Industrial control system and method, electronic equipment and storage medium
By introducing hardware acceleration modules to the industrial control system to handle computing-intensive tasks, the problem of insufficient PLC computing resources is solved, high-performance model prediction control is realized and the system real-time performance is improved.
Patent Information
- Application Number
- CN202510205180.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-24
- Publication Date
- 2025-06-06
Smart Images
Figure CN120103753A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of industrial control technology, and in particular to an industrial control system, method, electronic device and storage medium. Background Art
[0002] Compared with traditional proportional-integral-derivative control (Proportional-Integral-Derivative Control), Model Predictive Control (MPC) has shown significant advantages at the software algorithm level. MPC can effectively deal with multi-input and multi-output systems and complex control problems with constraints by predicting the future state of the system and dynamically generating optimal control strategies based on these predictions. In contrast, PID control relies on simple adjustment of single-input and single-output error feedback. Although the algorithm is simple to implement, it is unable to cope with multi-variable coupling and complex constraint problems. Therefore, MPC is increasingly used in complex industrial control fields such as chemical processes, energy systems, and manufacturing automation.
[0003] However, the original intention of the design of Programmable Logic Controller (PLC) is to meet the requirements of stable and reliable simple control tasks (such as PID control). Its computing power and parallel processing capabilities are usually limited, and it is difficult to support complex optimization algorithms such as MPC. Each control step of MPC needs to solve an online optimization problem. For example, Quadratic Programming (QP) is one of the most common optimization problems that MPC needs to solve online. These online optimization problems generally involve a large number of matrix operations and real-time data processing. This high computing density requires the hardware to have extremely high computing power and fast response capabilities. When executing MPC, traditional PLC hardware platforms often face problems such as insufficient computing resources and response delays, which makes it difficult to meet the needs of high-precision and high-real-time scenarios. Summary of the invention
[0004] In view of this, embodiments of the present application provide an industrial control system, method, electronic device and storage medium to solve the problem in the prior art that the computing resources of the programmable logic controller are limited, resulting in the inability to perform model predictive control.
[0005] According to a first aspect of an embodiment of the present application, an industrial control system is provided, which includes: a main control module, and a hardware acceleration module integrated into the industrial control system as an independent module; the main control module is used to receive industrial control data, and if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; the hardware acceleration module is used to perform computationally intensive tasks in the model predictive control task based on the industrial control data, and send the computational task results of the computationally intensive tasks to the main control module; the main control module is used to control the control device based on the computational task results.
[0006] According to a second aspect of an embodiment of the present application, an industrial control method is provided, which includes: receiving industrial control data through a main control module, and if the industrial control data is used to perform a model predictive control task, sending the industrial control data to a hardware acceleration module; performing computationally intensive tasks in the model predictive control task on the industrial control data through the hardware acceleration module, and sending the computational task results of the computationally intensive task to the main control module; and controlling the control device based on the computational task results through the main control module.
[0007] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0008] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0009] Compared with the prior art, the embodiments of the present application have the following beneficial effects: the industrial control system of the embodiments of the present application includes: a main control module, and a hardware acceleration module integrated into the industrial control system as an independent module; the main control module is used to receive industrial control data, and if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; the hardware acceleration module is used to perform a computationally intensive task in the model predictive control task based on the industrial control data, and the computational task results of the computationally intensive task are sent to the main control module; the main control module is used to control the control device based on the computational task results. By adding an independent hardware acceleration module to the industrial control system, the present application implements high-performance model predictive control on the industrial control system, so that the industrial control system can cope with complex computing tasks and improve the real-time performance of the industrial control system. The problem of the inability to perform model predictive control due to limited computing resources of the programmable logic controller is avoided. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0011] Figure 1 It is a basic schematic diagram of an industrial control system provided by an embodiment of the present application;
[0012] Figure 2 It is a basic schematic diagram of another industrial control system provided by an embodiment of the present application;
[0013] Figure 3 It is a flowchart of an industrial control method provided by an embodiment of the present application;
[0014] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0015] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0016] An industrial control system and method according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.
[0017] Figure 1 An industrial control system provided by an embodiment of the present application is as follows: Figure 1 As shown, the system includes: a main control module, and a hardware acceleration module integrated into the industrial control system as an independent module; the main control module is used to receive industrial control data, and if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; the hardware acceleration module is used to perform computationally intensive tasks in the model predictive control task based on the industrial control data, and send the computational task results of the computationally intensive tasks to the main control module; the main control module is used to control the control device based on the computational task results.
[0018] It can be understood that the main control module is responsible for receiving industrial control data from external devices, sensors or operators. The industrial control data includes at least one of real-time system status, operating parameters and control requirements. By receiving industrial data, the main control module can determine the type of control task that needs to be performed. In this application, if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; if the industrial control data is used for a simple device control task and no model predictive control task is required, the main control module directly generates a control signal based on the industrial control data and sends the control signal to the control device; after the control device receives the control signal, it will perform device operations according to the control signal.
[0019] It can be understood that if the industrial control data involves a model predictive control task, the data will be sent to the hardware acceleration module, where the main control module will detect the content of the industrial control data to determine whether an MPC task involving a large amount of calculation is required. If the industrial control data is related to the MPC task, it will be forwarded to the hardware acceleration module for processing, thereby avoiding the main control module directly processing complex computing tasks (such as online solution of QP), which leads to inefficiency, reducing the computing burden of the main control module, improving the real-time and processing efficiency of the industrial control system, and executing high-complexity tasks through dedicated hardware acceleration modules.
[0020] In some examples, the hardware acceleration module performs computationally intensive tasks based on industrial control data, that is, the hardware acceleration module is specifically responsible for processing the computationally intensive parts of MPC tasks, such as solving quadratic programming (QP) problems, performing matrix operations (such as prediction model construction, cost function calculation), and quickly calculating the optimal control sequence. The hardware acceleration module can improve the computational efficiency of MPC tasks and meet the needs of real-time industrial control. The hardware acceleration module is usually a high-performance computing device (such as FPGA, GPU or dedicated processor) that can quickly perform large-scale matrix operations and solve optimization problems. An independent hardware acceleration module is added to the industrial control system. On the basis of not changing the original structure, the addition of the hardware acceleration module effectively solves the problem of insufficient computing power of the main control module in the traditional PLC, so that the complex algorithm of MPC can be calculated in a short time.
[0021] In some examples, the hardware acceleration module sends the calculation task results to the main control module, wherein after the hardware acceleration module completes the calculation, it transmits the optimized results (such as the optimal control input sequence) back to the main control module, so that the main control module can use these results to perform the next control operation. At this point, the main control module and the hardware acceleration module complete the closed loop of data interaction, ensuring that the hardware acceleration module and the main control module work together.
[0022] Finally, the main control module generates a specific control signal based on the calculation results of the hardware acceleration module, and sends the control signal to the control device (such as a motor, valve, robot, etc.). Real-time control of the control device is achieved, and dynamic adjustment of the industrial control system is realized. In this application, the main control module converts the efficient decision-making results provided by the hardware acceleration module into actual device control actions, completes the entire control process, and improves control efficiency.
[0023] It is understandable that the main control module of the traditional PLC is difficult to execute complex MPC algorithms due to the limitation of computing power, especially when processing large-scale matrix calculations and solving optimization problems online in real time, response delays and reduced control accuracy often occur. In order to make up for this limitation, this application proposes a solution to accelerate the calculation by introducing an independent hardware acceleration module that can efficiently perform parallel calculations, so as to improve the computing performance and real-time performance of the main control module of the PLC when executing MPC.
[0024] It can be understood that the PLC master control module is responsible for the management and execution control of the MPC algorithm, while the hardware acceleration module is responsible for computationally intensive tasks; specifically, Figure 1 As shown, after the main control module receives the industrial control data, if the industrial control data is used to perform model predictive control tasks, the main control module will be responsible for constructing the optimization problem and sending the optimization problem to the hardware acceleration module, where the optimization problem includes but is not limited to matrix operations of QP problems, neuron activation values of neural networks, and other computationally intensive tasks involving a large number of parallel calculations.
[0025] like Figure 1 As shown, after the hardware acceleration module completes the calculation, it will feed back the optimization result (computation task result) to the main control module, so that the main control module can determine the control signal based on the above-mentioned calculation task result and transmit the control signal to the controlled device.
[0026] According to the technical solution provided by the embodiment of the present application, the embodiment of the present application provides an industrial control system, which includes: a main control module, and a hardware acceleration module integrated into the industrial control system as an independent module; the main control module is used to receive industrial control data, and if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; the hardware acceleration module is used to perform a computationally intensive task in the model predictive control task based on the industrial control data, and the computational task results of the computationally intensive task are sent to the main control module; the main control module is used to control the control device based on the computational task results. By adding an independent hardware acceleration module to the industrial control system, the present application implements high-performance model predictive control on the industrial control system, so that the industrial control system can cope with complex computing tasks and improve the real-time performance of the industrial control system. It avoids the problem that the computing resources of the programmable logic controller are limited, resulting in the inability to perform model predictive control.
[0027] In some examples, the hardware acceleration module includes a parallel computing unit and a communication interface. For example, the hardware acceleration module uses a field programmable gate array, and the field programmable gate array (FPGA) includes a parallel computing unit and a communication interface. The communication interface is used to communicate data with the main control module, and the parallel computing unit is used to perform calculations based on the received data. Specifically, the FPGA is designed as an independent hardware unit to process optimization problems through parallelization (for example, the matrix operations of the optimization problem, the neuron activation values of the neural network, etc., which are designed to perform a large number of parallel calculations, and the matrix operations of the QP solution process in the MPC, a computationally intensive task). Its hardware logic circuit can be configured as an efficient parallel computing pipeline, which significantly shortens the calculation time and ensures that the necessary optimization calculations are completed within each control step.
[0028] It can be understood that the communication interface of the hardware acceleration module is a high-speed communication interface (such as Ethernet, PCIe, etc.), in which the main control module is responsible for the management and execution control of the MPC algorithm, while the FPGA is responsible for computationally intensive tasks. Through the high-speed communication interface (such as Ethernet, PCIe, etc.), the main control module passes the data to be calculated to the FPGA for processing, and the FPGA completes the calculation and returns the result to the main control module, ensuring that the industrial control system completes the task within the specified control cycle.
[0029] It can be understood that the industrial control system architecture provided by this application adopts a modular design, and the FPGA module is used as an external acceleration unit, which is convenient for configuration and upgrading according to different application requirements. The main control module is responsible for control strategy and system management, while the FPGA is responsible for computing-intensive task sharing, and the two realize data interaction through standard interfaces.
[0030] In some examples, a parallel computing accelerator (such as a multi-core CPU, GPU, or DSP) may also be used as a hardware acceleration module, which may be flexibly configured by relevant personnel according to needs.
[0031] In some examples, the system also includes a configuration module, such as Figure 2 As shown, the configuration module is used to generate model information, set value information, constraint information, optimization interval information and cost function weight information according to the properties of the control device, and send the model information, set value information, constraint information, optimization interval information and cost function weight information to the main control module; the main control module is also used to construct an augmented model according to the model information and set value information, construct an augmented cost function weight matrix according to the optimization interval information and the cost function weight information, and construct a model predictive control task based on the augmented model, the augmented cost function weight matrix and the constraint information.
[0032] like Figure 2 As shown, the model information includes the state transfer matrix A and the input matrix B, and the setting value information includes the setting value transfer matrix A d , the optimization interval information includes the prediction interval N p and control interval N c The cost function weight information includes the final state cost weight matrix S, the process cost weight matrix Q and the control increment cost weight matrix. It can be understood that the above model information, set value information, constraint information, optimization interval information and cost function weight information can be set by relevant personnel according to the properties of the control device.
[0033] In some examples, after receiving the model information, the main control module will construct an augmented model based on the model information, and the augmented model includes an augmented state transfer matrix Φ and an augmented input increment matrix Γ. After receiving the cost function weight information, the main control module will construct an augmented process cost weight matrix Ω and an augmented control increment cost weight matrix Ψ based on the cost function weight information. The main control module will also construct a QP problem based on the constraint information, the augmented cost function weight matrix, and the augmented model. The QP problem includes a quadratic matrix H, a linear matrix F, a constraint matrix M, b. Subsequently, the QP problem is sent to the hardware acceleration module so that the hardware acceleration module can solve the QP problem. The hardware acceleration module returns the solved U vector to the main control module, and the main control module executes the first control vector u in the solved U vector.
[0034] In some examples, the industrial control system further includes an input / output expansion module (IO module), which is linked to the main control module and is used to obtain sensor acquisition signals and transmit the sensor acquisition signals to the main control module. Figure 2As shown, the main control module obtains the sensor acquisition signal for the control device through the IO module.
[0035] In some examples, such as Figure 1 and Figure 2 As shown, the input / output expansion module is also used to receive the control signal output by the main control module and transmit the control signal to the control device.
[0036] In some examples, the parallel computing unit in the hardware acceleration module uses a first-order optimization algorithm (such as a fast gradient method) to calculate the received data to reduce the computational complexity; a storage unit is also provided on the field programmable gate array (such as a field programmable gate array), and the storage unit is used to store data. In some examples, the storage unit can use a sparse matrix to store data, thereby reducing memory usage and achieving computational optimization.
[0037] It can be understood that when the hardware acceleration module adopts FPGA, the hardware control process is implemented on the FPGA, including data preprocessing, matrix operation acceleration, and control signal generation. Each functional module works in parallel through the pipeline to ensure the continuity and real-time performance of data processing. And the FPGA uses a fixed-point operation method to reduce computing power consumption and hardware resource occupation. A high-speed communication interface is integrated in the FPGA module design, so that it can complete the necessary computing tasks and feedback the control results within the control cycle.
[0038] The above embodiment of the present application connects the FPGA to the main control module, uses hardware-in-the-loop (HIL) testing to verify the control process, and simulates the MPC application in an actual industrial environment. The FPGA module performs calculations while collecting input data in real time and feeds the results back to the PLC main control module.
[0039] The above-mentioned embodiments of the present application utilize the parallel computing characteristics of FPGA, so that the industrial control system can run at a sampling rate of 1MHz, greatly reducing latency. Compared with the traditional method that relies only on the main control module, the response speed after FPGA acceleration has increased by an order of magnitude, achieving higher-frequency real-time control. And the main control module of the present application can generate optimized control signals in a short time, and can maintain steady-state tracking and fast control feedback even in a highly dynamic environment.
[0040] In some examples of this application, FPGA uses sparse matrix and fixed point operation technology, so that FPGA can run complex optimization algorithms while low power consumption. Compared with traditional floating point calculations, memory usage power consumption is significantly reduced, and efficient resource utilization is achieved in embedded systems. And this application achieves higher resource efficiency through the collaboration between FPGA and main control module, which is particularly suitable for industrial control scenarios with high computing resource requirements and limited power consumption. This application maintains high control accuracy in multivariable complex systems through hardware acceleration implemented by FPGA. This application can quickly return to steady state when dealing with external disturbances and rapid set point changes, meeting the stability requirements of industrial control. In practical applications, by setting the main control module after the hardware acceleration module, it is possible to provide high-precision control with less resource occupancy in complex control scenarios, broadening the application scenarios of MPC.
[0041] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.
[0042] The following is an embodiment of the method of the present application. For details not disclosed in the embodiment of the method of the present application, please refer to the above-mentioned system embodiment of the present application.
[0043] This embodiment also provides an industrial control method, such as Figure 3 As shown, the method includes:
[0044] S301, receiving industrial control data through a main control module, and if the industrial control data is used to perform a model prediction control task, sending the industrial control data to a hardware acceleration module;
[0045] S302, performing a computationally intensive task in a model predictive control task on the industrial control data through a hardware acceleration module, and sending the computational task result of the computationally intensive task to a main control module;
[0046] S303: Control the control device based on the calculation task result through the main control module.
[0047] It can be understood that the above industrial control method is applied to an industrial control system, which includes a main control module and a hardware acceleration module integrated into the industrial control system as an independent module. In some examples, the hardware acceleration module includes a field programmable gate array, the field programmable gate array includes a parallel computing unit and a communication interface, the communication interface is used to communicate data with the main control module, and the parallel computing unit is used to perform calculations based on received data.
[0048] It can be understood that the communication interface of the hardware acceleration module is a high-speed communication interface (such as Ethernet, PCIe, etc.), in which the main control module is responsible for the management and execution control of the MPC algorithm, while the FPGA is responsible for computationally intensive tasks. Through the high-speed communication interface (such as Ethernet, PCIe, etc.), the main control module passes the data to be calculated to the FPGA for processing, and the FPGA completes the calculation and returns the result to the main control module, ensuring that the industrial control system completes the task within the specified control cycle.
[0049] It can be understood that the industrial control system architecture provided by this application adopts a modular design, and the FPGA module is used as an external acceleration unit, which is convenient for configuration and upgrading according to different application requirements. The main control module is responsible for control strategy and system management, while the FPGA is responsible for computing-intensive task sharing, and the two realize data interaction through standard interfaces.
[0050] In some examples, a parallel computing accelerator (such as a multi-core CPU, GPU, or DSP) may also be used as a hardware acceleration module, which may be flexibly configured by relevant personnel according to needs.
[0051] In some examples, the system further includes a configuration module, which is used to generate model information, set value information, constraint information, optimization interval information, and cost function weight information according to the properties of the control device, and send the model information, set value information, constraint information, optimization interval information, and cost function weight information to the main control module;
[0052] In some examples, the main control module is also used to construct an augmented model based on model information and set value information, construct an augmented cost function weight matrix based on optimization interval information and cost function weight information, and construct a model predictive control task based on the augmented model, augmented cost function weight matrix and constraint information.
[0053] In some examples, the industrial control system also includes: an input / output expansion module, the input / output expansion module is linked to the main control module, the input / output expansion module is used to obtain sensor acquisition signals and transmit the sensor acquisition signals to the main control module.
[0054] In some examples, the parallel computing unit may use a first-order optimization algorithm to calculate the received data, and a storage unit is also provided on the field programmable gate array, and the storage unit uses a sparse matrix to store data.
[0055] According to the technical solution provided by the embodiment of the present application, the method provided by the present embodiment receives industrial control data through the main control module. If the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; the hardware acceleration module performs computationally intensive tasks in the model predictive control task on the industrial control data, and the computational task results of the computationally intensive tasks are sent to the main control module; the main control module controls the control device based on the computational task results. The present application realizes high-performance model predictive control on the industrial control system by adding a hardware acceleration module to the industrial control system, so that the industrial control system can cope with complex computing tasks and improve the real-time performance of the industrial control system. It avoids the problem that the computing resources of the programmable logic controller are limited, resulting in the inability to perform model predictive control.
[0056] Figure 4 Schematic diagram of an electronic device 4 provided in an embodiment of the present application. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 401 executes the computer program 403, the functions of the modules / units in the above-mentioned device embodiments are implemented.
[0057] The electronic device 4 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 4 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 The electronic device 4 is merely an example and does not limit the electronic device 4 , and may include more or less components than those shown in the figure, or different components.
[0058] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
[0059] The memory 402 may be an internal storage unit of the electronic device 4, for example, a hard disk or memory of the electronic device 4. The memory 402 may also be an external storage device of the electronic device 4, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. The memory 402 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device.
[0060] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
[0061] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of regional requirements and patent practice. For example, in some areas, according to regional requirements and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0062] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. An industrial control system, characterized in that: The system includes a main control module, and a hardware acceleration module integrated into the industrial control system as an independent module; The main control module is used to receive industrial control data, and if the industrial control data is used to perform a model predictive control task, the industrial control data is sent to the hardware acceleration module; The hardware acceleration module is used to perform a computationally intensive task in the model predictive control task based on the industrial control data, and send a computational task result of the computationally intensive task to the main control module; The main control module is used to control the control device based on the calculation task result.
2. The system according to claim 1, characterized in that The hardware acceleration module includes a parallel computing unit and a communication interface, wherein the communication interface is used for data communication with the main control module, and the parallel computing unit is used for performing calculations based on received data.
3. The system according to claim 1, characterized in that The system further comprises a configuration module, which is used to generate model information, set value information, constraint information, optimization interval information and cost function weight information according to the properties of the control device, and send the model information, set value information, constraint information, optimization interval information and cost function weight information to the main control module; The main control module is also used to construct an augmented model according to the model information and the set value information, construct an augmented cost function weight matrix according to the optimization interval information and the cost function weight information, and construct a model predictive control task based on the augmented model, the augmented cost function weight matrix and the constraint information.
4. The system according to claim 1, characterized in that The system further comprises: an input / output expansion module, the input / output expansion module is linked to the main control module, the input / output expansion module is used to obtain sensor acquisition signals and transmit the sensor acquisition signals to the main control module.
5. The system according to claim 4, characterized in that The input / output expansion module is also used to receive the control signal output by the main control module and transmit the control signal to the control device.
6. The system according to claim 2, characterized in that The hardware acceleration module is also provided with a storage unit, and the storage unit is used to store data.
7. An industrial control method, characterized in that: The method comprises: receiving industrial control data through a main control module, and if the industrial control data is used to perform a model predictive control task, sending the industrial control data to a hardware acceleration module; Performing a computationally intensive task in the model predictive control task on the industrial control data through a hardware acceleration module, and sending the computational task result of the computationally intensive task to the main control module; The control device is controlled by the main control module based on the calculation task result.
8. The method according to claim 7, characterized in that The hardware acceleration module includes a parallel computing unit and a communication interface, wherein the communication interface is used for data communication with the main control module, and the parallel computing unit is used for performing calculations based on received data.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 7 to 8 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 7 to 8 are implemented.