sparkline (block 1650), the example method 1600 may use a variable value associated with the time on the sparkline selected by the operator. May return to displaying a microchart containing (blocks 1654, 1628 and 1630).

  If the example method 1600 of FIG. 16C does not receive a sparkline selection (block 1638), the example method 1600 determines whether a selection of a variable displayed in the microchart bar chart has been received (see FIG. 16C). Block 1640). The example method 1600 of FIG. 16D determines a mean and / or standard deviation from previous batch data associated with a selected variable when a selection of the variable displayed in the bar chart is received. Continue (block 1656). The example method 1600 then generates a display of a variable trend graph for the selected variable that includes the mean and / or standard deviation determined from previous batch data (block 1658). The example method 1600 may also generate a variable trend graph by receiving a variable trend graph selection from an operator (block 1614). Next, the example method 1600 determines if a selection has been received to view the quality prediction graph (block 1660).

  If the quality prediction graph has not been selected, the example method 1600 may determine whether the operator intends to continue analyzing the batch data (block 1652). If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue batch analysis (block 1652), the operator may end the process and the example method 1600 ends.

  However, if a quality prediction graph is selected (block 1660), the example method 1600 continues to FIG. 16F. The quality prediction graph may also be selected by the operator in FIG. 16A (block 1614). Further, if exemplary method 1600 does not receive a selection of a variable in the bar chart (block 1640), but receives a selection to view the quality prediction graph in FIG. 16C (block 1642), the exemplary method 1600 continues to FIG. 16F.

  Alternatively, if the example method 1600 of FIG. 16B does not receive a selection to view the quality prediction graph (block 1642), the example method 1600 may indicate that the operator intends to continue analyzing the batch data. A determination may be made (block 1644). If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue batch analysis (block 1644), the operator may end the process and the example method 1600 ends.

  However, if the selection is not received to view the variable contribution to the variation and the contribution is selected to view in the contribution graph (block 1624), the example method 1600 of FIG. 16E is selected. Continue by calculating unexplained and / or explained variability of variables associated with defects over a period of time (block 1662). The explained variation may be calculated using T2 statistics, and the unexplained variation may be calculated using Q statistics. The selected time period may correspond to a time on the process variation graph and / or summary chart selected by the operator. The example method 1600 then generates a representation of a contribution graph that includes contributions of each described and / or unexplained variation of the associated variable (block 1664). Alternatively, the contribution graph may display the value associated with the variable contributing to the process defect, the average value of each value, and / or the standard deviation of each value.

  The example method 1600 continues by determining and displaying a recommendation action message (block 1666). The recommended action may include a correction that may be applied to the process control system to correct the detected defect. The example method 1600 then determines whether a time selection in the contribution chart has been received. The time section corresponds to the time in the current process. If a time selection is received, the explained variation and / or unexplained variation for the variable associated with the defect in the newly selected period is calculated (block 1662). If the example method 1600 does not receive a time selection, the example method 1600 determines if a selection of a variable in the contribution graph has been received (block 1670). If a variable selection is received, the exemplary method generates a variable trend graph for the selected variable (blocks 1656 and 1658 in FIG. 16D).

  However, if a selection of variables has not been received (block 1670), the example method 1600 determines if a selection has been received for viewing the quality prediction graph (block 1672). If a selection for viewing the quality prediction graph is received, the exemplary method generates the quality prediction graph of FIG. 16F. If a quality prediction graph has not been selected, the example method 1600 may determine whether the operator intends to continue analyzing the batch data (block 1684). If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue batch analysis (block 1674), the operator may end the process and the example method 1600 ends.

  If exemplary method 1600 receives a quality prediction graph (blocks 1614, 1642, 1660, 1672), the exemplary method continues to FIG. 16F by receiving a correction selection for a process defect. The process control operator can select a correction for the process defect by selecting a correction from the list of valid corrections or by entering the correction into the example method 1600. Alternatively, the example method 1600 may determine corrections for process defects from the correction models generated by the example OMS 102 of FIGS.

  The example method 1600 continues by predicting process quality when the selected remediation is applied to the process (block 1678). The example method 1600 includes any model determined by the process model generator 412 of FIG. 4 using any multivariate analysis, statistical analysis, algebra analysis, process control history data analysis, and / or optimization method and Process quality may be predicted using / or relationships. The predicted process quality may correspond to an overall quality variable, a calculated quality variation and / or a measured variable. Further, the example method 1600 may predict process quality based on a prediction process model generated by the example OMS 102. Next, the example method 1600 calculates confidence limits (eg, ranges) for the predicted quality (block 1680). The example method 1600 then displays a quality prediction graph that includes the predicted process quality and corresponding confidence limits (block 1682).

  The example method 1600 then determines if the remediation is implemented in the corresponding process control system (block 1684). If the correction is implemented, the example method 1600 transmits the correction to the process via the OMS 102 and / or the controller 108 (block 1686). By transmitting the correction, the process control system may receive instructions associated with the correction to change the operational characteristics of the field device associated with the correction. The example method 1600 then determines whether to continue batch analysis (block 1688). Further, if remediation is not implemented (block 1684), the example method 1600 determines whether batch analysis continues (block 1688). If the operator intends to continue batch analysis, the example method 1600 may display a process summary chart and continue to receive process control information (block 1602). If the operator does not intend to continue batch analysis (block 1688), the operator may abort the process and the example method 1600 ends.

  The example method 1700 of FIGS. 17A-17B determines corrective actions for detected process defects. The example method 1700 may be used to implement the example diagram 500 of FIG. Multiple example methods 1700 may be performed in parallel or sequentially to correct multiple process defects from a common process. Further, the plurality of exemplary methods 1700 may be implemented for defects detected by different processes. The example method 1700 begins when a process control operator logs into a workstation that includes a function for displaying a user interface (eg, the user interface 136 of FIG. 1).

  The example method 1700 of FIG. 17A begins by receiving a session start by a process control operator (block 1702). The example method 1700 then displays a user interface and queries the operator to select a process environment (block 1704). The example method 1700 receives a process environment selection from an operator (block 1706). Alternatively, the operator may select a plant, process control system, and / or multiple process control systems. The example method 1700 then generates and / or displays a summary chart associated with the selected process environment (block 1708). The example method 1700 then receives and processes measured variable values from the selected process control system, environment, and / or plant (block 1710).

  The example method 1700 continues by determining if there is a process defect detected (block 1712). A process defect may be a result of a variable that exceeds a threshold, a prediction that the variable exceeds a threshold, and / or a quality of the process that exceeds the threshold. If the example method 1700 determines that a defect has been detected, the example method continues to receive a measured variable value from the process control system (block 1710). However, if the example method 1700 detects a process defect, the example method 1700 indicates the detected defect in the overview chart (block 1714). Further, while the example method 1700 analyzes the variable value to determine the cause of the defect, the example method 1700 may continue to receive and / or process the process variable value.

  Next, the example method 1700 receives a selection of defects on the overview chart (block 1716). The example method 1700 then generates and / or displays a process variation graph associated with the detected defect (block 1718). Once the operator is able to verify information on the process variation graph, the example method 1700 may receive a selection of a time on the process variation graph (block 1720). The time selection may correspond to a point on the process variation graph where the variation exceeds the threshold during the detected defect. Upon receipt of the time selection, the example method 1700 determines whether the operator chooses to view contribution variables for variations in the microchart and / or contribution graph (block 1722).

  If the operator selects a microchart, the example method 1700 generates and displays a microchart that includes variables associated with the selected variation in the process variation graph (block 1724). The value associated with the variable may be present in a bar chart and / or sparkline in the microchart. While viewing the microchart, the operator may view a detailed display of the selected sparkline and / or change the time in the process corresponding to the displayed variable value.

  However, if the operator selects a contribution graph, the example method 1700 generates and displays a contribution graph that includes variables associated with the selected variation in the process variation graph (block 1726). The operator may select a graph by selecting the forward arrow in the process analysis section and / or select a tab to the corresponding graph in the user interface.

  Once the operator is able to view variable values in the microchart and / or contribution graph, the example method 1700 determines whether the operator has selected one or more variables in the microchart and / or contribution graph. (Block 1728). If a selection of at least one variable is received, the example method 1700 generates and / or displays a variable trend graph for each selected variable (block 1730). The example method 1700 then determines if a quality prediction graph selection has been received (block 1732). Further, if the operator has not selected a variable in the microchart and / or contribution graph, the example method 1700 determines if a selection of a quality prediction graph has been received (block 1732). The operator may choose to view the quality prediction graph by selecting the corresponding tab in the user interface and / or by selecting the quality prediction graph through the variable trend graph.

  If the example method 1700 did not receive a quality prediction graph selection, the example method 1700 may return to the overview chart and continue to receive and / or process the measured variable values (block 1710). ). However, if the example method 1700 receives a selection of a quality prediction graph (block 1732), the example method generates and / or displays a quality prediction graph (block 1734). Displaying the quality prediction graph 1700, the exemplary method determines whether remediation is implemented (block 1736). If the correction is implemented, the example method 1700 transmits the correction to the process via the OMS 102 and / or the controller 108 (block 1738). By transmitting the correction, the process control system may receive instructions associated with the correction to change the operational characteristics of the field device associated with the correction. The example method 1700 then determines whether to continue batch analysis (block 1740). Further, if remediation is not implemented (block 1736), the example method 1700 determines whether batch analysis continues (block 1740). If the operator intends to continue batch analysis, the example method 1700 may display a process summary chart and continue to receive process control information (block 1710). If the operator does not intend to continue batch analysis (block 1740), the example method stops the process (block 1742) and the example method 1700 ends.

  FIG. 21 illustrates an exemplary method 2000 for correlating candidate factors with predicted defects in a process control system. The method 2000 may be used with, for example, a process control system such as the system 110 of FIG. 1 or another process control system. In an embodiment, at least a portion of the method 2000 may be performed by an operations management system, such as the OMS 102 of FIG. 4 or some other suitable operations management system. The method 2000 is described below with reference to FIGS. 1, 4, 19 and 20 for illustrative (but not limiting) purposes.

  At block 2002, a value associated with a particular measured variable or parameter corresponding to a process controlled within the process control system may be obtained. In an embodiment, the process may be a batch process, and in another embodiment, the process may be a continuous process.

  At block 2005, a defect corresponding to the process may be predicted based on the value of the measured variable or parameter obtained at block 2002. For example, a defect may be predicted when a variation in the acquired value passes (eg, exceeds or falls below) a first threshold. In another example, a defect may be predicted based on a predicted process quality value (block 2005), where the predicted process quality value is the value of a measured variable or parameter obtained at block 2002. To be determined. For example, a defect may be predicted when the predicted quality of the process passes (eg, exceeds or falls below) a second threshold. In general, defects may be predicted using any of the techniques described above with reference to the evaluation process modeler 410 of FIG. 4 or using another suitable technique (block 2005). The predicted defects may be shown on a summary chart presented on a user interface in communication with the process control system, such as, for example, the summary chart 502 of FIG.

  At block 2008, a set of candidate factors corresponding to the predicted defect and / or process may be determined. In an embodiment, the candidate factors may include one or more measured variables or parameters corresponding to the process, and may include specific measured variables whose values were obtained at block 2002. In embodiments, the candidate factor may include one or more calculations based on one or more process parameters or variables. In some cases, the one or more calculations may be based on the values of one or more process parameters or variables over time. For example, the candidate factor may be a transition or change value in a calculated average value of one or more parameters, a transition or change value in a standard deviation of one or more parameter values, or a transition in frequency of variation in parameter values or A change value may be included. In some embodiments, a candidate factor that includes a transition or change in a calculated value may itself be based on time, eg, when a degree X transition occurs during time interval Y. Other candidate factors may be possible.

  Typically, but without limitation, each of the candidate factors may correspond to a model of the process. For example, the set of candidate factors may be determined by accessing the process model database 416 to invoke one or more variables or parameters corresponding to the model of the process.

  In an embodiment, each member index of the set of candidate factors determined at block 2008 may be displayed on the user interface. In an embodiment, each member's respective contribution to the predicted defect may be displayed on the user interface. In an embodiment, each member's respective deviation from a desired or average value may be displayed on the user interface. For example, FIG. 19 includes an exemplary section 1820 that presents an indicator for each member included in the set of candidate factors 1822, a corresponding contribution 1825 for each member, and a corresponding deviation 1828 for each member. A display 1800 of the display is shown. In an embodiment, the members of the set of candidate factors 1822 are selected by a user command or indicator, for example, “For a predicted defect, display all measured variables whose values each exceed the contribution of X”. May be.

  At block 2010, the predicted defect and the correlation of at least one candidate factor included in the set of candidate factors may be displayed or generated to be displayed on the user interface. The at least one displayed candidate factor may include a measured variable whose value was obtained at block 2002, or at least one displayed candidate factor is a specific measured value whose value was obtained at block 2002. One or more different candidate factors other than the variable may be included. In embodiments, the at least one candidate factor may be automatically or manually selected from the set of candidate factors determined at block 2008, and the correlation may be displayed or displayed based on the selection. May be generated (block 2010). In embodiments, the correlation may be displayed on a user interface in communication with the process control system, eg, at a local or remote workstation, computer, portable device in communication with the process control system.

  In an embodiment, the correlation considered for block 2010 may be a time-based correlation. In an embodiment, the time-based correlation may include a first graphical representation that corresponds to the predicted defect (eg, a first graph or other suitable graphical representation) and a second graphical representation that corresponds to the candidate factor (eg, , A second graph or other suitable graph representation). For example, FIG. 19 shows a first graphical representation (eg, first section 1802) corresponding to the predicted defect 604 and a second graphical representation (eg, third section 1840) corresponding to the measured variable 1822a. ) Represents an exemplary embodiment.

  The first graph representation and the second graph representation may be aligned with a time case (eg, a time case indicated by reference 1850, 1852, or 1855 in FIG. 19). In an embodiment, the first graphical representation and the second graphical representation may be aligned over the entire displayed time interval (eg, the displayed time interval 1810), so that their entire respective time axis is May share a common time scale.

  In an embodiment, the correlation between the predicted defect and the at least one measured variable or parameter (block 2010) may include a correlation between the predicted defect and two or more candidate factors. Therefore, each graph representation corresponding to each candidate factor may be displayed simultaneously with the graph representation corresponding to the predicted defect. In the example shown, FIG. 20 represents two graph representations 1840 and 1860 corresponding to two candidate factors, each graph representation 1840, 1860 corresponding to the value of a different measured variable (1822a, 1822b). Includes a graph over time. Both graphical representations 1840 and 1860 are illustrated as being presented simultaneously on the display 1800 with a graphical representation 1802 corresponding to the predicted defect 604. Of course, any number of additional graphical representations corresponding to any number of candidate factors may be displayed simultaneously. In an embodiment, all representations of the graph representation corresponding to each candidate factor are displayed in a particular time case (eg, as indicated by a common indicator 1850, 1852 or 1855) and / or the entire display. It may be aligned in time, such as over a time interval 1810. In an embodiment, one of the displayed graph representations may correspond to a measured variable whose value was obtained in block 2002, and in an embodiment, the displayed graph representation is a value that blocks It may not correspond to the measured variable obtained at 2002 at all.

  In an embodiment, the method 2000 may include optional blocks 2012-2018. At block 2012, the method 2000 changes an indication (eg, a “goal” graph representation or a “goal” graph display to change or adjust the display of one of the graph representations or graphs presented on the user interface. Receiving an indicator). In an embodiment, an indicator for changing or adjusting the target graph representation may be generated by a user or an operator. The target graph representation may be, for example, a graph representation corresponding to the predicted defect (eg, section 1802 of FIG. 20), or the target graph representation may be a graph representation corresponding to one of the candidate factors ( For example, it may be section 1840 or 1860) of FIG. For example, corrections or adjustments move the displayed time interval forward or backward in time, expand the target graph representation to expand the details of the displayed time interval, or display the displayed time It may correspond to a request to reduce the target graph representation so that the details of the interval shrink.

  Based on the received indication of the first modification or adjustment (block 2012), the display of the target presentation on the user interface may be adjusted accordingly (block 2015). Also, based on the received indication of the first modification or adjustment (block 2012), other graph representations have been changed and displayed relative to other graph representations presented simultaneously on the user interface. Subsequent corrections or adjustments may be made so as to remain in time alignment with the target graph representation changed over the entire time interval (block 2018).

  In an embodiment, the method 2000 may include optional blocks 2020-2022. At block 2020, a user selection, user mouse over, or some other user indication may be received for the displayed graph representation or a particular point included on the graph. In response to receiving a user indication of a particular point (block 2020), details corresponding to the indicated point and / or related point may be displayed, such as a pop-up window, drop-down window, or the like. Good (block 2022). For example, if the indicated point is included on a variation curve that corresponds to the measured variable, the details displayed are: timestamp, latest measured value, forecast, optimal or average value, deviation from average value And / or any other desired details. In another example, if the indicated point is included on the predicted process quality curve, the displayed details may include a timestamp, batch identification, recipe name, and / or any other desired detail information. is there. In an embodiment, the one or more details corresponding to the relevant points on the display do not explicitly and clearly indicate the points that the user is concerned with, but explicitly indicate certain points (block 2020). May also be presented (block 2020). For example, one or more details corresponding to a point of interest may be selected if a particular time case corresponding to the relevant point is selected (block 2020), or another point of the same particular case in time is selected. (Block 2020), it may be automatically presented on the display (2022).

  FIG. 18 is a block diagram of an example processor system P10 that may be used to implement the example methods and apparatus described herein. For example, a processor system similar or identical to exemplary processor system P10 may include exemplary OMS 102, exemplary batch data receiver 402, exemplary analysis processor 114, exemplary analysis of FIGS. 1 and / or FIG. Process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, exemplary display manager 420, exemplary session controller 422, exemplary online data processor 116, exemplary in-plant access server 424 and / or may be used to implement an exemplary web access server 428. Exemplary processor system P10 is described below as including a plurality of peripherals, interfaces, chips, memories, etc., one or more of which are an exemplary OMS 102, exemplary batch data reception 402, exemplary analysis processor 114, exemplary analysis process modeler 408, exemplary evaluation process modeler 410, exemplary process model generator 412, exemplary display manager 420, exemplary session controller 422, exemplary Omitted from other exemplary processor systems used to implement one or more of exemplary online processor 116, exemplary in-plant access server 424, and / or exemplary web access server 428. Also good.

  As shown in FIG. 18, the processor system P10 includes a processor P12 coupled to an interconnection bus P14. The processor P12 is represented entirely on-chip in FIG. 18 but alternatively completely or partially off-chip, via a dedicated electrical connection and / or via the interconnection bus P14 to the processor P12. It includes a register set or register space P16 that may be directly linked. The processor P12 may be any suitable processor, processing device, or microprocessor. Although not shown in FIG. 18, the system P10 may be a multiprocessor system, and thus is one or more additional ones that are the same or similar to the processor P12 and communicatively coupled to the interconnect bus P14. A processor may be included.

  The processor P12 of FIG. 18 is coupled to a chipset P18 that includes a memory controller P20 and a peripheral input / output (I / O) controller P22. As is well known, a chipset typically has I / O and memory management functions and a plurality of general purpose and / or dedicated registers accessible or used by one or more processors coupled to chipset P18. Provides a timer and the like. The memory controller P20 implements functions that allow the processor P12 (or multiple processors if there are multiple processors) to access the system memory P24 and the mass storage memory P25.

  The system memory P24 includes any type of volatile and / or nonvolatile memory such as, for example, static random access memory (SRAM), dynamic random access memory (DRAM), flash memory, read only memory (ROM), and the like. It's okay. The mass storage memory P25 may include any desired type of mass storage device. For example, if the exemplary processor system P10 is used to implement the OMS 102 (FIG. 2), the mass storage memory P25 may include a hard disk drive, an optical drive, a tape storage device, and the like. Alternatively, if the exemplary processor system P10 is used to implement the process model database 416 and / or the batch data database 406, the mass storage memory P25 is solid state memory (eg, flash memory, RAM memory, etc.). ), Magnetic memory (eg, hard drive), or any other memory suitable for mass storage within the process model database 416 and / or the batch data database 406.

  Peripheral I / O controller P22 has functions that allow processor P12 to communicate with peripheral input / output (I / O) devices P26 and 28 and network interface P30 via peripheral I / O bus P32. carry out. The I / O devices P26 and P28 are, for example, a keyboard, a display (for example, a liquid crystal display (LCD), a cathode ray tube (CRT) display, etc.), a navigation device (for example, a mouse, a trackball, a capacitive touch pad, a joystick, etc.) Any desired type of I / O device. The network interface P30 enables the processor system P10 to communicate with another processor system, such as an Ethernet device, an asynchronous transfer mode (ATM) device, an 802.11 device, a DSL modem, a cable modem, a cellular modem, etc. There may be.

  The memory controller P20 and the I / O controller P22 are represented in FIG. 18 as independent functional blocks within the chipset P18, but the functions performed by these blocks may be integrated within a single integrated circuit. Or may be implemented using two or more independent integrated circuits.

  At least some of the exemplary methods and / or apparatus described above are implemented by one or more software and / or firmware programs running on a computer processor. However, dedicated hardware implementations, including but not limited to application specific integrated circuits, programmable logic arrays, and other hardware devices, are similarly described herein either in whole or in part. Considered to implement some or all of the illustrated exemplary methods and / or apparatus. Further, alternative software implementations including, but not limited to, distributed processing or component / object distributed processing, parallel processing, or virtual machine processing also implement the exemplary methods and / or systems described herein. May be considered to.

  Also, the exemplary software and / or firmware implementations described herein can be a magnetic medium (eg, magnetic disk or tape), a magneto-optical or optical medium such as an optical disk, or a memory card or one or more reads. Note that it is stored on a tangible storage medium, such as dedicated (non-volatile) memory, random access memory, or other package containing other rewritable (volatile) memory. Accordingly, the example software and / or firmware described herein can be stored on a tangible storage medium, such as the above or next generation storage media. While the above specification describes exemplary components and functions with reference to specific standards and protocols, it should be understood that the scope of this patent is not limited to such standards and protocols. For example, Internet and other packet switched network transmissions (eg, Transmission Control Protocol (TCP) / Internet Protocol (IP), User Datagram Protocol (UDP) / IP, Hypertext Markup Language (HTML), Hypertext Transfer Protocol ( Each of the HTTP)) standards represents an example of the state of the art. Such standards are regularly replaced by faster or more efficient equivalents with the same general purpose functionality. Accordingly, alternative standards and protocols having the same functions are equivalent, are contemplated by this patent, and are intended to be included within the scope of the appended claims.

  Further, although this patent discloses exemplary methods and apparatus that include software or firmware running on hardware, such systems are merely illustrative and should not be considered as limiting. I want to be. For example, any or all of these hardware and software components may be in hardware only, only in software, only in firmware, or of hardware, firmware and / or software. It is contemplated that it can be embodied in any combination. Thus, while the above specification describes exemplary methods, systems, and machine-accessible media, the examples are not the only way to implement such systems, methods, and machine-accessible media. Thus, although certain exemplary methods, systems, and machine-accessible media are described herein, the scope of this patent is not limited thereto. Rather, this patent is directed to all methods, systems, and machine-accessible media that fall within the scope of the appended claims, either verbatim or under equivalence. By way of example and not limitation, the disclosure herein contemplates at least the following aspects.

  A method of correlating a candidate factor with a predicted defect in a process control system, comprising:

  Obtaining a value associated with a particular factor corresponding to the process being controlled in the process control system;

  The predicted quality of the process, determined based on a value associated with a particular factor, when the predicted quality of the process exceeds a first threshold or when a variation in the value of a particular factor is Predicting defects corresponding to the process at least at one of the times when the threshold of 2 is exceeded;

  Determining a set of candidate factors corresponding to the predicted defect, including a specific factor;

  Displaying at least one candidate factor of the set of candidate factors and a predicted defect correlation on a user interface of a computing device in communication connection with the process control system.

  The method of the foregoing aspect, further comprising receiving an indication of selection of at least one candidate factor, wherein displaying the correlation with the at least one candidate factor and the predicted defect is based on the received indicator.

  Displaying the correlation between at least one candidate factor and the predicted defect comprises displaying a correlation between two or more candidate factors and the predicted defect of the set of candidate factors. Either way.

  The method of any of the preceding aspects, further comprising simultaneously displaying a correlation, an indication of each member of the set of candidate factors corresponding to the predicted defect, and a respective contribution of each member to the predicted defect .

  The method of any of the preceding aspects, wherein displaying the correlation between the at least one candidate factor and the predicted defect comprises displaying a time-based correlation of the at least one candidate factor and the predicted defect. .

  Displaying on the user interface at least one candidate factor and the time-based correlation of the predicted defect is a first graphical representation corresponding to the predicted defect and at least one candidate factor on the user interface. Simultaneously displaying a second graph representation corresponding to, wherein the specific time case shown on the first graph representation is on the user interface with the specific time case shown on the second graph representation and The method of any of the preceding aspects being matched.

  The method of any of the preceding aspects, further comprising indicating a particular time instance by displaying a common indicator across the first graph representation and the second graph representation.

  The method of any of the preceding aspects further comprising aligning the first graph representation and the second graph representation according to a common time scale.

  Receiving a user indication for modifying the display of the first graph representation and maintaining a time alignment between the display of the first graph representation and the display of the second graph representation displayed on the user interface Adjusting the display of the first graph representation and the display of the second graph representation based on a user indicator. The method of any of the preceding aspects.

  The method further includes displaying at least one detail corresponding to a point included on the first graph representation or included on the second graph representation, wherein displaying the at least one detail is a point user. The method of any of the preceding aspects occurring in response to a selection or point user mouse over.

  The method of any of the preceding aspects, wherein obtaining a value associated with a particular factor corresponding to a process includes obtaining a value of a particular measured variable corresponding to the process.

  The method of any of the preceding aspects, wherein obtaining a value associated with a particular factor corresponding to a process includes obtaining a calculated value based on a value of a parameter corresponding to the process.

  Obtaining a calculated value based on the parameter value includes obtaining a value corresponding to a change to an average value corresponding to the parameter, obtaining a value corresponding to a change to a standard deviation corresponding to the parameter, Alternatively, the method of any of the preceding aspects, comprising at least one of obtaining a value corresponding to a frequency transition of parameter value variation.

  An apparatus for correlating factors contributing to predicted defects in a process control system, wherein the apparatus is configured to perform any of the foregoing aspects;

  A computing device in communication connection with a batch data receiver, the batch data receiver communicatively coupled to a process control system and associated with a particular factor corresponding to a process controlled by the process control system The computing device includes a processor and memory, the memory comprising:

  The predicted quality of the process when the predicted quality of the process determined based on the value associated with the specific factor exceeds a first threshold or when the variation of the value of the specific factor is a second Predicting defects occurring in the process control system at least one of the times when the threshold is exceeded;

  Determining a set of candidate factors, including a specific factor,

  Storing computer-executable instructions that are executable by the processor to cause a representation of a correlation between the predicted defect and at least one candidate factor of the set of candidate factors to be displayed on the user interface; apparatus.

  Any of the preceding aspects further comprising additional computer-executable instructions stored on a memory of the computing device and executable by the processor to receive an indication of selection of at least one candidate factor. Equipment.

  The apparatus of any of the preceding aspects, wherein the at least one candidate factor comprises two or more candidate factors.

  The apparatus of any of the preceding aspects, wherein the correlation between the predicted defect and the at least one candidate factor comprises a time-based correlation of the predicted defect and the at least one candidate factor.

  A representation of the correlation between the predicted defect and the at least one candidate factor is

  A first graph corresponding to the predicted defect; and a second graph corresponding to at least one candidate factor, the second graph being displayed simultaneously with the first graph on the user interface. The apparatus of any of the preceding aspects, wherein the time axis of the first graph and the time axis of the second graph are presented consistently over the displayed time interval on the user interface.

  The apparatus of any of the preceding aspects, wherein the representation of the correlation further comprises an indicator of a particular time instance, wherein the indicator is displayed across the first graph and the second graph.

  The apparatus of any of the preceding aspects, wherein the indicator of the particular time instance is movable over the displayed time interval.

  Executable by a processor to present a correction to a representation of a correlation between a predicted defect stored on a memory of a computing device and displayed on a user interface and at least one candidate factor; Further comprising instructions executable on the computer, the modification being a first adjustment to one of the first graph or the second graph, based on a user indicator, to the displayed time interval A first adjustment including a correction and a second adjustment to the other of the first graph or the second graph, corresponding to the correction of the displayed time interval based on the first adjustment; And the second adjustment. The apparatus of any of the preceding aspects.

  The at least one candidate factor comprises two or more candidate factors, and the representation of the correlation between the predicted defect and the two or more candidate factors is a first graph corresponding to the predicted defect, and 2 The apparatus of any of the preceding aspects, comprising a respective graph corresponding to each candidate factor of the one or more candidate factors, wherein each respective graph is presented simultaneously with the first graph on the user interface.

  The apparatus of any of the preceding aspects, wherein the particular factor is a particular measured variable.

  The apparatus of any of the preceding aspects, wherein the value associated with the particular measured variable is the value of the particular measured variable.

  The value associated with a particular measured variable is based on the value of the particular measured variable and is at least one of calculating a mean value transition, calculating a standard deviation change, or calculating a variation frequency transition. The apparatus of any of the preceding aspects being a calculated value, including one.

  A system for correlating factors contributing to predicted defects in a process control system, comprising any of the foregoing aspects,

  A batch data receiver configured to receive process control information corresponding to a process controlled in a process control system, wherein the process control information includes a value associated with a particular factor;

  Communicating with a batch data receiver to execute computer-executable instructions on the user interface to present a display of correlations between predicted defects corresponding to the process and specific factors A configured processor, wherein the predicted defect is determined based on at least a portion of the process control information, and the display is a first section corresponding to the predicted defect and a second corresponding to the specific factor. A specific time case shown in the first section is consistent with the specific time case shown in the second section on the display.

  The system of any of the preceding aspects, wherein the first section includes a graph over time corresponding to the predicted defect, and the second section includes a graph over time corresponding to a particular factor.

  The system of any of the preceding aspects, wherein the time axis corresponding to the first section and the time axis corresponding to the second section are scaled consistently.

  The display further includes at least one other section corresponding to each at least one other factor, and the particular time case shown in the at least one other section is shown in the first section on the display The system of any of the preceding aspects consistent with a particular time case.

  The processor is configured to execute additional computer-executable instructions to make corrections to the presentation of the display, wherein the correction is a first adjustment to the first section and includes a user indication A first adjustment, including a correction to the displayed time interval of the first section, and a second adjustment to the second section, based on the first adjustment, A system according to any of the preceding aspects, comprising a second adjustment, including a modification of the displayed time interval of the second section, to accommodate a change in the displayed time interval.

  The display is an indicator of one or more members of a set of candidate factors, where the set of candidate factors corresponds to a process and includes a specific set of indicators and a set of predicted defects. The system of any of the preceding aspects further comprising a third section that includes an indication of the respective contribution of each of the one or more members of the candidate factor.

  The system of any of the preceding aspects, wherein the particular factor is at least one of a measured parameter corresponding to the process or a calculation based on a value of the measured parameter corresponding to the process.

  The system of any of the preceding aspects, wherein the calculation corresponds to a mean, standard deviation, or frequency of variation.

Claims (18)

A method of correlating a candidate factor with a predicted defect in a process control system, comprising:
Obtaining a value associated with a particular factor corresponding to a process controlled in the process control system;
The quality determined based on the predicted value of the process and associated with the specific factor exceeds a first threshold, or the variation of the value of the specific factor exceeds a second threshold Predicting a defect corresponding to the process at at least one of the times;
Determining a set of candidate factors corresponding to the predicted defect, the set including the specific factors;
On the user interface of a computing device in communication connection with the process control system, and at least one candidate agent of the set of candidate agent, the method comprising: displaying the correlation between the predicted fault Displaying the correlation as a quality prediction graph showing the overall quality effect of the process of adjusting the at least one candidate factor;
Including the method. Wherein further comprising receiving an indication of selection of at least one candidate agent, wherein the displaying the correlation of at least one candidate agent and the predicted fault is-out based on the received index,
If the adjustment of the at least one candidate factor is predicted to improve the overall quality of the process within a certain threshold, the adjustment of the at least one candidate factor is performed automatically. The method of claim 1.   Displaying the correlation of the at least one candidate factor and the predicted defect includes displaying a correlation of two or more candidate factors of the set of candidate factors and the predicted defect. 3. A method according to claim 1 or claim 2.   2. The method further comprising simultaneously displaying the correlation, an indication of each member of the set of candidate factors corresponding to the predicted defect, and a respective contribution of each member to the predicted defect. The method according to claim 3.   2. The displaying of the correlation of the at least one candidate factor and the predicted defect comprises displaying a time-based correlation of the at least one candidate factor and the predicted defect. Item 5. The method according to any one of Items4.   6. The method of any of claims 1-5, wherein obtaining the value associated with the particular factor corresponding to the process comprises obtaining a value of a particular measured variable corresponding to the process. 2. The method according to item 1.   7. The method of claim 1, wherein obtaining the value associated with the particular factor corresponding to the process includes obtaining a calculated value based on a parameter value corresponding to the process. 2. The method according to item 1. An apparatus for correlating candidate factors contributing to predicted defects in a process control system,
A computing device communicatively connected to a batch data receiver, the batch data receiver communicatively coupled to the process control system and associated with a particular factor corresponding to a process controlled by the process control system Configured to receive a value, the computing device includes a processor and a memory, the memory comprising:
When the quality of the process determined and determined based on the value associated with the specific factor exceeds a first threshold, or when the variation of the value of the specific factor exceeds a second threshold Predicting defects occurring in the process control system at at least one of the following:
Determining a set of candidate factors comprising the specific factor; and
Of the predicted defect and the set of candidate factors to be displayed on a user interface in a quality prediction graph that indicates an overall quality effect of the process of adjusting the at least one candidate factor Expressing a correlation between at least one candidate factor of
An apparatus for storing computer-executable instructions that are executable by the processor to perform:   The apparatus of claim 8, wherein the correlation between the predicted defect and the at least one candidate factor comprises a time-based correlation of the predicted defect and the at least one candidate factor. The representation of the correlation between the predicted defect and the at least one candidate factor is a first graph corresponding to the predicted defect;
A second graph corresponding to the at least one candidate factor, the second graph being displayed simultaneously with the first graph on the user interface,
10. The apparatus according to claim 8 or claim 9, wherein the time axis of the first graph and the time axis of the second graph are presented consistently over the displayed time interval on the user interface. .   The apparatus of claim 10, wherein the representation of the correlation further comprises an indicator of a particular time instance, wherein the indicator is displayed across the first graph and the second graph.   The apparatus of claim 11, wherein the indicator of the particular time instance is movable over the displayed time interval. The specific factor is specific variables, device according to any one of claims 8 to claim 12. Wherein the values specified associated with variable, said a specific value of variable A device according to claim 13. The value associated with the particular variable is based on the value of the particular variable, and the calculation of the transition of the average value, at least one of the calculation of the calculation of the standard deviation changes, or the oscillation frequency changes The apparatus of claim 13, wherein the apparatus is a calculated value. A system for correlating factors contributing to predicted defects in a process control system,
A batch data receiver configured to receive process control information corresponding to a process controlled in the process control system and including a value associated with a particular factor;
Communicatively connecting with the batch data receiver and displaying on a user interface a correlation between a predicted defect corresponding to the process and determined based on at least a portion of the process control information and the particular factor. A processor configured to execute computer-executable instructions to make a presentation, the display comprising:
A first section corresponding to the predicted defect;
A processor including a second section corresponding to the particular factor,
The particular time case shown in the first section is the second section in the quality prediction graph showing the overall quality effect of the adjustment of the at least one candidate factor on the display. A system that is consistent with the specific time case shown in FIG. The processor is configured to execute additional computer-executable instructions to make modifications to the presentation of the display,
A first adjustment to the first section, wherein the first adjustment includes a correction to the displayed time interval of the first section based on a user indicator;
A second adjustment to the second section, the second adjustment corresponding to the correction of the displayed time interval of the first section based on the first adjustment. And a second adjustment comprising a modification of the displayed time interval of the second section. The display is
An indicator of one or more members of a set of candidate factors corresponding to the process and including the particular factor;
An indication of the respective contribution of each of the one or more members of the set of candidate factors to the predicted defect;
18. The system of claim 16 or claim 17, further comprising a third section comprising: