CN115793604A

CN115793604A - Controller operation and maintenance method, device and system

Info

Publication number: CN115793604A
Application number: CN202211445982.6A
Authority: CN
Inventors: 蒋元庆; 余明钊; 严玲晴
Original assignee: Alibaba Cloud Computing Ltd
Current assignee: Alibaba Cloud Computing Ltd
Priority date: 2022-11-18
Filing date: 2022-11-18
Publication date: 2023-03-14

Abstract

The application discloses a controller operation and maintenance method, device and system, relating to the technical field of industrial control, wherein the method comprises the following steps: collecting configuration parameters and operation data of an industrial field control subsystem; according to the configuration parameters and the operation data, performing performance evaluation on the operation performance of the controller and obtaining a performance evaluation result; when the performance evaluation result is that the operation performance of the controller is abnormal, judging whether the industrial process object has model mismatch according to the configuration parameters and the operation data, and obtaining a model mismatch detection result; determining the type of the influence factors influencing the operation performance of the controller according to the model mismatch detection result, and determining an operation and maintenance strategy for optimizing the operation performance of the controller based on the type of the influence factors. The method and the device can ensure that the industrial controller continuously keeps the operation performance at the initial commissioning stage, thereby realizing the real-time and targeted operation and maintenance of the control loop of the complex industrial process object and keeping the industrial production quality of the industrial process object stable.

Description

Controller operation and maintenance method, device and system

Technical Field

The application relates to the technical field of industrial control, in particular to a method, a device and a system for operation and maintenance of a controller.

Background

This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.

The industrial control software is used as the crystallization of industrial knowledge and experience accumulated for a long time in industrial automation, and an industrial controller built based on the industrial control software can not only control the operation of products and equipment in real time, but also optimize the operation state of a system, and realize continuous, stable and efficient production. However, the operation performance of the industrial controller is gradually reduced along with factors such as aging of industrial process object equipment, change of working conditions, and external disturbance in the operation process, so that the production efficiency, the quality and even the production safety are affected, and the traditional operation and maintenance mode usually needs manual work to periodically perform maintenance measures such as evaluation, detection and optimization to ensure the effective operation of the industrial controller.

The operation and maintenance of the traditional industrial controller rely on the experience of professional engineers to carry out the performance diagnosis of the controller, and a great deal of energy is required to discover an abnormal loop; after a loop with abnormal control performance is found, a large amount of debugging energy is consumed by professionals to trim and debug the controller model and parameters, and the operation and maintenance effect depends on the technical level of the professionals, so that the traditional operation and maintenance mode often causes that the industrial controller cannot continuously maintain the operation performance at the initial stage of operation, and an operation and maintenance system with automatic operation capability for monitoring, diagnosing and maintaining the performance of the industrial controller is urgently needed.

Disclosure of Invention

The embodiment of the application provides a method, a device and a system for operation and maintenance of a controller, so as to at least solve the problem that in the prior art, an industrial controller cannot continuously maintain the operation performance at the initial stage of commissioning in a traditional operation and maintenance mode.

According to an aspect of the present application, there is also provided a controller operation and maintenance method, wherein the controller controls an industrial process object in an industrial field control subsystem, the operation and maintenance method includes:

acquiring configuration parameters and operation data of the industrial field control subsystem, wherein the operation data comprises control instruction data of the controller, state data of the industrial process object and an initial model, the configuration parameters are parameters required for operation and maintenance of the operation performance of the controller, and the initial model is a mathematical model conforming to initial characteristics of the industrial process object;

according to the configuration parameters and the operation data, performing performance evaluation on the operation performance of the controller and obtaining a performance evaluation result;

when the performance evaluation result is that the operation performance of the controller is abnormal, judging whether the industrial process object has model mismatch according to the configuration parameters and the operation data, and obtaining a model mismatch detection result;

and when the performance evaluation result indicates that the operation performance of the controller is abnormal, determining the type of an influence factor influencing the operation performance of the controller according to the model mismatch detection result, and determining an operation and maintenance strategy for optimizing the operation performance of the controller based on the type of the influence factor.

In some of these embodiments, the step of determining the type of influencing factor influencing the operational performance of the controller according to the model mismatch detection result comprises:

when the model mismatch detection result is that the model of the industrial process object is mismatched, determining that the type of the influence factor is that the real characteristic of the industrial process object is different from the initial characteristic;

then, the step of determining an operation and maintenance strategy for optimizing the operation performance of the controller based on the type of the influence factor includes:

acquiring a recommended control model determined according to the operation data, wherein the recommended control model is a mathematical model conforming to the real characteristics of the industrial process object;

and determining a first recommended controller parameter matched with the design index of the controller according to the recommended control model so as to optimize the operation performance of the controller by using a first optimization result formed by the first recommended controller parameter and the recommended control model.

In some of these embodiments, determining the type of influencing factor influencing the operational performance of the controller based on the model mismatch detection result includes:

when the model mismatch detection result indicates that the industrial process object does not generate model mismatch, determining that the type of the influence factor is that the external environment in which the industrial process object currently operates is different from the initial operation environment;

and determining a second recommended controller parameter matched with the design index of the controller according to the initial model so as to optimize the operation performance of the controller by using a second optimization result formed by the second recommended controller parameter.

In some embodiments, the configuration parameters include a preset control performance variation threshold, a reference data time period, and an evaluation data time period, wherein the step of performing performance evaluation on the operation performance of the controller and obtaining a performance evaluation result according to the configuration parameters and the operation data includes:

acquiring reference operation data acquired in the reference data time period, wherein the reference operation data is the operation data acquired when the operation performance of the controller is not abnormal;

taking the operation data collected in the evaluation data time period as operation data to be evaluated;

and according to the control performance change threshold, the to-be-evaluated operation data and the reference operation data, performing performance evaluation on the operation performance of the controller and obtaining a performance evaluation result.

In some embodiments, the configuration parameters further include a preset model mismatch threshold and a mismatch detection data time period, and the step of determining whether the industrial process object has a model mismatch according to the configuration parameters and the operation data includes:

and acquiring the operation data acquired in the mismatch detection data time period, and judging whether the industrial process object has model mismatch or not according to the model mismatch threshold and the operation data.

In some of these embodiments, the configuration parameters further include a performance evaluation period specifying a time period for performance evaluation of the operational performance of the controller.

In some of these embodiments, the configuration parameters further include a mismatch detection period specifying a time period for determining whether a model mismatch occurs with the industrial process object.

According to another aspect of the present application, there is also provided a controller operation and maintenance device for operating and maintaining a controller for controlling an industrial process object in an industrial field control subsystem, the controller operation and maintenance device including:

the device comprises a first data reading module, a performance evaluation module, a mismatch detection module and a control optimization module;

the first data reading module is used for acquiring configuration parameters and operation data of the industrial field control subsystem, wherein the operation data comprises control instruction data of the controller, state data of the industrial process object and an initial model, the configuration parameters are parameters required for operation and maintenance of the operation performance of the controller, and the initial model is a mathematical model conforming to initial characteristics of the industrial process object;

the performance evaluation module is used for carrying out performance evaluation on the operation performance of the controller according to the configuration parameters and the operation data and obtaining a performance evaluation result;

the mismatch detection module is used for judging whether the industrial process object has model mismatch according to the configuration parameters and the operation data when the performance evaluation result is that the operation performance of the controller is abnormal, and obtaining a model mismatch detection result;

and the control optimization module is used for determining the type of an influence factor influencing the running performance of the controller according to the model mismatch detection result, and determining and optimizing the operation and maintenance strategy of the running performance of the controller based on the type of the influence factor.

In some embodiments, the method further includes a model updating module and a first data writing-out module, wherein the step of determining, by the control optimization module, the type of influencing factor influencing the operational performance of the controller according to the model mismatch detection result includes:

then, the step of determining, by the control optimization module, an operation and maintenance strategy for optimizing the operation performance of the controller based on the type of the influencing factor includes:

acquiring a recommended control model determined by the model updating module according to the operation data, wherein the recommended control model is a mathematical model conforming to the real characteristics of the industrial process object;

determining a first recommended controller parameter matched with a design index of the controller according to the recommended control model, sending the first recommended controller parameter to the first data writing-out module, and feeding back a first optimization result formed by the first recommended controller parameter and the recommended control model to the controller by the first data writing-out module so as to optimize the operation performance of the controller by using the first optimization result.

In some embodiments, the method further includes a first data writing module, and the step of determining, by the control optimization module according to the model mismatch detection result, the type of the influencing factor influencing the operation performance of the controller includes:

and determining a second recommended controller parameter matched with the design index of the controller according to the initial model, sending the second recommended controller parameter to the first data writing-out module, and feeding back a second optimization result formed by the second recommended controller parameter to the controller by the first data writing-out module so as to optimize the running performance of the controller by using the second optimization result.

According to another aspect of the present application, there is also provided a controller operation and maintenance system, including:

a controller operation and maintenance device;

an industrial field control subsystem comprising a controller to be operated and maintained and an industrial process object controlled by the controller;

the controller operation and maintenance device is used for operating and maintaining the controller.

In some embodiments, the controller further comprises a data acquisition and storage subsystem, and the data acquisition and storage subsystem is used for acquiring and storing the operation data generated by the industrial field control subsystem and the data generated when the controller operation and maintenance device operates and maintains the controller.

According to the embodiment of the application, the operation data of the industrial field control subsystem where the controller is located and the configuration parameters required by operation and maintenance are collected, and the reason for the control performance reduction of the controller is determined according to the configuration parameters and the operation data, so that the performance of a control loop is improved according to the type of the influence factors of the performance reduction, and the operation performance of the industrial controller is automatically monitored, diagnosed and maintained. The industrial controller is ensured to continuously maintain the operation performance at the initial commissioning stage, the real-time and targeted operation and maintenance of the control loop of the complex industrial process object are realized, and the industrial production quality of the industrial process object is kept stable.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this application, are included to provide a further understanding of the application, and the description of the exemplary embodiments of the application are intended to be illustrative of the application and are not intended to limit the application. In the drawings:

fig. 1 is a flowchart of a controller operation and maintenance method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a controller operation and maintenance device according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a controller operation and maintenance system according to an embodiment of the present application;

FIG. 4 is an operation and maintenance schematic block diagram of a controller operation and maintenance system according to an embodiment of the present application;

fig. 5 is a schematic flow chart of the operation and maintenance of the controller operation and maintenance system shown in fig. 4.

Wherein the figures include the following reference numerals:

10. a controller operation and maintenance device; 11. a first data read-in module; 12. a mismatch detection module; 13. a performance evaluation module; 14. a control optimization module; 15. a model update module; 16. a first data writing-out module; 17. monitoring an interface module; 20. a data acquisition and storage subsystem; 21. a second data writing-out module; 22. a data cloud storage module; 23. a second data read-in module; 30. an industrial field control subsystem; 31. a third data read-in module; 32. a controller; 33. an industrial process object; 34. a third data writing-out module; 35. and a set value input module.

Detailed Description

It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.

In a first embodiment of the present invention, a method for operating and maintaining a controller 32 is provided, where the controller 32 controls an industrial process object 33 in an industrial field control subsystem 30, and the industrial field control subsystem 30 and a controller operation and maintenance device 10 for operating and maintaining the controller 32 form an operation and maintenance system for the controller 32, please refer to fig. 1, where when the controller operation and maintenance device 10 performs operation and maintenance on the controller 32 by using the operation and maintenance method provided in the embodiment of the present invention, the operation and maintenance method includes the following steps:

step S11: the configuration parameters are parameters required for operation and maintenance of the operation performance of the controller 32, and the initial model is a mathematical model conforming to initial characteristics of the industrial process object 33.

In an embodiment of the present invention, the initial characteristic of the industrial process object 33 is a characteristic that the controller 32 had before the change in the operational performance. Because the operation and maintenance process is a control flow that continuously and circularly maintains the operation performance of the controller 32, the initial model of the industrial process object 33 in some operation and maintenance rounds can be a nominal model that is determined for the controller 32 during design and conforms to the original characteristics of the industrial process object 33, and before the operation and maintenance, a user configures the nominal model in configuration parameters, or can be a recommended control model that conforms to the real characteristics of the industrial process object 33 during the last operation and maintenance according to the operation data after the last operation and maintenance. The control command data of the controller 32, such as rotational speed, valve opening, feed rate, etc., controls the command data of the industrial process object 33, and the status data is determined according to the controlled industrial process object 33, such as temperature, flow rate, weight, density, etc.

Step S12: according to the configuration parameters and the operation data, the operation performance of the controller 32 is evaluated, and a performance evaluation result is obtained, wherein the performance evaluation result is used for determining whether the control performance of the controller 32 is deteriorated, if the control performance of the controller 32 is not deteriorated, the industrial field control subsystem where the controller 32 is located continuously operates, and if the performance is deteriorated, a corresponding operation and maintenance mechanism is made for the controller 32, so that unnecessary monitoring and diagnosis processes can be avoided, the operation and maintenance efficiency is improved, and the effectiveness and timeliness of the operation and maintenance of the controller 32 are ensured.

Step S13: and when the performance evaluation result is that the operation performance of the controller 32 is abnormal, judging whether the industrial process object 33 has model mismatch according to the configuration parameters and the operation data, and obtaining a model mismatch detection result.

In the embodiment of the present invention, when determining whether the model mismatch occurs in the industrial process object 33 according to the configuration parameters and the operation data, the model mismatch detection algorithm adopted includes, but is not limited to, a correlation analysis method, a system identification method, and the like. The configuration parameters used for the model mismatch detection include a preset model mismatch threshold and a mismatch detection data time period, and then step S13 determines whether the industrial process object 33 has model mismatch according to the configuration parameters and the operation data, so as to obtain the operation data collected in the mismatch detection data time period, and determines whether the industrial process object 33 has model mismatch according to the model mismatch threshold and the selected operation data. Mismatch detection is performed by selecting data from the time of year/month/day 12 to year/month/day 15. The configuration parameters further include a mismatch detection period, which is used to specify a time period for determining whether the industrial process object 33 has model mismatch, and determine how often to run a mismatch detection process, so as to automatically determine the operation performance of the controller 32 according to data in a specific time period, and implement regular automatic monitoring and diagnosis of the operation performance of the controller 32.

Step S14: determining the type of the influence factors influencing the operation performance of the controller 32 according to the model mismatch detection result, and determining an operation and maintenance strategy optimizing the operation performance of the controller 32 based on the type of the influence factors, so as to optimize the operation performance of the controller 32 according to different influence factors and improve the performance of a control loop.

When the performance of the controller 32 is evaluated according to the configuration parameters and the operation data, the performance evaluation algorithm used in the embodiment of the present invention includes, but is not limited to, a minimum variance control, a linear quadratic gaussian and other standard evaluation algorithm, an anomaly detection-based evaluation algorithm, and a data statistical index-based evaluation algorithm. The configuration parameters collected during the performance evaluation include a preset control performance change threshold, a reference data time period and an evaluation data time period, wherein the step S12 of performing the performance evaluation on the operation performance of the controller 32 and obtaining the performance evaluation result according to the configuration parameters and the operation data specifically includes:

reference operation data acquired within a reference data time period is acquired, wherein the reference operation data is operation data acquired when the operation performance of the controller 32 is not abnormal. And taking the operation data collected in the evaluation data time period as the operation data to be evaluated. And performing performance evaluation on the operation performance of the controller 32 according to the control performance change threshold, the operation data to be evaluated and the reference operation data, and obtaining a performance evaluation result. The reference operation data collected in the reference data time period is data when the operation performance of the controller 32 is good, and the operation data to be evaluated collected in the data time period is evaluated, for example, the operation data in the period from 11 to 14. The configuration parameters also include a performance evaluation period that specifies a time period for performing a performance evaluation of the operational performance of the controller 32 to determine how often to run the performance evaluation algorithm to perform the performance evaluation of the operational performance of the controller 32, such as running the performance evaluation algorithm once a day or a week to perform the performance evaluation of the operational performance of the controller 32. The operation and maintenance of the controller 32 can be achieved in the operation and maintenance modes of cost saving, instant access, uninterrupted operation and maintenance and the like, and the stability of the industrial production quality can be continuously kept.

In the embodiment of the present invention, when performing performance evaluation on the controller 32, a specific implementation process of performing performance evaluation on the controller 32 is introduced by taking an evaluation algorithm based on a data statistical indicator as an example, and a basic idea of the evaluation algorithm based on the data statistical indicator is to compare a change situation of the operational performance of the controller 32 in the evaluation data time period with respect to a reference data time period, the change situation including deterioration, substantial invariance or improvement, by calculating a statistical indicator related to reference operational data in the reference data time period and to-be-evaluated operational data in the evaluation data time period, and then indicate a performance improvement space of the industrial field control subsystem 30 under various change situations, wherein the statistical indicator includes, but is not limited to, a control error standard deviation, an on-line rate, a covariance, a saturation rate, a range rate, a change number, a minimum variance performance indicator, and the like. Taking an evaluation monitoring method based on covariance as an example, when the performance of the operation performance of the controller 32 is evaluated according to the control performance change threshold, the operation data to be evaluated and the reference operation data, the method mainly comprises the following steps:

11 Selecting output data with better performance in a reference data time period as reference data, acquiring operation data in a monitoring stage (namely, an evaluation data time period), and setting a control performance change threshold in configuration parameters by a user, wherein the control performance change threshold comprises a performance deterioration threshold and a performance improvement threshold;

12 The covariance matrix of the output variables of the industrial process objects 33 in the industrial field control subsystem 30 in the reference data time period and the covariance matrix of the evaluation data time period are calculated, the covariance matrix of the reference data time period and the covariance matrix of the evaluation data time period are subjected to generalized characteristic root decomposition, the matrix characteristic value of each covariance matrix is obtained, and the overall performance index of the monitoring stage is calculated;

13 Carrying out generalized eigenvalue statistical inference to obtain confidence intervals of matrix eigenvalues of each covariance matrix in corresponding eigen directions, comparing the confidence intervals with a performance deterioration threshold value and a performance improvement threshold value set by a user, and judging the change condition of performance in the corresponding eigen directions;

14 By vector projection, the primary output variables that cause the controller 32 to degrade in performance or improve the direction of the features are determined.

When the embodiment of the invention evaluates the performance of the controller 32, a specific implementation process of the performance evaluation of the controller 32 is introduced by taking an evaluation algorithm based on a minimum variance control reference as an example, and the basic idea of the minimum variance control evaluation algorithm is to calculate an idealized minimum variance output by the current control system process through analysis of process historical data and a disturbance model, and use the ideal minimum variance as an evaluation reference to indicate performance improvement spaces of the control system under various working conditions. The method mainly comprises the following steps: and constructing a time sequence model based on historical closed-loop output data, performing step response expansion, solving a minimum variance control output item, solving a control error variance based on real-time closed-loop output data, and calculating a minimum variance performance index, wherein when the minimum variance performance index is obviously smaller than 1, the performance of the controller 32 is possibly abnormal, and a space for improving the performance exists.

Wherein, the step S13 of determining the type of the influencing factor influencing the operation performance of the controller 32 according to the model mismatch detection result includes:

when the model mismatch detection result indicates that the industrial process object 33 has model mismatch, it is determined that the type of the influencing factor is that the actual characteristic of the industrial process object 33 is different from the initial characteristic. That is, if the model detection is mismatched, the initial characteristics such as the structure and parameters of the industrial process object 33 itself are changed significantly from the initial stage of commissioning or the last operation and maintenance. For example, at the time of first operation, the initial characteristics may be the original characteristics corresponding to the nominal model of the industrial process object 33 determined at the time of design of the controller 32, i.e., the original characteristics determined at the time of design of the industrial process object 33 have changed significantly. Then, the step S13 of determining the operation and maintenance strategy for optimizing the operation performance of the controller 32 based on the type of the influencing factor includes:

the method comprises the steps of obtaining a recommended control model determined according to operation data, wherein the recommended control model is a mathematical model conforming to real characteristics of an industrial process object 33. Then, a first recommended controller parameter matched with the design index of the controller 32 is determined according to a recommended control model, so as to optimize the operation performance of the controller 32 by using a first optimization result formed by the first recommended controller parameter and the recommended control model, thereby ensuring that the controller 32 continuously maintains the operation performance at the initial commissioning stage when the characteristics of the structure, the parameters and the like of the industrial process object 33 change, wherein the recommended control model comprises a finite step response model, a transfer function model and a state space equation model. The first recommended controller parameters comprise a proportional coefficient Kp, an integral coefficient Ti and a differential coefficient Td of a PID controller, a feedback gain of a linear quadratic controller LQR, a smoothing factor, an equivalent deviation, a closed-loop reference time, a model feedback correction parameter and the like of a model predictive controller MPC, wherein the PID controller is short for the proportional-integral-differential controller.

Next, the step S13 of determining the type of the influencing factor influencing the operation performance of the controller 32 according to the model mismatch detection result includes:

when the model mismatch detection result indicates that the industrial process object 33 does not have model mismatch, determining that the type of the influencing factor is that the external environment in which the industrial process object 33 currently operates is different from the initial operation environment. That is, it is the operating environment of the industrial process object 33 that has external disturbances or the like. The step S13 of determining the operation and maintenance strategy for optimizing the operation performance of the controller 32 based on the type of the influencing factor includes:

second recommended controller parameters matching the design criteria of the controller 32 are determined from the initial model to optimize the operational performance of the controller 32 using a second optimization result formed from the second recommended controller parameters to ensure that the controller 32 continuously maintains the operational performance at the initial stage of operation when changes are made outside the operating environment of the industrial process object 33. The second recommended controller parameters include a proportional coefficient Kp, an integral coefficient Ti, and a differential coefficient Td of the PID controller, a feedback gain of the linear quadratic controller LQR, a smoothing factor, an equivalent deviation, a closed-loop reference time, a model feedback correction parameter, and the like of the model predictive controller MPC.

The operation and maintenance method of the controller 32 provided by the embodiment of the invention comprises the steps of performance evaluation of the controller 32, model mismatch detection of a controlled industrial procedure object, model online identification, control parameter optimization and the like, and a complete and fully-autonomous closed-loop operation and maintenance process is formed. By collecting the operation data of the industrial field control subsystem 30 where the controller 32 is located and the configuration parameters required by operation and maintenance, the reason for the control performance degradation of the controller 32 is determined according to the configuration parameters, the initial model of the industrial process object 33 and the control instruction data of the controller 32, the performance of the control loop is improved in a targeted manner, and the operation performance of the industrial controller 32 is automatically monitored, diagnosed and maintained. The industrial controller 32 is ensured to continuously maintain the operation performance at the initial commissioning stage, the control loop of the complex industrial process object 33 is timely and purposefully operated and maintained, and the industrial production quality of the industrial process object 33 is ensured to be stable.

Compared with the traditional operation and maintenance method, the operation and maintenance method for the controller 32 provided by the embodiment of the invention avoids the complexity and low efficiency of frequent manual maintenance, can position the reason for the reduction of the control performance of the controller 32 according to the configured configuration parameters and the operation data of the industrial field control subsystem 30 where the controller 32 is located, and improves the performance of a control loop aiming at different reasons.

In the second embodiment of the present invention, a controller operation and maintenance device 10 is further provided, wherein the controller operation and maintenance device 10 is configured to operate and maintain a controller 32 for controlling an industrial process object 33 in an industrial field control subsystem 30. Referring to fig. 2, the controller operation and maintenance device 10 includes a first data reading module 11, a performance evaluation module 13, a mismatch detection module 12, and a control optimization module 14. The first data reading module 11 is used for collecting configuration parameters and operation data of the industrial field control subsystem 30. The operational data includes control command data for the controller 32 and state data and an initial model of the industrial process object 33, the configuration parameters are parameters required for operation and maintenance of the operational performance of the controller 32, and the initial model is a mathematical model conforming to initial characteristics of the industrial process object 33. The initial model of the industrial process object 33 may be a nominal model that conforms to the original characteristics of the industrial process object 33 as determined by the controller 32 during some of the operation and maintenance rounds, or a recommended control model that conforms to the real characteristics of the industrial process object 33 as determined by the operation data after the last operation and maintenance.

The performance evaluation module 13 is configured to perform performance evaluation on the operation performance of the controller 32 according to the configuration parameters and the operation data, and obtain a performance evaluation result. Under the condition that the performance evaluation result shows that the control performance of the controller 32 is deteriorated, the control optimization module 14 is used for executing the optimization updating process of the controller 32 on the controller 32, so that unnecessary monitoring and diagnosis processes are avoided, the operation and maintenance efficiency is improved, and the effectiveness and timeliness of the operation and maintenance are ensured.

When the performance evaluation module 13 performs performance evaluation on the operation performance of the controller 32 according to the configuration parameters and the operation data, the performance evaluation algorithm adopted in the embodiment of the present invention includes, but is not limited to, a minimum variance control, a linear quadratic gaussian and other benchmark evaluation algorithm, an anomaly detection-based evaluation algorithm, and a data statistical index-based evaluation algorithm. The configuration parameters collected during performance evaluation include a preset control performance change threshold, a reference data time period and an evaluation data time period, wherein the performance evaluation module 13 performs performance evaluation on the operation performance of the controller 32 according to the configuration parameters and the operation data and obtains a performance evaluation result specifically includes the following steps:

reference operation data acquired within a reference data time period is acquired, wherein the reference operation data is operation data acquired when the operation performance of the controller 32 is not abnormal. And taking the operation data collected in the evaluation data time period as the operation data to be evaluated. And performing performance evaluation on the operation performance of the controller 32 according to the control performance change threshold, the operation data to be evaluated and the reference operation data, and obtaining a performance evaluation result. The reference operation data acquired in the reference data time period is data when the operation performance of the controller 32 is good, the reference data time period is configured in the configuration parameters, and the controller operation and maintenance device 10 transmits the operation data of the industrial field control subsystem 30 acquired in the time period specified by the reference data time period as the reference operation data to the performance evaluation module 13 when the controller 32 operates normally. And evaluating the operation data to be evaluated collected in the data time period, such as selecting the operation data in the time period from 11. The configuration parameters also include a performance evaluation period that specifies a time period for performing a performance evaluation of the operational performance of the controller 32 to determine how often to run the performance evaluation algorithm to perform the performance evaluation of the operational performance of the controller 32, such as running the performance evaluation algorithm once a day or a week to perform the performance evaluation of the operational performance of the controller 32. The operation and maintenance of the controller 32 can be achieved in the operation and maintenance modes of cost saving, instant access, uninterrupted operation and maintenance and the like, and the stability of the industrial production quality can be continuously kept.

In the embodiment of the present invention, when performing performance evaluation on the controller 32, a specific implementation process of performing performance evaluation on the controller 32 is described by taking an evaluation algorithm based on a data statistical indicator as an example, and a basic idea of the evaluation algorithm based on the data statistical indicator is to compare changes of the operation performance of the controller 32 in the evaluation data time period with respect to a reference data time period by calculating a reference operation data of the reference data time period and a statistical indicator related to an operation data to be evaluated in the evaluation data time period, where the changes include deterioration, substantial invariance or improvement, and then indicate a performance improvement space of the controller 32 under various changes, where the statistical indicator includes, but is not limited to, a control error standard deviation, an on-line rate, a covariance, a saturation rate, a performance indicator in a range rate, a change number, a minimum variance, and the like. Taking the covariance-based evaluation monitoring method as an example, when the performance evaluation module 13 evaluates the performance of the controller 32 according to the control performance change threshold, the to-be-evaluated operation data and the reference operation data, the main implementation steps are as follows:

The mismatch detection module 12 is configured to, when the performance evaluation result is that the operation performance of the controller 32 is abnormal, determine whether the industrial process object 33 has model mismatch according to the configuration parameters and the operation data, and obtain a model mismatch detection result. In the embodiment of the present invention, when the mismatch detection module 12 determines whether the industrial process object 33 has a model mismatch according to the configuration parameters and the operation data, the model mismatch detection algorithm adopted includes, but is not limited to, a correlation analysis method, a system identification method, and the like. The configuration parameters adopted by the mismatch detection module 12 include a preset model mismatch threshold and a mismatch detection data time period when the model mismatch detection algorithm detects model mismatch. When judging whether the industrial process object 33 has model mismatch according to the configuration parameters and the operation data, the collected operation data in the time period specified by the mismatch detection data time period can be selected, and whether the industrial process object 33 has model mismatch is judged according to the model mismatch threshold and the selected operation data. Mismatch detection is performed by selecting data from the time of year/month/day 12 to year/month/day 15. The configuration parameters further include a mismatch detection period, which is used to specify a time period for determining whether the industrial process object 33 has model mismatch, and determine how often to run a mismatch detection process, so as to automatically determine the operation performance of the controller 32 according to data in a specific time period, and implement regular automatic monitoring and diagnosis of the operation performance of the controller 32.

The control optimization module 14 is configured to determine, according to the model mismatch detection result, an influence factor type that influences the operation performance of the controller 32, and determine an operation and maintenance strategy that optimizes the operation performance of the controller 32 based on the influence factor type, so as to optimize the operation performance of the controller 32 for different influence factors, thereby improving the performance of the control loop.

The controller operation and maintenance device 10 further includes a model updating module 15 and a first data writing-out module 16, wherein the step of determining the type of the influencing factor influencing the operation performance of the controller 32 by the control optimization module 14 according to the model mismatch detection result includes: when the model mismatch detection result indicates that the industrial process object 33 has model mismatch, it is determined that the type of the influencing factor is that the actual characteristic of the industrial process object 33 is different from the initial characteristic, that is, the initial characteristics of the industrial process object 33, such as the structure and the parameters, are obviously changed. The step of the control optimization module 14 determining an operation and maintenance strategy for optimizing the operational performance of the controller 32 based on the type of the influencing factor comprises: the control optimization module 14 obtains a recommended control model determined by the model update module 15 according to the operating data, where the recommended control model is a mathematical model that conforms to the real characteristics of the industrial process object 33. When the recommended control model conforming to the real characteristics of the industrial process object 33 is determined according to the operation data, the adopted model online identification algorithm includes, but is not limited to, a least square method, a prediction error algorithm, a subspace method and the like. Then, the control optimization module 14 determines a first recommended controller parameter matched with the design index of the controller 32 according to the recommended control model, and sends the first recommended controller parameter to the first data writing-out module 16, and the first data writing-out module 16 feeds back a first optimization result formed by the first recommended controller parameter and the recommended control model to the controller 32 to optimize the operation performance of the controller 32 by using the first optimization result, so that when the characteristics of the structure, the parameters and the like of the industrial process object 33 change, the controller 32 is ensured to continuously maintain the operation performance at the initial commissioning stage.

The step of determining, by the control optimization module 14, the type of the influencing factor influencing the operation performance of the controller 32 according to the model mismatch detection result includes: when the model mismatch detection result indicates that the industrial process object 33 does not have model mismatch, determining that the type of the influencing factor is that the external environment in which the industrial process object 33 currently operates is different from the initial operation environment. Such as external disturbances to the operating environment of the industrial process object 33. The step of the control optimization module 14 determining an operation and maintenance strategy for optimizing the operational performance of the controller 32 based on the type of the influencing factor comprises: and determining a second recommended controller parameter matched with the design index of the controller 32 according to the initial model, sending the second recommended controller parameter to the first data writing-out module 16, and feeding back a second optimization result formed by the second recommended controller parameter to the controller 32 by the first data writing-out module 16 so as to optimize the operation performance of the controller 32 by using the second optimization result, thereby ensuring that the controller 32 continuously maintains the operation performance at the initial commissioning stage when the operation environment of the industrial process object 33 is changed.

In the third embodiment of the present invention, a controller 32 operation and maintenance system is further provided, where the operation and maintenance system includes the controller operation and maintenance device 10, the data acquisition and storage subsystem 20, and the industrial field control subsystem 30 includes a controller 32 to be operated and maintained and an industrial process object 33 controlled by the controller 32. The controller operation and maintenance device 10 is used for operating and maintaining the controller 32. The data collection and storage subsystem 20 is used for collecting and storing operation data generated by the industrial field control subsystem and data generated when the controller operation and maintenance device 10 performs operation and maintenance on the controller 32, that is, the controller operation and maintenance device 10 performs data interaction with the industrial field control subsystem 30 through the data collection and storage subsystem 20.

Specifically, the controller operation and maintenance device 10 in the embodiment of the present invention is used as a cloud intelligent operation and maintenance subsystem combined with a cloud computing platform, and has potential large-scale application and duplication technical achievements in the industries of cement, solid waste, steel, and the like, and in the embodiment of the present invention, the data acquisition and storage subsystem 20 is used for acquiring and storing operation data generated by the industrial field control subsystem 30 and optimization result data generated by the cloud intelligent operation and maintenance subsystem. The cloud intelligent operation and maintenance subsystem performs control performance effect evaluation, detection and control optimization on the operating industrial controller 32 according to the collected field operation data and outputs optimization result data. The industrial field control subsystem 30 adjusts the parameters of the controller 32 according to the issued optimization result data and continuously operates. The embodiment of the invention carries out scheduling, operation and storage on the data acquisition and storage subsystem 20 based on the cloud platform and configuration, so that the whole operation and maintenance system is not limited by specific physical storage and computing equipment, and has the advantages of cost saving, instant access, uninterrupted data safety and the like.

As can be seen from the operation and maintenance schematic block diagram of the operation and maintenance system shown in fig. 4, the controller operation and maintenance device 10 serving as the cloud-side intelligent operation and maintenance subsystem includes a performance evaluation module 13, a mismatch detection module 12, a model update module 15, a control optimization module 14, a first data reading module 11, a first data writing module 16, and a monitoring interface module 17.

The performance evaluation module 13 is configured with a first input interface, a controller performance evaluation algorithm, and a first output interface, where the first input interface receives the operation data of the industrial field control subsystem 30 collected by the first data reading module 11 and the configuration parameters required by the operation and maintenance configured by the user at the monitoring interface module 17, where the operation data includes control instruction data of the controller 32, state data of the industrial process object 33, and a nominal model. The process control model in fig. 4 is a nominal model or a recommended control model recommended by the model update module 15 at the last operation and maintenance time. The first output interface outputs a performance evaluation result generated by the controller performance evaluation algorithm after evaluating the operating performance of the controller 32. The configuration parameters are mainly parameters required for the performance evaluation module 13 to perform performance evaluation and the mismatch detection module 12 to perform mismatch detection, and include parameters such as a performance degradation threshold, a performance improvement threshold, a model mismatch threshold, a performance evaluation data time period, a mismatch detection data time period, and an algorithm operation period, and the configuration parameters are input by a user from the monitoring interface module 17. Considering that the performance evaluation/mismatch detection is performed based on the collected input and output data, it is required to select which data segment to evaluate/mismatch detect, where the data time segments of the performance evaluation or mismatch detection are: for example, the data of the section from 12 to 00 in a certain year/month/day to 15 in a certain year/month/day is selected for performance evaluation or mismatch detection, the operation cycle of the algorithm is used for specifying how often the performance evaluation module 13 operates the evaluation algorithm, and the mismatch detection module 12 operates the mismatch detection algorithm, for example, once a day or a week, i.e., the data time period is used for determining the operation frequency of the performance evaluation algorithm and the model mismatch algorithm in the operation and maintenance system.

The mismatch detection module 12 is configured with a second input interface, a model mismatch detection algorithm, and a second output interface, the second input interface receives the configuration parameters and the operation data collected by the first data read-in module 11, and the second output interface outputs a mismatch detection result generated after the model mismatch detection algorithm performs model mismatch detection on the industrial process object 33.

The model updating module 15 is configured with a third input interface, an online model identification algorithm, and a third output interface, where the third input interface receives the operation data collected by the first data reading module 11 and the mismatch detection result output by the second output interface of the mismatch detection module 12, and the third output interface outputs the recommended control model to the control optimization module 14 and the first data writing module 16.

The control optimization module 14 is configured with a fourth input interface, a control parameter recommendation algorithm, and a fourth output interface, where the fourth input interface receives the recommended control model, and the fourth output interface outputs the recommended controller parameter that is determined by the control parameter recommendation algorithm by the control optimization module 14 according to the recommended control model and matches the design index of the controller 32.

The monitoring interface module 17 is configured with a fifth input interface, a result display interface, a trend analysis interface, a parameter editing interface, a fifth output interface, and the like, the fifth input interface receives the operation data, the evaluation result, the mismatch detection result, and the optimization result, and the fifth output interface sends the configuration parameters input by the user to the first data reading module 11.

The data acquisition and storage subsystem 20 comprises a data cloud storage module 22, a second data reading-in module 23 and a second data writing-out module 21. The second data reading module 23 acquires operation data from the industrial field control subsystem 30, and acquires recommended controller parameter data from the cloud intelligent operation and maintenance subsystem, and the data cloud storage module 22 is responsible for storing the operation data and the recommended controller parameter data. The second data writing-out module 21 writes out the operation data and the recommended controller parameter data to the cloud intelligent operation and maintenance subsystem and the industrial field control subsystem 30.

The industrial field control subsystem 30 includes a third data read-in module 31, a setpoint input module 35, a controller 32, an industrial process object 33, and a third data write-out module 34. The controller 32 is configured with a sixth input interface, a control algorithm, and a sixth output interface, where the sixth input interface is the state data, the instruction set value, and the optimization result carrying the recommended controller parameter of the industrial process object 33, and the sixth output interface outputs the control instruction data obtained through the operation of the control algorithm to the industrial process object 33. The industrial process object 33 module is configured with a seventh input interface, an industrial process object body and a seventh output interface, the seventh input interface receives the control instruction data issued by the controller 32, and the seventh output interface outputs the status data.

The operation and maintenance method based on the cloud intelligent operation and maintenance subsystem in the embodiment of the invention mainly comprises the following steps:

as can be seen from fig. 4 and 5, the operation and maintenance method includes four main steps, namely, control performance evaluation, model mismatch detection, model online identification, and control parameter optimization. Wherein:

1) During control performance evaluation, according to the operation data of the industrial field control subsystem obtained by the data acquisition and storage subsystem and the configuration parameters input by the user, the operation performance evaluation module 13 obtains an operation state evaluation result of the controller 32 by using a performance evaluation algorithm, and determines whether the operation performance of the controller 32 is abnormal according to the evaluation result, as can be seen from fig. 5, if no abnormality occurs, no maintenance processing is performed, the industrial field control subsystem 30 is allowed to operate continuously, and if the abnormality occurs, a model mismatch detection flow is entered, and the steps 2) to 4) are executed. The performance evaluation algorithm includes, but is not limited to, an evaluation algorithm based on a minimum variance control, linear quadratic gaussian, and other benchmarks, an evaluation algorithm based on anomaly detection, and an evaluation algorithm based on historical data statistical indexes.

The configuration parameters acquired by the performance evaluation module 13 during performance evaluation include a preset performance change threshold, a reference data time period and an evaluation data time period, wherein the step of performing performance evaluation on the operation performance of the controller 32 and obtaining a performance evaluation result by the performance evaluation module 13 according to the configuration parameters and the operation data specifically includes:

and acquiring reference operation data acquired in a reference data time period, wherein the reference operation data is operation data acquired by the cloud intelligent operation and maintenance subsystem when the operation performance of the controller 32 is not abnormal. And taking the operation data collected in the evaluation data time period as the operation data to be evaluated. And performing performance evaluation on the operation performance of the controller 32 according to the control performance change threshold, the operation data to be evaluated and the reference operation data, and obtaining a performance evaluation result. The reference operating data collected during the reference data period is data when the operating performance of the controller 32 is good. And evaluating the operation data to be evaluated collected in the data time period, such as selecting the operation data in the time period from 11. The configuration parameters also include a performance evaluation period that specifies a time period for performing a performance evaluation of the operational performance of the controller 32 to determine how often to run the performance evaluation algorithm to perform the performance evaluation of the operational performance of the controller 32, such as running the performance evaluation algorithm once a day or a week to perform the performance evaluation of the operational performance of the controller 32. The operation and maintenance of the controller 32 can be achieved in the operation and maintenance modes of cost saving, instant access, uninterrupted operation and maintenance and the like, and the stability of the industrial production quality can be continuously kept.

In the embodiment of the present invention, when performing performance evaluation on the controller 32, a specific implementation process of performing performance evaluation on the controller 32 is introduced by taking an evaluation algorithm based on a data statistical indicator as an example, and a basic idea of the evaluation algorithm based on the data statistical indicator is to compare a change situation of the operational performance of the controller 32 in the evaluation data time period with respect to a reference data time period, the change situation including deterioration, substantial invariance or improvement, by calculating a statistical indicator related to reference operational data in the reference data time period and to-be-evaluated operational data in the evaluation data time period, and then indicate a performance improvement space of the industrial field control subsystem 30 under various change situations, wherein the statistical indicator includes, but is not limited to, a control error standard deviation, an on-line rate, a covariance, a saturation rate, a range rate, a change number, a minimum variance performance indicator, and the like. Taking an evaluation monitoring method based on covariance as an example, the method mainly comprises the following steps:

When the embodiment of the invention evaluates the performance of the controller 32, a specific implementation process of the performance evaluation of the controller 32 is introduced by taking an evaluation algorithm based on a minimum variance control reference as an example, and the basic idea of the evaluation algorithm of the minimum variance control reference is to calculate an idealized minimum variance of the process output of the current control system through the analysis of process historical data and a disturbance model, and use the ideal minimum variance as an evaluation reference to indicate a performance improvement space of the control system under various working conditions. The method mainly comprises the following steps: and constructing a time sequence model based on historical closed-loop output data, performing step response expansion, solving a minimum variance control output item, solving a control error variance based on real-time closed-loop output data, and calculating a minimum variance performance index, wherein when the minimum variance performance index is obviously smaller than 1, the performance of the controller 32 is possibly abnormal, and a space for improving the performance exists.

2) During the model mismatch detection, in one round of mismatch detection, the performance evaluation result, the original or user-input nominal model of the industrial process object 33 during the commissioning of the controller, the configuration parameters input by the user, and the operation data of the industrial field control subsystem obtained through the data acquisition and storage subsystem 20 are used as the basis. The operation model mismatch detection module 12 obtains an accuracy detection result of the nominal model by using a model mismatch detection algorithm, and evaluates whether model mismatch occurs in the original model according to the detection result. The model mismatch detection algorithm includes, but is not limited to, correlation analysis, system identification, and the like. Taking a system identification method as an example, the core principle is that the collected operation data, configuration parameters and evaluation results are combined with a nominal model to obtain the prediction error data of the nominal model, then the input data and the prediction error data are combined to carry out system identification to construct an error model, and finally the error model and the nominal model are compared to obtain the mismatch degree to evaluate whether the nominal model is mismatched. The method comprises the following specific steps:

21 In combination with the collected input and output data and the nominal model of the industrial process object 33 as determined at the time of controller design, to construct prediction error data by model simulation;

22 Combining input and predicted error data to construct an extended data matrix of the error model at the past moment and the future moment;

23 Solving to obtain an expansion coefficient matrix of the error model by expanding the data matrix;

24 Solving a system matrix of the error model by expanding the coefficient matrix;

25 Comparing the system matrix of the error model with a nominal model to obtain a mismatching degree index for measuring the difference between the models;

26 According to the mismatch index and a mismatch threshold set by the configuration parameters, judging whether the nominal model is mismatched, and if the mismatch index is greater than the mismatch threshold, determining that the model is mismatched.

3) Under the condition of model mismatch, model online identification is carried out through the model updating module 15, operation data of the industrial field control system are obtained through data acquisition and storage according to the result of model mismatch detection, and the recommended control model which is closer to the current real characteristic of the industrial process object 33 is obtained through the model online identification algorithm of the operation model updating module 15. The recommended control model comprises a finite step response model, a transfer function model and a state space equation model. The model online identification algorithm includes, but is not limited to, a least square method, a prediction error algorithm, a subspace method, etc., and taking the subspace method as an example, the core principle is to obtain an estimation model of the characteristics of the industrial process object 33 by using the collected input and output data to perform parameter identification. The method comprises the following specific steps:

31 Combining input data and output data to construct an extended data matrix at the past moment and the future moment, wherein the input data and the output data are respectively operation data and a mismatch detection result;

32 Solving by expanding the data matrix to obtain an expansion coefficient matrix;

33 Solving a system matrix of the identification model through the expansion coefficient matrix;

34 According to the combination forgetting factor), the nominal model and the identification model are weighted to obtain a recommended control model closer to the current real characteristics of the industrial process object 33.

4) The control optimization module 14 has two working modes for optimizing the control parameters:

41 If the model mismatch detection module 12 detects that the model of the industrial process object 33 has mismatch, and the characteristics of the structure, parameters and the like of the industrial process object 33 itself have obvious changes, the operation control optimization module 14 obtains recommended controller parameters matching the design indexes of the controller 32 by adopting a control parameter optimization algorithm according to the recommended control model which is identified and output by the model update module 15, wherein the recommended controller parameters include a proportional coefficient Kp, an integral coefficient Ti and a differential coefficient Td of a PID controller, a feedback gain of a linear quadratic controller LQR, a smoothing factor, an equivalent deviation, a closed-loop reference time, model feedback correction parameters and the like of a model predictive controller MPC.

42 If the model detection is not mismatched and it is a significant change outside the operating environment of the industrial process object 33, the operation control optimization module 14 uses a control parameter optimization algorithm to obtain recommended controller parameters that match the design specifications of the controller 32 based on the nominal model and the results of the performance evaluation.

The control parameter optimization algorithm adopted by the control optimization module 14 includes, but is not limited to, a critical ratio method, an internal model control method, and the like. Taking the critical proportionality method as an example, the core principle is to use the collected input and output data to perform parameter identification to obtain an estimation model of the characteristics of the industrial process object 33. The method comprises the following specific steps:

121 According to the identified recommended control model, a closed-loop control loop is constructed, and the critical stability limit of the loop is determined;

122 According to the setting formula and the design index of the controller 32, calculating to obtain the recommended controller parameter of the controller 32, wherein the nominal model is a mathematical model which is determined when the controller 32 is put into operation and reflects the original characteristic of the industrial process object 33.

The operation and maintenance method comprises the following specific steps:

step S1, obtaining operation data generated by the operation of the industrial field control subsystem 30 from the data acquisition and storage subsystem 20 through the first data reading module 11.

And S2, operating the performance evaluation module 13 in a periodic scheduling or single scheduling mode based on the read-in operation data and configuration parameters input by a user, and evaluating each performance index of the controller 32 in the industrial field control subsystem 30 through a performance evaluation algorithm operated in the performance evaluation module 13 to obtain an evaluation result of the performance of the controller 32.

And step S3, judging whether the performance of the controller 32 is abnormal or not, executing step S4 if the performance of the controller 32 is abnormal, and otherwise executing step S9.

And S4, periodically scheduling or performing single scheduling on the mismatch detection module 12 based on the read operation data and the configuration parameters input by the user, detecting the characteristic change of the model of the industrial process object 33 in the industrial field control subsystem 30 through a model mismatch detection algorithm operated in the mismatch detection module 12, and obtaining the detection result of the model on which the parameters of the controller 32 depend.

And S5, judging whether the model characteristics of the industrial process object 33 are mismatched or not, if so, executing the step S6, otherwise, executing the step S9.

And S6, triggering the operation model updating module 15 based on the read operation data and the result of model mismatch detection, and obtaining a recommended control model closer to the latest characteristic of the industrial process object 33 through a model online identification algorithm operated in the model updating module 15.

And S7, operating the control optimization module 14 based on the recommended control model obtained by the model online identification, and obtaining recommended controller parameters of the controller 32 by combining various performance indexes designed by the controller 32 through a parameter recommendation algorithm operated in the control optimization module 14.

And S8, taking the recommended control model identified on line by the model and the recommended controller parameter optimized by the control parameter as an optimization result, transmitting the optimization result to the data acquisition and storage subsystem 20 through the first data writing-out module 16, sending the optimization result to the industrial field control subsystem 30 through the second data writing-out module 21 of the data acquisition and storage subsystem 20, reading the optimization result by the industrial field control subsystem 30 through the third data reading-in module 31, and updating the model and parameter configuration of the controller 32 by using the read optimization result.

And S9, continuously operating the industrial field control subsystem 30, and periodically scheduling and operating corresponding configuration modules in the cloud intelligent operation and maintenance subsystem according to the configuration parameters to evaluate, detect and optimize, so that the controller 32 is ensured to continuously maintain the operation performance at the initial commissioning stage.

All core modules, algorithms and data contained in the controller 32 operation and maintenance system provided by the embodiment of the invention are stored, scheduled and operated at the cloud, are not limited by specific physical storage and computing equipment, and have the advantages of cost saving, instant access, uninterrupted operation, data security and the like. The operation and maintenance method of the controller 32 comprises control performance evaluation, model mismatch detection, model online identification, control parameter optimization and the like, so that a complete and fully-autonomous closed-loop operation and maintenance process is formed.

The intelligent operation and maintenance method and the operation and maintenance system based on the automatic operation of the cloud computing technology can form a complete fully-autonomous closed-loop operation and maintenance flow at the cloud. The operation and maintenance system comprises a cloud operation and maintenance subsystem, a data acquisition and storage subsystem 20 and an industrial field control subsystem 30. Compared with the traditional operation and maintenance mode, the multiple industrial field controllers 32 can be accessed at the cloud end, cluster-level large-scale automatic operation, maintenance, monitoring and scheduling are achieved, the operation, maintenance and monitoring scale can be expanded, the operation and maintenance threshold is effectively reduced, and the automatic management level of industrial production is improved.

Therefore, the operation and maintenance system provided by the embodiment of the invention can avoid the problems of complexity and low efficiency existing when a large number of workers participate in the operation and maintenance of the controller 32, and can reduce the working pressure of the workers and improve the operation and maintenance quality when the controller 32 is operated and maintained. The performance of a control loop of the controller 32 is comprehensively improved from parameters such as an initial model of the industrial process object 33 and control instruction data of the controller 32, so that the adaptability of the controller 32 to complex and changeable working conditions of an industrial field is improved, the control effect of the controller 32 on the industrial process object 33 is improved, and the operation and maintenance cost of the controller 32 is reduced. The control loop of the complex industrial process object 33 can be operated and maintained timely and pertinently, and the industrial production quality of the industrial process object 33 is kept stable.

The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A controller operation and maintenance method, characterized in that the controller (32) controls an industrial process object (33) in an industrial field control subsystem (30), the operation and maintenance method comprising:

collecting configuration parameters, operation data of the industrial field control subsystem (30), wherein the operation data comprises control instruction data of the controller (32), state data of the industrial process object (33) and an initial model, the configuration parameters are parameters required for operation and maintenance of the operation performance of the controller (32), and the initial model is a mathematical model conforming to initial characteristics of the industrial process object (33);

according to the configuration parameters and the operation data, performing performance evaluation on the operation performance of the controller (32) and obtaining a performance evaluation result;

when the performance evaluation result is that the operation performance of the controller (32) is abnormal, judging whether the industrial process object (33) has model mismatch according to the configuration parameters and the operation data, and obtaining a model mismatch detection result;

determining the type of an influence factor influencing the operation performance of the controller (32) according to the model mismatch detection result, and determining an operation and maintenance strategy for optimizing the operation performance of the controller (32) based on the type of the influence factor.

2. The method of claim 1, wherein determining the type of influencing factor that influences the operational performance of the controller (32) based on the model mismatch detection comprises:

when the model mismatch detection result is that the industrial process object (33) has model mismatch, determining that the type of the influence factor is that the real characteristic currently possessed by the industrial process object (33) is different from the initial characteristic;

then, the step of determining an operation and maintenance strategy for optimizing the operation performance of the controller (32) based on the type of the influencing factor comprises:

obtaining a recommended control model determined from the operational data, the recommended control model being a mathematical model that conforms to the true characteristics of the industrial process object (33);

and determining a first recommended controller parameter matched with the design index of the controller (32) according to the recommended control model so as to optimize the operation performance of the controller (32) by using a first optimization result formed by the first recommended controller parameter and the recommended control model.

3. The method of claim 1, wherein determining a type of influencing factor that influences the operational performance of the controller (32) based on the model mismatch detection further comprises:

when the model mismatch detection result indicates that the industrial process object (33) does not generate model mismatch, determining that the type of the influence factor is that the external environment in which the industrial process object (33) operates currently is different from the initial operation environment;

and determining a second recommended controller parameter matched with the design index of the controller (32) according to the initial model so as to optimize the operation performance of the controller (32) by using a second optimization result formed by the second recommended controller parameter.

4. The method of claim 1, wherein the configuration parameters include a preset control performance variation threshold, a reference data time period, and an evaluation data time period, and wherein the step of performing a performance evaluation of the operating performance of the controller (32) and obtaining a performance evaluation result based on the configuration parameters and the operating data comprises:

acquiring reference operation data acquired in the reference data time period, wherein the reference operation data is the operation data acquired when the operation performance of the controller (32) is not abnormal;

and performing performance evaluation on the operation performance of the controller (32) according to the control performance change threshold, the operation data to be evaluated and the reference operation data, and obtaining a performance evaluation result.

5. The method of claim 4, wherein the configuration parameters further include a preset model mismatch threshold and a mismatch detection data time period, and the step of determining whether a model mismatch occurs in the industrial process object (33) based on the configuration parameters and the operational data comprises:

and acquiring the operation data acquired in the mismatch detection data time period, and judging whether the industrial process object (33) has model mismatch or not according to the model mismatch threshold and the operation data.

6. The method of claim 1, wherein the configuration parameters further include a performance evaluation period specifying a time period for performance evaluation of the operational performance of the controller (32).

7. The method of claim 6, wherein the configuration parameters further include a mismatch detection period specifying a time period for determining whether a model mismatch occurs with the industrial process object (33).

8. A controller operation and maintenance device, characterized in that the controller operation and maintenance device (10) is used for operating and maintaining a controller (32) for controlling an industrial process object (33) in an industrial field control subsystem (30), the controller operation and maintenance device (10) comprises:

the device comprises a first data reading module (11), a performance evaluation module (13), a mismatch detection module (12) and a control optimization module (14);

the first data reading module (11) is used for acquiring configuration parameters and operation data of the industrial field control subsystem (30), wherein the operation data comprises control instruction data of the controller (32), state data of the industrial process object (33) and an initial model, the configuration parameters are parameters required for operation and maintenance of the operation performance of the controller (32), and the initial model is a mathematical model conforming to initial characteristics of the industrial process object (33);

the performance evaluation module (13) is used for performing performance evaluation on the operation performance of the controller (32) according to the configuration parameters and the operation data and obtaining a performance evaluation result;

the mismatch detection module (12) is configured to, when the performance evaluation result is that the operation performance of the controller (32) is abnormal, determine whether a model mismatch occurs in the industrial process object (33) according to the configuration parameter and the operation data, and obtain a model mismatch detection result;

the control optimization module (14) is used for determining the type of an influence factor influencing the operation performance of the controller (32) according to the model mismatch detection result, and determining an operation and maintenance strategy for optimizing the operation performance of the controller (32) based on the type of the influence factor.

9. The controller operation and maintenance device according to claim 8, further comprising a model updating module (15) and a first data writing module (16), wherein the step of determining the type of influencing factor influencing the operation performance of the controller (32) by the control optimization module (14) according to the model mismatch detection result comprises:

then, the step of the control optimization module (14) determining an operation and maintenance strategy for optimizing the operation performance of the controller (32) based on the type of the influence factor comprises:

obtaining a recommended control model determined by the model update module according to the operating data, the recommended control model being a mathematical model that conforms to the real characteristics of the industrial process object (33);

determining a first recommended controller parameter matched with a design index of the controller (32) according to the recommended control model, sending the first recommended controller parameter to the first data writing-out module (16), and feeding back a first optimization result formed by the first recommended controller parameter and the recommended control model to the controller (32) by the first data writing-out module (16) so as to optimize the operation performance of the controller (32) by using the first optimization result.

10. The controller operation and maintenance device according to claim 8, further comprising a first data writing module (16), wherein the step of determining, by the control optimization module (14), the type of influencing factor influencing the operation performance of the controller (32) according to the model mismatch detection result comprises:

when the model mismatch detection result indicates that the industrial process object (33) does not generate model mismatch, determining that the type of the influence factor is that the external environment in which the industrial process object (33) currently operates is different from the initial operation environment;

and determining a second recommended controller parameter matched with the design index of the controller (32) according to the initial model, sending the second recommended controller parameter to the first data writing-out module, and feeding back a second optimization result formed by the second recommended controller parameter to the controller (32) by the first data writing-out module (16) so as to optimize the operation performance of the controller (32) by using the second optimization result.

11. A controller operation and maintenance system, comprising:

the controller operation and maintenance device (10) of any one of claims 8 to 10;

an industrial field control subsystem (30), the industrial field control subsystem (30) including a controller (32) to be operated and maintained and an industrial process object (33) controlled by the controller (32);

the controller operation and maintenance device (10) is used for operating and maintaining the controller (32).

12. The system of claim 11, further comprising a data collection and storage subsystem (20), wherein the data collection and storage subsystem (20) is configured to collect and store operational data generated by the industrial field control subsystem (30) and data generated by the controller operation and maintenance device (10) during operation and maintenance of the controller (32).