Data processing method and apparatus for control system fault prediction

Abstract

The application discloses a kind of data processing method and device for controlling system fault prediction.The method comprises the following steps: obtaining sample data to be processed, the sample data to be processed is used to represent control system sample use data;Sample data to be processed is carried out fault feature extraction processing, and sample fault feature data is obtained, and the sample fault feature data is used to control system fault feature data;Sample fault feature data is carried out model training processing based on multi-algorithm fusion, and control system fault prediction model is obtained;Obtain the use data to be processed, and the use data to be processed is used to represent the use data of predicted control system;The use data to be processed is carried out fault prediction processing based on control system fault prediction model, and fault prediction result data is obtained.The control system fault prediction model is trained by the method of multi-algorithm fusion, and the control system is carried out fault prediction, and the technical effect of improving control system fault prediction accuracy is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computers, in particular to a data processing method and device for control system fault prediction. BACKGROUND

[0002] The control system is the core unit of the equipment vehicle, has the characteristics of complex structure, parameter is many, and signal measurement is not easy. When the control system fails, it is difficult to determine the fault position and fault type, which greatly affects the performance of the equipment. Accurate prediction of control system failure is crucial to achieve timely intervention and more efficient maintenance planning.

[0003] Therefore, the present application is proposed. SUMMARY

[0004] The main purpose of the present application is to provide a data processing method and device for control system fault prediction, which realizes the technical effect of improving the accuracy of control system fault prediction.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a data processing method for control system fault prediction, comprising:

[0006] Obtaining to-be-processed sample data, wherein the to-be-processed sample data is used to represent control system sample usage data;

[0007] Performing fault feature extraction processing on the to-be-processed sample data to obtain sample fault feature data, wherein the to-be-processed sample fault feature data is feature data used for control system fault;

[0008] Performing model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model;

[0009] Obtaining to-be-processed usage data, wherein the to-be-processed usage data is used to represent usage data of a control system to be predicted;

[0010] Performing fault prediction processing based on the control system fault prediction model on the to-be-processed usage data to obtain fault prediction result data.

[0011] Further, the model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model comprises:

[0012] Performing first model training processing on the to-be-processed sample fault feature data to obtain a process first fault prediction model, wherein the process first fault prediction model is a fault prediction model trained based on a first algorithm;

[0013] The second model training based processing is performed on the to-be-processed sample fault feature data, and a process second fault prediction model is obtained, where the process second fault prediction model is a fault prediction model trained based on a second algorithm;

[0014] The third model training based processing is performed on the to-be-processed sample fault feature data, and a process third fault prediction model is obtained, where the process third fault prediction model is a fault prediction model trained based on a third algorithm;

[0015] The process first fault prediction model, the process second fault prediction model and the process third fault prediction model are subjected to model evaluation processing, and the control system fault prediction model is obtained.

[0016] Further, the model evaluation processing is performed on the process first fault prediction model, the process second fault prediction model and the process third fault prediction model, and the control system fault prediction model is obtained, which includes:

[0017] The process first fault prediction model, the process second fault prediction model and the process third fault prediction model are subjected to first evaluation processing respectively, and a first evaluation fault prediction model is obtained, where the first evaluation fault prediction model is a fault prediction model with the best first evaluation result among the process first fault prediction model, the process second fault prediction model and the process third fault prediction model;

[0018] The process first fault prediction model, the process second fault prediction model and the process third fault prediction model are subjected to second evaluation processing respectively, and a second evaluation fault prediction model is obtained, where the second evaluation fault prediction model is a fault prediction model with the best second evaluation result among the process first fault prediction model, the process second fault prediction model and the process third fault prediction model;

[0019] The control system fault prediction model is obtained according to the first evaluation fault prediction model and the second evaluation fault prediction model.

[0020] Further, the fault prediction processing based on the control system fault prediction model is performed on the to-be-processed use data, and fault prediction result data is obtained, which includes:

[0021] The fault feature extraction processing is performed on the to-be-processed use data, and to-be-processed fault feature data is obtained, where the to-be-processed fault feature data is data for representing fault features of a to-be-predicted control system;

[0022] Match the control system fault prediction model corresponding to the fault feature data to be processed in the preset prediction model database to obtain the matched fault prediction model. The matched fault prediction model is a control system fault prediction model used to represent the fault prediction model evaluation features and the fault features to be processed.

[0023] The fault feature data to be processed is subjected to fault prediction processing based on the matching fault prediction model to obtain the fault prediction result data.

[0024] Further, the fault feature extraction process is performed on the data to be processed to obtain the fault feature data to be processed, including:

[0025] The data to be processed is subjected to extraction processing based on the first fault feature to obtain the first fault feature data, wherein the first fault feature data is feature data used to represent the operation of the control system.

[0026] The data to be processed is subjected to extraction processing based on the second fault features to obtain the second fault feature data, wherein the second fault feature data is feature data used to represent the state switching of the control system.

[0027] The data to be processed is subjected to extraction processing based on the third fault feature to obtain the third fault feature data, wherein the third fault feature data is feature data used to represent abnormal parameters of the control system.

[0028] The fault feature data to be processed is obtained based on the first fault feature data, the second fault feature data, and the third fault feature data.

[0029] Further, the fault feature extraction process is performed on the data to be processed to obtain the fault feature data to be processed, including:

[0030] The data to be processed is preprocessed based on data filtering to obtain preprocessed data.

[0031] The preprocessed data is subjected to fault feature extraction processing to obtain the fault feature data to be processed.

[0032] According to a second aspect of this application, a data processing apparatus for predicting faults in a control system is provided, comprising:

[0033] The sample data module is used to acquire sample data to be processed, wherein the sample data to be processed is data used to represent the use of samples in the control system.

[0034] The fault feature module is used to extract fault features from the sample data to be processed to obtain sample fault feature data, wherein the sample fault feature data to be processed is feature data used to control system faults.

[0035] The model training module is used to perform model training processing on the sample fault feature data based on multi-algorithm fusion to obtain a control system fault prediction model.

[0036] The data acquisition module is used to acquire usage data to be processed, wherein the usage data to be processed is usage data used to represent the predictive control system.

[0037] The fault prediction module is used to perform fault prediction processing on the data to be processed based on the fault prediction model of the control system, and obtain fault prediction result data.

[0038] Furthermore, the model training module includes:

[0039] The first training module is used to perform training processing on the fault feature data of the sample to be processed based on the first model to obtain the first fault prediction model of the process, wherein the first fault prediction model of the process is used to represent the fault prediction model trained based on the first algorithm.

[0040] The second training module is used to perform training processing on the fault feature data of the sample to be processed based on the second model to obtain the process second fault prediction model, wherein the process second fault prediction model is used to represent the fault prediction model obtained by training based on the second algorithm.

[0041] The third training module is used to perform training processing on the fault feature data of the sample to be processed based on the third model to obtain the third fault prediction model of the process, wherein the third fault prediction model of the process is used to represent the fault prediction model obtained by training based on the third algorithm.

[0042] The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are evaluated to obtain the fault prediction model of the control system.

[0043] According to a third aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing the computer to perform the above-described data processing method for predicting system faults.

[0044] According to a fourth aspect of this application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the aforementioned data processing method for predicting system faults.

[0045] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0046] In this application, the following steps are taken: First, sample data to be processed is acquired, wherein the sample data to be processed is used to represent the sample usage data of the control system. Second, fault feature extraction processing is performed on the sample data to obtain sample fault feature data, wherein the sample fault feature data to be processed is used to represent the feature data of the control system to be predicted. Third, fault prediction processing is performed on the sample fault feature data based on the control system fault prediction model to obtain fault prediction result data. By training the control system fault prediction model using a multi-algorithm fusion method, and then using the control system fault prediction model to predict the faults of the control system, the technical effect of improving the accuracy of control system fault prediction is achieved. Attached Figure Description

[0047] The accompanying drawings, which form part of this application, are used to provide a further understanding of the application and to make other features, objects, and advantages of the application more apparent. The illustrative embodiments and descriptions of this application are used to explain the application and do not constitute an undue limitation of the application. In the drawings:

[0048] Figure 1 A flowchart of a data processing method for predicting control system faults provided in this application;

[0049] Figure 2 A flowchart of a data processing method for predicting control system faults provided in this application;

[0050] Figure 3 A flowchart of a data processing method for predicting control system faults provided in this application;

[0051] Figure 4 A schematic diagram of a data processing device for predicting control system faults provided in this application;

[0052] Figure 5A schematic diagram of another data processing device for predicting control system faults provided in this application. Detailed Implementation

[0053] 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.

[0054] 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 for the embodiments of this application 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.

[0055] In this application, the terms "upper," "lower," "left," "right," "front," "rear," "top," "bottom," "inner," "outer," "middle," "vertical," "horizontal," "lateral," and "longitudinal" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are primarily for the purpose of better describing this application and its embodiments, and are not intended to limit the indicated device, element, or component to having a specific orientation, or to be constructed and operated in a specific orientation.

[0056] Furthermore, in addition to indicating location or positional relationship, some of the aforementioned terms may also have other meanings. For example, the term "above" may also be used in some cases to indicate a certain dependency or connection relationship. Those skilled in the art can understand the specific meaning of these terms in this application based on the specific circumstances.

[0057] Furthermore, the terms "installation," "setup," "equipped with," "connection," "linked," and "socketing" should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral structure; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or an internal connection between two devices, components, or parts. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0058] Fault prediction models based on particle swarm optimization (PSO) for control systems exhibit poor prediction performance when the sample data has a high dimensionality. Furthermore, PSO algorithms are prone to local optima, affecting prediction accuracy. Fault prediction based on backpropagation (BP) neural networks also suffers from poor generalization ability and distorted prediction accuracy when the input data has a high dimensionality. Therefore, this application addresses the aforementioned problems in current research on control system prediction.

[0059] In an optional embodiment of this application, a data processing method for predicting control system faults is proposed. Figure 1 A flowchart of a data processing method for predicting control system faults is provided in this application, as shown below. Figure 1 As shown, the method includes the following steps:

[0060] S101: Obtain the sample data to be processed;

[0061] The sample data to be processed is used to represent the sample usage data of the control system;

[0062] S102: Perform fault feature extraction processing on the sample data to be processed to obtain sample fault feature data;

[0063] The fault feature data of the sample to be processed is feature data used for control system faults;

[0064] In an optional embodiment of this application, fault feature extraction of the sample data to be processed includes preprocessing the sample data based on data denoising to obtain preprocessed sample data, performing principal component analysis-based processing on the preprocessed sample data, and extracting the main features from the preprocessed sample data to obtain sample fault feature data. The sample fault feature data includes:

[0065] Sensor reading change characteristics: including the trend of sensor reading changes (slope, fluctuation range), extreme values, mean values, etc. These characteristics are used to control the operating status and abnormal changes of the control system;

[0066] Equipment uptime characteristics: cumulative uptime, number of operating cycles, etc. These characteristics are used to assess the wear and tear and lifespan of the equipment;

[0067] Abnormal parameter characteristics: The frequency of abnormal operating parameters and the degree of deviation from the normal range are used to indicate signs of improper operation or equipment failure.

[0068] System state characteristics: The frequency of system state switching, the duration of a specific state, etc. These characteristics are used to identify unstable states or potential faults in the system.

[0069] S103: Perform model training processing based on multi-algorithm fusion on the sample fault feature data to obtain the control system fault prediction model;

[0070] In some optional embodiments of this application, a data processing method for predicting control system faults is proposed. Figure 2 A flowchart of a data processing method for predicting control system faults provided in this application is shown below. Figure 2 As shown, the method includes the following steps:

[0071] S201: Perform fault feature data of the sample to be processed on the first model training process to obtain the first fault prediction model of the process;

[0072] The first fault prediction model in the process is used to represent the fault prediction model trained based on the first algorithm;

[0073] S202: Perform second-model training on the fault feature data of the sample to be processed to obtain the second fault prediction model of the process;

[0074] The second fault prediction model is used to represent the fault prediction model trained based on the second algorithm.

[0075] S203: Perform third-model training on the fault feature data of the sample to be processed to obtain the third fault prediction model of the process;

[0076] The third fault prediction model is used to represent the fault prediction model trained based on the third algorithm.

[0077] The first, second, and third algorithms mentioned above can be any multiple different algorithms such as Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Random Forest (RF), and the corresponding process fault prediction models are obtained by training according to the different algorithms mentioned above.

[0078] In an optional embodiment of this application, training a process fault prediction model based on the above algorithm includes: identifying fault data in the sample data to be processed to obtain fault data, wherein the fault data is relevant data used to represent the fault of the control system, including relevant data such as fault type, fault time, and fault location; using the fault feature data of the sample data to be processed as the input of the model to be trained, and using the fault data as the output of the model to be trained, to train the process fault prediction model and obtain the process fault prediction model.

[0079] S204: Perform model evaluation processing on the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model to obtain the control system fault prediction model.

[0080] In some optional embodiments of this application, a data processing method for predicting control system faults is proposed, including:

[0081] The first fault prediction model, the second fault prediction model, and the third fault prediction model of the process are subjected to a first evaluation process to obtain a first evaluation fault prediction model. The first evaluation fault prediction model is the fault prediction model with the best first evaluation result among the first fault prediction model, the second fault prediction model, and the third fault prediction model of the process.

[0082] The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are subjected to a second evaluation process to obtain a second evaluation fault prediction model. The second evaluation fault prediction model is the fault prediction model with the best second evaluation result among the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model.

[0083] The control system fault prediction model is obtained based on the first evaluation fault prediction model and the second evaluation fault prediction model.

[0084] In an optional embodiment of this application, multiple model evaluation processes are performed on each process fault prediction model to obtain multiple model evaluation feature data corresponding to the process fault prediction model; based on any model evaluation index, the model evaluation feature data corresponding to multiple fault prediction models are filtered to obtain the optimal fault prediction model corresponding to the evaluation index; the above-mentioned process fault prediction model and the multiple evaluation indices corresponding to the model are stored in a preset prediction model database so that the corresponding fault prediction model can be matched according to the evaluation index when performing control system prediction.

[0085] For example, the evaluation indicators mentioned above include root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and symmetric mean absolute percentage error (sMAPE), as shown in the following formula:

[0086]

[0087] Among them, X ′ Let X be the predicted value from n different predictions, and X be the actual value. SSE is the sum of squared errors, and TSS is the total sum of squares.

[0088] S104: Obtain the usage data to be processed;

[0089] The usage data to be processed is the usage data used to represent the predictive control system.

[0090] S105: Perform fault prediction processing on the data to be processed based on the fault prediction model of the control system to obtain fault prediction result data.

[0091] In some optional embodiments of this application, a data processing method for predicting control system faults is proposed. Figure 3 A flowchart of a data processing method for predicting control system faults provided in this application is shown below. Figure 3 As shown, the method includes the following steps:

[0092] S301: Perform fault feature extraction processing on the data to be processed to obtain fault feature data to be processed;

[0093] Among them, the fault feature data to be processed is the data used to represent the fault features of the control system to be predicted;

[0094] In some optional embodiments of this application, a data processing method for predicting control system faults is proposed, including:

[0095] The data to be processed is subjected to extraction processing based on a first fault feature to obtain first fault feature data, wherein the first fault feature data is feature data used to represent the operation of the control system; the data to be processed is subjected to extraction processing based on a second fault feature to obtain second fault feature data, wherein the second fault feature data is feature data used to represent the state switching of the control system; the data to be processed is subjected to extraction processing based on a third fault feature to obtain third fault feature data, wherein the third fault feature data is feature data used to represent abnormal parameters of the control system; and the fault feature data to be processed is obtained based on the first fault feature data, the second fault feature data, and the third fault feature data.

[0096] In some optional embodiments of this application, a data processing method for predicting control system faults is proposed, including: performing data filtering-based preprocessing on the data to be processed to obtain preprocessed data; and performing fault feature extraction processing on the preprocessed data to obtain fault feature data to be processed.

[0097] Preprocessing the data to be used includes performing statistical analysis on the data, obtaining statistical characteristics of the data based on sliding window statistics, detecting and filtering outliers, and predicting and imputing missing values ​​in the data to achieve the preprocessing of the data to be used.

[0098] S302: Match the control system fault prediction model corresponding to the fault feature data to be processed in the preset prediction model database to obtain the matched fault prediction model.

[0099] The matching fault prediction model is a fault prediction model for a control system that represents the evaluation features of the fault prediction model and the corresponding features of the fault to be processed.

[0100] Data analysis is performed on the fault feature data to be processed to obtain data analysis features, which are used to determine the statistical features of the fault feature data to be processed, including: central features, distribution features, discrete features, time series features, etc. Based on the above statistical features, the model evaluation features corresponding to the above statistical features are matched in the preset prediction model database, and the fault prediction model is determined based on the corresponding model evaluation features.

[0101] S303: Perform fault prediction processing on the fault feature data to be processed based on the matching fault prediction model to obtain fault prediction result data.

[0102] In some optional embodiments of this application, a data processing apparatus for predicting system faults is proposed. Figure 4 A schematic diagram of a data processing device for predicting control system faults provided in this application is shown below. Figure 4 As shown, the device includes:

[0103] The sample data module 41 is used to acquire sample data to be processed, wherein the sample data to be processed is used to represent the sample usage data of the control system.

[0104] The fault feature module 42 is used to extract fault features from the sample data to be processed to obtain sample fault feature data, wherein the sample fault feature data to be processed is feature data for controlling system faults.

[0105] The model training module 43 is used to perform model training processing on sample fault feature data based on multi-algorithm fusion to obtain a control system fault prediction model.

[0106] The data acquisition module 44 is used to acquire the usage data to be processed, wherein the usage data to be processed is the usage data used to represent the predictive control system.

[0107] The fault prediction module 45 is used to perform fault prediction processing on the data to be processed based on the fault prediction model of the control system, and obtain fault prediction result data.

[0108] In some optional embodiments of this application, a data processing apparatus for predicting system faults is proposed. Figure 5 A schematic diagram of another data processing device for predicting control system faults provided in this application is shown below. Figure 5 As shown, the device includes:

[0109] The first training module 51 is used to perform training processing on the fault feature data of the sample to be processed based on the first model to obtain the first fault prediction model of the process, wherein the first fault prediction model of the process is used to represent the fault prediction model trained based on the first algorithm.

[0110] The second training module 52 is used to perform training processing on the fault feature data of the sample to be processed based on the second model to obtain the process second fault prediction model, wherein the process second fault prediction model is used to represent the fault prediction model obtained by training based on the second algorithm.

[0111] The third training module 53 is used to train the fault feature data of the sample to be processed based on the third model to obtain the third fault prediction model of the process. The third fault prediction model of the process is used to represent the fault prediction model trained based on the third algorithm.

[0112] The first, second, and third process fault prediction models are evaluated to obtain the control system fault prediction model.

[0113] The specific methods of execution of each unit in the above embodiments have been described in detail in the embodiments of the method, and will not be elaborated here.

[0114] In summary, this application involves: acquiring sample data to be processed, wherein the sample data to be processed is used to represent sample usage data of the control system; extracting fault features from the sample data to obtain sample fault feature data, wherein the sample fault feature data to be processed is used to represent feature data of control system faults; training the sample fault feature data based on multi-algorithm fusion to obtain a control system fault prediction model; acquiring usage data to be processed, wherein the usage data to be processed is used to represent usage data of the control system to be predicted; and performing fault prediction processing on the usage data based on the control system fault prediction model to obtain fault prediction result data. By training the control system fault prediction model using a multi-algorithm fusion method, and then using the control system fault prediction model to predict faults in the control system, the technical effect of improving the accuracy of control system fault prediction is achieved.

[0115] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0116] Obviously, those skilled in the art should understand that the various units or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device, or fabricating them separately as individual integrated circuit modules, or fabricating multiple modules or steps into a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0117] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A data processing method for predicting faults in a control system, characterized in that, include: Acquire sample data to be processed, wherein the sample data to be processed is used to represent the sample usage data of the control system; The sample data to be processed is subjected to fault feature extraction processing to obtain sample fault feature data, wherein the sample fault feature data to be processed is feature data used to control system faults; The sample fault feature data is subjected to model training processing based on multi-algorithm fusion to obtain a control system fault prediction model; Acquire usage data to be processed, wherein the usage data to be processed is usage data used to represent the predictive control system; The data to be processed is subjected to fault prediction processing based on the fault prediction model of the control system to obtain fault prediction result data; The sample fault feature data is subjected to model training processing based on multi-algorithm fusion to obtain a control system fault prediction model, including: The fault feature data of the sample to be processed is processed based on the first model training to obtain the first process fault prediction model, wherein the first process fault prediction model is used to represent the fault prediction model trained based on the first algorithm. The fault feature data of the sample to be processed is processed based on the second model training to obtain the process second fault prediction model, wherein the process second fault prediction model is used to represent the fault prediction model obtained based on the second algorithm training; The fault feature data of the sample to be processed is processed by training based on a third model to obtain a third fault prediction model of the process, wherein the third fault prediction model of the process is used to represent the fault prediction model trained based on the third algorithm. The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are evaluated to obtain the fault prediction model of the control system.

2. The data processing method according to claim 1, characterized in that, The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are evaluated to obtain the control system fault prediction model, which includes: The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are respectively subjected to a first evaluation process to obtain a first evaluation fault prediction model, wherein the first evaluation fault prediction model is the fault prediction model with the best first evaluation result among the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model; The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are respectively subjected to a second evaluation process to obtain a second evaluation fault prediction model, wherein the second evaluation fault prediction model is the fault prediction model with the best second evaluation result among the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model; The control system fault prediction model is obtained based on the first evaluation fault prediction model and the second evaluation fault prediction model.

3. The data processing method according to claim 1, characterized in that, The fault prediction results obtained by performing fault prediction processing on the data to be processed based on the fault prediction model of the control system include: The data to be processed is subjected to fault feature extraction processing to obtain fault feature data to be processed, wherein the fault feature data to be processed is data used to represent the fault features of the control system to be predicted; Match the control system fault prediction model corresponding to the fault feature data to be processed in the preset prediction model database to obtain the matched fault prediction model. The matched fault prediction model is a control system fault prediction model used to represent the fault prediction model evaluation features and the fault features to be processed. The fault feature data to be processed is subjected to fault prediction processing based on the matching fault prediction model to obtain the fault prediction result data.

4. The data processing method according to claim 3, characterized in that, The fault feature extraction process is performed on the data to be processed to obtain the fault feature data to be processed, including: The data to be processed is subjected to extraction processing based on the first fault feature to obtain the first fault feature data, wherein the first fault feature data is feature data used to represent the operation of the control system. The data to be processed is subjected to extraction processing based on the second fault features to obtain the second fault feature data, wherein the second fault feature data is feature data used to represent the state switching of the control system. The data to be processed is subjected to extraction processing based on the third fault feature to obtain the third fault feature data, wherein the third fault feature data is feature data used to represent abnormal parameters of the control system. The fault feature data to be processed is obtained based on the first fault feature data, the second fault feature data, and the third fault feature data.

5. The data processing method according to claim 1, characterized in that, The fault feature extraction process is performed on the data to be processed to obtain the fault feature data to be processed, including: The data to be processed is preprocessed based on data filtering to obtain preprocessed data. The preprocessed data is subjected to fault feature extraction processing to obtain the fault feature data to be processed.

6. A data processing device for predicting faults in a control system, characterized in that, include: The sample data module is used to acquire sample data to be processed, wherein the sample data to be processed is data used to represent the use of samples in the control system. The fault feature module is used to extract fault features from the sample data to be processed to obtain sample fault feature data, wherein the sample fault feature data to be processed is feature data used to control system faults. The model training module is used to perform model training processing on the sample fault feature data based on multi-algorithm fusion to obtain a control system fault prediction model. The data acquisition module is used to acquire usage data to be processed, wherein the usage data to be processed is usage data used to represent the predictive control system. The fault prediction module is used to perform fault prediction processing on the data to be processed based on the fault prediction model of the control system, and obtain fault prediction result data. The model training module includes: The first training module is used to perform training processing on the fault feature data of the sample to be processed based on the first model to obtain the first fault prediction model of the process, wherein the first fault prediction model of the process is used to represent the fault prediction model trained based on the first algorithm. The second training module is used to perform training processing on the fault feature data of the sample to be processed based on the second model to obtain the process second fault prediction model, wherein the process second fault prediction model is used to represent the fault prediction model obtained by training based on the second algorithm. The third training module is used to perform training processing on the fault feature data of the sample to be processed based on the third model to obtain the third fault prediction model of the process, wherein the third fault prediction model of the process is used to represent the fault prediction model obtained by training based on the third algorithm. The first process fault prediction model, the second process fault prediction model, and the third process fault prediction model are evaluated to obtain the fault prediction model of the control system.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the data processing method for predicting system faults as described in any one of claims 1-5.

8. An electronic device, characterized in that, include: At least one processor; The system includes a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to cause the at least one processor to perform the data processing method for predicting system faults according to any one of claims 1-5.

Images