Industrial control system data feature extraction method and system, fault diagnosis method and system, and related device and storage medium
By improving the sparse autoencoder and particle swarm optimization algorithm to optimize the weight of the sparse penalty term, and combining data correction and normalization processing, the problem of relying on human experience and low accuracy of data feature extraction in fault diagnosis of industrial control systems is solved, and high-precision fault diagnosis is achieved.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- XIAN THERMAL POWER RES INST CO LTD
- Filing Date
- 2025-05-30
- Publication Date
- 2026-07-23
Smart Images
Figure CN2025098320_23072026_PF_FP_ABST
Abstract
Description
Methods and systems for extracting data features from industrial control systems, methods and systems for fault diagnosis, and related equipment and storage media.
[0001] Cross-reference of related applications
[0002] This application claims priority to Chinese Patent Application No. 202510077584.0, filed on January 17, 2025, entitled “Industrial Control System Data Feature Extraction Method, Fault Diagnosis Method and Related Device”, the entire contents of which are incorporated herein by reference. Technical Field
[0003] This application belongs to the field of industrial control systems, and relates to a method and system for extracting data features of industrial control systems, a method and system for fault diagnosis, and related equipment and storage media. Background Technology
[0004] The method for detecting abnormal operating conditions in industrial control systems mainly relies on the experience of maintenance personnel. By setting thresholds for key operating and detection parameters, an alarm signal is triggered once the parameter changes exceed the threshold range. Maintenance personnel then investigate the cause of the fault based on the alarm information.
[0005] However, this method suffers from limitations in diagnostic speed and accuracy due to the professional knowledge of maintenance personnel. Especially when a large number of alarm signals occur simultaneously, relying on manpower makes it impossible to quickly diagnose the cause of the fault from a massive amount of alarm information in a short time, which may lead to more serious accident consequences.
[0006] To address this, data-driven intelligent fault diagnosis methods do not rely on knowledge or experience and can start from operational data characteristics, offering advantages such as fast diagnosis speed and high accuracy. However, the effectiveness of intelligent fault diagnosis methods is closely related to the accuracy of the extracted data features. Existing data feature extraction methods often suffer from low accuracy when extracting features from high-dimensional, massive datasets, which in turn leads to low fault diagnosis accuracy in intelligent fault diagnosis methods. Summary of the Invention
[0007] The purpose of this application is to overcome the shortcomings of the prior art and provide a method and system for extracting data features from an industrial control system, a method and system for fault diagnosis, and related equipment and storage media.
[0008] To achieve the above objectives, this application adopts the following technical solution:
[0009] In a first aspect, this application provides a method for extracting features from industrial control system data, comprising: acquiring industrial control system operating data; inputting the industrial control system operating data into a preset improved sparse autoencoder to obtain feature data of the industrial control system operating data; wherein the improved sparse autoencoder is obtained by replacing the process of determining the weight of the sparse penalty term in the loss function of the sparse autoencoder with optimization using a particle swarm optimization algorithm.
[0010] Optionally, before inputting the industrial control system operation data into the preset improved sparse autoencoder, the method further includes: performing data correction processing and normalization processing on the industrial control system operation data.
[0011] Optionally, the normalization process specifically involves using the Z-Score method for normalization.
[0012] Optionally, the step of inputting the industrial control system operation data into a preset improved sparse autoencoder to obtain the feature data of the industrial control system operation data includes: S11: inputting the industrial control system operation data into a preset improved sparse autoencoder to obtain the loss function value of the improved sparse autoencoder; S12: when the loss function value of the improved sparse autoencoder is greater than a preset loss function setting value, adjusting the weights and bias coefficients of the improved sparse autoencoder and returning to S11; S13: when the loss function value of the improved sparse autoencoder is not greater than the preset loss function setting value, recording the output of the hidden layer of the improved sparse autoencoder; and using a particle swarm optimization algorithm to optimize the weights of the sparse penalty term in the loss function of the improved sparse autoencoder; S14: iterating from S11 to S13 to a preset number of iterations, selecting the output of the hidden layer of the improved sparse autoencoder with the smallest loss function value among all recorded outputs of the hidden layers of the improved sparse autoencoder, as the feature data of the industrial control system operation data.
[0013] Optionally, it also includes: dividing the industrial control system operation data and the characteristic data of the industrial control system operation data into normal operation data and abnormal operation data and storing them in partitions; wherein, the normal operation data is divided into normal steady-state operation data and normal transient operation data and stored in partitions; and the abnormal operation data is classified according to the fault type label and stored in partitions.
[0014] In a second aspect, this application provides a method for diagnosing faults in an industrial control system, comprising: using the aforementioned method for extracting features of industrial control system data to obtain feature data of the operating data of the industrial control system to be diagnosed; inputting the feature data of the operating data of the industrial control system to be diagnosed into a pre-trained industrial control system fault diagnosis model to obtain a fault diagnosis result of the industrial control system.
[0015] A third aspect of this application provides a data feature extraction system for an industrial control system, comprising: a data acquisition module for acquiring industrial control system operation data; and a feature extraction module for inputting the industrial control system operation data into a preset improved sparse autoencoder to obtain feature data of the industrial control system operation data; wherein the improved sparse autoencoder is obtained by replacing the process of determining the weight of the sparse penalty term in the loss function of the sparse autoencoder with optimization using a particle swarm optimization algorithm.
[0016] In a fourth aspect, this application provides an industrial control system fault diagnosis system, comprising: the aforementioned industrial control system data feature extraction system, used to acquire feature data of the operating data of the industrial control system to be diagnosed; and a fault diagnosis module, used to input the feature data of the operating data of the industrial control system to be diagnosed into a pre-trained industrial control system fault diagnosis model to obtain the industrial control system fault diagnosis result.
[0017] In a fifth aspect, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described industrial control system data feature extraction method or the steps of the above-described industrial control system fault diagnosis method.
[0018] In a sixth aspect, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described industrial control system data feature extraction method or the steps of the above-described industrial control system fault diagnosis method.
[0019] Compared with the prior art, this application has the following beneficial effects:
[0020] This application presents a method for extracting features from industrial control system (ICS) data. After acquiring the ICS operating data, the method inputs it into a pre-defined improved sparse autoencoder to obtain feature data of the ICS operating data, thus achieving feature extraction based on the improved sparse autoencoder. The improved sparse autoencoder replaces the process of determining the weights of the sparsity penalty term in the loss function of the sparse autoencoder with optimization using a particle swarm optimization algorithm. Compared to the current manual method of determining the sparsity penalty term weights, using particle swarm optimization can further optimize the weights. The selection of the sparsity penalty term weights directly affects the feature extraction effect. Therefore, optimizing the sparsity penalty term weights can effectively improve the high-precision and efficient extraction of ICS data features for use by intelligent algorithms such as fault diagnosis and pattern recognition, thereby improving the fault diagnosis accuracy of intelligent fault diagnosis methods. Attached Figure Description
[0021] Figure 1 is a flowchart of the data feature extraction method for industrial control systems according to an embodiment of this application.
[0022] Figure 2 is a detailed flowchart of data feature extraction from an industrial control system according to an embodiment of this application.
[0023] Figure 3 is a flowchart of the industrial control system fault diagnosis method according to an embodiment of this application.
[0024] Figure 4 is a block diagram of the data feature extraction system of the industrial control system according to an embodiment of this application.
[0025] Figure 5 is a block diagram of the fault diagnosis structure of the industrial control system according to an embodiment of this application. Detailed Implementation
[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0028] The present application will now be described in further detail with reference to the accompanying drawings:
[0029] Referring to Figure 1, in one embodiment of this application, a method for extracting data features from an industrial control system is provided. Specifically, it is a method for extracting data features from an industrial control system based on an improved sparse autoencoder. Existing data feature extraction methods often have low accuracy when extracting features from high-dimensional, massive data, which in turn leads to low fault diagnosis accuracy in intelligent fault diagnosis methods. By extracting high-precision feature data from the operating data of the industrial control system, the fault diagnosis accuracy of intelligent fault diagnosis methods can be improved.
[0030] Specifically, the method for extracting data features from an industrial control system includes the following steps:
[0031] S1: Obtain the operating data of the industrial control system.
[0032] S2: Input the industrial control system operation data into the preset improved sparse autoencoder to obtain the feature data of the industrial control system operation data.
[0033] The improved sparse autoencoder replaces the process of determining the weight of the sparse penalty term in the loss function of the sparse autoencoder with the optimization algorithm to obtain the weight.
[0034] This application presents a method for extracting features from industrial control system (ICS) data. After acquiring the ICS operating data, the method inputs it into a pre-defined improved sparse autoencoder to obtain feature data of the ICS operating data, thus achieving feature extraction based on the improved sparse autoencoder. The improved sparse autoencoder replaces the process of determining the weights of the sparsity penalty term in the loss function of the sparse autoencoder with optimization using a particle swarm optimization algorithm. Compared to the current manual method of determining the sparsity penalty term weights, using particle swarm optimization can further optimize the weights. The selection of the sparsity penalty term weights directly affects the feature extraction effect. Therefore, optimizing the sparsity penalty term weights can effectively improve the high-precision and efficient extraction of ICS data features for use by intelligent algorithms such as fault diagnosis and pattern recognition, thereby improving the fault diagnosis accuracy of intelligent fault diagnosis methods.
[0035] In one possible implementation, before inputting the industrial control system operation data into a preset improved sparse autoencoder, the process further includes data correction and normalization of the industrial control system operation data.
[0036] Specifically, data acquisition for industrial control system operation can utilize I / O cards to collect parameters such as digital signals, analog signals, and pulse signals. The acquired data is then filtered, with only the most relevant operational data stored. This data can be transmitted via a local area network to a historical database on the centralized control platform for storage.
[0037] Data correction processing includes filling, deleting, and correcting data that is missing, redundant, or erroneous.
[0038] Normalization can be performed using the Z-Score method. Also known as standard deviation standardization, the Z-Score method is a common data preprocessing technique that transforms raw data into a distribution with a mean of 0 and a standard deviation of 1. This eliminates the influence of different dimensions on the data, making it more suitable for subsequent data analysis and modeling. In this way, the raw data is transformed into Z-Score form, i.e., a distribution with a mean of 0 and a standard deviation of 1. This processing method preserves the distribution information of the original data while reducing the numerical differences between different features, facilitating comparison and analysis. The advantages of the Z-Score method are its simplicity and clear mathematical meaning. Normalization using the Z-Score method eliminates the influence of different dimensions on the data, making it easier to process and understand. It can also improve the performance of certain machine learning algorithms, such as logistic regression and support vector machines.
[0039] In one possible implementation, the step of inputting the industrial control system operating data into a preset improved sparse autoencoder to obtain the characteristic data of the industrial control system operating data includes:
[0040] S11: Input the industrial control system operation data into the preset improved sparse autoencoder to obtain the loss function value of the improved sparse autoencoder.
[0041] S12: When the loss function value of the improved sparse autoencoder is greater than the preset loss function setting value, adjust the weights and bias coefficients of the improved sparse autoencoder and return to S11.
[0042] S13: When the loss function value of the improved sparse autoencoder is not greater than the preset loss function setting value, record the output of the hidden layer of the improved sparse autoencoder; and use the particle swarm optimization algorithm to optimize the weight of the sparse penalty term in the loss function of the improved sparse autoencoder.
[0043] S14: Iterate through S11 to S13 until the preset number of iterations, and select the output of the hidden layer of the improved sparse autoencoder with the smallest loss function value from all recorded outputs of the improved sparse autoencoder as the feature data of the industrial control system operation data.
[0044] Specifically, the improved sparse autoencoder has been further optimized and improved compared to the traditional sparse autoencoder. It uses the particle swarm optimization algorithm to perform self-optimization operations on some parameters in the sparse autoencoder.
[0045] The implementation process of a sparse autoencoder can be divided into the following two parts:
[0046] Encoding process: h1 = σ e (W1x+b1)
[0047] Decoding process: y = σ d (W2h1+b2)
[0048] Where W1 and b1 are the encoding weights and biases; W2 and b2 are the decoding weights and biases; σ e and σ d For nonlinear transformation, x is the input data, h1 is the output data of the hidden layer, and y is the reconstructed data.
[0049] The loss function of a traditional autoencoder is: the objective function that minimizes the error between y and x, expressed in terms of mean square error, which can be represented as J(W,b):
[0050] Where L(x,y) is the mean square error of x and y.
[0051] To achieve the suppression effect, the sparse autoencoder constrains the average activation value of the hidden layer neurons' outputs, using KL divergence to force it to approximate a given sparse value, and adds this as a penalty term to the loss function. Therefore, the loss function of the sparse autoencoder can be expressed as J SAE (W):
[0052] Where β is the weight of the sparsity penalty term. For sparse penalty terms, for The KL divergence, where h is the number of hidden layer neurons and ρ is the activation value of the input data. is the average activation value of the input data in hidden layer neuron j.
[0053] Using β as a variable, a further improvement to the loss function optimization of sparse autoencoders based on particle swarm optimization is: minJ SAE (W) = pso(β)
[0054] Where pso is the particle swarm optimization algorithm function.
[0055] Referring to Figure 2, the process of feature extraction from industrial control system operating data using an improved sparse autoencoder is as follows:
[0056] The operating data of the industrial control system is used as input parameters to initialize the parameters of the improved sparse autoencoder. An activation function is then used to map input layer nodes to hidden layer nodes for encoding. Subsequently, an activation function is used to map the hidden layer nodes to the output layer nodes to achieve the decoding process.
[0057] Using the reconstruction results of the output layer nodes and the input parameters as input, the loss function value Loss of the improved sparse autoencoder is calculated. If the Loss value is less than the loss function set value SetValue, the calculation result meets the requirements, and the data of the hidden layer nodes is output as the feature data of the industrial control system operation data. Otherwise, the weights and biases of the improved sparse encoder are adjusted and iterative calculation is performed. The weights and biases here include both encoding and decoding parts until the loss function value calculation result meets the requirements.
[0058] Since the sparse penalty term weight β in the sparse autoencoder needs to be set manually, the choice of the sparse penalty term weight β will directly affect the feature extraction effect.
[0059] Therefore, this application further improves the sparse autoencoder based on the particle swarm optimization algorithm, sets a maximum number of iterations MaxValue, and when the number of iterations t is not less than MaxValue, the particle swarm optimization algorithm is used to further optimize the weight β of the sparse penalty term until the number of iterations t reaches the requirement that it is greater than MaxValue. Then, the output of the hidden layer of the improved sparse autoencoder with the smallest loss value among all iteration results is output as the feature data of the industrial control system operation data.
[0060] In one possible implementation, the industrial control system data feature extraction method further includes:
[0061] The industrial control system operation data and its characteristic data are divided into normal operation data and abnormal operation data and stored in separate partitions. Among them, the normal operation data is further divided into normal steady-state operation data and normal transient operation data and stored in separate partitions; the abnormal operation data is classified according to the fault type label and stored in separate partitions.
[0062] Specifically, the data storage process follows the principle of separating operating conditions. Steady-state operating data and transient operating data under normal operating conditions are stored according to their respective operating conditions. For operating data under abnormal operating conditions, they are stored separately according to the fault type of the abnormal operating condition.
[0063] The characteristic data of the industrial control system operation data are also stored in the same storage settings to facilitate data retrieval according to different operating conditions and to adapt to intelligent algorithms such as fault diagnosis and pattern recognition.
[0064] Referring to Figure 3, in another embodiment of this application, a fault diagnosis method for an industrial control system is provided, which achieves high-precision fault diagnosis based on the feature data extracted by the above-mentioned industrial control system data feature extraction method.
[0065] Specifically, the industrial control system fault diagnosis method includes the following steps:
[0066] S20: Using the above-mentioned industrial control system data feature extraction method, the feature data of the industrial control system operation data to be diagnosed is obtained.
[0067] S21: Input the feature data of the operating data of the industrial control system to be diagnosed into the pre-trained industrial control system fault diagnosis model to obtain the fault diagnosis result of the industrial control system.
[0068] Specifically, fault diagnosis models for industrial control systems can be built using neural network models, such as backpropagation (BP) neural networks, convolutional neural networks, and recurrent neural networks, to map the feature data of the industrial control system's operating data to the fault types of the industrial control system. Pre-training of the industrial control system fault diagnosis model involves using labeled feature data from historical industrial control system data and corresponding fault type labels as training data.
[0069] The following are device embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the device embodiments, please refer to the method embodiments of this application.
[0070] Referring to Figure 4, in another embodiment of this application, an industrial control system data feature extraction system is provided, which can be used to implement the above-mentioned industrial control system data feature extraction method. Specifically, the industrial control system data feature extraction system includes a data acquisition module and a feature extraction module.
[0071] The data acquisition module is used to acquire the operating data of the industrial control system; the feature extraction module is used to input the operating data of the industrial control system into a preset improved sparse autoencoder to obtain the feature data of the operating data of the industrial control system; the improved sparse autoencoder is obtained by replacing the process of determining the weight of the sparse penalty term in the loss function of the sparse autoencoder with the optimization algorithm of particle swarm optimization.
[0072] In one possible implementation, before inputting the industrial control system operation data into a preset improved sparse autoencoder, the method further includes: performing data correction and normalization processing on the industrial control system operation data.
[0073] In one possible implementation, the normalization process specifically involves using the Z-Score method for normalization.
[0074] In one possible implementation, the step of inputting the industrial control system operating data into a preset improved sparse autoencoder to obtain the characteristic data of the industrial control system operating data includes:
[0075] S11: Input the industrial control system operation data into the preset improved sparse autoencoder to obtain the loss function value of the improved sparse autoencoder.
[0076] S12: When the loss function value of the improved sparse autoencoder is greater than the preset loss function setting value, adjust the weights and bias coefficients of the improved sparse autoencoder and return to S11.
[0077] S13: When the loss function value of the improved sparse autoencoder is not greater than the preset loss function setting value, record the output of the hidden layer of the improved sparse autoencoder; and use the particle swarm optimization algorithm to optimize the weight of the sparse penalty term in the loss function of the improved sparse autoencoder.
[0078] S14: Iterate through S11 to S13 until the preset number of iterations, and select the output of the hidden layer of the improved sparse autoencoder with the smallest loss function value from all recorded outputs of the improved sparse autoencoder as the feature data of the industrial control system operation data.
[0079] In one possible implementation, a storage module is also included, which is used to divide the industrial control system operation data and the characteristic data of the industrial control system operation data into normal operation data and abnormal operation data and store them in partitions; wherein, the normal operation data is divided into normal steady-state operation data and normal transient operation data and stored in partitions; the abnormal operation data is classified according to the fault type label and stored in partitions.
[0080] All relevant content of each step involved in the aforementioned embodiments of the industrial control system data feature extraction method can be referenced to the functional description of the corresponding functional module of the industrial control system data feature extraction system in the embodiments of this application, and will not be repeated here.
[0081] Referring to Figure 5, in another embodiment of this application, an industrial control system fault diagnosis system is provided, which can be used to implement the above-mentioned industrial control system fault diagnosis method. Specifically, the industrial control system fault diagnosis system includes an industrial control system data feature extraction system and a fault diagnosis module.
[0082] Among them, the industrial control system data feature extraction system is used to obtain feature data of the operating data of the industrial control system to be diagnosed; the fault diagnosis module is used to input the feature data of the operating data of the industrial control system to be diagnosed into the pre-trained industrial control system fault diagnosis model to obtain the fault diagnosis result of the industrial control system.
[0083] All relevant content of each step involved in the aforementioned embodiments of the industrial control system fault diagnosis method can be referenced to the functional description of the corresponding functional module of the industrial control system fault diagnosis system in the embodiments of this application, and will not be repeated here.
[0084] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.
[0085] In another embodiment of this application, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in the computer storage medium to achieve a corresponding method flow or corresponding function. The processor described in this application embodiment can be used for the operation of data feature extraction methods or fault diagnosis methods in industrial control systems.
[0086] In another embodiment of this application, a storage medium is provided, specifically a computer-readable storage medium (Memory). This computer-readable storage medium is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the industrial control system data feature extraction method or industrial control system fault diagnosis method in the above embodiments.
[0087] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0088] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.
[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.
[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.
[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit them. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of this application. Any modifications or equivalent substitutions that do not depart from the spirit and scope of this application should be covered within the protection scope of the claims of this application.
Claims
1. A method for extracting data features of an industrial control system, characterized in that, The method comprises the following steps: obtaining industrial control system running data; inputting the industrial control system running data into a preset improved sparse autoencoder to obtain feature data of the industrial control system running data; wherein, the improved sparse autoencoder is obtained by replacing the determination process of the sparse penalty term weight in the loss function of the sparse autoencoder with the optimization and determination by using a particle swarm optimization algorithm.
2. The method of claim 1, wherein, Before the inputting, the method further comprises: performing data correction processing and normalization processing on the industrial control system running data.
3. The method of claim 2, wherein, The normalization processing is specifically performed by using a Z-Score method.
4. The method of claim 1, wherein, The inputting the industrial control system running data into the preset improved sparse autoencoder to obtain the feature data of the industrial control system running data comprises the following steps: S11: inputting the industrial control system running data into the preset improved sparse autoencoder to obtain a loss function value of the improved sparse autoencoder; S12: when the loss function value of the improved sparse autoencoder is greater than a preset loss function setting value, adjusting the weight and bias coefficient of the improved sparse autoencoder, and returning to S11; S13: when the loss function value of the improved sparse autoencoder is not greater than the preset loss function setting value, recording the output of the hidden layer of the improved sparse autoencoder; and optimizing the sparse penalty term weight in the loss function of the improved sparse autoencoder by using a particle swarm optimization algorithm; S14: iterating S11-S13 to a preset iteration number, selecting the output of the hidden layer of the improved sparse autoencoder with the minimum loss function value from all the recorded outputs of the hidden layer of the improved sparse autoencoder as the feature data of the industrial control system running data.
5. The method of claim 1, wherein, The method further comprises: dividing the industrial control system running data and the feature data of the industrial control system running data into normal running data and abnormal running data and storing them in different zones; wherein, the normal running data is divided into normal steady-state running data and normal transient running data and stored in different zones; and the abnormal running data is classified according to fault type labels and stored in different zones.
6. An industrial control system fault diagnosis method characterized by comprising: The method comprises the following steps: obtaining feature data of the industrial control system running data by using the industrial control system data feature extraction method according to any one of claims 1 to 5; inputting the feature data of the industrial control system running data into a pre-trained industrial control system fault diagnosis model to obtain an industrial control system fault diagnosis result.
7. An industrial control system data feature extraction system, comprising: The method comprises the following steps: a data acquisition module, configured to obtain industrial control system running data; a feature extraction module, configured to input the industrial control system running data into a preset improved sparse autoencoder to obtain feature data of the industrial control system running data; 8. An industrial control system fault diagnostic system characterized by comprising: wherein, the improved sparse autoencoder is obtained by replacing the determination process of the sparse penalty term weight in the loss function of the sparse autoencoder with the optimization and determination by using a particle swarm optimization algorithm. The method comprises the following steps: the industrial control system data feature extraction system according to claim 7, configured to obtain feature data of the industrial control system running data to be diagnosed; a fault diagnosis module, configured to input the feature data of the industrial control system running data to be diagnosed into a pre-trained industrial control system fault diagnosis model to obtain an industrial control system fault diagnosis result.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the data feature extraction method of the industrial control system according to any one of claims 1 to 5, or implement the steps of the fault diagnosis method of the industrial control system according to claim 6.
10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the data feature extraction method of the industrial control system according to any one of claims 1 to 5, or implement the steps of the fault diagnosis method of the industrial control system according to claim 6.