Collaborative control method, system and device, and storage medium and related product

Abstract

Provided are a collaborative control method, system and device, and an industrial gateway, a cloud computing platform, a storage medium and a product, which relate to the technical field of big data edge computing. The collaborative control method comprises: by means of an industrial gateway, inputting a first system control instruction to a target industrial control system and a corresponding system mathematical model, wherein the system mathematical model is constructed by means of a cloud computing platform (S1000); collecting first response data generated by the target industrial control system in response to the first system control instruction, and first analog data generated by the system mathematical model (S2000); and performing backhaul on the first response data and the first analog data, such that after receiving the first response data and the first analog data, the cloud computing platform performs intelligent parameter identification on the basis of the first response data and the first analog data, and updates the system mathematical model on the basis of a result of the intelligent parameter identification, so as to obtain a dynamic update model (S3000). The collaborative control method supports the real-time update of a complex system model of an industrial control system, thereby improving the efficiency and effects of model establishment and optimization.

Description

Cooperative control method, system, device, storage medium and related products

[0001] Cross-reference to related applications

[0002] The present application is based on and claims priority to Chinese Patent Application No. 202411292153.8, filed on September 13, 2024, the entire contents of which are hereby incorporated by reference into the present application. TECHNICAL FIELD

[0003] The present application relates to the technical field of big data edge computing, and in particular to a cooperative control method, system, device, industrial gateway, cloud computing platform, storage medium and product. BACKGROUND

[0004] With the rapid development of intelligent manufacturing and high-end manufacturing, there are high requirements for the control accuracy of systems composed of industrial robots, numerical control machine tools and other industrial equipment.

[0005] At present, in the control process in the industrial field, the proportional integral derivative (PID) control strategy is a common technical method. The selection of the control parameters of the PID controller has a great influence on the control performance. Suitable control parameters can ensure the stable operation and control effect of the control system. Currently, the trial-and-error method or the experience method is usually directly used to adjust the proportional control parameter, the integral control parameter and the derivative control parameter of the controller. However, it is highly dependent on expert experience and time-consuming and laborious.

[0006] With the advancement of technology, the industry has begun to study the modeling of control systems. For example, in the system design stage, a dynamic modeling based on theoretical analysis is used. In the system use stage, a big data modeling simulation is performed based on system operation data and neural network big data. However, the dynamic modeling based on theoretical analysis is difficult to completely and accurately describe the model, and has a large error in the prediction of dynamic error. The use of high-order or finite element models brings problems such as low calculation efficiency and difficulty in model parameter identification. The big data modeling based on device data and neural network has a relatively simple modeling process and insufficient robustness without theoretical support. Meanwhile, once the identification of the parameters is successful, the PID of the control system is determined and cannot be modified at any time. Factors such as manufacturing, assembly, wear and tear of parts, gravity and load, temperature and the like can cause deviations between the control system itself and the theoretical model. Such identification is not accurate and cannot detect the current state of the device in real time, making the control less accurate.

[0007] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0008] The main purpose of the present application is to provide a collaborative control method, system, device, industrial gateway, cloud computing platform, storage medium and computer program product, aiming to improve the efficiency and effect of the establishment and optimization of the industrial control system model.

[0009] To achieve the above-mentioned purpose, the present application provides a collaborative control method, which is applied to an industrial gateway, and the method comprises:

[0010] inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, wherein the system mathematical model is constructed by a cloud computing platform according to the dynamic analysis result of the components of the target industrial control system;

[0011] collecting first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction;

[0012] returning the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs parameter intelligent identification according to the first response data and the first simulation data, updates the system mathematical model according to the result of the parameter intelligent identification, and obtains a dynamic updated model.

[0013] In addition, the present application also provides a collaborative control method, which is applied to a cloud computing platform, and the method comprises:

[0014] constructing a system mathematical model of a target industrial control system according to the dynamic analysis result of the components in the target industrial control system, so that an industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction, and returns the first response data and the first simulation data;

[0015] receiving the first response data and the first simulation data returned by the industrial gateway;

[0016] performing parameter intelligent identification according to the first response data and the first simulation data;

[0017] updating the system mathematical model according to the result of the parameter intelligent identification, and obtaining a dynamic updated model.

[0018] In addition, to achieve the above-mentioned purpose, the present application also provides an industrial gateway, which is applied to a collaborative control device, wherein the industrial gateway comprises:

[0019] a control module configured to input a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, the system mathematical model being constructed by a cloud computing platform according to a dynamic analysis result of a component of the target industrial control system;

[0020] a collection module configured to collect first response data generated by the target industrial control system in response to the first system control instruction and first simulation data generated by the system mathematical model based on the first system control instruction; and

[0021] a feedback module configured to feed back the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs parameter intelligent identification according to the first response data and the first simulation data, and updates the system mathematical model according to a result of the parameter intelligent identification to obtain a dynamic updated model.

[0022] In addition, to achieve the above object, the application further provides a cloud computing platform applied to the collaborative control device, the cloud computing platform comprising:

[0023] a construction module configured to construct a system mathematical model of a target industrial control system according to a dynamic analysis result of a component of the target industrial control system, so that an industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction and first simulation data generated by the system mathematical model based on the first system control instruction, and feeds back the first response data and the first simulation data;

[0024] a receiving module configured to receive the first response data and the first simulation data fed back by the industrial gateway;

[0025] an identification module configured to perform parameter intelligent identification according to the first response data and the first simulation data; and

[0026] an updating module configured to update the system mathematical model according to a result of the parameter intelligent identification to obtain a dynamic updated model.

[0027] In addition, to achieve the above object, the application further provides a cooperative control system, comprising: a target industrial control system; a cloud computing platform connected with the target industrial control system, configured to construct a system mathematical model according to a dynamic analysis result of a component of the target industrial control system; and an industrial gateway connected with the target industrial control system and the cloud computing platform, the industrial gateway being configured to: issue a first system control instruction received from the cloud computing platform to the target industrial control system and a system mathematical model corresponding to the target industrial control system; collect first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction; and return the first response data and the first simulation data to the cloud computing platform; and the cloud computing platform is further configured to: perform parameter intelligent identification according to the received first response data and the first simulation data, and update the system mathematical model according to a result of the parameter intelligent identification to obtain a dynamic updated model.

[0028] In addition, to achieve the above object, the application further provides a cooperative control device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the operations of the cooperative control method.

[0029] In addition, to achieve the above object, the application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executable on a processor to implement the operations of the cooperative control method.

[0030] In addition, to achieve the above object, the application further provides a computer program product, which comprises a computer program, and the computer program is executable on a processor to implement the operations of the cooperative control method. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application together with the specification.

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the application or the related art, the accompanying drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, for those of ordinary skill in the art, without paying creative labor, other drawings can also be obtained from these drawings.

[0033] FIG. 1 is a flowchart of a cooperative control method according to an embodiment of the application;

[0034] Fig. 2 is a schematic diagram of the overall architecture of the collaborative control system corresponding to the collaborative control method of the present application;

[0035] Fig. 3 is a schematic diagram of the flow of the cloud-edge-terminal collaborative control method based on intelligent parameter identification in the collaborative control method of the present application;

[0036] Fig. 4 is a schematic diagram of the component units of the data acquisition and processing module of the cloud computing platform in the collaborative control method of the present application;

[0037] Fig. 5 is a schematic diagram of the flow provided in Embodiment 2 of the collaborative control method of the present application;

[0038] Fig. 6 is a schematic diagram of the data flow of the mathematical model establishment module based on intelligent parameter identification in the collaborative control method of the present application;

[0039] Fig. 7 is a schematic diagram of the flow of the mathematical model establishment in the collaborative control method of the present application;

[0040] Fig. 8 is a schematic diagram of the basic principle of parameter identification based on the L-M least square method in the collaborative control method of the present application;

[0041] Fig. 9 is a schematic diagram of the brief flow of the collaborative control method provided in the present application;

[0042] Fig. 10 is a schematic diagram of the device structure of the hardware operating environment involved in the collaborative control method in the present application.

[0043] The object implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and do not limit the present application.

[0045] In order to better understand the technical solutions of the present application, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0046] The main solution of the embodiment of the application is to provide an industrial system cloud edge end collaborative control method and system based on intelligent parameter identification, wherein the cloud computing platform is used to establish and update the dynamic model of the industrial system; the new industrial gateway is used to execute control commands, efficiently collect, store and return the business data, pressure data, temperature data, network data, location data, room temperature data, equipment operation data and the like of the system; the input and output data collected by the gateway and returned to the cloud and the deployed parameter intelligent identification algorithm are used to correct the modeling parameters of the industrial system by the cloud computing platform, and the dynamic update of the model is realized at the side of the new industrial gateway through the 5G network, and the rapid verification is performed by the new industrial gateway. Based on the above process, one-time identification of the model parameters can be realized, and the problem of relying on manual experience for parameter identification is solved; meanwhile, the intelligent parameter identification algorithm based on the L-M least square method and the cloud edge end collaborative technology support real-time update of the complex system model, and the efficiency and effect of model establishment and optimization are improved.

[0047] The cloud computing platform is used to establish and update the dynamic model of the industrial system, correct the modeling parameters of the industrial system, and realize the dynamic update of the model at the side of the gateway through 5G. The new industrial gateway is used to execute control commands, collect and return data, and verify the updated model.

[0048] Since the control method for the industrial equipment composition system in the related art mostly adopts proportional integral differential (PID) control or control system modeling, the adjustment of the PID controller on the parameters is relatively blind, and the debugging of the system is very difficult; the prediction error of the dynamic error based on the theoretical analysis modeling is large; the system modeling based on big data has the problems of poor robustness, difficulty in real-time modification of the PID and the like, and therefore the related art is not conducive to the realization of accurate control and efficient parameter identification of the system.

[0049] A permanent magnet synchronous motor control system and a control parameter intelligent identification method are disclosed in Chinese Patent Application No. 202110676192.8, which is applied to a permanent magnet synchronous motor control system, can ensure that the motor accurately reaches the specified position and outputs accurate torque, and realizes accurate position control and accurate torque control of the permanent magnet synchronous motor.

[0050] The patent identifies the parameters of the permanent magnet synchronous motor under different states of motor operation, obtains the electromechanical response parameters and equivalent servo inertia parameters when the motor rotor is controlled according to the motor response parameter formula. The overall implementation logic of this method is relatively simple, and depends on the accuracy of the response parameter formula; at the same time, the method uses a fixed parameter formula, and the obtained motor parameters are fixed. In fact, the type of the obtained parameters is real-time changing, and therefore it is difficult to adapt to large and complex control systems. Therefore, the above disadvantages may cause more inaccurate control.

[0051] The application provides a solution, inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, the system mathematical model being constructed by a cloud computing platform according to a dynamic analysis result of a component of the target industrial control system; collecting first response data generated by the target industrial control system in response to the first system control instruction and first simulation data generated by the system mathematical model based on the first system control instruction; and returning the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs intelligent identification of parameters according to the first response data and the first simulation data, updates the system mathematical model according to a result of the intelligent identification of parameters, and obtains a dynamic updated model, thereby supporting real-time updating of a complex system model of an industrial control system and improving the efficiency and effect of model establishment and optimization.

[0052] It should be noted that the execution subject of the embodiment can be a computing service device with functions of cooperative control, network communication and program running, such as a tablet computer, a personal computer, a mobile phone and the like, or an electronic device, a cooperative control system and the like capable of realizing the above functions. The embodiment and the following embodiments will be described below by taking the cooperative control system as an example.

[0053] Based on this, the embodiment of the application provides a cooperative control method, and reference is made to FIG. 1, which is a flowchart of a first embodiment of the cooperative control method of the application.

[0054] In the embodiment, the cooperative control method is applied to an industrial gateway, and the method comprises operations S1000-S3000.

[0055] Operation S1000: inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, the system mathematical model being constructed by a cloud computing platform according to a dynamic analysis result of a component of the target industrial control system.

[0056] It should be noted that in the embodiment, the implementation of the cooperative control method takes a numerical control system containing a drive, a motor and a mechanical transmission mechanism as an example, and reference can be made to FIG. 2, which is a system overall architecture diagram of a cooperative control system corresponding to the cooperative control method of the application, wherein the cloud computing platform is used to establish and update a dynamic model of an industrial system, correct modeling parameters of the industrial system, and realize dynamic updating of the model on the gateway side through 5G.

[0057] The new industrial gateway is used to execute control commands, efficiently collect, store and return service data, pressure data, temperature data, network data, location data, room temperature data, equipment operation data and the like of the system, input and output data collected by the gateway and deployed parameter intelligent identification algorithm are returned to the cloud, the cloud computing platform corrects the modeling parameters of the industrial system, and the dynamic update of the model is realized on the side of the new industrial gateway through the 5G network, and the new industrial gateway performs rapid verification.

[0058] In addition, it should be noted that the main process of the collaborative control method implemented by the collaborative control system based on FIG. 2 is shown in FIG. 3, which is a flowchart of an industrial system cloud edge collaborative control method based on intelligent parameter identification in the collaborative control method of the present application. The collaborative control method mainly passes through the model establishment module based on intelligent parameter identification, the model execution and verification module and the data acquisition and processing module shown in FIG. 3.

[0059] Among them, the industrial gateway side is mainly responsible for the model execution and verification module and the data acquisition and processing module. In some embodiments, the model establishment module based on intelligent parameter identification is used to establish a mathematical model of an industrial control system, i.e., a system mathematical model of a target industrial control system. The system mathematical model is based on a dynamic basic model, and the intelligent parameter identification algorithm is used to intelligently optimize the parameters based on the data of the real industrial control system, and finally a precise mathematical model is established.

[0060] The model execution and verification module is used to execute the mathematical model generated by the model establishment module. The gateway executes the control command based on the mathematical model, collects various data in the control system, and then transmits the data to the cloud through 5G for real-time updating of the model parameters by the model establishment module based on intelligent parameter identification. After updating the model parameters in the cloud, the latest model can be downloaded to the gateway through 5G, and execution and rapid verification are completed.

[0061] The data acquisition and processing module is used to obtain real-time data in the industrial control system. The real-time data is the data of key points in the industrial control system collected by the gateway, and the interpolation technique is used to fill in the missing values, which are the data missing due to unstable transmission caused by the actual environment of the factory during monitoring. Time series database is used to store and analyze the collected data to support rapid verification of the model and cloud query analysis.

[0062] In some embodiments, the model execution and verification module is carried by an end-side industrial gateway, wherein the execution and verification of the model includes input of system control instructions, and the same system control instructions are respectively input into the industrial control system and the corresponding system mathematical model during the first parameter intelligent identification and the subsequent continuous parameter intelligent maintenance. The new industrial gateway can synchronize the system control instructions in real time through 5G communication technology, thereby maximizing the effectiveness of the fitting results of the response data of the industrial control system and the system mathematical model.

[0063] Referring to FIG. 2, the cloud computing platform is responsible for establishing a precise mathematical model, and the incentive signal is a control command given when the system is first modeled. The system real-time data are pre-processed system running data returned by the gateway after the system runs, and provide a data basis for model parameter updating. The dynamic basic model is a mathematical model established according to theory. The intelligent parameter identification is based on the L-M algorithm (Levenberg-Marquardt method) to realize one-time identification of model parameters and subsequent continuous optimization.

[0064] Operation S2000: collecting first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction.

[0065] It should be noted that in the first parameter intelligent identification and the subsequent continuous parameter intelligent maintenance, the collaborative control system inputs the same system control instruction (in this embodiment, the "first system control instruction") into the target industrial control system (for example, the "real industrial control system" in FIG. 2) and the corresponding system mathematical model (for example, the "dynamic basic model" in FIG. 2). The new industrial gateway can synchronize the system control instructions in real time through 5G, thereby maximizing the effectiveness of the fitting results of the response data of the two systems. The dynamic model constructed in the cloud can be run synchronously in the new industrial gateway. The new industrial gateway is built-in with rich communication protocol analysis applications, and supports the collection of multi-point data of multiple devices through rich peripheral interfaces. At the same time, the gateway has basic computing power, and supports basic data processing and analysis on the end side. The gateway has 5G transmission capability, and supports real-time transmission of data to the cloud for subsequent data analysis and intelligent parameter identification and modeling, which includes the first response data generated by the target industrial control system when it runs after receiving the first system control instruction, and the first simulation data generated by the system mathematical model when it runs based on the first system control instruction.

[0066] Operation S3000: The first response data and the first simulation data are returned, so that the cloud computing platform receives the first response data and the first simulation data, performs parameter intelligent identification according to the first response data and the first simulation data, updates the system mathematical model according to the result of the parameter intelligent identification, and obtains a dynamic updating model.

[0067] It should be noted that in the embodiment, the industrial gateway is built-in with rich communication protocol analysis application, supports collecting multi-point data of multiple devices through rich peripheral interface, and has basic computing power, supports basic data processing and analysis on the side, has 5G transmission capability, supports real-time transmission of data to the cloud for subsequent data analysis and intelligent parameter identification and modeling. This includes the first response data generated when the target industrial control system runs after receiving the first system control instruction and the first simulation data generated by the system mathematical model when running based on the first system control instruction.

[0068] After the industrial gateway returns the collected first response data and first simulation data to the cloud computing platform, the cloud computing platform intelligently tunes the parameters based on the intelligent parameter identification algorithm through the data of the real industrial control system, and finally establishes a more accurate mathematical model, i.e., a dynamic updating model.

[0069] In a feasible implementation, the method can further include operations A1000-A4000.

[0070] Operation A1000: Input a second system control instruction into the target industrial control system and the dynamic updating model.

[0071] Operation A2000: Collect second response data generated by the target industrial control system in response to the second system control instruction, and second simulation data generated by the dynamic updating model based on the second system control instruction.

[0072] Operation A3000: Determine whether the difference between the second response data and the second simulation data is greater than a preset difference threshold.

[0073] Operation A4000: If the difference between the second response data and the second simulation data exceeds the preset difference threshold, roll back the second system control instruction.

[0074] It should be noted that in this embodiment, the dynamic model constructed in the cloud can be run synchronously in the new industrial gateway. After the gateway side issues the system control instruction, it can preliminarily fit the actual response data and the simulation prediction data on the end side. If the difference between the two is large, it is considered that the original physical model / dynamic model is invalid or the optimized physical model / dynamic update model is updated incorrectly, and the related control instruction based on the system dynamics model is quickly rolled back to maximize the stable operation of the control system.

[0075] In the entire collaborative control method, the input of the second system control instruction is a key operation for further verifying the dynamic update model. This instruction not only acts on the actual industrial control system, but also acts on its corresponding mathematical model, so that the effect of the control strategy can be evaluated on both the actual and theoretical levels. In this way, it can be ensured that the system control instruction is fully tested and verified before actual application, thereby improving the stability and reliability of the system.

[0076] Additionally, it should be noted that collecting the second response data and the second simulation data is an important link for evaluating the effect of the second system control instruction. The second response data reflects the performance of the target industrial control system in actual operation, while the second simulation data is the response prediction of the system mathematical model (in this embodiment, the "dynamic update model") to the same control instruction (i.e., the second system control instruction). By comparing the difference between the two, it can be determined whether the actual effect of the second system control instruction meets the expectations and how accurate the system mathematical model is.

[0077] Furthermore, it should be noted that determining whether the difference between the second response data and the second simulation data exceeds the preset difference threshold is the key to deciding whether the second system control instruction needs to be adjusted. If the difference exceeds the preset difference threshold, it means that the current system control instruction (i.e., the second system control instruction) or the system mathematical model has a problem and needs to be corrected. At this time, the second system control instruction is rolled back, i.e., the control instruction is revoked, to avoid possible system instability or performance degradation and ensure the safety and efficiency of the system.

[0078] For example, in a possible implementation, the target industrial control system can include an automated assembly line containing multiple robotic arms and conveyor belts. The second system control instruction can involve adjusting the speed of movement of the robotic arms or the speed of operation of the conveyor belts. The new industrial gateway is responsible for collecting data such as the speed and acceleration of the robotic arms and conveyor belts after the execution of the new system control instruction, as the second response data. At the same time, the dynamic updating model will also generate predicted speed and acceleration data as the second simulation data according to the same system control instruction. The cloud computing platform will compare the two sets of data, and if it finds that the difference between the actual running data and the model predicted data exceeds the preset threshold, it will trigger the rollback mechanism of the system control instruction to prevent possible system failure or performance degradation. Through this series of operations, the efficient and stable operation of the industrial control system is ensured, and at the same time the accuracy of the mathematical model is verified and optimized.

[0079] In a possible implementation, the target industrial control system includes a plurality of target devices and target points, and the operation S2000 can include operations S2100-S2300.

[0080] Operation S2100: Collecting original response data generated by the target devices and target points in response to the first system control instruction of the target industrial control system;

[0081] Operation S2200: Based on the data variation pattern of the original response data, the missing values in the original response data are interpolated to obtain the first response data;

[0082] Operation S2300: Collecting data output generated by the system mathematical model after running based on the first system control instruction, and taking the data output as the first simulation data.

[0083] It should be noted that in this embodiment, the new industrial gateway can be based on 5G transmission, and by virtue of the characteristics of low latency and large bandwidth, the response data of the real industrial control system is synchronized to the cloud for parameter error analysis, and at the same time, it also provides support for the operation data of the upper three-party platform, such as the digital twin platform.

[0084] The original response data generated by the target device and target point when the target industrial control system responds to the first system control instruction is the basis for implementing the collaborative control method. These data reflect the state of the target industrial control system in actual operation and are the key to evaluating the effectiveness of the first system control instruction and system performance. In addition, as shown in FIG. 3, the data acquisition and processing module is configured on the side of the new industrial gateway, and the module includes various units as shown in FIG. 4. Among them, the real-time data acquisition unit is responsible for collecting data. The new industrial gateway has a built-in rich communication protocol analysis application, supports collecting data from multiple devices and multiple points through a rich peripheral interface; at the same time, the gateway has basic computing power, supports basic data processing and analysis on the side; the gateway has 5G transmission capability, supports real-time transmission of data to the cloud for subsequent data analysis and intelligent parameter identification and modeling.

[0085] In addition, it should be noted that real industrial control systems are mostly deployed in factory environments, and harsh factory environments will cause data to be missing or lost during data collection due to various reasons. The missing data filling unit estimates missing values based on the pattern and trend of existing data using interpolation techniques, thereby maintaining the continuity and integrity of the data. Linear interpolation can be used to maintain the continuity and integrity of the data by assuming that the change between data is linear. For missing values, linear interpolation estimates the missing values based on the linear relationship between known adjacent data points.

[0086] Interpolating and completing missing values in the original response data is an important operation to ensure data integrity. Due to uncertainties in the industrial environment, such as sensor failure or communication interference, data may be missing. Through interpolation techniques, these missing values can be estimated and filled in, thereby obtaining continuous and complete data to provide an accurate basis for subsequent data analysis and model optimization.

[0087] In addition, it should be noted that the acquisition system mathematical model is based on the data output generated after the first system control instruction is run, and these data are used as the first simulation data, which is a key link for verifying and optimizing the system mathematical model. By comparing the first response data and the first simulation data, the accuracy of the model and the effectiveness of the system control instruction can be evaluated. This process is the basis for implementing intelligent parameter identification and dynamic updating of the system mathematical model.

[0088] For example, in a feasible implementation, the motor running angle and speed are obtained. At some time points, due to acquisition device failure or communication problems, there may be some missing values in the data. Interpolation techniques can be used to fill in these missing values for subsequent intelligent parameter analysis and digital twin modeling. Linear interpolation can be used to fill in missing values in the motor running angle and speed. Assuming that the data set is as follows in Table One:

[0089] Table One: Missing Table

[0090] For the missing motor operating angle and speed, linear interpolation can be used with known adjacent data points. For example, the motor angle at timestamp 1467627248000 can be estimated by using linear interpolation with the motor angles at timestamps 1467627247000 and 1467627249000. Similarly, the motor speed at timestamp 1467627248000 can be estimated using linear interpolation with the motor speeds at adjacent timestamps. After interpolation, the data set will become as shown in Table 2 below:

[0091] Table 2: Completed table

[0092] In this way, the missing values are successfully filled in, and the continuity and integrity of the data are maintained for subsequent prediction and analysis related to modeling work.

[0093] In addition, it should be noted that, in order to ensure the effectiveness of parameter intelligent identification and modeling, the data collected by the industrial gateway is large-scale, high-dimensional, time-based, and needs to be queried and analyzed, which requires the gateway data to achieve efficient collection, insertion, storage, and query.

[0094] In the method, the gateway uses a time series database through a time series data storage unit to achieve high throughput and low latency of data; uses special data structures and indexing techniques to efficiently store and query data, uses compression algorithms and data partitioning techniques to reduce storage space and improve query performance; has data analysis functions, provides rich time series analysis functions and algorithms, thereby minimizing the impact of model errors on preliminary model judgment at the end side.

[0095] The embodiment provides a cooperative control method, which comprises the following steps: inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system by an industrial gateway, wherein the system mathematical model is constructed by a cloud computing platform according to a dynamic analysis result of a component of the target industrial control system; collecting first response data generated by the target industrial control system in response to the first system control instruction and first simulation data generated by the system mathematical model based on the first system control instruction; and returning the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs parameter intelligent identification according to the first response data and the first simulation data, updates the system mathematical model according to a result of the parameter intelligent identification, and obtains a dynamic updated model. The above method supports real-time updating of a complex system model of an industrial control system, and improves the efficiency and effect of model establishment and optimization.

[0096] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above-mentioned embodiment one can be referred to the above introduction, and the subsequent will not be described. On this basis, please refer to Figure 5, the cooperative control method provided by the second embodiment of the present application is applied to the cloud computing platform, and the method comprises operations B1000-B4000.

[0097] Operation B1000: according to the dynamic analysis result of the components in the target industrial control system, a system mathematical model of the target industrial control system is constructed, so that the industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction, and returns the first response data and the first simulation data.

[0098] It should be noted that constructing the system mathematical model of the target industrial control system is the primary operation to achieve precise control. The model is based on the dynamic analysis result of each component in the target industrial control system, and is established by the cloud computing platform. This model not only captures the static characteristics of the system, but also simulates the dynamic behavior, providing a theoretical framework for the industrial gateway to input the first system control instruction and predict the system response.

[0099] In addition, it should be noted that the industrial gateway applies the first system control instruction to the target industrial control system and its corresponding mathematical model after receiving it. Then, the gateway collects the first response data generated by the actual response of the system to the first system control instruction, and the first simulation data generated by the system mathematical model, and returns these data to the cloud computing platform. This process ensures the accuracy and practicality of the model, providing necessary data support for subsequent parameter identification and model updating.

[0100] Operation B2000: receiving the first response data and the first simulation data returned by the industrial gateway.

[0101] It should be noted that receiving the first response data and the first simulation data returned by the industrial gateway is a key task of the cloud computing platform. These data provide an empirical basis for the cloud computing platform to evaluate and optimize the control strategy. By analyzing the consistency between the actual response of the system and the model prediction, the cloud computing platform can accurately evaluate the effectiveness of the current system mathematical model.

[0102] Operation B3000: intelligent parameter identification according to the first response data and the first simulation data.

[0103] It should be noted that the parameter intelligent identification is an analysis process performed by the cloud computing platform based on the received first response data and first simulation data. This process utilizes advanced algorithms, such as the L-M least squares method, to finely adjust the model parameters to minimize the difference between the actual response (i.e., the first response data) and the simulation data (i.e., the first simulation data). The goal of intelligent identification is to find the optimal parameter set so that the system mathematical model can accurately reflect the real behavior of the target industrial control system as much as possible.

[0104] Operation B4000: updating the system mathematical model according to the result of the parameter intelligent identification to obtain a dynamic updated model.

[0105] It should be noted that updating the system mathematical model according to the result of the parameter intelligent identification is the core link to realize the continuous optimization and accurate control of the model. The generation of the dynamic updated model marks that the model has been iteratively improved and is closer to the characteristics of the actual system. This updating process not only improves the prediction accuracy of the model, but also lays a foundation for realizing a more automated and intelligent industrial control system.

[0106] For example, in some embodiments, the target industrial control system can be an automated manufacturing pipeline including multiple sensors, actuators, and mechanical devices. The cloud computing platform first constructs a system mathematical model according to the dynamic characteristics of these devices. The industrial gateway then applies the first system control instruction to the target industrial control system and the system mathematical model, and collects the response data of the two. After receiving these data, the cloud computing platform performs parameter intelligent identification to find the model parameters that need to be adjusted, and updates the model. Finally, the updated model can more accurately predict the effect of the first system control instruction, providing reliable decision support for the optimization of the manufacturing pipeline.

[0107] In a feasible implementation, operation B1000 can include operations B1100-B1300.

[0108] Operation B1100: determining the input-output relationship and input-output data of the components of the target industrial control system according to the dynamic analysis results of the components.

[0109] Operation B1200: establishing a system transfer function and determining the system parameters of the system transfer function according to the input-output relationship and input-output data.

[0110] Operation B1300: constructing a system mathematical model of the target industrial control system based on the system transfer function and system parameters.

[0111] It should be noted that in this embodiment, the system mathematical model is mainly constructed through the cloud computing platform, that is, through the model establishment module based on intelligent parameter identification shown in FIG. 3, the system mathematical model of the target industrial control system is established. The system mathematical model is based on a dynamic basic model, and the intelligent parameter identification algorithm is used to intelligently optimize the parameters based on the data of the real industrial control system, and finally a precise system mathematical model is established.

[0112] The purpose of in-depth dynamic analysis of the components of the target industrial control system is to determine the input-output relationship between each component and the input-output data performance under these relationships. These information is the cornerstone of building a system mathematical model, which ensures that the model can truly reflect the dynamic characteristics of the system.

[0113] In addition, it should be noted that once the input-output relationship and input-output data are determined, the next task is to establish the system transfer function. The system transfer function is used to describe the dynamic relationship between the system input and output. By analyzing these data, the system parameters in the system transfer function can be further determined, which are the key variables in the model and determine the response characteristics of the system to the control command.

[0114] Further, it should be noted that the system mathematical model is constructed by the transfer function and system parameters obtained above. This model is an abstraction and simulation of the behavior of the target industrial control system, and can be used to predict the response of the system to various control strategies. The construction of the model is the basis for realizing the collaborative control method, and provides necessary theoretical support for subsequent system control command input, data acquisition, parameter identification and model updating. Referring to FIGS. 6 and 7, FIG. 6 is a data flow diagram of a mathematical model establishment module based on intelligent parameter identification in the collaborative control method of the present application, and FIG. 7 is a flowchart of the establishment of the system mathematical model in the collaborative control method of the present application. The excitation signal shown in FIG. 6 is the control command given when the system is first modeled. The system real-time data shown in FIG. 2 is the pre-processed system running data returned by the gateway after the system runs, which provides a data basis for model parameter updating. The dynamic basic model shown in FIG. 6 is a system mathematical model established according to theory; the intelligent parameter identification is a one-time identification of model parameters and subsequent continuous optimization based on L-M algorithm. In the process shown in FIG. 7, taking a numerical control system containing a drive, a motor and a mechanical transmission mechanism as an example, in this operation, each part of the above feeding system is reasonably considered and included in the overall feeding system dynamic basic model, and dynamic modeling is performed for the controlled object in the control system, including the establishment of transfer function and parameter identification.

[0115] The establishment of the transfer function is to establish the relationship between the input and output of the feeding system based on the simplified description of the control and the motion relationship of the components, and the function obtained by Laplace transform is used to represent it, which is called transfer function.

[0116] Parameter identification is to determine a set of parameter values of the model according to the experimental data and the established model, so that the numerical results calculated by the model can best fit the test data, such as temperature and friction identification. Through the above mathematical and physical method, each module contained in the control system is expressed, and a complete parameter transfer function is formed.

[0117] For example, in a feasible implementation, the target industrial control system can be a high-precision industrial robot arm. First, through dynamic analysis, the input-output relationship of each joint of the robot arm is determined, such as the relationship between the input voltage of the motor and the output angle of the joint. Then, using these relationships and actual measurement data, a system transfer function describing the dynamic behavior of the robot arm is established, and system parameters such as moment of inertia and damping ratio are determined. Finally, based on these transfer functions and parameters, a system mathematical model of the robot arm is constructed, which can be used to simulate and predict the motion state of the robot arm under different system control instructions. Through the comparison and analysis of the simulation results of the system mathematical model and the actual running data, intelligent identification of model parameters and continuous optimization of the model can be carried out to ensure the control accuracy and efficiency of the robot arm.

[0118] In a feasible implementation, operation B3000 can include operations B3100-B3500.

[0119] Operation B3100: determining a model parameter vector based on system parameters.

[0120] Operation B3200: determining target point information in the target industrial control system based on the first response data.

[0121] Operation B3300: calculating a Jacobian matrix corresponding to the model parameter vector based on the first simulation data and the system mathematical model to obtain predicted point information.

[0122] Operation B3400: determining a response-prediction error between the target point information and the predicted point information.

[0123] Operation B3500: determining a model parameter error correction amount based on the L-M least squares method and the response-prediction error.

[0124] It should be noted that the parameter intelligent identification process is based on system parameters, first response data and first simulation data to accurately adjust the model parameter vector. The key of this process is to accurately reflect the characteristics of the target industrial control system, and to ensure that the prediction of the system mathematical model is consistent with the actual system behavior.

[0125] For example, system parameters can include spring stiffness, damping ratio, etc., which determine the dynamic response of the system. The determination of the model parameter vector is achieved by minimizing the difference between the predicted output of the system and the actual output, which usually involves the application of optimization algorithms.

[0126] Additionally, it should be noted that the first response data provides the feedback of the actual system (real industrial control system) to the control input, while the first simulation data is the prediction result of the system mathematical model based on the same input. By comparing the two sets of data, the response-prediction error between the target point information and the predicted point information can be determined, which is an important indicator for evaluating the accuracy of the model.

[0127] In some embodiments, the process of intelligent parameter identification of the dynamic model is to ignore the high-order differential in the nonlinear model for linear analysis. As the error ΔX' of parameter identification becomes smaller and smaller, the output of the dynamic model will be closer to the actual response value of the real industrial control system. The most commonly used method for linearization of the nonlinear model in parameter identification is the least squares method. The least squares method takes the approximate intermediate value, which will cause calculation error and make the objective function deviate from the minimum value during the convergence process, and finally the fitting effect is difficult to accept. The L-M least squares method uses the damping coefficient μ to limit the iterative operation to avoid singularity and improve the fitting effect of the least squares method. The basic principle of parameter identification using L-M least squares method is shown in FIG. 8.

[0128] First, initialize the system dynamics model, determine the parameters based on theory and modeling, and calculate the model parameter vector X k Then a certain number of points are taken as parameter identification sampling points, and the response value returned by the new industrial gateway is taken as the actual position P of these parameter identification sampling points, which is substituted into the system dynamics model under the model parameter vector X k The Jacobian matrix J(X k ) of the current identification is calculated, the predicted position P' is obtained, and then the error ΔP(X k ) between P and P' is solved, and the model parameter error correction amount ΔX k is solved, that is: ΔX k = -[J T (X k )J(X k )+μ k I] -1 J T (Xk )ΔP(X k )

[0129] wherein μ k is the system damping coefficient. Then, the model parameter vector X k+1 at the k+1th iteration is updated as X k+1 = X k + ΔX k , k = k + 1.

[0130] The damping coefficient μ k+1 at the k+1th iteration is updated as

[0131] wherein ‖ΔP(X k+1 )‖ and ‖ΔP(X k )‖ are the two-norms of the position errors at the k+1th and kth iterations, respectively, and δ is an iteration parameter. When ‖ΔP(X k+1 )‖ - ‖ΔP(X k )‖ > ε, the k+1th modeling parameter vector is updated, and the above operation is iterated until ‖ΔP(X k+1 )‖ - ‖ΔP(X k )‖ ≤ ε, i.e., the difference between the two iteration error norms approaches ε = 0.0001, which proves that the convergence has been achieved, i.e., the optimal parameter error is obtained.

[0132] In an implementable embodiment, the operation of updating the system mathematical model according to the result of the intelligent identification of the parameters comprises:

[0133] The system transfer function is corrected by the model parameter error correction amount, to obtain a dynamic updated model.

[0134] That is, the system parameters of the system transfer function are corrected by the parameter error ΔX identified by the above L-M algorithm, and the related dynamic model is updated, so as to improve the use effect of the three parties referring to the model, such as the accuracy of the cloud digital twin platform modeling and the accuracy of the control command of the end-side intelligent industrial gateway.

[0135] By way of example, in order to assist in understanding the implementation process of the collaborative control method obtained after the above-mentioned embodiment one, please refer to FIG. 9, which provides a brief flowchart of a collaborative control method. In some embodiments:

[0136] The collaborative control method of the present application is mainly applied to an industrial gateway to improve the accuracy and efficiency of an industrial control system. The scheme realizes accurate control and real-time optimization of a target industrial control system through close cooperation between a cloud computing platform and an industrial gateway.

[0137] Firstly, the cloud computing platform determines the input-output relationships and input-output data of the target industrial control system based on the results of the dynamic analysis of each component in the system. Dynamic analysis is the study of how system components respond to external stimuli such as force, heat, electricity, etc. It provides the basis for establishing an accurate mathematical model. Through analysis, the interaction between components and their response characteristics to control inputs can be clearly defined.

[0138] Subsequently, the platform uses these input-output relationships and input-output data to establish the system transfer function and determine the system parameters. The system transfer function is a mathematical model that describes the output response of the system to input signals in the time or frequency domain. System parameters such as damping ratio, natural frequency, etc. are key variables in the system transfer function, which determine the dynamic characteristics of the system.

[0139] Based on the system transfer function and system parameters, the cloud computing platform constructs a system mathematical model of the target industrial control system. This model is virtual, but it can simulate the behavior of the actual industrial control system, including response under different control strategies. The construction of the system mathematical model is the core of the collaborative control method, which provides a theoretical basis for subsequent system control instruction design and optimization.

[0140] Next, the industrial gateway inputs system control instructions into the target industrial control system and its corresponding system mathematical model. These system control instructions aim to adjust the behavior of the industrial control system to achieve the desired control objectives such as speed, position or pressure, etc. At the same time, the gateway collects the first response data generated by the target industrial control system in response to the system control instructions, as well as the first simulation data generated by the system mathematical model based on the same system control instructions.

[0141] The first response data and the first simulation data are returned to the cloud computing platform. After receiving these data, the cloud computing platform performs intelligent parameter identification. This process involves complex calculations based on the L-M least squares method, aiming to find the optimal model parameters so that the system mathematical model can accurately predict the behavior of the actual system as much as possible.

[0142] The identification process includes determining the model parameter vector, calculating the Jacobian matrix, determining the response-prediction error, and correcting the model parameters based on the error. The Jacobian matrix is a matrix that describes the sensitivity of model output to parameter changes, and it plays a crucial role in parameter identification. By calculating the response-prediction error, the accuracy of the current model parameters can be evaluated, and the parameters can be adjusted accordingly to reduce the error.

[0143] Once the model parameters are intelligently identified and corrected, the system mathematical model will be updated to generate a dynamic updated model. This updated model can more accurately reflect the characteristics of the actual industrial control system, providing a basis for further optimization of system control instructions.

[0144] In addition, the scheme further includes the operation of inputting a second system control instruction into the target industrial control system and the dynamic updating model. In this way, the control strategy can be further verified and optimized. After the second system control instruction is implemented, the system will collect second response data and second simulation data, and determine whether the difference between the two is greater than a preset difference threshold. If the difference exceeds the threshold, it indicates that the current second system control instruction or model needs to be further adjusted, and the system will perform a rollback operation to revoke the second system control instruction.

[0145] The above process, according to the dynamic analysis of the components of the industrial control system (i.e., the target industrial control system), establishes the corresponding dynamic basic model of the system, then inputs the first system control instruction into the industrial control system and its corresponding dynamic basic model, respectively, the edge device intelligent gateway collects relevant data and transmits it to the cloud, updates the model parameters based on the intelligent parameter identification algorithm, perfects the dynamic basic model, continuously feeds back the collected data to support the updating of the model parameters, maintains the accuracy of the model, and the cloud end issues the latest model, so that the control model in the edge intelligent gateway device is updated, and then the corresponding control command is changed, while the gateway supports rapid verification, so that the performance of the control system is optimized as a whole, the information given by the model is fully utilized, and the optimal control effect on the controlled object can be achieved.

[0146] Through a series of operations, the scheme realizes accurate control and real-time optimization of the industrial control system, improves the response speed and control accuracy of the system, and meets the demand for efficient and reliable control systems in the field of intelligent manufacturing.

[0147] It should be noted that the above examples are only used to understand the present application and do not limit the cooperative control method of the present application. Further simple transformations based on this technical concept are within the protection scope of the present application.

[0148] Some embodiments of the present application also provide a cooperative control device. The cooperative control device includes an industrial gateway. The industrial gateway includes a control module, a collection module, and a backhaul module. The control module is configured to input a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system. The system mathematical model is constructed by a cloud computing platform according to the dynamic analysis results of the components of the target industrial control system. The collection module is configured to collect first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction. The backhaul module is configured to backhaul the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs intelligent parameter identification according to the first response data and the first simulation data, updates the system mathematical model according to the results of the intelligent parameter identification, and obtains a dynamic updating model.

[0149] The cooperative control device further comprises a cloud computing platform. The cloud computing platform comprises a construction module, a receiving module, an identification module, and an updating module. The construction module is configured to construct a system mathematical model of the target industrial control system according to a result of dynamic analysis of components of the target industrial control system, so that the industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction, and collects first simulation data generated by the system mathematical model based on the first system control instruction, and returns the first response data and the first simulation data. The receiving module is configured to receive the first response data and the first simulation data returned by the industrial gateway. The identification module is configured to perform intelligent parameter identification according to the first response data and the first simulation data. The updating module is configured to update the system mathematical model according to a result of the intelligent parameter identification to obtain a dynamic updated model.

[0150] The cooperative control device provided in the application can solve the technical problem of cooperative control by using the cooperative control method in the above embodiments. Compared with the related art, the cooperative control device provided in the application has the same beneficial effects as the cooperative control method provided in the above embodiments, and other technical features in the cooperative control device are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0151] Some embodiments of the application further provide a cooperative control system, comprising: a target industrial control system; a cloud computing platform connected to the target industrial control system, configured to construct a system mathematical model according to a result of dynamic analysis of components of the target industrial control system; and an industrial gateway connected to the target industrial control system and the cloud computing platform, the industrial gateway being configured to: issue a first system control instruction received from the cloud computing platform to the target industrial control system and the system mathematical model corresponding to the target industrial control system; collect first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction; and return the first response data and the first simulation data to the cloud computing platform; the cloud computing platform is further configured to: perform intelligent parameter identification according to the received first response data and first simulation data, and update the system mathematical model according to a result of the intelligent parameter identification to obtain a dynamic updated model. The cloud computing platform is configured to issue the updated dynamic updated model to the industrial gateway, and the industrial gateway is configured to execute and verify the dynamic updated model.

[0152] The industrial gateway is further configured to: input a second system control instruction into the target industrial control system and the dynamic updating model; collect second response data generated by the target industrial control system in response to the second system control instruction, and second simulation data generated by the dynamic updating model based on the second system control instruction; determine whether a difference between the second response data and the second simulation data exceeds a preset difference threshold; and if the difference between the second response data and the second simulation data exceeds the preset difference threshold, roll back the second system control instruction.

[0153] The target industrial control system includes a plurality of target devices and target points; the industrial gateway is further configured to: collect original response data generated by the target devices and the target points in response to the first system control instruction; perform interpolation completion on missing values in the original response data based on a data change pattern of the original response data to obtain first response data; and collect data output generated by the system mathematical model after running based on the first system control instruction, and use the data output as first simulation data.

[0154] The cloud computing platform is further configured to: determine input-output relationships and input-output data of components of the target industrial control system according to dynamic analysis results of the components; establish a system transfer function and determine system parameters of the system transfer function according to the input-output relationships and the input-output data; and construct a system mathematical model of the target industrial control system based on the system transfer function and the system parameters.

[0155] The cloud computing platform is further configured to: determine a model parameter vector based on the system parameters; determine target point information in the target industrial control system based on the first response data; calculate a Jacobian matrix corresponding to the model parameter vector based on the first simulation data and the system mathematical model to obtain predicted point information; determine a response-prediction error between the target point information and the predicted point information; determine a model parameter error correction amount based on the L-M least square method and the response-prediction error; and correct the system transfer function based on the model parameter error correction amount to obtain the dynamic updating model.

[0156] The application provides a cooperative control device, which comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the cooperative control method in the above embodiment I.

[0157] Reference is now made to FIG. 10, which shows a configuration diagram of a cooperative control device suitable for implementing embodiments of the present application. The cooperative control device in embodiments of the present application can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Portable Application Description), a PMP (Portable Media Player), a car terminal (e.g., a car navigation terminal), and the like, as well as a stationary terminal such as a digital TV, a desktop computer, and the like. The cooperative control device shown in FIG. 10 is merely an example and should not impose any limitation on the functions and use range of embodiments of the present application.

[0158] As shown in FIG. 10, the cooperative control device can include a processing device 1001 (e.g., a central processor, a graphic processor, etc.) that can perform various appropriate actions and processes according to a program stored in a ROM (Read Only Memory) 1002 or a program loaded from a storage device 1003 into a RAM (Random Access Memory) 1004. Various programs and data required for operation of the cooperative control device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An I / O (Input / Output) interface 1006 is also connected to the bus. In general, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; an output device 1008 including, for example, an LCD (Liquid Crystal Display), a speaker, a vibrator, and the like; the storage device 1003 including, for example, a magnetic tape, a hard disk, and the like; and a communication device 1009. The communication device 1009 can allow the cooperative control device to communicate with other devices wirelessly or by wire to exchange data. Although a cooperative control device having various systems is shown in the figure, it should be understood that all of the shown systems are not required to be implemented or provided. More or less systems can be alternatively implemented or provided.

[0159] In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, the embodiments of the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present application are executed.

[0160] The cooperative control device provided by the present application adopts the cooperative control method in the above-mentioned embodiments. Compared with the related art, the cooperative control device provided by the present application has the same beneficial effects as the cooperative control method provided by the above-mentioned embodiments, and other technical features in the cooperative control device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0161] It should be understood that parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0162] The above is only some embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0163] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the cooperative control method in the above-mentioned embodiments.

[0164] The computer readable storage medium provided in the present application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination of the above. Some examples of the computer readable storage medium may include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer disk, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), an optical fiber, a portable compact disk read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted in any suitable medium, including but not limited to electrical wires, optical cables, RF (Radio Frequency), and the like, or any suitable combination of the above.

[0165] The above computer readable storage medium can be included in the cooperative control device, or can exist separately without being assembled into the cooperative control device.

[0166] Computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including object oriented programming languages such as Java, Smalltalk, C++ or conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0167] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may be executed in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or combinations of hardware and software.

[0168] The modules involved in the embodiments of the present application can be implemented in software or in hardware. In some cases, the names of the modules do not limit the modules themselves.

[0169] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the above-mentioned cooperative control method, and can solve the technical problem of cooperative control. Compared with the related art, the computer readable storage medium provided by the present application has the same beneficial effects as the cooperative control method provided by the above-mentioned embodiments, which will not be repeated here.

[0170] The present application also provides a computer program product, which includes a computer program, and the computer program is executed by a processor to realize the operations of the above-mentioned cooperative control method.

[0171] The computer program product provided by the present application can solve the technical problem of cooperative control. Compared with the related art, the computer program product provided by the present application has the same beneficial effects as the cooperative control method provided by the above-mentioned embodiments, which will not be repeated here.

[0172] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation made by using the content of the present application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the present application.

Claims

1. A method of cooperative control applied to an industrial gateway, wherein, The method comprises: inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, the system mathematical model being constructed by a cloud computing platform according to a dynamic analysis result of constituent components of the target industrial control system; collecting first response data generated by the target industrial control system in response to the first system control instruction and first simulation data generated by the system mathematical model based on the first system control instruction; returning the first response data and the first simulation data to enable the cloud computing platform to receive the first response data and the first simulation data, perform parameter intelligent identification according to the first response data and the first simulation data, update the system mathematical model according to a result of the parameter intelligent identification, and obtain a dynamic updated model.

2. The method of claim 1, wherein, The method further comprises: inputting a second system control instruction into the target industrial control system and the dynamic updated model; collecting second response data generated by the target industrial control system in response to the second system control instruction and second simulation data generated by the dynamic updated model based on the second system control instruction; judging whether a difference degree between the second response data and the second simulation data exceeds a preset difference degree threshold; if the difference degree between the second response data and the second simulation data exceeds the preset difference degree threshold, rolling back the second system control instruction.

3. The method of claim 1, wherein, The target industrial control system comprises a plurality of target devices and target positions, and the operation of collecting the first response data generated by the target industrial control system in response to the first system control instruction and the first simulation data generated by the system mathematical model based on the first system control instruction further comprises: collecting original response data generated by the target devices and the target positions in response to the first system control instruction; based on a data change pattern of the original response data, interpolating and completing missing values in the original response data to obtain the first response data; collecting data output generated by the system mathematical model after running based on the first system control instruction, and taking the data output as the first simulation data.

4. The method of claim 3, wherein, The interpolating and completing missing values in the original response data comprises: using a linear interpolation method to complete the missing values according to a linear relationship of adjacent data points of the missing values.

5. The method of claim 1, wherein, The inputting of the first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system comprises: synchronously inputting the first system control instruction into the target industrial control system and the system mathematical model in real time.

6. The method of claim 1, wherein, After the step of collecting the first response data and the first simulation data, the method further comprises: storing the first response data and the first simulation data in a time sequence type database local to the industrial gateway.

7. A method of cooperative control, wherein, The collaborative control method is applied to a cloud computing platform, and the method comprises: According to the kinetic analysis result of the components in the target industrial control system, a system mathematical model of the target industrial control system is constructed, so that the industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction, and returns the first response data and the first simulation data; The first response data and the first simulation data returned by the industrial gateway are received; Parameter intelligent identification is performed according to the first response data and the first simulation data; The system mathematical model is updated according to the result of the parameter intelligent identification, and a kinetic updated model is obtained.

8. The method of claim 7, wherein, The operation of constructing the system mathematical model of the target industrial control system according to the kinetic analysis result of the components in the target industrial control system includes: According to the kinetic analysis result of the components in the target industrial control system, the input-output relationship and input-output data of the components in the target industrial control system are determined; According to the input-output relationship and input-output data, a system transfer function is established and system parameters of the system transfer function are determined; Based on the system transfer function and the system parameters, the system mathematical model of the target industrial control system is constructed.

9. The method of claim 8, wherein, The operation of performing parameter intelligent identification according to the first response data and the first simulation data includes: A model parameter vector is determined based on the system parameters; Target point position information in the target industrial control system is determined based on the first response data; A Jacobian matrix corresponding to the model parameter vector is calculated based on the first simulation data and the system mathematical model, and predicted point position information is obtained; A response-prediction error between the target point position information and the predicted point position information is determined; and A model parameter error correction amount is determined based on the L-M least square method and the response-prediction error; The operation of updating the system mathematical model according to the result of the parameter intelligent identification to obtain a kinetic updated model includes: The system transfer function is corrected by the model parameter error correction amount to obtain a kinetic updated model.

10. The method of claim 9, wherein, The operation of determining the model parameter error correction amount based on the L-M least square method and the response-prediction error includes: Based on the response-prediction error, the Jacobian matrix, and the damping coefficient of the target industrial control system, the model parameter error correction amount is iteratively calculated until the error norm of adjacent two iterations meets a preset convergence condition.

11. An industrial gateway applied to a cooperative control device, wherein, The industrial gateway includes: A control module for inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system, the system mathematical model being constructed by a cloud computing platform according to the kinetic analysis result of the components of the target industrial control system; A collection module for collecting first response data generated by the target industrial control system in response to the first system control instruction, and first simulation data generated by the system mathematical model based on the first system control instruction; and The back transmission module is configured to back transmit the first response data and the first simulation data, so that the cloud computing platform receives the first response data and the first simulation data, performs parameter intelligent identification according to the first response data and the first simulation data, updates the system mathematical model according to a result of the parameter intelligent identification, and obtains a dynamic updating model.

12. The industrial gateway of claim 11, wherein, The collection module comprises: The real-time data collection unit is configured to collect original response data of a target point in the target industrial control system; The missing data filling unit is configured to perform interpolation completion on missing values in the original response data, and obtain preprocessed system real-time data; The time series data storage unit is configured to store the system real-time data by using a time series database.

13. A cloud computing platform applied to a cooperative control device, wherein, The cloud computing platform comprises: The construction module is configured to construct a system mathematical model of the target industrial control system according to a dynamic analysis result of a component of the target industrial control system, so that the industrial gateway inputs a first system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects first response data generated by the target industrial control system in response to the first system control instruction, and collects first simulation data generated by the system mathematical model based on the first system control instruction, and back transmits the first response data and the first simulation data; The receiving module is configured to receive the first response data and the first simulation data back transmitted by the industrial gateway; The identification module is configured to perform parameter intelligent identification according to the first response data and the first simulation data; and The updating module is configured to update the system mathematical model according to a result of the parameter intelligent identification, and obtain a dynamic updating model.

14. A coordinated control system wherein, Comprise: A target industrial control system; A cloud computing platform connected with the target industrial control system, configured to construct the system mathematical model according to a dynamic analysis result of a component of the target industrial control system; And An industrial gateway connected with the target industrial control system and the cloud computing platform, the industrial gateway being configured to: Distribute a first system control instruction received and distributed by the cloud computing platform into the target industrial control system and a system mathematical model corresponding to the target industrial control system; Collect first response data generated by the target industrial control system in response to the first system control instruction, and collect first simulation data generated by the system mathematical model based on the first system control instruction; And Back transmit the first response data and the first simulation data to the cloud computing platform; The cloud computing platform is further configured to perform parameter intelligent identification according to the received first response data and first simulation data, and update the system mathematical model according to a result of the parameter intelligent identification, and obtain a dynamic updating model.

15. The coordinated control system of claim 14, wherein, The cloud computing platform is configured to distribute the updated dynamic updating model to the industrial gateway, and the industrial gateway is configured to execute and verify the dynamic updating model.

16. The coordinated control system of claim 15, wherein, The industrial gateway is further configured to: Input a second system control instruction into the target industrial control system and the dynamic updating model; collect second response data generated by the target industrial control system in response to the second system control instruction, and second simulation data generated by the kinetic update model based on the second system control instruction; determine whether a difference between the second response data and the second simulation data exceeds a preset difference threshold; if the difference between the second response data and the second simulation data exceeds the preset difference threshold, roll back the second system control instruction.

17. The coordinated control system of claim 14 wherein, The target industrial control system includes a plurality of target devices and target points. The industrial gateway is further configured to: collect original response data generated by the target devices and the target points in response to the first system control instruction; based on a data change pattern of the original response data, interpolate and complete missing values in the original response data to obtain the first response data; collect data output generated by the system mathematical model after running based on the first system control instruction, and use the data output as the first simulation data.

18. The coordinated control system of claim 14 wherein, The cloud computing platform is further configured to: determine input-output relationships and input-output data of the components of the target industrial control system according to the kinetic analysis results of the components of the target industrial control system; establish a system transfer function and determine system parameters of the system transfer function according to the input-output relationships and the input-output data; construct the system mathematical model of the target industrial control system based on the system transfer function and the system parameters.

19. The coordinated control system of claim 18, wherein, The cloud computing platform is further configured to: determine a model parameter vector based on the system parameters; determine target point information in the target industrial control system based on the first response data; calculate a Jacobian matrix corresponding to the model parameter vector based on the first simulation data and the system mathematical model to obtain predicted point information; determine a response-prediction error between the target point information and the predicted point information; determine a model parameter error correction amount based on the L-M least square method and the response-prediction error; and modify the system transfer function based on the model parameter error correction amount to obtain a kinetic update model. The device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the operations of the collaborative control method according to any one of claims 1 to 10.

20. A synergic control device, wherein, A computer program is stored thereon, and the computer program is executed by a processor to implement the operations of the collaborative control method according to any one of claims 1 to 10.

21. A computer readable storage medium, wherein, The computer program product includes a computer program, and the computer program is executed by a processor to implement the operations of the collaborative control method according to any one of claims 1 to 10.

22. A computer program product, wherein, ​

Images