Fault prediction and health management method for high-speed rail vehicle-mounted equipment

Abstract

The invention discloses a high-speed rail vehicle-mounted equipment fault prediction and health management method, and relates to the technical field of high-speed rail vehicle-mounted equipment fault prediction, and the method comprises the steps: monitoring high-speed rail vehicle-mounted equipment through employing a high-precision sensor network, and obtaining an original monitoring data set; cleaning the original monitoring data set by adopting a multi-source data integration and preprocessing method to obtain a high-quality data set, and extracting key features based on the high-quality data set to obtain a feature data set; constructing a fault prediction model based on a deep learning method and the feature data set, inputting the high-quality data set to the fault prediction model, and outputting a fault early warning result; based on the fault early warning result, a decision support method is adopted to evaluate the equipment state, and a maintenance strategy suggestion is obtained; obtaining a comprehensive analysis report based on the maintenance strategy suggestion and the equipment evaluation state; environmental data and historical maintenance record data from a ground monitoring system are integrated, and the data are fused by using a weighted average method.

Description

Technical Field

[0001] The present invention relates to the technical field of high - speed rail on - vehicle equipment fault prediction, and particularly to a method for high - speed rail on - vehicle equipment fault prediction and health management. Background Art

[0002] High - speed rail on - vehicle equipment fault prediction refers to the real - time monitoring and data analysis of the states of key equipment on high - speed rail trains to identify potential fault hazards in advance so as to take preventive measures before the occurrence of faults.

[0003] In the field of high - speed rail on - vehicle equipment fault prediction, traditional fault prediction methods usually rely only on data from a single source and fail to make full use of data from different platforms, resulting in an incomplete understanding of the equipment health status. Moreover, when traditional methods predict equipment faults, due to the limitations of the model or insufficient training data, the prediction results are often inaccurate or cannot give timely warnings. At the same time, existing maintenance strategies are usually based on fixed time intervals or simple threshold judgments, lacking pertinence and flexibility, which may lead to over - maintenance or under - maintenance. Summary of the Invention

[0004] In view of the above - mentioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for high - speed rail on - vehicle equipment fault prediction and health management to solve the problems that traditional fault prediction methods usually rely only on data from a single source, fail to make full use of data from different platforms, resulting in an incomplete understanding of the equipment health status, and when traditional methods predict equipment faults, due to the limitations of the model or insufficient training data, the prediction results are often inaccurate or cannot give timely warnings.

[0006] To solve the above - mentioned technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a method for high - speed rail on - vehicle equipment fault prediction and health management, which includes: Monitoring high - speed rail on - vehicle equipment using a high - precision sensor network to obtain an original monitoring data set; Cleaning the original monitoring data set using a multi - source data integration and pre - processing method to obtain a high - quality data set, and extracting key features based on the high - quality data set to obtain a feature data set; Constructing a fault prediction model based on a deep - learning method and the feature data set, and inputting the high - quality data set into the fault prediction model to output a fault warning result; Based on the fault warning result, using a decision - support method to evaluate the equipment status and obtain maintenance strategy suggestions; Based on the maintenance strategy suggestions and the equipment evaluation status, obtaining a comprehensive analysis report.

[0007] As a preferred solution of the method for fault prediction and health management of high-speed rail onboard equipment of the present invention, wherein: the high-precision sensor network is used to monitor the high-speed rail onboard equipment to obtain the original monitoring data set, and the specific steps are: Select the sensor based on fiber Bragg grating FBG technology as the core monitoring equipment; Deploy FBG sensor networks at key locations of high-speed rail onboard equipment, with at least one sensor node installed at each key location; The key parts include wheels, brake system and engine; The output signal of each FBG sensor node is used to indicate the change of the device status; The output signals of all sensor nodes are collected at a fixed sampling frequency, and a timestamp is added to each data point to form the original monitoring data set.

[0008] As a preferred solution of the high-speed rail onboard equipment fault prediction and health management method of the present invention, wherein: the original monitoring data set is cleaned by using a multi-source data integration and preprocessing method to obtain a high-quality data set, and key features are extracted based on the high-quality data set to obtain a feature data set. The specific steps are: Integrate environmental data from ground monitoring systems and historical maintenance record data; The environmental data of the ground monitoring system includes track vibration and external temperature. The environmental data of the ground monitoring system and the original monitoring data set are fused by using a weighted average method to obtain fused data; Use wavelet transform to reduce noise on the fused data; Perform preliminary anomaly detection on the cleaned data, remove data points that are obviously illogical, and use local linear interpolation to correct the detected abnormal data points; Based on the cleaned data, time domain features, frequency domain features and statistical features are extracted to form a feature data set; The principal component analysis method PCA is used to reduce the dimension of the feature data set to obtain a high-quality data set.

[0009] As a preferred solution of the high-speed rail onboard equipment fault prediction and health management method of the present invention, wherein: the fault prediction model is constructed based on the deep learning method and the feature data set, and a high-quality data set is input into the fault prediction model, and the fault warning result is output. The specific steps are: A Transformer-based deep learning model is used to capture the changing trend of device status over time using its attention mechanism; The Transformer model is trained using the feature dataset, and the optimization goal is to minimize the prediction error; Input the high-quality data collected in real time into the trained model to generate a fault risk index, and the expression is: ; Wherein, is the fault risk index, is the output of the th hidden layer, is the weight parameter, is the bias term, is the Sigmoid activation function.

[0010] As a preferred solution of the method for fault prediction and health management of high-speed rail on-vehicle equipment described in the present invention, wherein: based on the fault warning result, a decision support method is adopted to evaluate the equipment status and obtain maintenance strategy suggestions. The specific steps are as follows: According to the fault risk index , combined with the historical operation data of the equipment, calculate the equipment health status score, and the expression is: ; Wherein, is the health status score, and are weight parameters determined by experimental calibration, is the cumulative operation time of the equipment; According to the health status score and the fault risk index , classify the equipment status into three categories: normal, warning, and emergency; When ≥ 0.8 and < 0.3, the equipment status is "normal"; When 0.5 ≤ < 0.8 or 0.3 ≤ < 0.7, the equipment status is "warning"; When < 0.5 or ≥ 0.7, the equipment status is "emergency"; Based on the equipment status classification result, generate specific maintenance strategy suggestions.

[0011] As a preferred solution of the method for fault prediction and health management of high-speed rail on-vehicle equipment described in the present invention, wherein: the specific value range explanation of the health status score is as follows: When < 0.5, it means that the equipment health condition is poor and needs to be focused on; When 0.5 ≤ When <0.8, it indicates that the equipment health condition is average, and regular inspections are recommended; When ≥0.8, it indicates that the equipment health condition is good and no special intervention is required.

[0012] As a preferred solution of the method for fault prediction and health management of high - speed rail on - vehicle equipment described in the present invention, wherein: based on the equipment status classification results, specific maintenance strategy suggestions are generated, specifically: When the equipment is in normal state, continue monitoring and no special maintenance operations are required.

[0013] When the equipment is in the warning state, regularly check the wheels, braking system and engine parts of the equipment, and adjust the maintenance plan according to the inspection results; When the equipment is in the emergency state, immediately stop the machine for maintenance and replace the parts that may have problems; Conduct a comprehensive diagnosis on the equipment to determine the specific location and cause of the fault, formulate a detailed repair plan according to the diagnosis results, including the list of parts to be replaced, the estimated repair time and cost estimate, perform the repair operations, and record all relevant data.

[0014] As a preferred solution of the method for fault prediction and health management of high - speed rail on - vehicle equipment described in the present invention, wherein: based on the maintenance strategy suggestions and the equipment evaluation status, a comprehensive analysis report is obtained, and the specific steps are as follows: Design the basic framework of the comprehensive analysis report; The basic framework of the comprehensive analysis report includes basic equipment information, an overview of the current health condition, fault warning and diagnosis results, maintenance strategies and implementation status, and maintenance effect evaluation; For the maintenance effect evaluation, the expression is: ; Wherein, is the maintenance effect evaluation index, is the time of the next fault occurrence; is the time of the current fault occurrence; Generate a comprehensive analysis report according to the basic framework and analysis results.

[0015] In a second aspect, the present invention provides a computer device, including a memory and a processor, and the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for fault prediction and health management of high - speed rail on - vehicle equipment described in the first aspect of the present invention is implemented.

[0016] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the method for fault prediction and health management of high-speed rail on-vehicle equipment described in the first aspect of the present invention is implemented.

[0017] The beneficial effects of the present invention are as follows: By integrating environmental data and historical maintenance record data from the ground monitoring system, using the weighted average method to fuse these data, and then using wavelet transform to denoise the fused data, the noise interference is effectively removed, and the purity of the data is improved. By selecting a deep learning model based on Transformer and using its attention mechanism to capture the change trend of the equipment state over time, an efficient modeling of the complex equipment operation state is realized, which not only improves the accuracy of fault prediction, but also can dynamically adjust the attention degree of the model to the data in different time periods to adapt to the rapid change of the equipment state. By calculating the equipment health status score according to the fault risk index combined with the historical operation data of the equipment and classifying the equipment state into three categories: normal, warning and emergency, a scientific evaluation of the equipment health status is realized, achieving the effects of extending the service life of the equipment, reducing the maintenance cost, and improving the operation efficiency and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0019] Figure 1 It is a flowchart of the method for fault prediction and health management of high-speed rail on-vehicle equipment in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings in the specification.

[0021] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention, but the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0022] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not all refer to the same embodiment, nor is it an individual or alternative embodiment that is mutually exclusive with other embodiments.

[0023] Embodiment 1, referring to Figure 1 , is an embodiment of the present invention. This embodiment provides a method for fault prediction and health management of high-speed rail on-vehicle equipment, including the following steps: S1. Monitor high-speed rail on-vehicle equipment using a high-precision sensor network to obtain an original monitoring data set; Furthermore, select sensors based on Fiber Bragg Grating (FBG) technology as the core monitoring equipment; Deploy an FBG sensor network at key parts of high-speed rail on-vehicle equipment, and install at least one sensor node at each key part; The key parts include wheels, braking systems, and engines; The output signal of each FBG sensor node is used to represent the change in the equipment state; Collect the output signals of all sensor nodes at a fixed sampling frequency, and add a timestamp mark to each data point to form an original monitoring data set; It should be noted that the selection of sensors based on Fiber Bragg Grating (FBG) technology is not only due to its high sensitivity and anti-electromagnetic interference ability, but also because it can provide long-term stable performance, which is particularly important for a high-speed rail system with high-speed operation and complex environment. By deploying an FBG sensor network at key parts and adding a timestamp mark to each data point, the time series characteristics of the data are ensured, thus providing an accurate time reference for subsequent data processing and fault prediction.

[0024] S2. Clean the original monitoring data set using a multi-source data integration and preprocessing method to obtain a high-quality data set, and extract key features based on the high-quality data set to obtain a feature data set; Furthermore, integrate environmental data and historical maintenance record data from the ground monitoring system; The environmental data of the ground monitoring system includes track vibration and external temperature. Use the weighted average method to perform data fusion on the environmental data of the ground monitoring system and the original monitoring data set to obtain the fused data; Use wavelet transform to perform noise reduction processing on the fused data; Perform preliminary anomaly detection on the cleaned data, eliminate data points that are clearly illogical, and use the local linear interpolation method to correct the detected abnormal data points; Based on the cleaned data, extract time-domain features, frequency-domain features, and statistical features to form a feature dataset; Use the principal component analysis method PCA to reduce the dimension of the feature dataset and obtain a high-quality dataset; It should be noted that the integration of multi-source data not only improves the comprehensiveness and accuracy of the data, but also better reflects the actual operating state of the equipment. The combined use of the weighted average method and wavelet transform makes the data fusion and noise reduction processing more efficient, reducing the impact of noise on subsequent analysis. The application of the local linear interpolation method further improves the integrity and consistency of the data, providing a more reliable basis for the principal component analysis PCA, thus optimizing the feature extraction process and enhancing the effect of model training.

[0025] S3. Construct a fault prediction model based on the deep learning method and the feature dataset, input the high-quality dataset into the fault prediction model, and output the fault warning result; Furthermore, select a deep learning model based on Transformer and use its attention mechanism to capture the changing trend of the equipment state over time; Use the feature dataset to train the Transformer model, and the optimization goal is to minimize the prediction error; Input the high-quality data collected in real time into the trained model to generate a fault risk index, and the expression is: ; Among them, is the fault risk index, is the output of the th hidden layer, is the weight parameter, is the bias term, is the Sigmoid activation function; It should be noted that the attention mechanism of the Transformer model can effectively capture the changing trend of the equipment state over time, especially suitable for dealing with complex and dynamically changing systems such as high-speed rail on-board equipment. Optimize the model by minimizing the prediction error to ensure the accuracy and reliability of the fault risk index. The application of the Sigmoid activation function gives the fault risk index a clear probability meaning, which is convenient for maintenance personnel to understand and apply, thus improving the effectiveness and operability of the warning information.

[0026] S4. Based on the fault warning result, adopt a decision support method to evaluate the equipment state and obtain maintenance strategy suggestions; Furthermore, according to the fault risk index , combined with the historical operation data of the equipment, calculate the equipment health status score, and the expression is: ; Among them, is the health status score, and are weight parameters, determined by experimental calibration, is the cumulative operating time of the device; According to the health status score and the fault risk index , the device status is divided into three categories: normal, warning, and emergency; When ≥0.8 and <0.3, the device status is "normal"; When 0.5 ≤ <0.8 or 0.3 ≤ <0.7, the device status is "warning"; When <0.5 or ≥0.7, the device status is "emergency"; Based on the device status classification results, generate specific maintenance strategy suggestions; When the device is in the normal state, continue to monitor without special maintenance operations.

[0027] When the device is in the warning state, regularly check the wheels, braking system, and engine parts of the device, and adjust the maintenance plan according to the inspection results; When the device is in the emergency state, immediately stop the machine for repair and replace the parts that may have problems; Conduct a comprehensive diagnosis of the device to determine the specific location and cause of the fault, and formulate a detailed repair plan according to the diagnosis results, including the list of parts to be replaced, the estimated repair time, and cost estimation, perform the repair operations, and record all relevant data; The health status score The specific value range is explained as follows: When <0.5, it indicates that the device health condition is poor and needs key attention; When 0.5 ≤ <0.8, it indicates that the device health condition is average, and regular inspections are recommended; When ≥0.8, it indicates that the device health condition is good and no special intervention is required; It should be noted that the calculation of the equipment health status score combines the fault risk index and the cumulative operation time, providing a comprehensive evaluation index to help the operation and maintenance personnel quickly judge the equipment status. The equipment status is classified into normal, warning, and emergency according to different health status score ranges, enabling the formulation of precise maintenance strategies. In the "emergency" state, the equipment is immediately shut down for maintenance to avoid the occurrence of larger-scale faults; while in the "warning" state, regular inspections are carried out, which helps to detect potential problems in advance and reduce unnecessary downtime, thus improving the overall operation efficiency and service quality.

[0028] S5. Obtain a comprehensive analysis report based on the maintenance strategy suggestions and the equipment evaluation status; Furthermore, design the basic framework of the comprehensive analysis report; The basic framework of the comprehensive analysis report includes the basic information of the equipment, an overview of the current health status, fault warning and diagnosis results, maintenance strategies and implementation status, and maintenance effect evaluation; For the maintenance effect evaluation, the expression is: ; Wherein, is the maintenance effect evaluation index, is the time of the next fault occurrence; is the time of the current fault occurrence; Generate a comprehensive analysis report according to the basic framework and the analysis results; It should be noted that the design of the comprehensive analysis report is not only to record the current status and maintenance history of the equipment, but more importantly, through the quantitative evaluation of the maintenance effect, it provides a scientific basis for future maintenance plans. The maintenance effect evaluation index can not only measure the effectiveness of maintenance measures, but also guide the subsequent optimization direction, forming a continuous improvement closed-loop system, which not only improves the self-optimization ability of the system, but also provides a strong guarantee for the safe and stable operation of the high-speed railway.

[0029] This embodiment also provides a computer device applicable to the situation of the high-speed railway vehicle equipment fault prediction and health management method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the high-speed railway vehicle equipment fault prediction and health management method as proposed in the above embodiment.

[0030] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0031] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the method for predicting faults and managing the health of high-speed rail on-board equipment as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read Only Memory (EPROM for short), Programmable Read-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0032] In summary, the present invention integrates environmental data and historical maintenance record data from the ground monitoring system, uses the weighted average method to fuse these data, and then uses wavelet transform to denoise the fused data, effectively removing noise interference and improving the purity of the data. By selecting a deep learning model based on Transformer and using its attention mechanism to capture the changing trend of the device state over time, an efficient modeling of the complex device operating state is achieved. This not only improves the accuracy of fault prediction but also dynamically adjusts the model's attention to data in different time periods to adapt to the rapid changes in the device state. By calculating the device health status score based on the fault risk index and the historical operation data of the device and classifying the device state into three categories: normal, warning, and emergency, a scientific evaluation of the device health condition is realized, achieving the effects of extending the service life of the device, reducing maintenance costs, and improving operation efficiency and service quality.

[0033] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for fault prediction and health management of high-speed rail on-vehicle equipment, characterized in that: Including: Monitoring high-speed rail on-vehicle equipment using a high-precision sensor network to obtain an original monitoring data set; Cleaning the original monitoring data set using a multi-source data integration and preprocessing method to obtain a high-quality data set, and extracting key features based on the high-quality data set to obtain a feature data set; Constructing a fault prediction model based on a deep learning method and the feature data set, and inputting the high-quality data set into the fault prediction model to output a fault warning result; Evaluating the equipment status using a decision support method based on the fault warning result, and obtaining maintenance strategy suggestions; Obtaining a comprehensive analysis report based on the maintenance strategy suggestions and the equipment evaluation status.

2. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 1, wherein: The step of monitoring high-speed rail on-vehicle equipment using a high-precision sensor network to obtain an original monitoring data set is as follows: Selecting a sensor based on the fiber Bragg grating (FBG) technology as the core monitoring device; Deploying an FBG sensor network at key parts of high-speed rail on-vehicle equipment, with at least one sensor node installed at each key part; The key parts include wheels, braking systems, and engines; The output signal of each FBG sensor node is used to represent the change in equipment status; Collecting the output signals of all sensor nodes at a fixed sampling frequency, and adding a timestamp mark to each data point to form an original monitoring data set.

3. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 2, characterized in that: The step of cleaning the original monitoring data set using a multi-source data integration and preprocessing method to obtain a high-quality data set, and extracting key features based on the high-quality data set to obtain a feature data set is as follows: Integrating environmental data from the ground monitoring system and historical maintenance record data; The environmental data of the ground monitoring system includes track vibration and external temperature. Using the weighted average method to perform data fusion on the environmental data of the ground monitoring system and the original monitoring data set to obtain the fused data; Using wavelet transform to perform noise reduction processing on the fused data; Performing preliminary anomaly detection on the cleaned data, removing data points that are clearly illogical, and using the local linear interpolation method to correct the detected abnormal data points; Based on the cleaned data, extracting time-domain features, frequency-domain features, and statistical features to form a feature data set; Using the principal component analysis (PCA) method to perform dimensionality reduction processing on the feature data set to obtain a high-quality data set.

4. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 3, characterized in that: The step of constructing a fault prediction model based on a deep learning method and the feature data set, and inputting the high-quality data set into the fault prediction model to output a fault warning result is as follows: Selecting a deep learning model based on Transformer, and using its attention mechanism to capture the change trend of equipment status over time; Using the feature data set to train the Transformer model, and the optimization goal is to minimize the prediction error; Inputting the real-time collected high-quality data into the trained model to generate a fault risk index, and the expression is: ; Among them, is the fault risk index, is the output of the th hidden layer, is the weight parameter, is the bias term, is the Sigmoid activation function.

5. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 4, characterized in that: The step of evaluating the equipment status using a decision support method based on the fault warning result, and obtaining maintenance strategy suggestions is as follows: According to the failure risk index , combined with the historical operation data of the equipment, calculate the equipment health status score. The expression is as follows: ； Among them, is the health status score, and are weight parameters determined by experimental calibration, is the cumulative operating time of the device; According to the health status score and the failure risk index , the device status is divided into three categories: normal, warning, and emergency; When ≥0.8 and <0.3, the device status is "normal"; When 0.5 ≤ < 0.8 or 0.3 ≤ < 0.7, the device status is "warning"; When <0.5 or ≥0.7, the device status is "urgent"; Generating specific maintenance strategy suggestions based on the equipment status classification result.

6. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 5, wherein: The health status score The specific value range interpretation is as follows: When <0.5, it indicates that the device health status is poor and requires key attention; When 0.5 ≤ < 0.8, it indicates that the equipment is in general health condition, and regular inspections are recommended; When ≥ 0.8, it indicates that the equipment is in good health condition and no special intervention is required.

7. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 6, wherein: The step of generating specific maintenance strategy suggestions based on the equipment status classification result is specifically: When the device is in normal condition, continue monitoring without special maintenance operations; When the device is in a warning state, regularly check the wheels, braking system, and engine parts of the device, and adjust the maintenance plan according to the inspection results; When the device is in an emergency state, immediately stop the machine for repair and replace the parts that may have problems; Conduct a comprehensive diagnosis of the device to determine the specific location and cause of the fault, formulate a detailed repair plan based on the diagnosis results, including a list of parts to be replaced, estimated repair time, and cost estimate, perform the repair operations, and record all relevant data.

8. The method for fault prediction and health management of high-speed rail on-vehicle equipment according to claim 6, characterized in that: Based on the maintenance strategy recommendations and the device evaluation status, obtain a comprehensive analysis report. The specific steps are as follows: Design the basic framework of the comprehensive analysis report; The basic framework of the comprehensive analysis report includes basic device information, an overview of the current health status, fault warning and diagnosis results, maintenance strategies and implementation status, and maintenance effect evaluation; For the maintenance effect evaluation, the expression is: ； Among them, is the maintenance effect evaluation index, is the time of the next failure; is the time of the current failure; Generate a comprehensive analysis report according to the basic framework and analysis results.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the fault prediction and health management method for high-speed rail on-vehicle equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the fault prediction and health management method for high-speed rail on-vehicle equipment according to any one of claims 1 to 7.

Images