CN111650898B - Distributed control system and method with high fault tolerance performance - Google Patents
Distributed control system and method with high fault tolerance performance Download PDFInfo
- Publication number
- CN111650898B CN111650898B CN202010402387.9A CN202010402387A CN111650898B CN 111650898 B CN111650898 B CN 111650898B CN 202010402387 A CN202010402387 A CN 202010402387A CN 111650898 B CN111650898 B CN 111650898B
- Authority
- CN
- China
- Prior art keywords
- data
- server
- fault
- process knowledge
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/4184—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by fault tolerance, reliability of production system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
- G05B19/41885—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by modeling, simulation of the manufacturing system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25232—DCS, distributed control system, decentralised control unit
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention belongs to the technical field of automatic control, and particularly relates to a distributed control system and method with high fault tolerance. The system comprises: a failsafe controller, a server, a process knowledge system, and an operator station; the fault safety controller is in signal connection with the server; the server is in signal connection with the process knowledge system; the process knowledge system is signally connected to an operator station; the fault safety controller is also in signal connection with the process knowledge system through a communication module. The invention acquires the operation parameters of the system by monitoring the operation state of the system in real time, analyzes the operation parameters, predicts faults, and solves the problem of the system before the system has the problem. Further improving the security of the system.
Description
Technical Field
The invention belongs to the technical field of automatic control, and particularly relates to a distributed control system and method with high fault tolerance.
Background
DCS (Distributed Control System), also known as distributed control systems. The instrument control system is a new generation instrument control system based on a microprocessor and adopting the design principles of decentralized control functions, centralized display operation and autonomy and comprehensive coordination. The distributed control system is called DCS for short, and can be also translated into a distributed control system or a distributed computer control system.
The system adopts a basic design idea of control dispersion, operation and management concentration, and adopts a multi-layer hierarchical and cooperative autonomous structural form. Its main feature is its centralized management and decentralized control. DCS has been widely used in electric power, metallurgy, petrochemical industry and other industries.
DCS typically employs a hierarchical structure, each stage consisting of several subsystems, each subsystem implementing several specific finite targets, forming a pyramid structure.
Reliability is life of development of DCS, and three measures are mainly used for ensuring high reliability of DCS: firstly, hardware equipment and a production process with high reliability are widely applied; secondly, a redundancy technology is widely adopted; thirdly, fault tolerance technology, fault self-diagnosis and automatic processing technology and the like of the system are widely realized on the software design. The MTBF of most distributed control systems today can reach tens of thousands or even hundreds of thousands of hours.
The development of the DCS system is mainly focused on the following aspects:
the system functions develop in an open direction: the structure of the traditional DCS is closed, and the DCS of different manufacturers is difficult to be compatible. The open DCS can give the user greater system integration autonomy, and the user can select equipment of different manufacturers to be connected with the software resource into the control system according to actual needs, so that the optimal system integration is achieved. The method not only comprises the integration of DCS and DCS, but also comprises the generalized integration of DCS and PLC, FCS and various control equipment and software resources.
The intelligent and networked development of the industrial control equipment is developed in the direction of digitalization, intellectualization and networking of the instrument technology, so that the functions of process control can be further dispersed and moved downwards, and the full digital and full dispersion control in the true sense is realized. In addition, the intelligent meters have the characteristics of high precision, good repeatability, high reliability, bidirectional communication, self-diagnosis function and the like, so that the installation, the use and the maintenance of the system are more convenient.
The development of industrial control software in the forward advanced control direction is widely applied to various advanced control and optimization technologies, which are the most effective, direct and valuable development directions for mining and improving the comprehensive performance of DCS, and mainly comprise development and industrialization application of software such as advanced control, process optimization, information integration, system integration and the like. In the future, industrial control software will also continue to evolve toward standardization, networking, intelligence, and openness.
For the system architecture to develop purely from the technology in the FCS direction, the integration of the field bus in DCS at the present stage can have three modes: (1) the integration of the Fieldbus onto the I/O bus of the DCS system-the interface card of the Fieldbus is hooked up to the I/O bus of the DCS so that the information on the Fieldbus seen by the DCS controller is as if it were from a conventional DCS device card. Such integration schemes are employed, for example, by the DeltaV system from Fisher-Rosemount. (2) The field bus is integrated with the DCS system network layer, namely the field bus system is integrated on a higher layer network of the DCS, and the DCS control station is not required to be changed in the integration mode, so that the influence on the original system is small. Such as the 302 series fieldbus product from Smar corporation, can implement the integration of its fieldbus functionality at the DCS system network layer. (3) The field bus is integrated with the DCS system in parallel through the gateway, and the field bus and the DCS can realize parallel integration through gateway bridging. Such as the SUPCON field bus system, utilizes a HART protocol bridge to connect the system operator and the field instrument, thereby implementing the communication function between the field bus device management system operator and the HART protocol field instrument.
The focus of DCS has been on control, which uses "dispersion" as a key. However, the modern development is focused on comprehensive management of whole system information, and the comprehensive will become the key word, and the development is advanced to the comprehensive automation of the control system, the operation system, the planning system and the management system, and the implementation goes up from the real-time control and the optimization control of the bottommost layer to the production scheduling and the operation management, so that the strategic decision of the highest layer is formed, and a flexible and highly-automated management and control integrated system is formed.
Disclosure of Invention
Therefore, the main objective of the present invention is to provide a distributed control system and method with high fault tolerance, which improves the safety and robustness of the system by adding a communication line connecting the fail-safe controller and the process knowledge system; meanwhile, the invention acquires the operation parameters of the system by monitoring the operation state of the system in real time, analyzes the operation parameters, predicts faults, and solves the problem of the system before the system has problems. Further improving the security of the system.
In order to achieve the above purpose, the technical scheme of the invention is realized as follows:
a distributed control system having high fault tolerance, said system comprising: a failsafe controller, a server, a process knowledge system, and an operator station; the fault safety controller is in signal connection with the server; the server is in signal connection with the process knowledge system; the process knowledge system is signally connected to an operator station; the fault safety controller is also in signal connection with the process knowledge system through a communication module.
Further, the system further comprises: a fault prediction system; the fault prediction system includes: a temperature sensor, a device operation monitoring subsystem and a fault analysis and prediction subsystem; the plurality of temperature sensors are respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and acquire temperature data of the fault safety controller, the server, the communication module and the process knowledge system; the equipment operation monitoring subsystem is a computer readable storage medium stored in a non-transitory mode, is respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and is used for acquiring operation parameters of the fault safety controller, the server, the communication module and the process knowledge system in real time and sending the acquired operation parameters to the fault analysis prediction subsystem; the operating parameters include at least: processor occupancy, data throughput, storage hard disk rotation speed, and processor processing speed.
Further, the fault analysis prediction subsystem includes: the system comprises a data preprocessing unit, a data protocol unit, a data standardization unit, an algorithm prediction unit and a modeling analysis unit; the data preprocessing unit sequentially performs detection processing of removing unique attributes, processing missing values and abnormal values on the operation parameters and the temperature data; the data protocol unit is used for carrying out protocol processing on the data after the data pretreatment, so that the data after the protocol processing are irrelevant in pairs, but original information is kept; the data normalization unit is used for scaling the data subjected to the protocol processing to enable the data to fall into a set interval; the algorithm prediction unit is used for carrying out data modeling according to the data processed by the data normalization unit; the modeling analysis unit is used for carrying out accuracy calculation on the failure rate generated by the calculation model and the original failure rate.
Further, the method for performing the protocol processing by the data protocol unit comprises the following steps: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; and finally, obtaining processed new data, wherein the data are irrelevant in pairs, but original information is kept.
Further, the method for performing data normalization processing by the data normalization unit includes: performing data normalization processing, and scaling data to fall into a specific interval; wherein the data is linearly transformed using the following transformation function, such that the result falls to [0.1,1]]The interval, transfer function is as follows:wherein x is * A result after data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data.
A distributed control method with high fault tolerance performance, the method comprising the steps of:
step 1: the process knowledge system adjusts the on-site analog quantity, and optimally adjusts and controls the pressure, the temperature and the liquid level; the process knowledge system is in signal connection with the server and sends data information to the server; meanwhile, the process knowledge system is in signal connection with the fault safety controller through a communication module;
step 2: the server rewards the received data information to send to the operator station;
step 3: the fault safety controller is connected with the server, and when the server does not have a fault, data information is acquired from the server; when the server fails, the data information is directly obtained from the process knowledge system through the communication module.
Further, the method further comprises: and acquiring operation parameters and temperature data of other devices and systems in the system, and performing data analysis on the operation parameters and the temperature data to perform fault prediction.
Further, the method for obtaining the operation parameters and temperature data of other devices and systems in the system, performing data analysis on the operation parameters and temperature data, and performing fault prediction executes the following steps:
step S1: performing data preprocessing, including: removing unique attributes, processing missing values and abnormal value detection and processing;
step S2: performing data protocol processing, including: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; and finally, obtaining processed new data, wherein the data are irrelevant in pairs, but original information is kept.
Step S3: performing data normalization processing, and scaling data to fall into a specific interval; wherein the data is linearly transformed using the following transformation function, such that the result falls to [0.1,1]]The interval, transfer function is as follows:wherein x is * A result after data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data;
step S4: carrying out data modeling;
step S5: performing effect analysis, including: after model training is finished, adopting the following formula to calculate the failure rate generated by the model and calculate the accuracy of the original failure rate to obtain R 2 The higher the score, the better the model accuracy;
wherein y represents a power equipment failure rate (predicted value) generated by the model;
representing the failure rate of the original power equipment;
n samples representing the sample size of the incoming model.
Further, the operating parameters include at least: processor occupancy, data throughput, storage hard disk rotation speed, and processor processing speed.
Further, the step S4: the method for data modeling performs the steps of:
step S4.1: acquiring data for modeling, using x as an input variable i A representation, wherein i represents the ith variable in the data; the x is i At least comprises: voltage value, current value, arc value, temperature value and humidity value when the power equipment operates;
step S4.2: setting a weight function by w i The method comprises the steps of representing, carrying out convolution operation on each input variable and a corresponding weight function to obtain a first intermediate result;
step S4.3: setting an excitation function, anThe excitation function is:the neuron threshold of the neural network is set as follows: Θ; and calculating the first intermediate result and the excitation function and the neuron threshold value to obtain the result of the forward neural network, wherein the result is as follows: />
Step S4.4: calculating a training error of the forward neural network; since the output variable E of the present training is the "power equipment failure rate", but a predicted value O is generated after model training, the error function is obtained as follows:
where m represents the number of modeling samples entered this time and i represents the i-th variable.
Step S4.5: back propagation update weights w
In order to make the error smaller and improve the accuracy of model prediction, the neural network can reversely transmit data from the output layer to the input layer, readjust the value of the weight w, stop training until the model error reaches the minimum, and complete the model creation.
The distributed control system and method with high fault tolerance have the following beneficial effects: in the system, the communication between the fault safety controller and the process knowledge system can be carried out without passing through the server under the condition that the server fails, so that the communication interruption between the fault safety controller and the process knowledge system and the field equipment lose monitoring are avoided, and the communication mode has the advantages of high stability, high anti-interference capability and the like. Meanwhile, the operation data of each device and each system and the temperature data of each device and each system are analyzed, and before the device fails, the device and each system can be subjected to failure prediction analysis through data analysis, so that the occurrence of device failure is greatly reduced. Besides the reduction of the equipment failure rate, the production efficiency can be ensured not to be reduced due to the equipment failure, and the occurrence of the problem can be avoided before the problem occurs.
Drawings
Fig. 1 is a schematic system structure diagram of a distributed control system with high fault tolerance according to an embodiment of the present invention;
fig. 2 is a flow chart of a distributed control method with high fault tolerance according to an embodiment of the present invention.
Detailed Description
The method of the present invention will be described in further detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, a distributed control system with high fault tolerance performance, the system comprises: a failsafe controller, a server, a process knowledge system, and an operator station; the fault safety controller is in signal connection with the server; the server is in signal connection with the process knowledge system; the process knowledge system is signally connected to an operator station; the fault safety controller is also in signal connection with the process knowledge system through a communication module.
By adopting the technical scheme, the communication between the fault safety controller and the process knowledge system is realized without passing through the server, so that the communication interruption between the two parties caused by the server fault is avoided, and the field equipment loses monitoring.
Example 2
On the basis of the above embodiment, the system further includes: a fault prediction system; the fault prediction system includes: a temperature sensor, a device operation monitoring subsystem and a fault analysis and prediction subsystem; the plurality of temperature sensors are respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and acquire temperature data of the fault safety controller, the server, the communication module and the process knowledge system; the equipment operation monitoring subsystem is a computer readable storage medium stored in a non-transitory mode, is respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and is used for acquiring operation parameters of the fault safety controller, the server, the communication module and the process knowledge system in real time and sending the acquired operation parameters to the fault analysis prediction subsystem; the operating parameters include at least: processor occupancy, data throughput, storage hard disk rotation speed, and processor processing speed.
Specifically, the fault prediction refers to predicting equipment faults, services and accessory demands based on data stored in a big data storage and analysis platform through equipment use data, working condition data, host and accessory performance data, accessory replacement data and other equipment and service data, so as to provide technical support for active service, prolong the service life of the equipment and reduce the fault rate.
Example 3
On the basis of the above embodiment, the fault analysis prediction subsystem includes: the system comprises a data preprocessing unit, a data protocol unit, a data standardization unit, an algorithm prediction unit and a modeling analysis unit; the data preprocessing unit sequentially performs detection processing of removing unique attributes, processing missing values and abnormal values on the operation parameters and the temperature data; the data protocol unit is used for carrying out protocol processing on the data after the data pretreatment, so that the data after the protocol processing are irrelevant in pairs, but original information is kept; the data normalization unit is used for scaling the data subjected to the protocol processing to enable the data to fall into a set interval; the algorithm prediction unit is used for carrying out data modeling according to the data processed by the data normalization unit; the modeling analysis unit is used for carrying out accuracy calculation on the failure rate generated by the calculation model and the original failure rate.
Specifically, data reduction refers to minimizing the data volume (the necessary premise for completing the task is to understand the mining task and familiarize with the content of the data itself) on the premise of keeping the original appearance of the data as much as possible. Data reduction has two main approaches: attribute selection and data sampling are respectively directed to attributes and records in the original dataset. Suppose that data is selected at a company's data warehouse for analysis. So that the data set will be very large. Complex data analysis button mining on massive amounts of data would take a long time making such analysis impractical or infeasible. Data reduction techniques can be used to derive a reduced representation of the dataset that, while small, still substantially preserves the integrity of the original data. In this way, mining on the reduced dataset will be more efficient and produce the same (or nearly the same) analysis results.
Prior to data analysis, we generally need to normalize (normalization) the data and use the normalized data for data analysis. Data normalization is the indexing of statistical data. The data normalization processing mainly comprises two aspects of data isotacticity processing and dimensionless processing. The data isotactics processing mainly solves the problem of data with different properties, and the direct summation of indexes with different properties can not correctly reflect the comprehensive results of different acting forces, and the inverse index data properties are considered to be changed first, so that all indexes can be used for isotactics of acting forces of an evaluation scheme, and then the summation can obtain correct results. The dimensionless data processing mainly solves the comparability of data. There are various methods for data normalization, and "min-max normalization", "Z-score normalization" and "decimal scale normalization" are commonly used. Through the standardization processing, the original data are converted into dimensionless index evaluation values, namely, all index values are in the same number level, and comprehensive evaluation analysis can be performed.
Example 4
On the basis of the above embodiment, the method for performing reduction processing by the data reduction unit includes: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; and finally, obtaining processed new data, wherein the data are irrelevant in pairs, but original information is kept.
Example 5
On the basis of the above embodiment, the method for performing data normalization processing by the data normalization unit includes: data standardization processing is carried out, and data are processed according to the following modeScaling to fall within a specified interval; wherein the data is linearly transformed using the following transformation function, such that the result falls to [0.1,1]]The interval, transfer function is as follows:wherein x is * A result after data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data.
Example 6
A distributed control method with high fault tolerance performance, the method comprising the steps of:
step 1: the process knowledge system adjusts the on-site analog quantity, and optimally adjusts and controls the pressure, the temperature and the liquid level; the process knowledge system is in signal connection with the server and sends data information to the server; meanwhile, the process knowledge system is in signal connection with the fault safety controller through a communication module;
step 2: the server rewards the received data information to send to the operator station;
step 3: the fault safety controller is connected with the server, and when the server does not have a fault, data information is acquired from the server; when the server fails, the data information is directly obtained from the process knowledge system through the communication module.
Specifically, a control system of the Honeywell is used for maintaining a DCS system, the system consists of a PKS system of the Honeywell and an FSC system, wherein the PKS system mainly serves for adjusting field analog quantity equipment and mainly is used for optimally adjusting and controlling pressure, temperature and liquid level, namely a process knowledge system; the FSC system is mainly used for safely and controllably controlling field devices, namely a fault safety controller, the system is updated and reformed in 2016, the communication mode between the systems is SCADA communication, all communication points are stored on a server, and the server adopts redundant configuration and is responsible for reading data from the controller and then sending the data to an operator station picture. If the server fails (the server crashes, the server is powered off, etc.), the communication of the FSC system is interrupted, the field device is uncontrollable, another communication mode (without passing through the server) needs to be designed, the communication redundancy control is realized, the PKS controller and the FSC controller are subjected to real-time data transmission, and the safety and controllability of the field device are ensured.
Specifically, the PKS system is physically connected to the PCDI device: there are three main types of physical connections of FSC systems to PKS systems: serial connection, ethernet connection and terminal server connection; in the invention, the adopted communication mode is a serial port-to-Ethernet connection mode of the FSC system, and the middle is converted by a PCDI communication module.
Specifically, the invention applies Quick Builder software, and establishes peer-to-peer connection between the controller of the PKS system C300 and the FSC system controller equipment by using PCDI series modules of the function block library, and the PKS system controller C300 exchanges data with the FSC system, wherein a data communication path is an FCS system, a PKS system C300 controller, a server and an operator station. The Experion PKS system communicates with FSC system equipment, typically the PKS system is the master station and the FSC system is the slave station, and all slave station addresses must be unique to the master station, otherwise communication failures may occur, and the communication parameter settings of the master station and the slave station must be consistent.
Specifically, the distributed control system of the present invention is configured to: the Quick Builder software is opened, wherein the PCDI module is used to define the type and IP address of the FSC system device. Dragging the PCDI module in the Library to the C300 control execution configuration logic, and selecting the device type: device Type, populating the IP address of the FSC Device. The configuration communication points write the configuration of all communication points of the FSC system equipment into a PCDI configuration database, and after the configuration is completed, the C300 controller can flexibly apply the data of the FSC system equipment, wherein the PCDIFLAGARRCH.PVFL [ N ], PCDINUMARRHA.PV [ N ]. Pins corresponding to the data and internal logic control of the PKS system. The scheme is characterized in that: the PCDI series communication module corresponds to an I/O channel connecting the PKS system controller C300 and FSC system equipment, and the C300 controller can conveniently and quickly apply PCDI communication data to process control inside the C300 controller, for example: logic comparison, picture display and chain protection.
Example 7
On the basis of the above embodiment, the method further includes: and acquiring operation parameters and temperature data of other devices and systems in the system, and performing data analysis on the operation parameters and the temperature data to perform fault prediction.
Example 8
On the basis of the above embodiment, the method for obtaining the operation parameters and temperature data of other devices and systems in the system, performing data analysis on the operation parameters and temperature data, and performing fault prediction executes the following steps:
step S1: performing data preprocessing, including: removing unique attributes, processing missing values and abnormal value detection and processing;
step S2: performing data protocol processing, including: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; and finally, obtaining processed new data, wherein the data are irrelevant in pairs, but original information is kept.
Step S3: performing data normalization processing, and scaling data to fall into a specific interval; wherein the data is linearly transformed using the following transformation function, such that the result falls to [0.1,1]]The interval, transfer function is as follows:wherein x is * A result after data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data;
step S4: carrying out data modeling;
step S5: performing effect analysis, including: after model training is finished, adopting the following formula to calculate the failure rate generated by the model and calculate the accuracy of the original failure rate to obtain R 2 The higher the score, the better the model accuracy;
wherein y represents a power equipment failure rate (predicted value) generated by the model;
representing the failure rate of the original power equipment;
n samples representing the sample size of the incoming model.
Example 9
On the basis of the above embodiment, the operation parameters include at least: processor occupancy, data throughput, storage hard disk rotation speed, and processor processing speed.
Example 10
On the basis of the above embodiment, the step S4: the method for data modeling performs the steps of:
step S4.1: acquiring data for modeling, using x as an input variable i A representation, wherein i represents the ith variable in the data; the x is i At least comprises: voltage value, current value, arc value, temperature value and humidity value when the power equipment operates;
step S4.2: setting a weight function by w i The method comprises the steps of representing, carrying out convolution operation on each input variable and a corresponding weight function to obtain a first intermediate result;
step S4.3: setting an excitation function, wherein the excitation function is as follows:the neuron threshold of the neural network is set as follows: Θ; and calculating the first intermediate result and the excitation function and the neuron threshold value to obtain the result of the forward neural network, wherein the result is as follows: />
Step S4.4: calculating a training error of the forward neural network; since the output variable E of the present training is the "power equipment failure rate", but a predicted value O is generated after model training, the error function is obtained as follows:
where m represents the number of modeling samples entered this time and i represents the i-th variable.
Step S4.5: back propagation update weights w
In order to make the error smaller and improve the accuracy of model prediction, the neural network can reversely transmit data from the output layer to the input layer, readjust the value of the weight w, stop training until the model error reaches the minimum, and complete the model creation.
It will be clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the system described above and the related description may refer to the corresponding process in the foregoing method embodiment, which is not repeated here.
It should be noted that, in the system provided in the foregoing embodiment, only the division of the foregoing functional modules is illustrated, in practical application, the foregoing functional allocation may be performed by different functional modules, that is, the modules or steps in the embodiment of the present invention are further decomposed or combined, for example, the modules in the foregoing embodiment may be combined into one module, or may be further split into multiple sub-modules, so as to complete all or part of the functions described above. The names of the modules and steps related to the embodiments of the present invention are merely for distinguishing the respective modules or steps, and are not to be construed as unduly limiting the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the storage device and the processing device described above and the related description may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
Those of skill in the art will appreciate that the various illustrative modules, method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the program(s) corresponding to the software modules, method steps, may be embodied in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. To clearly illustrate this interchangeability of electronic hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as electronic hardware or software depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality using different approaches for each particular application, but such implementation is not intended to be limiting.
The terms "first," "second," and the like, are used for distinguishing between similar objects and not for describing a particular sequential or chronological order.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus/apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus/apparatus.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention.
Claims (8)
1. A distributed control system having high fault tolerance, said system comprising: a failsafe controller, a server, a process knowledge system, and an operator station; the fault safety controller is in signal connection with the server; the server is in signal connection with the process knowledge system; the process knowledge system is signally connected to an operator station; the system is characterized in that the fault safety controller is also in signal connection with a process knowledge system through a communication module;
the system further comprises: a fault prediction system; the fault prediction system includes: a temperature sensor, a device operation monitoring subsystem and a fault analysis and prediction subsystem; the plurality of temperature sensors are respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and acquire temperature data of the fault safety controller, the server, the communication module and the process knowledge system; the equipment operation monitoring subsystem is a computer readable storage medium stored in a non-transitory mode, is respectively arranged on the fault safety controller, the server, the communication module and the process knowledge system, and is used for acquiring operation parameters of the fault safety controller, the server, the communication module and the process knowledge system in real time and sending the acquired operation parameters to the fault analysis prediction subsystem; the operating parameters include at least: processor occupancy rate, data throughput, storage hard disk rotation speed and processor processing speed;
a method of controlling the system, the method performing the steps of:
step 1: the process knowledge system adjusts the on-site analog quantity, and optimally adjusts and controls the pressure, the temperature and the liquid level; the process knowledge system is in signal connection with the server and sends data information to the server; meanwhile, the process knowledge system is in signal connection with the fault safety controller through a communication module;
step 2: the server rewards the received data information to send to the operator station;
step 3: the fault safety controller is connected with the server, and when the server does not have a fault, data information is acquired from the server; when the server fails, the data information is directly obtained from the process knowledge system through the communication module.
2. The system of claim 1, wherein the failure analysis prediction subsystem comprises: the system comprises a data preprocessing unit, a data protocol unit, a data standardization unit, an algorithm prediction unit and a modeling analysis unit; the data preprocessing unit sequentially performs detection processing of removing unique attributes, processing missing values and abnormal values on the operation parameters and the temperature data; the data protocol unit is used for carrying out protocol processing on the data after the data pretreatment, so that the data after the protocol processing are irrelevant in pairs, but original information is kept; the data normalization unit is used for scaling the data subjected to the protocol processing to enable the data to fall into a set interval; the algorithm prediction unit is used for carrying out data modeling according to the data processed by the data normalization unit; the modeling analysis unit is used for carrying out accuracy calculation on the failure rate generated by the calculation model and the original failure rate.
3. The system of claim 2, wherein the data reduction unit performs reduction processing by a method comprising: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; and finally, obtaining processed new data, wherein the data are irrelevant in pairs, but original information is kept.
4. The system of claim 3, wherein the method for data normalization by the data normalization unit comprises: performing data normalization processing, and scaling data to fall into a specific interval; the data were linearly transformed using the following transfer function, which falls the result to the [0.1,1] interval:
wherein x is the result of data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data.
5. The system of claim 1, wherein the method further comprises: and acquiring operation parameters and temperature data of other devices and systems in the system, and performing data analysis on the operation parameters and the temperature data to perform fault prediction.
6. The system of claim 5, wherein the method for obtaining the operating parameters and temperature data of each of the other devices and systems in the system, performing data analysis on the operating parameters and temperature data, and performing fault prediction performs the steps of:
step S1: performing data preprocessing, including: removing unique attributes, processing missing values and abnormal value detection and processing;
step S2: performing data protocol processing, including: removing average value, calculating covariance matrix, calculating eigenvalue and eigenvector of covariance matrix, sorting eigenvalue from big to small, reserving k largest eigenvectors, and converting data into new space constructed by k eigenvectors; finally, the processed new data are obtained, the data are irrelevant in pairs, but the original information is kept,
step S3: performing data normalization processing, and scaling data to fall into a specific interval; the data were linearly transformed using the following transfer function, which falls the result to the [0.1,1] interval:
wherein x is the result of data normalization processing; x is the data to be processed; min is the minimum value in the data; max is the maximum value in the data;
step S4: carrying out data modeling;
step S5: performing effect analysis, including: after model training is finished, calculating the failure rate generated by the model and the original failure rate by adopting the following formula, namely obtaining an R2 score, wherein the higher the score is, the better the model accuracy is;
wherein y represents the failure rate of the power equipment generated by the model;
representing the failure rate of the original power equipment;
nsamples represents the sample size into the model.
7. The system of claim 6, wherein the operating parameters include at least: processor occupancy, data throughput, storage hard disk rotation speed, and processor processing speed.
8. The system of claim 7, wherein said step S4: the method for data modeling performs the steps of:
step S4.1: obtaining data for modeling, which is represented by xi as input variables, wherein i represents an ith variable in the data; the xi at least comprises: voltage value, current value, arc value, temperature value and humidity value when the power equipment operates;
step S4.2: setting a weight function, using wi to represent, and carrying out convolution operation on each input variable and the corresponding weight function to obtain a first intermediate result;
step S4.3: setting an excitation function, wherein the excitation function is as follows:the neuron threshold of the neural network is set as follows: Θ; and calculating the first intermediate result and the excitation function and the neuron threshold value to obtain the result of the forward neural network, wherein the result is as follows: />
Step S4.4: calculating a training error of the forward neural network; since the output variable E of the present training is the "power equipment failure rate", but a predicted value O is generated after model training, the error function is obtained as follows:
where m represents the number of modeling samples entered this time, i represents the i-th variable,
step S4.5: back-propagating the update weights w;
in order to make the error smaller and improve the accuracy of model prediction, the neural network can reversely transmit data from the output layer to the input layer, readjust the value of the weight w, stop training until the model error reaches the minimum, and complete the model creation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010402387.9A CN111650898B (en) | 2020-05-13 | 2020-05-13 | Distributed control system and method with high fault tolerance performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010402387.9A CN111650898B (en) | 2020-05-13 | 2020-05-13 | Distributed control system and method with high fault tolerance performance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111650898A CN111650898A (en) | 2020-09-11 |
| CN111650898B true CN111650898B (en) | 2023-10-20 |
Family
ID=72352092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010402387.9A Active CN111650898B (en) | 2020-05-13 | 2020-05-13 | Distributed control system and method with high fault tolerance performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111650898B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116399400B (en) * | 2023-04-13 | 2023-12-15 | 大唐绥化热电有限公司 | Method and system for detecting operation faults of boiler unit |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178837A (en) * | 2007-10-16 | 2008-05-14 | 西安交通大学 | Wireless sensor network controller |
| WO2008125989A2 (en) * | 2007-04-16 | 2008-10-23 | Saarland University | Polyketide based proteasome inhibitor |
| CN102436226A (en) * | 2011-09-14 | 2012-05-02 | 文存润 | Online monitoring and condition maintenance management system |
| CN202789324U (en) * | 2012-09-13 | 2013-03-13 | 成都阜特科技股份有限公司 | Distributed condition monitoring system |
| CN103201690A (en) * | 2010-11-11 | 2013-07-10 | 霍尼韦尔国际公司 | Local control network processor (LCNP) emulator for multi-generation control systems |
| CN103309230A (en) * | 2012-03-07 | 2013-09-18 | 皮尔茨公司 | Sensor arrangement for detecting the safe condition of an automatically operated system |
| CN103459610A (en) * | 2011-01-28 | 2013-12-18 | 阿迈瑞斯公司 | Gel-encapsulated microcolony screening |
| CN103501047A (en) * | 2013-10-09 | 2014-01-08 | 云南电力调度控制中心 | Intelligent fault wave recording main station information management system |
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| CN104062968A (en) * | 2014-06-10 | 2014-09-24 | 华东理工大学 | Continuous chemical process fault detection method |
| CN105374209A (en) * | 2015-11-05 | 2016-03-02 | 北京航空航天大学 | Urban region road network running state characteristic information extraction method |
| CN106020257A (en) * | 2016-08-01 | 2016-10-12 | 大唐七台河发电有限责任公司 | Ash field water drainage control system |
| CN206386966U (en) * | 2016-12-19 | 2017-08-08 | 大唐黑龙江发电有限公司哈尔滨第一热电厂 | Novel fuel IGNITION CONTROL loop |
| CN107947156A (en) * | 2017-11-24 | 2018-04-20 | 国网辽宁省电力有限公司 | Based on the electric network fault critical clearing time method of discrimination for improving Softmax recurrence |
| CN108595667A (en) * | 2018-04-28 | 2018-09-28 | 广东电网有限责任公司 | A kind of correlation analysis method of Network Abnormal data |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN110113214A (en) * | 2019-05-16 | 2019-08-09 | 青岛博展智能科技有限公司 | A kind of 5G network automatic evaluation system neural network based, method and device |
| CN110213774A (en) * | 2019-05-23 | 2019-09-06 | 超讯通信股份有限公司 | A kind of 5G network automatic evaluation system neural network based, method and device |
-
2020
- 2020-05-13 CN CN202010402387.9A patent/CN111650898B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008125989A2 (en) * | 2007-04-16 | 2008-10-23 | Saarland University | Polyketide based proteasome inhibitor |
| CN101178837A (en) * | 2007-10-16 | 2008-05-14 | 西安交通大学 | Wireless sensor network controller |
| CN103201690A (en) * | 2010-11-11 | 2013-07-10 | 霍尼韦尔国际公司 | Local control network processor (LCNP) emulator for multi-generation control systems |
| CN103459610A (en) * | 2011-01-28 | 2013-12-18 | 阿迈瑞斯公司 | Gel-encapsulated microcolony screening |
| CN102436226A (en) * | 2011-09-14 | 2012-05-02 | 文存润 | Online monitoring and condition maintenance management system |
| CN103309230A (en) * | 2012-03-07 | 2013-09-18 | 皮尔茨公司 | Sensor arrangement for detecting the safe condition of an automatically operated system |
| CN202789324U (en) * | 2012-09-13 | 2013-03-13 | 成都阜特科技股份有限公司 | Distributed condition monitoring system |
| CN103501047A (en) * | 2013-10-09 | 2014-01-08 | 云南电力调度控制中心 | Intelligent fault wave recording main station information management system |
| CN103745229A (en) * | 2013-12-31 | 2014-04-23 | 北京泰乐德信息技术有限公司 | Method and system of fault diagnosis of rail transit based on SVM (Support Vector Machine) |
| CN104062968A (en) * | 2014-06-10 | 2014-09-24 | 华东理工大学 | Continuous chemical process fault detection method |
| CN105374209A (en) * | 2015-11-05 | 2016-03-02 | 北京航空航天大学 | Urban region road network running state characteristic information extraction method |
| CN106020257A (en) * | 2016-08-01 | 2016-10-12 | 大唐七台河发电有限责任公司 | Ash field water drainage control system |
| CN206386966U (en) * | 2016-12-19 | 2017-08-08 | 大唐黑龙江发电有限公司哈尔滨第一热电厂 | Novel fuel IGNITION CONTROL loop |
| CN107947156A (en) * | 2017-11-24 | 2018-04-20 | 国网辽宁省电力有限公司 | Based on the electric network fault critical clearing time method of discrimination for improving Softmax recurrence |
| CN108595667A (en) * | 2018-04-28 | 2018-09-28 | 广东电网有限责任公司 | A kind of correlation analysis method of Network Abnormal data |
| CN109491816A (en) * | 2018-10-19 | 2019-03-19 | 中国船舶重工集团公司第七六研究所 | Knowledge based engineering method for diagnosing faults |
| CN110113214A (en) * | 2019-05-16 | 2019-08-09 | 青岛博展智能科技有限公司 | A kind of 5G network automatic evaluation system neural network based, method and device |
| CN110213774A (en) * | 2019-05-23 | 2019-09-06 | 超讯通信股份有限公司 | A kind of 5G network automatic evaluation system neural network based, method and device |
Non-Patent Citations (1)
| Title |
|---|
| 曹力军.火电站分散控制系统的升级优化.发电设备.2012,339-342. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111650898A (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Serradilla et al. | Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects | |
| JP2009087350A (en) | Adaptive process control loop controller, process control system and process control system control method | |
| CN110530650B (en) | Method for monitoring performance state of heavy-duty gas turbine based on generalized regression neural network and box diagram analysis | |
| CN106383916B (en) | Data processing method based on predictive maintenance of industrial equipment | |
| CN109697570B (en) | State evaluation method, system and equipment for secondary equipment of transformer substation | |
| EP3671571A1 (en) | A method and system for generating an artificial intelligence model | |
| US11656589B2 (en) | Systems and methods for automatic power topology discovery | |
| WO2019209146A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
| Lindemann et al. | Cloud-based control approach in discrete manufacturing using a self-learning architecture | |
| CN111650898B (en) | Distributed control system and method with high fault tolerance performance | |
| Meesublak et al. | A cyber-physical system approach for predictive maintenance | |
| CN113283602A (en) | Power grid system fault diagnosis method based on offline knowledge learning and online dynamic correction | |
| CN117041029A (en) | Network equipment fault processing method and device, electronic equipment and storage medium | |
| CN112241606A (en) | Cooperative decision-making method for operation and maintenance of ship intelligent equipment based on CPS decision-making module | |
| Lutska et al. | Forecasting the efficiency of the control system of the technological object on the basis of neural networks | |
| Villalonga et al. | Visual analytics framework for condition monitoring in cyber-physical systems | |
| CN111338876B (en) | Decision method, system and storage medium for fault mode and influence analysis | |
| Chen | Production planning and control in semiconductor manufacturing: Big data analytics and industry 4.0 applications | |
| CN111614504A (en) | Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis | |
| CN115033893B (en) | Information vulnerability data analysis method of improved clustering algorithm | |
| Gęca | Performance comparison of machine learning algotihms for predictive maintenance | |
| CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
| CN113076217A (en) | Disk fault prediction method based on domestic platform | |
| CN112800110A (en) | Weak sensitive data abnormity detection system of power internet of things sensor | |
| CN112115640A (en) | Control valve viscosity detection method based on transfer learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |