Data processing method and device for fault prediction of control system

Abstract

The invention discloses a data processing method and device for fault prediction of a control system. The method comprises the following steps: acquiring to-be-processed sample data, wherein the to-be-processed sample data is used for representing sample use data of a control system; fault feature extraction processing is carried out on the to-be-processed sample data to obtain sample fault feature data, and the to-be-processed sample fault feature data is feature data used for controlling system faults; performing model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model; obtaining to-be-processed use data, wherein the to-be-processed use data is used for representing use data of the to-be-predicted control system; and performing fault prediction processing based on the control system fault prediction model on the to-be-processed use data to obtain fault prediction result data. The control system fault prediction model is obtained through training of a multi-algorithm fusion method, fault prediction is carried out on the control system, and the technical effect of improving the fault prediction accuracy of the control system is achieved.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly, to a data processing method and apparatus for predicting control system failures. Background Art

[0002] The control system is the core unit of equipment and vehicles, characterized by a complex structure, numerous parameters, and difficult signal measurement. When a failure occurs in the control system, it is difficult to determine the failure location and type, greatly affecting the performance of the equipment. Accurately predicting control system failures is crucial to enable timely intervention and a more efficient maintenance plan.

[0003] Therefore, this application is proposed. Summary of the Invention

[0004] The main objective of this application is to provide a data processing method and apparatus for predicting control system failures, achieving the technical effect of improving the accuracy of predicting control system failures.

[0005] To achieve the above objective, in the first aspect of this application, a data processing method for predicting control system failures is proposed, including:

[0006] Obtain sample data to be processed, where the sample data to be processed is used to represent the usage data of the control system samples;

[0007] Perform failure feature extraction processing on the sample data to be processed to obtain sample failure feature data, where the sample failure feature data to be processed is the feature data for control system failures;

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

[0009] Obtain usage data to be processed, where the usage data to be processed is used to represent the usage data of the control system to be predicted;

[0010] Perform failure prediction processing on the usage data to be processed based on the control system failure prediction model to obtain failure prediction result data.

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

[0012] Perform first model training processing on the sample failure feature data to be processed to obtain a first process failure prediction model, where the first process failure prediction model is a failure prediction model obtained by training based on the first algorithm;

[0013] Perform training processing on the to-be-processed sample fault feature data based on the second model to obtain a second process fault prediction model, where the second process fault prediction model is a fault prediction model representing the one trained based on the second algorithm;

[0014] Perform training processing on the to-be-processed sample fault feature data based on the third model to obtain a third process fault prediction model, where the third process fault prediction model is a fault prediction model representing the one trained based on the third algorithm;

[0015] 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.

[0016] Further, performing 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 includes:

[0017] Perform first evaluation processing on the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model respectively to obtain a first evaluation fault prediction model, where 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;

[0018] Perform second evaluation processing on the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model respectively to obtain a second evaluation fault prediction model, where 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;

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

[0020] Further, performing fault prediction processing on the to-be-processed usage data based on the control system fault prediction model to obtain fault prediction result data includes:

[0021] Perform fault feature extraction processing on the to-be-processed usage data to obtain to-be-processed fault feature data, where the to-be-processed fault feature data is data representing the fault features of the to-be-predicted control system;

[0022] Match the control system fault prediction model corresponding to the to-be-processed fault feature data in the preset prediction model database to obtain a matching fault prediction model, where the matching fault prediction model is a control system fault prediction model used to represent the correspondence between the fault prediction model evaluation features and the to-be-processed fault features;

[0023] Perform fault prediction processing on the to-be-processed fault feature data based on the matching fault prediction model to obtain the fault prediction result data.

[0024] Further, performing fault feature extraction processing on the to-be-processed usage data to obtain the to-be-processed fault feature data includes:

[0025] Perform extraction processing on the to-be-processed usage data based on the first fault feature to obtain first fault feature data, where the first fault feature data is feature data used to represent the operation of the control system;

[0026] Perform extraction processing on the to-be-processed usage data based on the second fault feature to obtain second fault feature data, where the second fault feature data is feature data used to represent the state transition of the control system;

[0027] Perform extraction processing on the to-be-processed usage data based on the third fault feature to obtain third fault feature data, where the third fault feature data is feature data used to represent the abnormal parameters of the control system;

[0028] Obtain the to-be-processed fault feature data according to the first fault feature data, the second fault feature data, and the third fault feature data.

[0029] Further, performing fault feature extraction processing on the to-be-processed usage data to obtain the to-be-processed fault feature data includes:

[0030] Perform preprocessing on the to-be-processed usage data based on data filtering to obtain preprocessed usage data;

[0031] Perform fault feature extraction processing on the preprocessed usage data to obtain the to-be-processed fault feature data.

[0032] According to the second aspect of the present application, a data processing device for control system fault prediction is proposed, including:

[0033] A sample data module for obtaining to-be-processed sample data, where the to-be-processed sample data is sample usage data used to represent the control system;

[0034] A fault feature module, configured to perform fault feature extraction processing on the to-be-processed sample data to obtain sample fault feature data, where the to-be-processed sample fault feature data is feature data for controlling system faults;

[0035] A model training module, configured to perform model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model;

[0036] A data acquisition module, configured to acquire to-be-processed usage data, where the to-be-processed usage data is usage data for representing the to-be-predicted control system;

[0037] A fault prediction module, configured to perform fault prediction processing on the to-be-processed usage data based on the control system fault prediction model to obtain fault prediction result data.

[0038] Further, the model training module includes:

[0039] A first training module, configured to perform first model training processing on the to-be-processed sample fault feature data to obtain a process first fault prediction model, where the process first fault prediction model is a fault prediction model obtained by training based on a first algorithm;

[0040] A second training module, configured to perform second model training processing on the to-be-processed sample fault feature data to obtain a process second fault prediction model, where the process second fault prediction model is a fault prediction model obtained by training based on a second algorithm;

[0041] A third training module, configured to perform third model training processing on the to-be-processed sample fault feature data to obtain a process third fault prediction model, where the process third fault prediction model is a fault prediction model obtained by training based on a third algorithm;

[0042] Perform model evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model to obtain the control system fault prediction model.

[0043] According to the third aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the above data processing method for predicting control system faults.

[0044] According to a fourth aspect of the present application, there is provided an electronic device, including: 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, and when the computer program is executed by the at least one processor, the at least one processor is caused to execute the above-mentioned data processing method for predicting control system failures.

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

[0046] In the present application, by obtaining sample data to be processed, where the sample data to be processed is used to represent the usage data of control system samples; performing failure feature extraction processing on the sample data to be processed to obtain sample failure feature data, where the sample failure feature data to be processed is the feature data for control system failures; performing model training processing based on multi-algorithm fusion on the sample failure feature data to obtain a control system failure prediction model; obtaining usage data to be processed, where the usage data to be processed is used to represent the usage data of the control system to be predicted; and performing failure prediction processing on the usage data to be processed based on the control system failure prediction model to obtain failure prediction result data. By training a control system failure prediction model through a multi-algorithm fusion method and performing failure prediction on the control system according to the control system failure prediction model, the technical effect of improving the accuracy of control system failure prediction is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings constituting a part of this application are used to provide a further understanding of this application, making other features, objects, and advantages of this application more obvious. The schematic embodiments and descriptions thereof of this application are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0048] Figure 1 is a flowchart of a data processing method for predicting control system failures provided by this application;

[0049] Figure 2 is a flowchart of a data processing method for predicting control system failures provided by this application;

[0050] Figure 3 is a flowchart of a data processing method for predicting control system failures provided by this application;

[0051] Figure 4 is a schematic diagram of a data processing device for predicting control system failures provided by this application;

[0052] Figure 5Schematic diagram of another data processing device for control system fault prediction provided by this application. Detailed implementation manners

[0053] To enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances for the embodiments of this application described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0055] In this application, the orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", etc. is based on the orientation or positional relationship shown in the drawings. These terms are mainly used to better describe this application and its embodiments, and are not used to limit that the indicated devices, elements, or components must have a specific orientation, or be constructed and operated in a specific orientation.

[0056] Moreover, in addition to being able to represent an orientation or positional relationship, some of the above terms may also be used to represent other meanings. For example, the term "upper" may also be used to represent a certain attachment relationship or connection relationship in some cases. For those of ordinary skill in the art, the specific meanings of these terms in this application can be understood according to specific circumstances.

[0057] In addition, the terms "installed", "set up", "equipped with", "connected", "linked", "socketed" should be understood in a broad sense. For example, "connected" 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. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] For the fault prediction of the control system by the fault prediction model based on particle swarm optimization, when the dimension of the sample data is relatively high, the prediction effect is poor, and the particle swarm optimization algorithm is prone to the problem of local optimum, which affects the prediction accuracy; for the fault prediction based on the BP neural network, when the dimension of the input data is relatively high, problems such as poor generalization ability and distorted prediction accuracy are likely to occur. Therefore, in view of the above problems existing in the current research on the prediction of the control system, this application is proposed.

[0059] In an alternative embodiment of the present application, a data processing method for fault prediction of a control system is proposed. Figure 1 As shown in the flowchart of the data processing method for fault prediction of a control system provided by this application, 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 sample fault feature data to be processed is the feature data for the faults of the control system;

[0064] In an alternative embodiment of the present application, the 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 processing on the preprocessed sample data, extracting the main features in the preprocessed sample data to obtain sample fault feature data, and the sample fault feature data includes:

[0065] Sensor reading change features: including the change trend (slope, fluctuation range), extreme values, mean values, etc. of the sensor readings, and these features are used for the operating state and abnormal changes of the control system;

[0066] Equipment operation time features: the cumulative value of the equipment operation time, the number of operation cycles, etc., and these features are used to evaluate the wear degree and service life of the equipment;

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

[0068] System status characteristics: The number of frequent switches of the system status, the duration of a specific status, etc. These characteristics are used to identify unstable states or potential faults of the system.

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

[0070] In some alternative embodiments of the present application, a data processing method for control system fault prediction is proposed. Figure 2 As shown in the flowchart of a data processing method for control system fault prediction provided by the present application, Figure 2 The method includes the following steps:

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

[0072] The process first fault prediction model is a fault prediction model obtained by training based on the first algorithm;

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

[0074] The process second fault prediction model is a fault prediction model obtained by training based on the second algorithm;

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

[0076] The process third fault prediction model is a fault prediction model obtained by training based on the third algorithm;

[0077] The above first algorithm, second algorithm, and third algorithm can be any different multiple algorithms among algorithms such as long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and random forest (RF). The corresponding process fault prediction models are trained according to the above different algorithms respectively.

[0078] In an alternative embodiment of the present application, the process fault prediction model trained based on the above algorithm includes: identifying fault data from the sample data to be processed, where the fault data is relevant data indicating the faults of the control system, including relevant data such as fault type, fault time, and fault location. Using the above sample fault feature data to be processed as the input of the model to be trained, and the above fault data as the output of the model to be trained, the process fault prediction model is trained to 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 alternative embodiments of the present application, a data processing method for control system fault prediction is proposed, including:

[0081] Perform first evaluation processing on the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model respectively to obtain the first evaluation fault prediction model, where 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;

[0082] Perform second evaluation processing on the first process fault prediction model, the second process fault prediction model, and the third process fault prediction model respectively to obtain the second evaluation fault prediction model, where 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] Obtain the control system fault prediction model according to the first evaluation fault prediction model and the second evaluation fault prediction model.

[0084] In an alternative embodiment of the present application, perform multiple model evaluation processes on each process fault prediction model respectively, and obtain multiple model evaluation feature data corresponding to the process fault prediction model; according to any model evaluation index, screen the model evaluation feature data corresponding to multiple fault prediction models to obtain the optimal fault prediction model corresponding to the evaluation index, and store the above process fault prediction model and multiple evaluation indexes corresponding to the model in a preset prediction model database, so as to match the corresponding fault prediction model according to the evaluation index when performing control system prediction.

[0085] For example, the above evaluation indexes include root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and symmetric mean absolute percentage error (sMAPE), and the formulas are as follows:

[0086]

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

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

[0089] The data to be processed for use is the data used to represent the control system to be predicted.

[0090] S105: Perform a fault prediction process on the data to be processed for use based on the control system fault prediction model to obtain the fault prediction result data.

[0091] In some alternative embodiments of the present application, a data processing method for control system fault prediction is proposed. Figure 3 is a flowchart of a data processing method for control system fault prediction provided by the present application, as Figure 3 shown, the method includes the following steps: including:

[0092] S301: Perform a fault feature extraction process on the data to be processed for use to obtain the data of the fault features to be processed;

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

[0094] In some alternative embodiments of the present application, a data processing method for control system fault prediction is proposed, including:

[0095] Perform an extraction process on the data to be processed for use based on the first fault feature to obtain the first fault feature data, where the first fault feature data is the feature data used to represent the operation of the control system; perform an extraction process on the data to be processed for use based on the second fault feature to obtain the second fault feature data, where the second fault feature data is the feature data used to represent the state transition of the control system; perform an extraction process on the data to be processed for use based on the third fault feature to obtain the third fault feature data, where the third fault feature data is the feature data used to represent the abnormal parameters of the control system; obtain the data of the fault features to be processed according to the first fault feature data, the second fault feature data, and the third fault feature data.

[0096] In some alternative embodiments of the present application, a data processing method for control system fault prediction is proposed, including: performing a preprocessing based on data filtering on the data to be processed for use to obtain the preprocessed data for use; performing a fault feature extraction process on the preprocessed data for use to obtain the data of the fault features to be processed.

[0097] The preprocessing of the usage data to be processed includes performing statistical analysis on the usage data to be processed. Data statistical features can be obtained according to the sliding window statistics, and outlier detection processing is performed on the usage data to be processed. The outliers are filtered, and the missing values in the usage data to be processed are predicted and filled to achieve the preprocessing of the usage data to be processed.

[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 matching fault prediction model;

[0099] The matching fault prediction model is the control system fault prediction model used to represent the correspondence between the fault prediction model evaluation features and the fault features to be processed;

[0100] Perform data analysis processing on the fault feature data to be processed to obtain data analysis features, so as to judge the data statistical features of the fault feature data to be processed, including: central features, distribution features, discrete features, time series features, etc. Match the model evaluation features corresponding to the above data statistical features in the preset prediction model database, and determine the fault prediction model according to 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 the present application, a data processing device for control system fault prediction is proposed. Figure 4 The schematic diagram of a data processing device for control system fault prediction provided by the present application is shown in Figure 4 As shown, the device includes:

[0103] The sample data module 41 is used to obtain the sample data to be processed, where the sample data to be processed is the usage data representing the control system samples;

[0104] The fault feature module 42 is used to perform fault feature extraction processing on the sample data to be processed to obtain sample fault feature data, where the sample fault feature data to be processed is the feature data for the control system fault;

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

[0106] The data acquisition module 44 is used to obtain the usage data to be processed, where the usage data to be processed is the usage data representing the control system to be predicted;

[0107] A fault prediction module 45 is configured to perform fault prediction processing on the data to be processed for use based on a control system fault prediction model, and obtain fault prediction result data.

[0108] In some alternative embodiments of the present application, a data processing device for control system fault prediction is proposed. Figure 5 As shown in the schematic diagram of another data processing device for control system fault prediction provided by the present application, Figure 5 as shown, the device includes:

[0109] A first training module 51 is configured to perform first model training processing on the sample fault feature data to be processed, and obtain a process first fault prediction model, where the process first fault prediction model is a fault prediction model used to represent the one trained based on the first algorithm;

[0110] A second training module 52 is configured to perform second model training processing on the sample fault feature data to be processed, and obtain a process second fault prediction model, where the process second fault prediction model is a fault prediction model used to represent the one trained based on the second algorithm;

[0111] A third training module 53 is configured to perform third model training processing on the sample fault feature data to be processed, and obtain a process third fault prediction model, where the process third fault prediction model is a fault prediction model used to represent the one trained based on the third algorithm;

[0112] Perform model evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model to obtain a control system fault prediction model.

[0113] The specific manners of the execution operations of the units in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0114] In summary, in the present application, by obtaining sample data to be processed, where the sample data to be processed is used to represent the usage data of the control system samples; performing fault feature extraction processing on the sample data to be processed to obtain sample fault feature data, where the sample fault feature data to be processed is the feature data for the control system faults; performing model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model; obtaining usage data to be processed, where the usage data to be processed is used to represent the usage data of the control system to be predicted; performing fault prediction processing on the usage data to be processed based on the control system fault prediction model to obtain fault prediction result data. By training a control system fault prediction model through a multi-algorithm fusion method and performing fault prediction on the control system according to the control system fault prediction model, 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 of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0116] Obviously, those skilled in the art should understand that the above-mentioned units or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module to be implemented. In this way, the present application is not limited to any specific combination of hardware and software.

[0117] The above is only the preferred embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A data processing method for control system fault prediction, characterized in that, Including: Obtain sample data to be processed, where the sample data to be processed is used to represent the sample usage data of the control system; Perform fault feature extraction processing on the sample data to be processed to obtain sample fault feature data, where the sample fault feature data to be processed is the feature data for the control system fault; Perform model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model; Obtain usage data to be processed, where the usage data to be processed is used to represent the usage data of the control system to be predicted; Perform fault prediction processing on the usage data to be processed based on the control system fault prediction model to obtain fault prediction result data.

2. The data processing method according to claim 1, wherein Performing model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model includes: Perform first model training processing on the sample fault feature data to be processed to obtain a process first fault prediction model, where the process first fault prediction model is a fault prediction model obtained by training based on the first algorithm; Perform second model training processing on the sample fault feature data to be processed to obtain a process second fault prediction model, where the process second fault prediction model is a fault prediction model obtained by training based on the second algorithm; Perform third model training processing on the sample fault feature data to be processed to obtain a process third fault prediction model, where the process third fault prediction model is a fault prediction model obtained by training based on the third algorithm; Perform model evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model to obtain the control system fault prediction model.

3. The data processing method according to claim 2, wherein Performing model evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model to obtain the control system fault prediction model includes: Perform first evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model respectively to obtain a first evaluation fault prediction model, where the first evaluation fault prediction model is the 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; Perform second evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model respectively to obtain a second evaluation fault prediction model, where the second evaluation fault prediction model is the 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; Obtain the control system fault prediction model according to the first evaluation fault prediction model and the second evaluation fault prediction model.

4. The data processing method according to claim 1, characterized in that, Performing fault prediction processing on the usage data to be processed based on the control system fault prediction model to obtain fault prediction result data includes: Perform fault feature extraction processing on the to-be-processed usage data to obtain to-be-processed fault feature data, where the to-be-processed fault feature data is data used to represent the fault features of the to-be-predicted control system; Match a control system fault prediction model corresponding to the to-be-processed fault feature data in a preset prediction model database to obtain a matched fault prediction model, where the matched fault prediction model is a control system fault prediction model used to represent the correspondence between the fault prediction model evaluation features and the to-be-processed fault features; Perform fault prediction processing on the to-be-processed fault feature data based on the matched fault prediction model to obtain the fault prediction result data.

5. The data processing method according to claim 4, wherein Performing fault feature extraction processing on the to-be-processed usage data to obtain to-be-processed fault feature data includes: Perform extraction processing on the to-be-processed usage data based on the first fault feature to obtain first fault feature data, where the first fault feature data is data used to represent the operating characteristics of the control system; Perform extraction processing on the to-be-processed usage data based on the second fault feature to obtain second fault feature data, where the second fault feature data is data used to represent the feature data of the control system state transition; Perform extraction processing on the to-be-processed usage data based on the third fault feature to obtain third fault feature data, where the third fault feature data is data used to represent the feature data of the abnormal parameters of the control system; Obtain the to-be-processed fault feature data according to the first fault feature data, the second fault feature data, and the third fault feature data.

6. The data processing method according to claim 1, wherein Performing fault feature extraction processing on the to-be-processed usage data to obtain to-be-processed fault feature data includes: Perform preprocessing on the to-be-processed usage data based on data filtering to obtain preprocessed usage data; Perform fault feature extraction processing on the preprocessed usage data to obtain the to-be-processed fault feature data.

7. A data processing device for control system fault prediction, characterized in that, Includes: A sample data module for obtaining to-be-processed sample data, where the to-be-processed sample data is data used to represent the sample usage data of the control system; A fault feature module for performing fault feature extraction processing on the to-be-processed sample data to obtain sample fault feature data, where the to-be-processed sample fault feature data is data used for the faults of the control system; A model training module for performing model training processing based on multi-algorithm fusion on the sample fault feature data to obtain a control system fault prediction model; A data acquisition module for acquiring to-be-processed usage data, where the to-be-processed usage data is data used to represent the usage data of the to-be-predicted control system; A fault prediction module for performing fault prediction processing on the to-be-processed usage data based on the control system fault prediction model to obtain fault prediction result data.

8. The data processing apparatus according to claim 7, wherein The model training module includes: A first training module for performing first model training processing on the to-be-processed sample fault feature data to obtain a process first fault prediction model, where the process first fault prediction model is a fault prediction model used to represent the model trained based on the first algorithm; A second training module, configured to perform training processing on the to-be-processed sample fault feature data based on a second model to obtain a process second fault prediction model, where the process second fault prediction model is a fault prediction model used to represent a model trained based on a second algorithm; A third training module, configured to perform training processing on the to-be-processed sample fault feature data based on a third model to obtain a process third fault prediction model, where the process third fault prediction model is a fault prediction model used to represent a model trained based on a third algorithm; Perform model evaluation processing on the process first fault prediction model, the process second fault prediction model, and the process third fault prediction model to obtain the control system fault prediction model.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the data processing method for control system fault prediction according to any one of claims 1-6.

10. An electronic device, characterized in that, 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, and the computer program is executed by the at least one processor to cause the at least one processor to execute the data processing method for control system fault prediction according to any one of claims 1-6.

Images