WO2016099451A9

WO2016099451A9 - Method and apparatus for case management foresight and insight

Info

Publication number: WO2016099451A9
Application number: PCT/US2014/070482
Authority: WO
Inventors: David Sean FARRELL; Brian Scott COURTNEY; Sunil Mathur
Original assignee: Ge Intelligent Platforms, Inc.
Priority date: 2014-12-16
Filing date: 2014-12-16
Publication date: 2017-02-02
Also published as: WO2016099451A1

Abstract

Approaches are provided where, at a local computing device, time series data is received from an industrial component and automatically converted to a format readable by an analytic system. The time series data is transmitted to the analytic system and processed to identify at least on anomaly associated with the industrial component. A resolution is then determined to address the anomaly based on information accessible by the analytic system. A local computing device is notified of the presence of the anomaly, and the resolution is transmitted to the local computing device.

Description

METHOD AND APPARATUS FOR CASE MANAGEMENT FORESIGHT AND

INSIGHT

BACKGROUND OF THE INVENTION

FIELD OF THE INVENTION

[0001] The subject matter disclosed herein generally relates to remote-equipment monitoring,

BRIEF DESCRIPTION OF THE RELATED ART

[0002] In industrial control operations, equipment is monitored to ensure proper operation and/or detect anomalies which may arise. The monitoring devices may include both edge devices, local components running at a customer's location, in cooperation with remote computing components used to analyze data and provide operating or repair guidance. These remote computing components are oftentimes "cloud-based" devices allowing any number of edge devices to be communicatively coupled thereto.

[0003] Upon detecting an issue with the operation of the industrial system,

troubleshooting procedures are typically employed by end users. In some environments, there may be numerous identical components which may have experienced problems and/or failures at some point. End users tasked to address these problems may lack the requisite skill to understand the problems occurring in the system and thus may not properly address and/or fix the anomaly. Further, operators may lack an understanding of the system architecture and how the particular component fits into this architecture. Providing training for a number of operators to address problems may be costly and time-consuming.

[0004] In many of these industrial environments, tendencies exist with regards to anomalies and particular components. These trends, however, are oftentimes only known by a few skilled analysts or operators and may not be fully understood by the majority of individuals tasked with addressing problems with components and/or systems.

[0005] Some present approaches offer client support, but issues are oftentimes managed on a case-by-case basis in which an individual may be tasked with determining trends and/or related issues. The compilation of cases and their resolution is oftentimes limited to a single analyst's experience and their ability to expose solutions to end users. This may require a substantial amount of time and individual effort on the part of the analyst. Other present approaches detect anomalies in customer assets and produce an advisory which is accessed by an individual (e.g., a reliability engineer) to determine whether a case should be opened and/or discussion with the user or client should occur. These analysts must categorize and annotate expert analysis into a comprehensive package to deliver to the end customer, which may be exceedingly time consuming,

[0006] The above-mentioned problems have resulted in some user dissatisfaction with previous approaches.

BRIEF DESCRIPTION OF THE INVENTION

[0007] The approaches described herein provide systems and related methods ihai allow for analytics to be provided to system operators upon detection of a particular anomaly or anomalies. These approaches extend beyond simply providing information regarding detected anomalies, but also extend to assist users in understanding the issue they are facing and offer guidance regarding possible solutions. Based partially on analytics performed at a remote computing environment, a user may receive preeonfigured instructions on how to address and correct issues.

[0008] These approaches also provide for a "foresight" analysis in which based on a combination of received data and information stored in a knowledge base, the remote computing device may inform an operator of upcoming issues to be addressed before they present themselves in obvious daia or alarms. When an analytic in the remote processing device detects this anomaly, it may also look to a knowledge base consuming information from various sources regarding the components in the system. The remote processing device may then offer an analysis pack to the operator with clear information and instructions to preemptively address any issues detected in the system.

[0009] By combining comprehensive case analytics with remote predictive analytic functions, improved system operator and/or analyst efficiencies may be realized due to a decrease in the amount of time required to troubleshoot an issue or number of issues with components. Further, users of varying levels of experience may access expert analysis based on their past experiences and knowledge to optimally perform maintenance decisions. By maintaining a database of known issues, analysis may create templates or standard procedures to address problems, thus resulting in faster resolution of issues and reduced system down time. This in turn may lead to increased system productivity and profitability.

[0018] By using the systems described herein, users may provide an initial mapping and remedying procedures on the edge device that is based on preexisting know ledge of the system. These procedures may be based in part on expert analysis and may be determined to be the most efficient processes for addressing issues or anomalies within the system. In the event that an anomaly does occur in an identical or similar manner as what was initially described, the analytical device may alert the user of the presence of the anomaly and provide the user with the predetermined remediating measures. As such, operator efficiencies may be greatly increased, as extraneous observation and decision making is no longer required.

[0011] Through these approaches, not only is foresight added to the control system, but insight is also offered such that the operator has viable solutions to apply to their situation. A learning mechanism located at the remote processing device gathers information and data of actions being taken and their corresponding success rate is used to assist in determining viable solutions.

[0012] m many of these embodiments, approaches are provided where, at a local computing device, time series data is received from a piece of industrial equipment and is automatically converted to a format that is readable by an analytic system. The time series data is then transmitted to the analytic system.

[0013] At the analytic system, the time series data is then processed and at least one anomaly associated with the industrial component is identified. The analytic system may then determine a resolution to address the anomaly. The analytic system may use information accessible by the analytic system to assist in determining the resolution.

[0014] The approaches then notify the local computing device of the presence of the anomaly and transmit the resolution to the local computing device. The user or operator may- then proceed with addressing the anomaly as specified by the resolution.

[001 S] In some approaches, the time series data is transmitted to a remote processing device. This remote processing device may be a remote networking device located in the cloud. In yet other examples, the analytic system may include an analytic system blueprint which includes diagnostic steps and resolutions based on historical information provided by users. A user may manually provide this information upon initializing the system or at any- other time during the system's operation. The analytic system blueprint may also include preferred resolutions which have an indication of a high success rate of addressing the anomaly.

[0016] In some of these approaches, the time series data is periodically transmitted as specified by the analytic system blueprint to provide a current, up-to-date analysis.

[0017] In many of these embodiments, a case management apparatus is provided and includes an interface with an input and an output and a processor coupled to the interface. The processor is configured to receive converted time series data from an industrial component that is readable by the analytic system.

[0018] The processor is further configured to process the time series data and identify at least one anomaly associated with the industrial component. The processor also determines a resolution to address the anomaly based on information accessible by the analytic system and notify the local computing device of the presence of the anomaly. The processor is also configured to transmit the resolution to the local computing device.

BRIEF DESCRIPTION OF THE DRAWINGS

[0019] For a more complete understanding of the disclosure, reference should be made to the following detailed description and accompanying drawings wherein:

[0020] FIG. 1 comprises a block diagram illustrating an exemplary system for case management foresight and insight according to various embodiments of the present invention; and

[0021] FIG. 2 comprises an operational flow chart illustrating an approach for case management foresight and insight according to various embodiments of the present invention.

[0022] Skilled artisans will appreciate that elements in the figures are illustrated for simplicity and clarify. It will further be appreciated that certain actions and/or steps may be described or depicted in a particular order of occurrence while those skilled in the art will understand that such specificity with respect to sequence is not actually required. It will also be understood that the terms and expressions used herein have the ordinary meaning as is accorded to such terms and expressions with respect to their corresponding respective areas of inquiry and study except where specific meanings have otherwise been set forth herein.

DETAILED DESCRIPTION OF THE INVENTION

[0023] Approaches are provided that overcome time consuming and expensive case management and remediation procedures obtained from industrial systems and local or edge devices to remote analytic systems and their corresponding analysts. In one aspect, upon automatically detecting an anomaly and determining an appropriate response, an electronic message may be transmitted to an end user containing an analysis package (e.g., a blueprint that includes a framework in which the end user may perform additional investigation and/or remediation) which may be downloaded to the local device. By "automatic" and as used herein, it is meant without user intervention or involvement. The end user is guided while observing what is occurring within the system and may be provided with further assistance as additional insights are gathered. As such, the analysis package or case may be used as a communication vehicle between remote analysis and end users or operators.

[0024] The analytic system may automatically access a knowledge base containing information on how to remedy or address the anomaly derived from various sources. For example, an end user may directly provide remediation information during the initial setup of the system. Alternatively, the end user may provide remediation information at a later stage as more information pertaining to the control system is known. The end user may map this information to a format that is readable by the analytic system framework.

[0025] The knowledge base may also include a historical information relating to the system as well as information obtained from other similar industrial systems. This knowledge base may perform a statistical analysis of best practices to determine appropriate corrective measures. This knowledge base may be periodically updated to provide an end user with the best solution.

[0026] As a result of these approaches, the user may then address the problem as described by the analytic system.

[0027] Referring now to FIG. 1, one example of a system 100 for case management foresight and insight is described. The system 100 includes an apparatus 102 which includes an interface 104 having an input 106 and an output 108, a processor 1 10, and a memory 1 12 which includes an analytic blueprint 1 13. The apparatus 102 may be stored on a cloud-based network 120. The system 100 further includes an industrial system 1 14, a local computing device 1 16, data from an industrial system 118, and an analysis pack 1 19.

[0028] The apparatus 102 is any combination of hardware devices and/or software selectively chosen to generate, display, and/or transmit communications. The interface 104 is a computer based program and/ or hardware configured to accept a command at the input 106 and transmit the generated communication at the output 108. Thus, the function of the interface 104 is to allow the apparatus 102 to communicate with and receive information from the industrial system 1 14, the local computing device 1 16, and the memory 1 12. The apparatus 102 may be deployed at the cloud 12.0 or any other networking construct. The cloud 120 may be any combination of networking components such as servers, switches, constructs, and/or other coniponenis used to provide network access to a number of systems. In some forms, the cloud 120 may include multiple networks or apparatuses which serve different purposes in the system.

[0029] The memory 112 may be stored on the apparatus 102. or any known system. In some examples, a portion of the memory stores the analytic blueprint 1 13 and is stored directly on the apparatus 102, The knowledge base may be a portion of the blueprint 113, and may contain information from various sources. Alternatively, the memory 112 may store the analytic blueprint 1 13 and/or the knowledge base on a cloud-based device separate from the apparatus 102, It is understood that in some forms, only a portion of the memory'- 1 12 stores the blueprint 1 13 and/or knowledge base, and the remainder is stored at a remote location (e.g., on the cloud 120 or another remote networking device). Further, it is understood that the blueprint 1 13 and/or the knowledge base may be derived from a catalog based on historical trends. The analytic blueprint 1 13 may be a data structure that includes any number of data elements used to interpret and'or analyze data relating to the industrial system 1 14.

[0030] The local computing device 1 16 may be any combination of hardware and/or software elements configured to execute a task. In some forms, the local computing device 1 16 may be a remote networking control device accessible by the apparatus 102 and any number of additional computing devices. In some forms, the local computing device 1 16 may communicate with cloud-based apparatuses and'or remote servers which networked to provide a centralized data storage access to services or resources. [0031] The data from the industrial system 1 18 may be derived from any type of component capable of providing time series data to the input 106. By "time series data" and as used herein, it is meant data relating to the operation of the industrial system 114 being obtained, presented, and/or organized in a sequential manner according to time. Thus, time series data allows for a user or system to measure a change in a characteristic of the industrial system 1 14 over a provided period of time. This data 1 18 may be derived from pumps, turbines, diesel engines, jet engines, or other industrial systems having any number of sensors, gauges, and other components for measuring time series data. Other examples are possible.

[0032] The data structures utilized herein may utilize any type of programming construct or combination of constructs such as linked lists, tables, pointers, and array s, to mention a few examples. Other examples are possible.

[0033] The processor 1 10 is a combination of hardware devices and/or software selectively chosen to monitor settings of the desired system and determine if anomalies are present. The processor 1 10 may be physically coupled to the interface 104 through a data connection (e.g., an Ethernet connection), or it may communicate with the interface 104 through any number of wireless communications protocols.

[0034] It will be appreciated that the various components described herein may be implemented using a general purpose processing device executing computer instructions stored in memory .

[0035] The local computing device 1 16 communicates with the interface 104 and transmits only the required data from the industrial system 1 18 according to the analytic system blueprint 1 13. This may be a variety of information pertaining to the industrial components of the industrial system 1 14. The processor 1 10 is configured to automatically accept the input data and determine whether an anomaly is present based on information contained within the knowledge base, which may be stored on the memory 1 12.

[0036] In operation, the processor 1 10 is configured to receive converted time series data from the industrial system 11 8 from an industrial system 1 14. This data 1 18 is already in a format that is readable by the analytic system. In some forms, the data 1 18 may have previously undergone a translation at the user's system 1 16. This translation may be a result of an end user mapping data inputs to a form understood by the analytic system or apparatus 102.

[0037] After this initial mapping has occurred, the apparatus 102 may automatically recognize subsequent data as being in a form that is readable by the analytic system or apparatus 102, The processor 1 10 may then automatically process ihe data 1 14 and automatically identify at least one anomaly associated with the industrial component. The processor 1 10 may then access the memory 1 12 to determine a resolution to address the anomaly based on information accessible by the analytic system. By resolution, it is meant an approach or method in which an end user may attempt to solve the anomaly . The processor 1 10 then may automatically notify the local computing device 116 of the presence of the anomaly via an electronic message thereto. This electronic message may contain the notification of the presence of the anomaly and further may contain the resoluiion. It is understood that the transmission of the electronic message may occur through any number of communication links or constructs known by those having skill in the art.

[0038] These approaches also provide for a "foresight" analysis in which based on a combination of received data 1 18 and information stored in the blueprint 1 13 of the memory 1 12, the apparatus 102 may transmit a message to the local computing device 1 16 via the output 108 which informs an operator of upcoming issues to be addressed before they present themselves. When the processor 1 10 detects this anomaly, it may automatically look to the knowledge base stored on the memory 112 which contains information from various sources regarding the components in the industrial system 1 14. The apparatus 102 may then automatically transmit to ihe local computing device the analysis pack 1 19 which may be used to address any issues encountered in the system both preemptively as well as after the anomaly may lead to control system damage. This analysis pack 1 19 may further control aspects of the industrial system to automatically attempt to resolve the anomaly.

[0039] It is understood that during the process of acting on the resolution obtained from the apparatus 102, additional information or diagnostic steps may be added at the industrial system 1 14 and/or the local computing device 1 16. These locally supplemented diagnostic steps are automatically added to any future instances of anomalies sent from the apparatus 102 for similar cases in the industrial system. [0048] Referring now to FIG. 2, one example of an approach for case management foresight and insight is described. First, at step 202, time series data is received at a local computing device. The time series data may be derived from an industrial component. This data is automatically converted to a format that is readable by an analytic system. At step 204, the time series data is transmitted to the analytic system.

[0041] At step 206, the data is automatically processed at the analytic system. At least one anomaly is automatically detected which is associated with the industrial component. At step 208, a resolution is automatically determined to address the anomaly based on information accessible by the analytic system.

[0042] At step 210, the local computing device is notified of the presence of the anomaly via an electronic transmission. Finally, at step 212, the resolution is electronically transmitted to the local computing device.

[0043] It will be appreciated by those skilled in the art that modifications to the foregoing embodiments may be made in various aspects. Other variations clearly would also work, and are within the scope and spirit of the invention. The present invention is set forth with particularity in the appended claims. It is deemed that the spirit and scope of that invention encompasses such modifications and alterations to the embodiments herein as would be apparent to one of ordinary skill in the art and familiar with the teachings of the present application.

Claims

CLAIMS What is claimed is:

1. A method comprising :

at a local computing device, receiving time series data from an industrial component and automatically converting the time series data to a format readable by an analytic system;

transmitting the time series data to the analytic system;

at the analytic system, automatically processing the data and identifying at least one anomaly associated with the industrial component;

automatically determining a resolution to address the anomaly based on information accessible by the analytic system;

notifying the local computing device of the presence of the anomaly; and electronically transmitting a message to the local computing device containing the resolution,

2. An analytic system comprising:

an interface having an input and an output: and

a processor coupled to the interface, the processor configured to receive converted time series data from an industrial component that is readable by the analytic system, process the time series data and identify at least one anomaly associated with the industrial component, determine a resolution to address the anomaly based on information accessible by the analytic system, notify the local computing device of the presence of the anomaly, and transmit the resolution to the local computing device.