Cooperative control method and device, equipment, storage medium and product

Abstract

The invention discloses a cooperative control method and device, equipment, a storage medium and a product, and relates to the technical field of big data edge computation.The method comprises the steps that a first system control instruction is input into a target industrial control system and a corresponding system mathematical model through an industrial gateway, and the system mathematical model is constructed by a cloud computing platform; collecting first response data generated by the target industrial control system in response to the system control instruction and first simulation data generated by the system mathematical model; the first response data and the first simulation data are transmitted back, so that after the cloud computing platform receives the first response data and the first simulation data, parameter intelligent identification is carried out according to the first response data and the first simulation data, the system mathematical model is updated according to a parameter intelligent identification result, and a dynamics updating model is obtained; by means of the method, real-time updating of the complex system model of the industrial control system is supported, and the efficiency and effect of model building and tuning are improved.

Description

Technical Field

[0001] The present application relates to the field of big data edge computing technology, and in particular to a collaborative control method, device, equipment, storage medium and product. Background Art

[0002] With the rapid development of intelligent manufacturing and high-end manufacturing, there are higher requirements for the control accuracy of systems composed of industrial equipment such as industrial robots and CNC machine tools.

[0003] At present, in the control process of industrial sites, proportional-integral-differential PID control strategy is a common technical method. The selection of control parameters of PID controller has a great influence on the control performance. Appropriate control parameters can ensure the stable operation and control effect of the control system. At present, the proportional control parameters, integral control parameters and differential control parameters of the controller are usually adjusted directly by trial and error or empirical method, but it is heavily dependent on expert experience and is time-consuming and labor-intensive.

[0004] With the advancement of technology, the industry has begun to study the modeling of control systems. For example, in the system design stage, dynamic modeling based on theoretical analysis is used, and in the system commissioning stage, big data modeling and simulation is performed based on system operation data and neural network big data. However, dynamic modeling based on theoretical analysis is difficult to fully and accurately describe its model, and the error in the prediction of dynamic errors is large. The use of high-order or finite element models brings problems such as low computational efficiency and difficulty in model parameter identification. Big data modeling based on equipment data and neural networks has a relatively simple modeling process and is not robust enough without theoretical support. At the same time, once the identification of its parameters is successful, the PID of its control system is determined, and it cannot support the modification of PID at any time. Factors such as manufacturing, assembly, component wear, gravity and load, temperature, etc. will cause deviations between the control system itself and the theoretical model. Such identification is inaccurate and cannot detect the current status of the equipment in real time, making the control more inaccurate.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a collaborative control method, device, equipment, storage medium and computer program product, aiming to improve the efficiency and effectiveness of establishing and tuning industrial control system models.

[0007] To achieve the above objectives, the present application proposes a collaborative control method, which is applied to an industrial gateway and includes:

[0008] 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 dynamic analysis results of components of the target industrial control system;

[0009] Collecting first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction;

[0010] The first response data and the first simulation data are transmitted back 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, and updates the system mathematical model according to the result of the intelligent parameter identification to obtain a dynamic update model.

[0011] In addition, the present application also proposes a collaborative control method, which is applied to a cloud computing platform and includes:

[0012] According to the dynamic analysis results 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 the system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects the first response data generated by the target industrial control system in response to the system control instruction, and the first simulation data generated by the system mathematical model based on the system control instruction, and transmits the first response data and the first simulation data back;

[0013] Receiving first response data and first simulation data returned by the industrial gateway;

[0014] Performing intelligent parameter identification according to the first response data and the first simulation data;

[0015] The system mathematical model is updated according to the result of the intelligent identification of the parameters to obtain a dynamic update model.

[0016] In addition, to achieve the above-mentioned purpose, the present application also proposes a collaborative control device, which includes:

[0017] The device includes an industrial gateway, and the industrial gateway includes:

[0018] A control module, used 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, wherein the system mathematical model is constructed by a cloud computing platform according to a dynamic analysis result of components of the target industrial control system;

[0019] An acquisition module, used for acquiring first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction;

[0020] A feedback module, used for transmitting the first response data and the first simulation data back, 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, and updates the system mathematical model according to the result of the intelligent parameter identification to obtain a dynamic update model;

[0021] The device further includes a cloud computing platform, and the cloud computing platform includes:

[0022] A construction module, used to construct a system mathematical model of the target industrial control system according to the dynamic analysis results of the components in the target industrial control system, so that the industrial gateway inputs the system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects the first response data generated by the target industrial control system in response to the system control instruction, and the first simulation data generated by the system mathematical model based on the system control instruction, and transmits the first response data and the first simulation data back;

[0023] A receiving module, used for receiving the first response data and the first simulation data returned by the industrial gateway;

[0024] an identification module, used for performing intelligent parameter identification according to the first response data and the first simulation data;

[0025] The updating module is used to update the system mathematical model according to the result of the intelligent identification of the parameters to obtain a dynamic update model.

[0026] In addition, to achieve the above-mentioned purpose, the present application also proposes a collaborative control device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the collaborative control method described above.

[0027] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the collaborative control method described above are implemented.

[0028] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the collaborative control method described above.

[0029] One or more technical solutions proposed in the present application include inputting a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system through an industrial gateway, wherein the system mathematical model is constructed by a cloud computing platform based on the dynamic analysis results of the components of the target industrial control system; collecting first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction; transmitting the first response data and the first simulation data back so that the cloud computing platform receives the first response data and the first simulation data, performs intelligent parameter identification based on the first response data and the first simulation data, and updates the system mathematical model based on the results of the intelligent parameter identification to obtain a dynamic update model. The above method supports real-time updating of complex system models of industrial control systems, thereby improving the efficiency and effect of model establishment and tuning. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0032] Figure 1 A flowchart of the collaborative control method embodiment 1 of the present application is provided;

[0033] Figure 2 Schematic diagram of the overall system architecture of the collaborative control system corresponding to the collaborative control method of the present application;

[0034] Figure 3 A flowchart of the cloud-edge collaborative control method for an industrial system based on intelligent parameter identification in the collaborative control method of this application;

[0035] Figure 4 This is a schematic diagram of the components of the cloud computing platform data acquisition and processing module in the collaborative control method of this application;

[0036] Figure 5 A flowchart of the second embodiment of the collaborative control method of the present application is provided;

[0037] Figure 6 A data flow diagram of a mathematical model building module based on intelligent parameter identification in the collaborative control method of this application;

[0038] Figure 7A schematic diagram of the process of establishing the mathematical model in the collaborative control method of this application;

[0039] Figure 8 This is a schematic diagram of the basic principle of parameter identification based on the LM least squares method of the collaborative control method of this application;

[0040] Fig. 9 A brief flowchart of the collaborative control method provided in the embodiment of the present application;

[0041] Fig.10 A schematic diagram of the device structure of the hardware operating environment involved in the collaborative control method in the embodiment of the present application.

[0042] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0044] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0045] The main solution of the embodiment of the present application is: to provide a cloud-edge collaborative control method and system for industrial systems based on intelligent parameter identification, in which the cloud computing platform is used to establish and update the industrial system dynamics model; the new industrial gateway is used to execute control commands, efficiently collect, store and return the system's business data, pressure data, temperature data, network data, location data, room temperature data, equipment operation data, etc.; through the gateway to collect and return to the cloud input and output data and the deployed parameter intelligent identification algorithm, the cloud computing platform corrects the industrial system modeling parameters, and realizes dynamic update of the model on the new industrial gateway side through the 5G network, and the new industrial gateway performs rapid verification. Based on the above process, one-time identification of model parameters can be achieved, which solves the problem of relying on manual experience for parameter identification; at the same time, the intelligent parameter identification algorithm based on the LM least squares method and the cloud-edge collaborative technology support the real-time update of complex system models, improving the efficiency and effect of model establishment and tuning.

[0046] Cloud computing platform: used to establish and update the industrial system dynamics model, modify the industrial system modeling parameters, and dynamically update the model on the gateway side through 5G. New industrial gateway: execute commands, collect data and transmit data back. Verify model update

[0047] Since most of the existing control methods for industrial equipment systems in the prior art adopt proportional-integral-differential PID control or control system modeling, the PID controller is relatively blind in adjusting parameters, and it is very difficult to debug the system; the modeling based on theoretical analysis has large prediction errors of dynamic errors; the system modeling based on big data has problems such as poor robustness and difficulty in real-time modification of PID. Therefore, the existing technology is not conducive to the realization of precise control of the system and efficient parameter identification.

[0048] For example, the Chinese patent application number 202110676192.8 discloses a permanent magnet synchronous motor control system and a control parameter intelligent identification method. This method is applied to the permanent magnet synchronous motor control system, which can ensure that the motor reaches the specified position accurately as required and outputs precise torque, thereby realizing precise position control and accurate torque control of the permanent magnet synchronous motor.

[0049] This patent identifies the parameters of the permanent magnet synchronous motor under different operating conditions of the motor, and obtains the electromechanical response parameters and equivalent servo inertia parameters when controlling the motor rotor according to the motor response parameter formula. The overall implementation logic of this method is relatively simple and relies on the accuracy of the response parameter formula; at the same time, the parameter formula used in this method is fixed, and the motor parameters obtained are fixed. In fact, the parameter type obtained changes in real time, so it is difficult to adapt to large and complex control systems. Therefore, the above disadvantages may lead to more inaccurate control.

[0050] The present application provides a solution, which inputs a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system through an industrial gateway, wherein 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; collects first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction; transmits the first response data and the first simulation data back 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, and updates the system mathematical model according to the results of the intelligent parameter identification to obtain a dynamic update model. The above method supports real-time updating of complex system models of industrial control systems, thereby improving the efficiency and effect of model establishment and tuning.

[0051] It should be noted that the execution subject of this embodiment can be a computing service device with collaborative control, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a collaborative control system, etc. The following takes the collaborative control system as an example to illustrate this embodiment and the following embodiments.

[0052] Based on this, the embodiment of the present application provides a collaborative control method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the collaborative control method of the present application.

[0053] In this embodiment, the collaborative control method is applied to an industrial gateway, and the method includes steps S1000 to S3000:

[0054] Step 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, wherein the system mathematical model is constructed by a cloud computing platform according to dynamic analysis results of components of the target industrial control system;

[0055] It should be noted that in this embodiment, the implementation of the collaborative control method takes a numerical control system including a drive, a motor, and a mechanical transmission mechanism as an example. Figure 2 , Figure 2 This is the overall system architecture of the collaborative control system corresponding to the collaborative control method of this application, in which the cloud computing platform is used to establish and update the industrial system dynamics model, correct the industrial system modeling parameters, and realize dynamic model updating on the gateway side through 5G.

[0056] The new industrial gateway is used to execute control commands, efficiently collect, store and transmit the system's business data, pressure data, temperature data, network data, location data, room temperature data, equipment operation data, etc. The gateway collects and transmits input and output data and deployed parameter intelligent identification algorithms to the cloud. The cloud computing platform corrects the industrial system modeling parameters, and dynamically updates the model on the new industrial gateway side through the 5G network, which is quickly verified by the new industrial gateway.

[0057] In addition, it should be noted that based on Figure 2 The collaborative control method implemented by the collaborative control system has the following main processes: Figure 3 As shown, Figure 3 This is a flow chart of the cloud-edge collaborative control method for industrial systems based on intelligent parameter identification. The collaborative control method is mainly carried out through the model building module based on intelligent parameter identification, the model execution and verification module, and the data acquisition and processing module shown in the figure.

[0058] Among them, the industrial gateway side is mainly responsible for the model execution and verification module and the data acquisition and processing module. Specifically, the model building module based on intelligent parameter identification is used to establish the mathematical model of the industrial control system, that is, the system mathematical model of the target industrial control system. The system mathematical model is based on the basic dynamics model, and the parameters are intelligently tuned through the data of the real industrial control system based on the intelligent parameter identification algorithm, and finally an accurate mathematical model is established.

[0059] The model execution and verification module is used to execute the mathematical model generated by the model building module. The gateway executes the control commands based on the mathematical model and collects various data in the control system, and then transmits them to the cloud via 5G, so that the model building module based on intelligent parameter identification can update the model parameters in real time. After the model parameters in the cloud are updated, the latest model can be sent to the gateway with one click via 5G, and execution and rapid verification can be completed.

[0060] The data acquisition and processing module is used to obtain real-time data in the industrial control system. The data is collected through the gateway and the data of key points in the control system are filled with missing values ​​using interpolation technology. The missing values ​​are data missing due to transmission instability caused by the actual factory environment during the monitoring process; the collected data is stored and analyzed using a time series database to support rapid verification of the model and cloud query analysis.

[0061] More specifically, the industrial model execution and verification module is carried by the industrial gateway on the terminal side, where the execution and verification of the model include the input of control instructions. During the first intelligent parameter identification and subsequent continuous intelligent parameter maintenance, the same control instructions need to be input into the industrial control system and its corresponding system mathematical model respectively. The new industrial gateway can synchronize control instructions in real time through 5G communication technology, thereby maximizing the effectiveness of the results of fitting the response data of the industrial control system and the simulation system.

[0062] The cloud computing platform is responsible for establishing an accurate mathematical model. The excitation signal is the control command given when the system is first modeled. The real-time system data is the pre-processed system operation data returned by the gateway after the system is running. It provides a data basis for updating model parameters. The basic dynamics model is a mathematical model established according to theory. The intelligent parameter identification is a one-time identification of model parameters based on the LM algorithm and subsequent continuous optimization.

[0063] Step S2000: collecting first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction;

[0064] It should be noted that in this embodiment, during the first intelligent parameter identification and subsequent continuous intelligent parameter maintenance, the collaborative control system inputs the same control instruction into the industrial control system and its corresponding basic dynamics model respectively. The new industrial gateway can synchronize the control instruction in real time through 5G, and maximize 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 has a rich communication protocol parsing application built in, and supports the collection of multi-point data of multiple devices through a rich peripheral interface. At the same time, the gateway has basic computing power and supports basic data processing and analysis on the terminal 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, including the first response data generated by the target public system when it receives the control instruction and the first simulation data generated by the system mathematical model based on the control instruction.

[0065] Step S3000: The first response data and the first simulation data are transmitted back 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, and updates the system mathematical model according to the result of the intelligent parameter identification to obtain a dynamic update model.

[0066] It should be noted that, in this embodiment, the industrial gateway has built-in rich communication protocol parsing applications, and supports the collection of multi-point data from 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 capabilities and supports real-time transmission of data to the cloud for subsequent data analysis and intelligent parameter identification and modeling, including the first response data generated by the target public system when it receives a control instruction and the first simulation data generated by the system mathematical model when it is running based on the control instruction.

[0067] After the industrial gateway transmits the collected first response data and the first simulation data back to the cloud computing platform, the cloud computing platform will intelligently adjust the parameters based on the intelligent parameter identification algorithm through the data of the real industrial control system, and finally establish a more accurate mathematical model, namely the dynamic update model.

[0068] In a feasible implementation manner, the method may further include steps A1000 to A4000:

[0069] Step A1000: inputting a second system control instruction into the target industrial control system and the dynamic update model;

[0070] Step A2000: collecting second response data generated by the target industrial control system in response to the second control instruction of the system, and second simulation data generated by the system mathematical model based on the second control instruction of the system;

[0071] Step A3000: determining whether the difference between the second response data and the second simulation data is greater than a preset difference threshold;

[0072] Step A4000: If the difference between the second response data and the second simulation data exceeds a preset difference threshold, the second control instruction of the system is rolled back.

[0073] 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 sends the control instructions, it can preliminarily fit the actual response data and the simulation prediction data on the terminal side. If the difference between the two is large, it is considered that the original basic physics model is invalid or the optimized physics model is updated incorrectly, and the relevant control instructions based on the system dynamics model will be quickly rolled back to ensure the stable operation of the control system to the greatest extent.

[0074] In the entire collaborative control method, the input of the second control instruction of the system is a key step to further verify the dynamic update model. This instruction not only acts on the actual industrial control system, but also on its corresponding mathematical model, allowing us to evaluate the effect of the control strategy at both practical and theoretical levels. In this way, it can ensure that the control instruction is fully tested and verified before actual application, thereby improving the stability and reliability of the system.

[0075] In addition, it should be noted that collecting the second response data and the second simulation data is an important part of evaluating the effect of the second control instruction of the system. The second response data reflects the performance of the industrial control system in actual operation, while the second simulation data is the response prediction of the mathematical model to the same control instruction. By comparing the difference between the two, we can judge whether the actual effect of the control instruction meets expectations and the accuracy of the mathematical model.

[0076] In addition, it should be noted that judging whether the difference between the second response data and the second simulation data exceeds the preset difference threshold is the key to determining whether the control instruction needs to be adjusted. If the difference exceeds the threshold, it means that there is a problem with the current control instruction or mathematical model and it needs to be corrected. At this time, the second control instruction of the system is rolled back, that is, the control instruction is revoked to avoid possible system instability or performance degradation and ensure the safety and efficiency of the system.

[0077] For example, in a feasible implementation, the target industrial control system may include an automated assembly line, which includes multiple robotic arms and conveyor belts. The second control instruction of the system may involve adjusting the movement speed of the robotic arm or the operating rate of the conveyor belt. The new industrial gateway is responsible for collecting the speed, acceleration and other data of the robotic arm and the conveyor belt after executing the new control instruction as the second response data. At the same time, the dynamic update model will also generate predicted speed and acceleration data according to the same control instruction as the second simulation data. The cloud computing platform will compare the two sets of data. If it is found that the difference between the actual operating data and the model predicted data exceeds the preset threshold, the rollback mechanism of the control instruction will be triggered 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 the accuracy of the mathematical model is also verified and optimized.

[0078] In a feasible implementation manner, the target industrial control system includes a plurality of target devices and target points, and step S2000 may include steps S2100 to S2300:

[0079] Step S2100: collecting original response data generated by the target device and target point when the target industrial control system responds to the system control instruction;

[0080] Step S2200: Based on the data change mode of the original response data, interpolate and complete the missing values ​​in the original response data to obtain first response data;

[0081] Step S2300: collecting data output generated by the system mathematical model after the system control instruction is executed, and using the data output as the first simulation data.

[0082] It should be noted that in this embodiment, the new industrial gateway can be based on 5G transmission, and with the characteristics of low latency and large bandwidth, it can synchronize the response data of the real control system to the cloud for parameter error analysis, while also providing operation data support for upper-level third-party platforms such as digital twin platforms.

[0083] When the target industrial control system responds to the system control command, the original response data generated by the target device and target point is the basis for implementing the collaborative control method. These data reflect the status of the industrial control system in actual operation and are the key to evaluating the effect of control commands and system performance. In addition, Figure 3 The data acquisition and processing module shown is configured on the new industrial gateway side. The module specifically includes the following Figure 4Among the units shown, the real-time data acquisition unit is responsible for collecting data. The new industrial gateway has built-in rich communication protocol parsing applications, and supports the collection of multi-point data from 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 terminal 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.

[0084] In addition, it should be noted that most real control systems are deployed in factory environments. The harsh factory environment will lead to missing or lost data due to various reasons during the data acquisition process. The missing data filling unit estimates the missing values ​​according to the patterns and trends of the existing data by using interpolation technology, 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 changes between the data are linear. For missing values, linear interpolation estimates the missing values ​​based on the known linear relationship between adjacent data points.

[0085] Interpolation of missing values ​​in the original response data is an important step to ensure data integrity. Due to uncertainties in industrial environments, such as sensor failure or communication interference, data may be missing. Through interpolation technology, these missing values ​​can be estimated and filled to obtain continuous and complete data, providing an accurate basis for subsequent data analysis and model optimization.

[0086] In addition, it should be noted that collecting the data output generated by the system mathematical model based on the system control instructions and using these data as the first simulation data is a key link in verifying and optimizing the mathematical model. By comparing the first response data and the first simulation data, the accuracy of the model and the effectiveness of the control instructions can be evaluated. This process is the basis for realizing intelligent identification of model parameters and dynamic updating of the system mathematical model.

[0087] For example, in a feasible implementation, the motor running angle and speed are obtained. At certain time points, there may be some missing values ​​in the data due to acquisition equipment failure or communication problems. Interpolation technology can be used to fill these missing values ​​for subsequent intelligent parameter analysis and digital twin modeling. We can use linear interpolation to fill the missing values ​​in the motor running angle and speed. Assume that the data set is as shown in Table 1:

[0088] Table 1: Missing tables

[0089] Timestamp Motor angle Motor speed 1467627245000 23.3 3.4 1467627246000 23.2 3.3 1467627247000 23.3 Missing 1467627248000 Missing Missing 1467627249000 23.3 3.2

[0090] For the missing motor running angle and speed, linear interpolation can be performed using known adjacent data points. For example, the motor angle at timestamp 1467627248000 can be estimated by linear interpolation using the motor angles at times 1467627247000 and 1467627249000. Similarly, the memory usage at time 1467627248000 can be estimated by linear interpolation using the motor speeds of adjacent timestamps. After interpolation, the data set becomes as shown in Table 2 below:

[0091] Table 2: Completed table

[0092] Timestamp Motor angle Motor speed 1467627245000 23.3 3.4 1467627246000 23.2 3.3 1467627247000 23.3 3.2 1467627248000 23.3 3.2 1467627249000 23.3 3.2

[0093] In this way, missing values ​​were successfully filled and the continuity and integrity of the data were maintained for predictions and analysis related to subsequent modeling work.

[0094] In addition, it should be noted that in order to ensure the effectiveness of intelligent parameter identification and modeling, the data collected by the industrial gateway is large-scale, high-dimensional, time-related, and requires query and analysis. This requires the gateway data to be efficiently collected, inserted, stored, and queried.

[0095] In this method, the gateway uses a time series database through a time series data storage unit to achieve high data throughput and low latency; it uses a special data structure and indexing technology to efficiently store and query data, and uses compression algorithms and data segmentation technologies to reduce storage space and improve query performance; it has data analysis capabilities and provides a wealth of time series analysis functions and algorithms, thereby achieving preliminary judgment of the model on the end side and minimizing the impact of model errors.

[0096] The present embodiment provides a collaborative control method, which inputs a first system control instruction into a target industrial control system and a system mathematical model corresponding to the target industrial control system through an industrial gateway, wherein 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; collects first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction; transmits the first response data and the first simulation data back 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, and updates the system mathematical model according to the results of the intelligent parameter identification to obtain a dynamic update model. The above method supports real-time updating of complex system models of industrial control systems, thereby improving the efficiency and effect of model establishment and tuning.

[0097] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 The collaborative control method is also applied to a cloud computing platform, and the method includes steps B1000 to B4000:

[0098] Step B1000: constructing a system mathematical model of the target industrial control system according to the dynamic analysis results of the components in the target industrial control system, so that the industrial gateway inputs the system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects the first response data generated by the target industrial control system in response to the system control instruction, and the first simulation data generated by the system mathematical model based on the system control instruction, and transmits the first response data and the first simulation data back;

[0099] It should be noted that building a mathematical model of the target industrial control system is the first step to achieve precise control. The model is based on the dynamic analysis results of each component in the 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 control instructions and predict system responses.

[0100] In addition, it should be noted that after receiving the system control instruction, the industrial gateway applies it to the target industrial control system and its corresponding mathematical model. Subsequently, the gateway collects the first response data generated by the actual response of the system to the control instruction, as well as the first simulation data generated by the mathematical model prediction, and transmits these data back to the cloud computing platform. This process ensures the accuracy and practicality of the model, and provides the necessary data support for subsequent parameter identification and model update.

[0101] Step B2000: receiving the first response data and the first simulation data returned by the industrial gateway;

[0102] It should be noted that receiving the first response data and the first simulation data sent back by the industrial gateway is a key task of the cloud computing platform. These data provide the platform with an empirical basis for evaluating and optimizing control strategies. By analyzing the consistency between the actual system response and the model prediction, the cloud computing platform can accurately evaluate the effectiveness of the current mathematical model.

[0103] Step B3000: performing intelligent parameter identification according to the first response data and the first simulation data;

[0104] It should be noted that intelligent parameter identification is an analysis process performed by the cloud computing platform based on the received first response data and first simulation data. This process uses advanced algorithms, such as the LM least squares method, to fine-tune the model parameters to minimize the difference between the actual response and the simulation data. The goal of intelligent identification is to find the optimal set of parameters so that the mathematical model can reflect the real behavior of the industrial control system as accurately as possible.

[0105] Step B4000: Update the system mathematical model according to the result of the intelligent identification of the parameters to obtain a dynamic update model.

[0106] It should be noted that updating the system mathematical model based on the results of intelligent parameter identification is the core link to achieve continuous optimization and precise control of the model. The generation of the dynamic update model indicates that the model has been iteratively improved and is closer to the characteristics of the actual system. This update process not only improves the prediction accuracy of the model, but also lays the foundation for realizing a more automated and intelligent industrial control system.

[0107] For example, in a specific implementation, the target industrial control system may be an automated manufacturing assembly line, including multiple sensors, actuators, and mechanical equipment. The cloud computing platform first builds a mathematical model based on the dynamic characteristics of these devices. The industrial gateway then applies the control instructions to the actual system and the mathematical model, and collects the response data of both. After receiving this data, the cloud computing platform performs intelligent parameter identification, finds the model parameters that need to be adjusted, and updates the model. Ultimately, the updated model can more accurately predict the effect of the control instructions, providing reliable decision support for the optimization of the manufacturing assembly line.

[0108] In a feasible implementation manner, step B1000 may include steps B1100 to B1300:

[0109] Step 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 in the target industrial control system;

[0110] Step B1200: establishing a system transfer function and determining system parameters of the system transfer function according to the input-output relationship and the input-output data;

[0111] Step B1300: constructing a system mathematical model of the target industrial control system based on the system transfer function and system parameters.

[0112] It should be noted that in this embodiment, the system mathematical model is mainly constructed through the cloud computing platform, that is, through Figure 3The model building module based on intelligent parameter identification is shown to build a mathematical model of the industrial control system. The mathematical model is based on the basic dynamics model, and the parameters are intelligently tuned through the data of the real industrial control system based on the intelligent parameter identification algorithm, and finally an accurate mathematical model is established.

[0113] The purpose of in-depth dynamic analysis of the components of the target industrial control system is to clarify the input-output relationship between the components and the specific input-output data performance under these relationships. This information is the cornerstone of building a mathematical model of the system to ensure that the model can truly reflect the dynamic characteristics of the system.

[0114] In addition, it should be noted that once the input-output relationship and data are determined, the next task is to establish the transfer function of the system. The transfer function is used to describe the dynamic relationship between the input and output of the system. By analyzing these data, the system parameters in the system transfer function can be further determined. These parameters are the key variables in the model and determine the response characteristics of the system to the control command.

[0115] Furthermore, it should be noted that the construction of the system mathematical model is achieved through 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 the necessary theoretical support for the subsequent control command input, data acquisition, parameter identification and model update. Figure 6 and Figure 7 As shown, Figure 6 This is a data flow diagram of a mathematical model building module based on intelligent parameter identification in the collaborative control method of this application. Figure 7 A flow chart showing the establishment of a mathematical model in the collaborative control method of this application. Figure 6 The excitation signal is the control command given when the system is first modeled; the real-time system data is the pre-processed system operation data returned by the gateway after the system is running; it provides a data basis for updating model parameters; the basic dynamics model is a mathematical model established based on theory, and the intelligent parameter identification is based on the LM algorithm to achieve one-time identification of model parameters and subsequent continuous tuning, such as Figure 7 The process shown takes the CNC system including drive, motor and mechanical transmission mechanism as an example. In this step, it is necessary to reasonably consider the various parts of the above-mentioned feed system, incorporate them into the basic dynamics model of the overall feed system, and perform dynamic modeling for the controlled object in the control system, including the establishment of transfer function and parameter identification.

[0116] The establishment of transfer function refers to the establishment of a simplified description of the relationship between the input and output of the feed system based on the control and component motion relationship, which is expressed by a function obtained by Laplace transformation, called transfer function;

[0117] Parameter identification is to determine a set of model parameter values ​​based on experimental data and established models, so that the numerical results calculated by the model can best fit the test data, such as temperature, friction identification, etc. Through the above-mentioned form of mathematical and physical methods, each module included in the control system is expressed to form a complete parameter transfer function.

[0118] For example, in a feasible implementation, the target industrial control system may 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 control instructions. By comparing and analyzing the simulation results of the model with the actual operation data, the intelligent identification of the model parameters and the continuous optimization of the model can be carried out to ensure the control accuracy and efficiency of the robot arm.

[0119] In a feasible implementation manner, step B3000 may include steps B3100 to B3500:

[0120] Step B3100: Determine a model parameter vector based on the system parameters;

[0121] Step B3200: determining target point information in the target public system based on the first response data;

[0122] Step B3300: Calculate the Jacobian matrix corresponding to the model parameter vector based on the first simulation data and the system mathematical model to obtain prediction point information;

[0123] Step B3400: determining a response-prediction error between the target point information and the predicted point information;

[0124] Step B3500: Determine the model parameter error correction amount based on the LM least squares method and the response-prediction error;

[0125] It should be noted that the parameter intelligent identification process is to accurately adjust the model parameter vector based on the system parameters, the first response data and the first simulation data. The key to this process is to accurately reflect the characteristics of the target industrial control system and ensure that the prediction of the mathematical model is consistent with the actual system behavior.

[0126] For example, system parameters may include spring stiffness, damping ratio, etc., which determine the dynamic response of the system. The model parameter vector is determined by minimizing the difference between the predicted output of the system and the actual output, which usually involves the application of optimization algorithms.

[0127] In addition, it should be noted that the first response data provides the feedback of the actual system to the control input, while the first simulation data is the prediction result of the mathematical model based on the same input. By comparing these two sets of data, we can determine the response-prediction error between the target point information and the predicted point information, which is an important indicator for evaluating the accuracy of the model.

[0128] Specifically, the process of intelligent parameter identification of the dynamic model is to ignore the high-order differential components in the nonlinear model and analyze according to the linear method. When 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 actual industrial control system. When identifying parameters, the most commonly used method to linearize the nonlinear model is the least squares method. The least squares method takes an approximate intermediate value, which will cause calculation errors. During the convergence process, the objective function will be farther and farther away from the minimum value, and the final fitting effect will be unacceptable. The LM least squares method uses the damping coefficient μ to limit the iterative operation to avoid singularities and improve the least squares fitting effect. The basic principle of parameter identification using the LM least squares method is as follows: Figure 8 shown.

[0129] First, initialize the system dynamics model, determine the parameters and model based on the theory, and calculate the modeling parameter vector X k Then, a certain number of points are used as parameter identification sampling points, and the response value returned by the new industrial gateway is used as the actual position P of the parameter identification sampling point, which is substituted into the modeling parameter vector X k The system dynamics model under the current identification is calculated by the Jacobian matrix J(X k ), obtain the predicted position P′, and then solve the error ΔP(X k ), solve the modeling parameter error correction ΔX k , that is: ΔX k =-[J T (X k )J(X k )+μ k I] -1 , J T (X k)ΔP(X k )

[0130] Among them, μ k is the system damping coefficient, and then the modeling parameter vector X is updated at the k+1th iteration k+1 and the number of iterations k is X k+1 =X k +ΔX k , k=k+1.

[0131] Update the damping coefficient μ at the k+1th iteration k+1 for

[0132]

[0133] In the formula, ||ΔP(X k+1 )|| and||ΔP(X k )|| are the second norms of the position errors of the k+1th and kth iterations, δ is the iteration parameter, when ||ΔP(X k+1 )||-||ΔP(X k )||>ε, update the k+1th modeling parameter vector, and iterate the above steps until ||ΔP(X k+1 )||-||ΔP(X k )||≤ε, the error norm of two iterations approaches ε=0.0001, which proves that it has converged, that is, the optimal parameter error is obtained.

[0134] In a feasible implementation manner, the step of updating the system mathematical model according to the result of the intelligent identification of the parameters to obtain a dynamic update model includes:

[0135] The system transfer function is corrected by the model parameter error correction amount to obtain a dynamic update model.

[0136] That is, the parameter error ΔX identified by the above-mentioned L-M algorithm is used to correct the control system transfer function parameters and update the relevant dynamic model, thereby improving the usage effect of the three parties that reference the model, such as the modeling accuracy of the cloud-based digital twin platform and the accuracy of the control commands of the terminal-side intelligent industrial gateway.

[0137] For example, to help understand the implementation process of the collaborative control method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Fig. 9 , Fig. 9 A brief flow chart of a collaborative control method is provided, specifically:

[0138] The collaborative control method of this application is mainly used in industrial gateways to improve the accuracy and efficiency of industrial control systems. This solution achieves precise control and real-time optimization of the target industrial control system through close collaboration between the cloud computing platform and the industrial gateway.

[0139] First, the cloud computing platform determines the input-output relationship and data of the system based on the dynamic analysis results of each component in the target industrial control system. Dynamic analysis is the study of how system components respond to external stimuli (such as force, heat, electricity, etc.), which provides a basis for establishing accurate mathematical models. Through analysis, we can clarify the interactions between components and their response characteristics to control inputs.

[0140] The platform then uses these input-output relationships and data to establish the system's transfer function and determine the system parameters. The transfer function is a mathematical model that describes the system's output response to input signals in the time domain or frequency domain. System parameters, such as damping ratio and natural frequency, are key variables in the transfer function, which determine the dynamic characteristics of the system.

[0141] Based on the 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 the response under different control strategies. The construction of the mathematical model is the core of the collaborative control method, which provides a theoretical basis for the subsequent control instruction design and optimization.

[0142] Next, the industrial gateway inputs system control instructions into the target industrial control system and its corresponding system mathematical model. These control instructions are intended to adjust the behavior of the industrial control system to achieve the desired control target, such as speed, position or pressure. At the same time, the gateway collects the first response data generated by the target industrial control system in response to the control instruction, and the first simulation data generated by the system mathematical model based on the same control instruction.

[0143] The first response data and the first simulation data are transmitted back 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 LM least squares method, the purpose of which is to find the optimal model parameters so that the mathematical model can predict the behavior of the actual system as accurately as possible.

[0144] 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 the model output to parameter changes, and it plays a vital role in parameter identification. By calculating the response-prediction error, we can evaluate the accuracy of the current model parameters and adjust the parameters accordingly to reduce the error.

[0145] Once the model parameters are intelligently identified and corrected, the system mathematical model will be updated to generate a dynamic update model. This updated model can more accurately reflect the characteristics of the actual industrial control system and provide a basis for further optimization of control instructions.

[0146] In addition, the solution also includes the step of inputting the second control instruction of the system into the target industrial control system and the dynamic update model. This can further verify and optimize the control strategy. After implementing the second control instruction, the system will collect the second response data and the second simulation data, and determine whether the difference between the two is greater than the preset difference threshold. If the difference exceeds the threshold, it indicates that the current control instruction or model needs further adjustment, and the system will perform a rollback operation to cancel the second control instruction.

[0147] In the above process, based on the dynamic analysis of the components of the industrial control system, the corresponding basic dynamic model of the system is established, and then the control instructions are respectively input into the industrial control system and its corresponding basic dynamic model. The edge device intelligent gateway collects relevant data and transmits it to the cloud. Based on the intelligent parameter identification algorithm, the model parameters are updated and the basic dynamic model is improved. The collected data is continuously fed back to support the update of model parameters and maintain the accuracy of the model. The latest model is sent from the cloud, so that the control model in the edge intelligent gateway device is updated, and then the corresponding control commands are changed. At the same time, the gateway supports rapid verification, so that the performance of the control system is optimized as a whole. By making full use of the information given by the model, the optimal control effect of the controlled object can be achieved.

[0148] Through this series of steps, this solution achieves precise control and real-time optimization of industrial control systems, improves the system's response speed and control accuracy, and meets the needs of intelligent manufacturing and other fields for efficient and reliable control systems.

[0149] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the collaborative control method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0150] The collaborative control device provided by the present application adopts the collaborative control method in the above embodiment, which can solve the technical problems of collaborative control. Compared with the prior art, the beneficial effects of the collaborative control device provided by the present application are the same as the beneficial effects of the collaborative control method provided by the above embodiment, and the other technical features in the collaborative control device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0151] The present application provides a collaborative control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the collaborative control method in the above-mentioned embodiment one.

[0152] Reference below Fig.10 , which shows a schematic diagram of the structure of a collaborative control device suitable for implementing the embodiment of the present application. The collaborative control device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.10 The collaborative control device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0153] like Fig.10 As shown, the collaborative control device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the collaborative control device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the collaborative control device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a collaborative control device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0154] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through 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 method of the embodiment disclosed in the present application are executed.

[0155] The collaborative control device provided in the present application adopts the collaborative control method in the above-mentioned embodiment. Compared with the prior art, the beneficial effects of the collaborative control device provided in the present application are the same as the beneficial effects of the collaborative control method provided in the above-mentioned embodiment, and other technical features in the collaborative control device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0156] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0157] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0158] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the collaborative control method in the above-mentioned embodiment.

[0159] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more 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 this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0160] The above-mentioned computer-readable storage medium may be included in the collaborative control device; or it may exist independently without being assembled into the collaborative control device.

[0161] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0163] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0164] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned collaborative control method, and can solve the technical problems of collaborative control. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the collaborative control method provided in the above-mentioned embodiment, and will not be repeated here.

[0165] The present application also provides a computer program product, including a computer program, which implements the steps of the collaborative control method as described above when executed by a processor.

[0166] The computer program product provided by this application can solve the technical problem of cooperative control. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the cooperative control method provided by the above embodiment, which will not be repeated here.

[0167] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A collaborative control method, characterized in that: The collaborative control method is applied to an industrial gateway, and the method includes: 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 dynamic analysis results of components of the target industrial control system; Collecting first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction; The first response data and the first simulation data are transmitted back 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, and updates the system mathematical model according to the result of the intelligent parameter identification to obtain a dynamic update model.

2. The method according to claim 1, characterized in that The method further comprises: Inputting a second system control instruction into the target industrial control system and the dynamic update model; Collecting second response data generated by the target industrial control system in response to the second control instruction of the system, and second simulation data generated by the system mathematical model based on the second control instruction of the system; Determining whether the 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 a preset difference threshold, the second control instruction of the system is rolled back.

3. The method according to claim 1, characterized in that The target industrial control system includes a plurality of target devices and target points, and the step of collecting the first response data generated by the target industrial control system in response to the system control instruction and the first simulation data generated by the system mathematical model based on the system control instruction also includes: Collecting original response data generated by the target device and target point when the target industrial control system responds to the system control instruction; Based on the data change pattern of the original response data, interpolate and complete the missing values ​​in the original response data to obtain first response data; The data output generated by the system mathematical model after the system control instruction is executed is collected, and the data output is used as the first simulation data.

4. A collaborative control method, characterized in that: The collaborative control method is applied to a cloud computing platform, and the method includes: According to the dynamic analysis results 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 the system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects the first response data generated by the target industrial control system in response to the system control instruction, and the first simulation data generated by the system mathematical model based on the system control instruction, and transmits the first response data and the first simulation data back; Receiving first response data and first simulation data returned by the industrial gateway; Performing intelligent parameter identification according to the first response data and the first simulation data; The system mathematical model is updated according to the result of the intelligent identification of the parameters to obtain a dynamic update model.

5. The method according to claim 4, characterized in that The step of constructing a system mathematical model of the target industrial control system according to the dynamic analysis results of the components in the target industrial control system includes: Determining input-output relationships and input-output data of components of the target industrial control system according to the dynamic analysis results of the components in the target industrial control system; According to the input-output relationship and the 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 system parameters, a system mathematical model of the target industrial control system is constructed.

6. The method according to claim 5, characterized in that The step of performing intelligent parameter identification according to the first response data and the first simulation data comprises: determining a model parameter vector based on the system parameters; Determine the target point information in the target public system based on the first response data; Calculate the Jacobian matrix corresponding to the model parameter vector based on the first simulation data and the system mathematical model to obtain prediction point information; Determining a response-prediction error between the target point information and the predicted point information; Determine the model parameter error correction amount based on the LM least squares method and the response-prediction error; The step of updating the system mathematical model according to the result of the intelligent identification of the parameters to obtain a dynamic update model comprises: The system transfer function is corrected by the model parameter error correction amount to obtain a dynamic update model.

7. A collaborative control device, characterized in that: The device includes an industrial gateway, and the industrial gateway includes: A control module, used 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, wherein the system mathematical model is constructed by a cloud computing platform according to a dynamic analysis result of components of the target industrial control system; An acquisition module, used for acquiring first response data generated by the target industrial control system in response to the system control instruction, and first simulation data generated by the system mathematical model based on the system control instruction; A feedback module, used for transmitting the first response data and the first simulation data back, 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, and updates the system mathematical model according to the result of the intelligent parameter identification to obtain a dynamic update model; The device further includes a cloud computing platform, and the cloud computing platform includes: A construction module, used to construct a system mathematical model of the target industrial control system according to the dynamic analysis results of the components in the target industrial control system, so that the industrial gateway inputs the system control instruction into the target industrial control system and the system mathematical model corresponding to the target industrial control system, collects the first response data generated by the target industrial control system in response to the system control instruction, and the first simulation data generated by the system mathematical model based on the system control instruction, and transmits the first response data and the first simulation data back; A receiving module, used for receiving the first response data and the first simulation data returned by the industrial gateway; an identification module, used for performing intelligent parameter identification according to the first response data and the first simulation data; The updating module is used to update the system mathematical model according to the result of the intelligent identification of the parameters to obtain a dynamic update model.

8. A collaborative control device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the cooperative control method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the collaborative control method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the cooperative control method according to any one of claims 1 to 6 are implemented.

Images