PLC control system performance evaluation method based on graph neural network and related device
By abstracting the PLC control system device components into graph nodes, constructing a performance evaluation model based on graph neural network, and optimizing the model weights with reducing energy consumption as the objective function, the limitations of traditional PLC control system performance evaluation methods are overcome, and more efficient system optimization and evaluation are achieved.
Patent Information
- Application Number
- CN202510574789.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-06
- Publication Date
- 2025-09-12
AI Technical Summary
Traditional PLC control system performance evaluation methods have limitations when dealing with complex nonlinear industrial systems and are difficult to adapt to multiple variables and multiple constraints, resulting in poor optimization results.
The device components in the PLC control system are abstracted as graph nodes, and the association relationships between device components are abstracted as graph edges. A performance evaluation model based on graph neural network (GCN) is constructed. By stacking multiple GCN layers with reducing energy consumption as the objective function, the stochastic gradient descent algorithm (SGD) is used to update the GNN model weights and optimize the performance evaluation model.
It improves the performance evaluation accuracy of PLC control systems, realizes effective evaluation and optimization of system stability, accuracy, real-time performance and reliability, and improves industrial automation performance.
Smart Images
Figure CN120630847A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of industrial automation technology, specifically to technical fields such as PLC control and performance evaluation optimization, and in particular to a PLC control system performance evaluation method and related devices based on graph neural network. Background Art
[0002] Programmable logic controller (PLC) control systems are widely used in manufacturing, process control, and automated production. They are primarily responsible for monitoring various industrial processes, and their performance directly impacts production line efficiency, product quality, and system stability. However, the increasing complexity of industrial systems places higher demands on the performance evaluation and optimization of PLC control systems.
[0003] Traditional PLC control system performance evaluation methods often rely on empirical formulas, statistical data, or simple model analysis, which are limited when dealing with complex, nonlinear industrial systems. Furthermore, traditional optimization algorithms often struggle to adapt to the multivariable and multi-constraint conditions found in PLC control systems, resulting in poor optimization results.
[0004] Therefore, it is urgent to find a new performance evaluation and optimization solution, which is of great significance to improving the performance of PLC control systems. Summary of the Invention
[0005] This application provides a PLC control system performance evaluation method and related devices based on graph neural networks to break through the limitations of traditional solutions, improve the accuracy and optimization effect of PLC control system performance evaluation, and thus enhance the overall performance and reliability of industrial automation systems.
[0006] The technical solution is as follows:
[0007] In the first aspect, a PLC control system performance evaluation method based on a graph neural network is provided, comprising:
[0008] Determine all devices and the relationships between devices in the PLC control system to be evaluated, wherein the devices include at least operating devices, sensors, and actuators, and the relationships are relationships that characterize signal transmission and / or control logic;
[0009] All the determined devices are used as graph nodes, and the association relationships between the devices are used as graph edges to construct the graph structure of the PLC control system;
[0010] Inputting the graph structure into a trained performance evaluation model, and iteratively updating graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model;
[0011] The output is the performance evaluation result predicted by the PLC control system; the performance evaluation result is used to reflect the stability, accuracy, real-time performance and reliability of the PLC control system.
[0012] In one possible implementation, the graph node features are iteratively updated by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model, specifically including:
[0013] Neighbor node information is aggregated through each layer of the graph convolutional neural network of the performance evaluation model, and the graph node features are updated based on the following formula:
[0014]
[0015] Among them, N i is the set of neighbor nodes of node i, C ij is the edge weight between node i and node j, W (l) is the weight matrix of the lth layer, and σ is the ReLU activation function.
[0016] In a possible implementation, the method further includes:
[0017] Determining a graph convolution layer of the performance evaluation model and defining an objective function; the objective function is used to represent the goal of reducing energy consumption of the PLC control system;
[0018] Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolutional layer.
[0019] In one possible implementation, determining the graph convolution layer of the performance evaluation model and defining the objective function specifically include:
[0020] The graph convolution layer of the performance evaluation model is determined by the following formula:
[0021]
[0022] Wherein, σ is the ReLU activation function, is the degree matrix, is the adjacency matrix, W (l) is the weight matrix of the lth layer;
[0023] The objective function is defined as:
[0024]
[0025] Among them, V executor is the set of graph nodes, E i is the energy consumption of node i in the PLC control system.
[0026] In one possible implementation, based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolutional layer, specifically including:
[0027] Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolution layer using the following formula:
[0028]
[0029] in, It means finding the gradient of W.
[0030] In a possible implementation, the method further includes:
[0031] Based on the performance evaluation model after optimizing and updating the weights, the graph structure constructed by the PLC control system to be evaluated is processed and the performance evaluation results are output.
[0032] In a second aspect, a PLC control system performance evaluation device based on a graph neural network is provided, comprising:
[0033] A determination module, configured to determine all devices in the PLC control system to be evaluated and the relationships between the devices, wherein the devices include at least operating devices, sensors, and actuators, and the relationships are relationships that characterize signal transmission and / or control logic;
[0034] A construction module is used to construct a graph structure of the PLC control system by taking all determined devices as graph nodes and the association relationships between the devices as graph edges;
[0035] An evaluation module, configured to input the graph structure into a trained performance evaluation model and iteratively update graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model;
[0036] The output module is used to output the performance evaluation results predicted for the PLC control system; the performance evaluation results are used to reflect the stability, accuracy, real-time performance and reliability of the PLC control system.
[0037] According to a third aspect, an electronic device is provided, including:
[0038] at least one processor; and
[0039] a memory communicatively connected to the at least one processor; wherein,
[0040] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any possible implementation manner and the aspects described above.
[0041] In a fourth aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method of the above-mentioned aspect and any possible implementation manner.
[0042] In a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the above-mentioned aspects and any possible implementation method.
[0043] The beneficial effects of the technical solution provided by this application include at least:
[0044] As can be seen from the above technical solution, the embodiment of this application abstracts the device components in the PLC control system as graph nodes, and the relationships between device components as graph edges, to construct a GCN-based performance evaluation model. This performance evaluation model can effectively handle complex network structures and data, accurately evaluating key performance indicators such as system stability, accuracy, real-time performance, and reliability. At the same time, with energy reduction as the objective function, by stacking multiple GCN layers and using the SGD algorithm to update the GNN model weights, the performance evaluation model is optimized. This application improves evaluation accuracy, achieves effective system optimization, and enhances automation performance in the industrial field.
[0045] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.
[0047] Figure 1 This is a schematic diagram of the steps of a PLC control system performance evaluation method based on graph neural network proposed in an embodiment of the present application.
[0048] Figure 2a This embodiment of the present application provides Figure 1 Schematic diagram of one of the steps in optimizing the performance evaluation model shown.
[0049] Figure 2b This is the second schematic diagram of the steps for optimizing the performance evaluation model provided in the embodiment of the present application.
[0050] Figure 3 This is a schematic diagram comparing system output fluctuations after optimization based on PID and GNN optimization algorithms, respectively, provided in an embodiment of the present application.
[0051] Figure 4 This is a structural block diagram of a PLC control system performance evaluation device based on graph neural network provided in another embodiment of the present application.
[0052] Figure 5 This is a block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0053] The following description of exemplary embodiments of the present application is provided in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.
[0054] Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0055] It should be noted that the terminal devices involved in the embodiments of the present application may include but are not limited to mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers and other smart devices; display devices may include but are not limited to personal computers, televisions and other devices with display functions.
[0056] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.
[0057] Given the limitations of traditional PLC control system performance evaluation methods and their difficulty adapting to the multi-variable and multi-constraint conditions in PLC control systems, this application proposes a new performance evaluation and optimization solution. Its main inventive concept is to abstract the device components in the PLC control system into graph nodes, and the relationships between device components into graph edges, and construct a performance evaluation model based on GCN. This performance evaluation model can effectively handle complex network structures and data, and accurately evaluate key performance indicators such as system stability, accuracy, real-time performance, and reliability. At the same time, with energy reduction as the objective function, by stacking multiple GCN layers and using the SGD algorithm to update the GNN model weights, the performance evaluation model is optimized. This application improves evaluation accuracy, achieves effective system optimization, and enhances automation performance in the industrial field.
[0058] Before this, it is necessary to build an initial model for the PLC control system based on GNN and GCN. First, the device components in the PLC control system (for example, sensors and actuators, etc.) are used as graph nodes, and the association relationships between these device components are used as graph edges to construct a graph structure. Each node in the graph structure has initial features based on the device type, status, and control parameters. Then, these graph structure data are processed by GCN. Each layer of GCN iteratively updates the node features by aggregating neighbor information, enabling the nodes to learn more advanced abstract features. Finally, the output layer designs the corresponding output nodes based on the preset performance evaluation indicators - stability, accuracy, real-time and reliability, which directly reflect the evaluation results of the system in these key performance aspects.
[0059] Reference Figure 1 FIG2 is a schematic diagram of the steps of a PLC control system performance evaluation method based on a graph neural network proposed in an embodiment of the present application. The performance evaluation method may include the following steps:
[0060] Step 102: Determine all devices in the PLC control system to be evaluated and the relationships between the devices, wherein the devices at least include component devices, sensors, and actuators, and the relationships are relationships that characterize signal transmission and / or control logic.
[0061] Step 104: Build a graph structure of the PLC control system by using all the determined devices as graph nodes and the association relationships between the devices as graph edges.
[0062] Step 106: Input the graph structure into a trained performance evaluation model, and iteratively update the graph node features by aggregating neighbor node information through each layer of the graph convolutional neural network of the performance evaluation model.
[0063] Optionally, neighbor node information is aggregated through each layer of the graph convolutional neural network of the performance evaluation model, and graph node features are updated based on the following formula:
[0064]
[0065] Among them, N i is the set of neighbor nodes of node i, C ij is the edge weight between node i and node j, W (l) is the weight matrix of the lth layer, and σ is the ReLU activation function.
[0066] Step 108: Outputting a performance evaluation result predicted for the PLC control system; the performance evaluation result is used to reflect the stability, accuracy, real-time performance, and reliability of the PLC control system.
[0067] Among them, stability can be reflected through characteristics such as failure rate and recovery time, which are used to reflect the system's ability to maintain normal working conditions when facing external interference and / or internal changes; accuracy can be reflected through characteristics such as control error and control accuracy, which are used to reflect the accuracy of the system's control output; real-time performance can be reflected through characteristics such as response time and delay, which are used to reflect the system's response speed to input signals; reliability can be reflected through characteristics such as mean time between failures and time between failures, which are used to reflect the system's ability to operate stably in the long term.
[0068] For example, operating data from a PLC control system under different operating conditions, including performance indicators such as device status, sensor measurements, actuator outputs, fault conditions, recovery time, control error, and response time, is collected as benchmark data for model training and validation. Based on this data, a GNN-based performance evaluation model is constructed and trained. This model treats system components as graph nodes and inter-component connections as graph edges. A GCN is used to iteratively update node features to learn higher-level abstract representations. At the model output layer, corresponding output nodes are designed for four key performance aspects: stability, accuracy, real-time, and reliability, reflecting the system performance evaluation results.
[0069] Table 1 compares the performance evaluation results of the PLC control system under different operating conditions. Operating conditions 1 and 2 exhibit high stability, while operating condition 5 exhibits low stability. In terms of control accuracy, the error for all operating conditions remains at approximately 2%, indicating good control accuracy. However, the error for operating condition 3 is relatively large, indicating room for improvement. In terms of real-time performance, operating condition 2 has the fastest response time, while operating condition 3 has the slowest, suggesting that the latter may require real-time optimization. In terms of reliability, operating condition 2 exhibits the longest mean time between failures and the highest reliability; conversely, operating condition 3 exhibits the lowest performance, indicating a need for enhanced maintenance. The GNN-based PLC control system performance evaluation model effectively assesses system stability, accuracy, real-time performance, and reliability. The model evaluation results closely match the actual system conditions, demonstrating the model's accuracy and effectiveness. This model can provide strong support for the optimization, adjustment, and maintenance of PLC control systems, helping to improve overall system performance and reliability.
[0070] Working conditions stability Accuracy Real-time reliability 1 0.872 1.95 118.7 103.5 2 0.891 2.05 109.3 147.6 3 0.845 2.20 130.5 90.8 4 0.860 1.80 120.1 112.3 5 0.820 2.15 125.4 98.7
[0071] Table 1
[0072] Reference Figure 2a As shown, the embodiment of the present application provides Figure 1 The schematic diagram of the steps for optimizing the performance evaluation model shown in FIG. Specifically, the following steps may be included:
[0073] Step 202: Determine the graph convolution layer of the performance evaluation model and define an objective function; the objective function is used to represent the goal of reducing the energy consumption of the PLC control system.
[0074] Optionally, the graph convolution layer of the performance evaluation model is determined by the following formula:
[0075]
[0076] Wherein, σ is the ReLU activation function, is the degree matrix, is the adjacency matrix, W (l) is the weight matrix of the lth layer;
[0077] The objective function is defined as:
[0078]
[0079] Among them, V executor is the set of graph nodes, E i is the energy consumption of node i in the PLC control system.
[0080] Step 204: Based on the defined objective function, the weights of each graph convolution layer are optimized and updated using the stochastic gradient descent algorithm.
[0081] Optionally, based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolutional layer, specifically including:
[0082] Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolution layer using the following formula:
[0083]
[0084] in, It means finding the gradient of W.
[0085] Furthermore, after optimizing and updating the weights of each graph convolution layer using the stochastic gradient descent algorithm based on the defined objective function, refer to Figure 2b As shown, it may also include:
[0086] Step 206: Based on the performance evaluation model after optimizing and updating the weights, the graph structure constructed by the PLC control system to be evaluated is processed, and a performance evaluation result is output.
[0087] For example, a simulated dataset containing 10,000 records covering various operating conditions and system states, including sensor readings, controller states, actuator actions, and energy consumption records, was used. Traditional PID control was selected as the baseline algorithm for comparison. The raw data was cleaned and normalized, and a graph-structured data set was constructed. 70% of the data was used as the training set to train the GNN model and adjust hyperparameters for optimal performance. 15% of the data was used as the validation set to evaluate the model's generalization capabilities. The remaining 15% of the data was used as the test set.
[0088] Table 2 shows that the GNN algorithm outperforms the PID algorithm in reducing energy consumption, achieving an 18.3% reduction. This demonstrates that the GNN algorithm can more effectively optimize control systems and improve energy efficiency. In terms of computational time, the GNN algorithm takes 15.2 milliseconds, slightly longer than the PID algorithm's 12.5 milliseconds, but still meets real-time control requirements. This demonstrates that the GNN algorithm can significantly reduce energy consumption while maintaining real-time performance.
[0089] Optimization Type Energy consumption reduction rate time consuming PID optimization algorithm 0 12.5 GNN optimization algorithm 18.3 15.2
[0090] Table 2
[0091] The GNN optimization algorithm performs well in terms of system stability, and the fluctuation range of the system output is significantly smaller than that of the baseline algorithm. Figure 3As can be seen, the GNN optimization algorithm's system output value fluctuates relatively narrowly. Its output value ranges roughly between 1.1 and 1.4, indicating overall stability and a narrow fluctuation range. However, the PID control algorithm's output value fluctuates more widely, roughly between 1.8 and 2.3. This indicates that, under the same time metrics, the GNN optimization algorithm performs better in terms of system stability, with significantly less output fluctuation than the PID control algorithm.
[0092] Experimental results show that the algorithm can significantly reduce system energy consumption, improve control stability, and meet real-time requirements. By optimizing the model structure, training algorithm, and real-time performance, the algorithm's performance and application scope can be further improved.
[0093] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.
[0094] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0095] Figure 4 FIG1 shows a structural block diagram of a PLC control system performance evaluation device based on a graph neural network provided by an embodiment of the present application, as shown in FIG1 Figure 4 As shown. The PLC control system performance evaluation device 400 based on graph neural network of this embodiment may include a determination module 401, a construction module 402, an evaluation module 403 and an output module 404. Among them, the determination module 401 is used to determine all devices in the PLC control system to be evaluated and the association relationship between the devices, wherein the devices at least include operating devices, sensors and actuators, and the association relationship is a relationship that characterizes signal transmission and / or control logic; the construction module 402 is used to construct the graph structure of the PLC control system by taking all the determined devices as graph nodes and the association relationship between the devices as graph edges; the evaluation module 403 is used to input the graph structure into a trained performance evaluation model, and iteratively update the graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model; the output module 404 is used to output the performance evaluation result predicted for the PLC control system; the performance evaluation result is used to reflect the stability, accuracy, real-time performance and reliability of the PLC control system.
[0096] It should be noted that part or all of the graph neural network-based PLC control system performance evaluation device of this embodiment can be an application located in the local terminal, or it can also be a functional unit such as a plug-in or software development kit (SDK) set in the application located in the local terminal, or it can also be a processing engine located in the network side server, or it can also be a distributed system located on the network side.
[0097] It is understandable that the application may be a native program (nativeApp) installed on the local terminal, or may be a webpage program (webApp) of a browser on the local terminal, which is not limited in this embodiment.
[0098] Optionally, in a possible implementation of this embodiment, when the evaluation module 403 iteratively updates the graph node features by aggregating neighbor node information through each layer of the graph convolutional neural network of the performance evaluation model, it is specifically configured to update the graph node features based on the following formula by aggregating neighbor node information through each layer of the graph convolutional neural network of the performance evaluation model:
[0099]
[0100] Among them, N i is the set of neighbor nodes of node i, C ij is the edge weight between node i and node j, W (l) is the weight matrix of the lth layer, and σ is the ReLU activation function.
[0101] Optionally, in a possible implementation of this embodiment, the evaluation device further includes:
[0102] A definition module is used to determine the graph convolution layer of the performance evaluation model and define an objective function; the objective function is used to represent the goal of reducing the energy consumption of the PLC control system;
[0103] The optimization module is used to optimize and update the weights of each graph convolution layer using the stochastic gradient descent algorithm based on the defined objective function.
[0104] Optionally, in a possible implementation of this embodiment, when determining the graph convolution layer of the performance evaluation model and defining the objective function, the definition module is specifically configured to determine the graph convolution layer of the performance evaluation model using the following formula:
[0105]
[0106] Wherein, σ is the ReLU activation function, is the degree matrix, is the adjacency matrix, W(l) is the weight matrix of the lth layer;
[0107] The objective function is defined as:
[0108]
[0109] Among them, V executor is the set of graph nodes, E i is the energy consumption of node i in the PLC control system.
[0110] Optionally, in a possible implementation of this embodiment, when the optimization module optimizes and updates the weight of each graph convolution layer using the stochastic gradient descent algorithm based on the defined objective function, the optimization module is specifically configured to optimize and update the weight of each graph convolution layer using the stochastic gradient descent algorithm based on the defined objective function using the following formula:
[0111]
[0112] in, It means finding the gradient of W.
[0113] Optionally, in a possible implementation of this embodiment, the evaluation module is further configured to process the graph structure constructed by the PLC control system to be evaluated based on the performance evaluation model after optimizing and updating the weights, and output a performance evaluation result.
[0114] In this embodiment, the device components in the PLC control system can be abstracted as graph nodes, and the relationships between device components can be abstracted as graph edges to construct a GCN-based performance evaluation model. This performance evaluation model can effectively handle complex network structures and data, accurately evaluating key performance indicators such as system stability, accuracy, real-time performance, and reliability. At the same time, with energy reduction as the objective function, the performance evaluation model is optimized by stacking multiple GCN layers and using the SGD algorithm to update the GNN model weights. This application improves evaluation accuracy, achieves effective system optimization, and enhances industrial automation performance.
[0115] One embodiment of the present application provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method for evaluating the performance of a PLC control system based on a graph neural network as described above.
[0116] An embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method for evaluating the performance of a PLC control system based on a graph neural network as described above.
[0117] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0118] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.
[0119] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.
[0120] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0121] The computing unit 501 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the method for evaluating the performance of a PLC control system based on a graph neural network. For example, in some embodiments, the method for evaluating the performance of a PLC control system based on a graph neural network can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method for evaluating the performance of a PLC control system based on a graph neural network described above can be performed. Alternatively, in other embodiments, the computing unit 501 may be configured in any other appropriate manner (e.g., by means of firmware) to execute the method for evaluating the performance of a PLC control system based on a graph neural network.
[0122] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, at least one input device, and at least one output device.
[0123] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0124] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, 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 foregoing.
[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0126] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.
[0127] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.
[0128] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.
[0129] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the scope of protection of this application.
Claims
1. A PLC control system performance evaluation method based on graph neural network, characterized in that: include: Determine all devices and the relationships between devices in the PLC control system to be evaluated, wherein the devices include at least operating devices, sensors, and actuators, and the relationships are relationships that characterize signal transmission and / or control logic; All the determined devices are used as graph nodes, and the association relationships between the devices are used as graph edges to construct the graph structure of the PLC control system; Inputting the graph structure into a trained performance evaluation model, and iteratively updating graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model; The output is the performance evaluation result predicted by the PLC control system; the performance evaluation result is used to reflect the stability, accuracy, real-time performance and reliability of the PLC control system.
2. The method according to claim 1, wherein Iteratively updating graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model specifically includes: Neighbor node information is aggregated through each layer of the graph convolutional neural network of the performance evaluation model, and the graph node features are updated based on the following formula: Among them, N i is the set of neighbor nodes of node i, C ij is the edge weight between node i and node j, W (l) is the weight matrix of the lth layer, and σ is the ReLU activation function.
3. The method according to claim 1 or 2, wherein: The method further comprises: Determining a graph convolution layer of the performance evaluation model and defining an objective function; the objective function is used to represent the goal of reducing energy consumption of the PLC control system; Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolutional layer.
4. The method according to claim 3, wherein Determine the graph convolution layer of the performance evaluation model and define the objective function, specifically including: The graph convolution layer of the performance evaluation model is determined by the following formula: Wherein, σ is the ReLU activation function, is the degree matrix, is the adjacency matrix, W ( l ) is the weight matrix of the lth layer; The objective function is defined as: Among them, V executor is the set of graph nodes, E i is the energy consumption of node i in the PLC control system.
5. The method according to claim 3, wherein Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolution layer, including: Based on the defined objective function, the stochastic gradient descent algorithm is used to optimize and update the weights of each graph convolution layer using the following formula: in, It means finding the gradient of W.
6. The method according to any one of claims 3 to 5, characterized in that The method further comprises: Based on the performance evaluation model after optimizing and updating the weights, the graph structure constructed by the PLC control system to be evaluated is processed and the performance evaluation results are output.
7. A PLC control system performance evaluation device based on graph neural network, characterized in that: include: A determination module, configured to determine all devices in the PLC control system to be evaluated and the relationships between the devices, wherein the devices include at least operating devices, sensors, and actuators, and the relationships are relationships that characterize signal transmission and / or control logic; A construction module is used to construct a graph structure of the PLC control system by taking all determined devices as graph nodes and the association relationships between the devices as graph edges; An evaluation module, configured to input the graph structure into a trained performance evaluation model and iteratively update graph node features by aggregating neighbor node information at each layer of the graph convolutional neural network of the performance evaluation model; The output module is used to output the performance evaluation results predicted for the PLC control system; the performance evaluation results are used to reflect the stability, accuracy, real-time performance and reliability of the PLC control system.
8. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.