Train control equipment intelligent maintenance method, maintenance system, medium and product

Abstract

The invention discloses an intelligent train control equipment maintenance method, a maintenance system, a medium and a product, and relates to the field of rail transit maintaining.By implementing the method, the maintenance system collects the working temperature, the working voltage and the working current of a preset electronic element in train control equipment in real time so as to generate an actual parameter change curve, and the actual parameter change curve is compared with a preset parameter change curve for analysis; according to the method, the operation abnormity of the train control equipment can be found in time, the abnormity type is automatically identified, and the corresponding fault prediction result is retrieved in the preset fault mode library, so that a targeted maintenance strategy is formulated. Compared with a traditional regular maintenance mode, the method based on multi-dimensional parameter monitoring and intelligent analysis can find potential faults earlier, improve the accuracy of fault prediction, achieve preventive maintenance and effectively reduce the equipment fault rate so as to improve the reliability and safety of train control equipment operation.

Description

Technical Field

[0001] This application relates to the field of rail transit maintenance, and particularly to an intelligent maintenance method, a maintenance system, a medium and a product for train control equipment. Background Art

[0002] With the rapid development of the railway transportation industry, people's requirements for the reliability and safety of train operation are constantly increasing. As the core component to ensure the safety of train operation, the normal working state of train control equipment directly affects the safety of train operation and the efficiency of railway transportation. Therefore, it is urgent to maintain and repair train control equipment to ensure the stable operation of trains.

[0003] Currently, the maintenance method of train control equipment is mainly to carry out maintenance after the train control equipment has run for a certain period of time according to a pre-established maintenance plan, record the operating parameters of each component of the train control equipment through measuring instruments, and judge whether there are potential faults in the train control equipment according to the operating parameters.

[0004] However, the related technology still has certain defects. For example, relying solely on operating parameters for fault judgment, lacking in-depth analysis of the changing trends of operating parameters, it is difficult to accurately predict the possible types of faults, which affects the maintenance efficiency and quality. Summary of the Invention

[0005] This application provides an intelligent maintenance method, a maintenance system, a medium and a product for train control equipment, which are used to improve the reliability and safety of train control equipment operation.

[0006] In a first aspect, this application provides an intelligent maintenance method for train control equipment, which is applied to a maintenance system. The method includes: collecting the working temperature, working voltage and working current of a preset electronic component in the train control equipment within a preset time window; based on the working temperature, the working voltage and the working current, determining the actual working temperature change curve, actual working voltage change curve and actual working current change curve of the preset electronic component in the train control equipment within the preset time window; respectively comparing the actual working temperature change curve with a preset working temperature change curve, the actual working voltage change curve with a preset working voltage change curve, and the actual working current change curve with a preset working current change curve to obtain a temperature curve deviation, a voltage curve deviation and a current curve deviation; when the temperature curve deviation exceeds a preset temperature deviation, the voltage curve deviation exceeds a preset voltage deviation and / or the current curve deviation exceeds a preset current deviation, determining the abnormal type of the train control equipment, where the abnormal type includes the working temperature, the working voltage and / or the working current; retrieving multiple fault prediction results corresponding to the abnormal type in a preset fault mode library, where the preset fault mode library includes the corresponding relationship between the abnormal type and the fault prediction result; and based on the multiple fault prediction results, determining the maintenance strategy of the train control equipment.

[0007] By adopting the above technical solution, the maintenance system can collect the working temperature, working voltage, and working current of preset electronic components in the train control equipment in real time to generate an actual parameter change curve, and compare and analyze it with the preset parameter change curve. It can promptly detect abnormal operation of the train control equipment, automatically identify the type of abnormality, and retrieve the corresponding fault prediction result in the preset fault mode library, thereby formulating a targeted maintenance strategy. This method based on multi-dimensional parameter monitoring and intelligent analysis can detect potential faults earlier than the traditional regular maintenance method, improve the accuracy of fault prediction, achieve preventive maintenance, effectively reduce the equipment failure rate, and enhance the reliability and safety of the train control equipment operation.

[0008] Combined with some embodiments of the first aspect, in some embodiments, the actual working temperature change curve is compared with the preset working temperature change curve, the actual working voltage change curve is compared with the preset working voltage change curve, and the actual working current change curve is compared with the preset working current change curve to obtain the temperature curve deviation, voltage curve deviation, and current curve deviation. Specifically, it includes: performing Fourier transform on the actual working temperature change curve, the actual working voltage change curve, and the actual working current change curve respectively to obtain the corresponding spectral features; performing Fourier transform on the preset working temperature change curve, the preset working voltage change curve, and the preset working current change curve respectively to obtain the corresponding standard spectral features; calculating the Euclidean distance between the spectral features and the corresponding standard spectral features to obtain the temperature curve deviation, the voltage curve deviation, and the current curve deviation.

[0009] By adopting the above technical solution, the maintenance system uses Fourier transform to perform frequency-domain analysis on the actual parameter change curve and the preset parameter change curve, and calculates the Euclidean distance between the spectral features and the standard spectral features to quantify the parameter deviation. This analysis method based on frequency-domain features can more comprehensively reflect the dynamic characteristics of parameter changes. It can not only detect the deviation of the absolute value of the parameter, but also identify the abnormality of the parameter change trend. Compared with simple numerical comparison, it can more accurately judge the operation state of the train control equipment, improve the accuracy of fault diagnosis, and provide a more reliable basis for formulating maintenance strategies.

[0010] In some embodiments in combination with some embodiments of the first aspect, after the step of determining the actual working temperature change curve, the actual working voltage change curve, and the actual working current change curve of a preset electronic component in a train control device within a preset time window based on the working temperature, working voltage, and working current, the method further includes: extracting the temperature curve slope, temperature fluctuation characteristics, and temperature mutation characteristics of the actual working temperature change curve; extracting the voltage curve slope, voltage fluctuation characteristics, and voltage mutation characteristics of the actual working voltage change curve; and extracting the current curve slope, current fluctuation characteristics, and current mutation characteristics of the actual working current change curve; determining the temperature change mode of the preset electronic component according to the temperature curve slope, the temperature fluctuation characteristics, and the temperature mutation characteristics; determining the voltage change mode of the preset electronic component according to the voltage curve slope, the voltage fluctuation characteristics, and the voltage mutation characteristics; determining the current change mode of the preset electronic component according to the current curve slope, the current fluctuation characteristics, and the current mutation characteristics; and establishing a health status evaluation model of the preset electronic component based on the temperature change mode, the voltage change mode, and the current change mode.

[0011] By adopting the above technical solution, the maintenance system extracts the curve slopes, fluctuation characteristics, and mutation characteristics of the actual working temperature change curve, the actual working voltage change curve, and the actual working current change curve, and establishes a complete health status evaluation model. This multi-dimensional feature analysis method can comprehensively characterize the dynamic operation characteristics of the train control device, not only considering the change rate of parameters, but also paying attention to the fluctuation law and mutation situation of parameters, so as to establish a health status evaluation model of the preset electronic component, which can more accurately evaluate the performance degradation degree of the train control device, predict the remaining service life, and realize the health management of the whole life cycle of the device.

[0012] In some embodiments in combination with some embodiments of the first aspect, after the step of determining the abnormal type of the train control device when the temperature curve deviation exceeds a preset temperature deviation, the voltage curve deviation exceeds a preset voltage deviation, and / or the current curve deviation exceeds a preset current deviation, the method further includes: determining the corresponding abnormal curve slope, abnormal fluctuation characteristics, and abnormal mutation characteristics according to the abnormal type; and retrieving a fault prediction result in a preset fault mode library whose relevance to the abnormal curve slope, the abnormal fluctuation characteristics, and the abnormal mutation characteristics exceeds a preset relevance threshold.

[0013] By adopting the above technical solution, after the maintenance system detects an abnormality in the train control equipment, it further analyzes the slope of the abnormal curve, the characteristics of abnormal fluctuations, and the characteristics of abnormal mutations, and retrieves the fault prediction results with a relevance exceeding the preset relevance threshold in the preset fault mode library. This intelligent retrieval method based on feature correlation significantly improves the accuracy of fault diagnosis, can quickly locate the possible causes of faults, and improves the maintenance efficiency.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of collecting the operating temperature, operating voltage, and operating current of the preset electronic components in the train control equipment within the preset time window, the method further includes: real-time recording the system startup information, system stop information, function call information, and error prompt information of the train control equipment; generating a software operation log information stream based on the system startup information, the system stop information, the function call information, and the error prompt information.

[0015] By adopting the above technical solution, the maintenance system monitors the train control equipment in a combination of software and hardware, breaking through the limitation of only focusing on hardware parameters in the traditional way, achieving a comprehensive monitoring of the operating state of the train control equipment, and improving the comprehensiveness and accuracy of fault diagnosis.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of real-time recording the system startup information, system stop information, function call information, and error prompt information of the train control equipment, the method further includes: if the occurrence frequency of the target error prompt information of the target module within the preset time period exceeds the preset frequency threshold, marking the target module as an abnormal module; performing a timing analysis on the target error prompt information according to the timestamp information of the target error prompt information to establish a fault propagation chain; determining the root cause of the fault according to the fault propagation chain.

[0017] By adopting the above technical solution, the maintenance system analyzes the occurrence frequency and timestamp information of the error prompt information to establish a fault propagation chain, thereby tracing the root cause of the fault. This fault location method based on timing analysis can effectively identify the propagation path and causal relationship of the fault, not only can quickly locate the root cause of the fault, but also can predict other modules that may be affected by the fault, providing a basis for taking timely preventive measures and effectively reducing the risk of fault spread.

[0018] In some embodiments in combination with some embodiments of the first aspect, after the step of marking the target module as an abnormal module if the occurrence frequency of the target error prompt information of the target module exceeds a preset frequency threshold within the preset time period, the method further includes: establishing a data flow diagram of the abnormal module and other modules, where the data flow diagram includes the sender of the data packet, the sending time, the receiver, the receiving time, and the transmission path; detecting the packet loss rate, retransmission rate, and data error rate of the data packet during the transmission process; judging the communication quality between the abnormal module and the other modules based on the packet loss rate, the retransmission rate, and the data error rate; and optimizing the network nodes with a communication quality lower than a preset quality threshold.

[0019] By adopting the above technical solution, the maintenance system establishes a data flow diagram of the abnormal module and other modules, and monitors the packet loss rate, retransmission rate, and error rate during the data transmission process, realizing a comprehensive evaluation of the communication quality between modules. This analysis method based on network communication quality can timely discover problems existing in the data transmission between modules, effectively improve the communication reliability, reduce the abnormality of train control equipment caused by communication failures, and provide guarantee for the stable operation of train control equipment.

[0020] In a second aspect, an embodiment of the present application provides a maintenance system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the maintenance system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product containing instructions, when the above computer program product runs on a maintenance system, enabling the above maintenance system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions, when the above instructions run on a maintenance system, enabling the above maintenance system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0023] It can be understood that the maintenance system provided in the second aspect above, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, and will not be elaborated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By adopting the above technical solution, the maintenance system can collect the working temperature, working voltage, and working current of preset electronic components in the train control equipment in real time to generate the actual parameter change curve, and compare and analyze it with the preset parameter change curve. It can timely detect the abnormal operation of the train control equipment, automatically identify the type of abnormality, and retrieve the corresponding fault prediction result in the preset fault mode library, so as to formulate a targeted maintenance strategy. This method based on multi-dimensional parameter monitoring and intelligent analysis can detect potential faults earlier than the traditional regular maintenance method, improve the accuracy of fault prediction, achieve preventive maintenance, effectively reduce the equipment failure rate, and enhance the reliability and safety of the train control equipment operation.

[0025] 2. By adopting the above technical solution, the maintenance system extracts the curve slopes, fluctuation characteristics, and mutation characteristics of the actual working temperature change curve, actual working voltage change curve, and actual working current change curve, and establishes a complete health status evaluation model. This multi-dimensional feature analysis method can comprehensively describe the dynamic operation characteristics of the train control equipment, not only considering the change rate of parameters, but also paying attention to the fluctuation law and mutation situation of parameters, so as to establish a health status evaluation model for preset electronic components, and can more accurately evaluate the performance degradation degree of the train control equipment, predict the remaining service life, and realize the health management of the whole life cycle of the equipment.

[0026] 3. By adopting the above technical solution, the maintenance system analyzes the occurrence frequency and timestamp information of error prompt messages to establish a fault propagation chain, so as to trace the root cause of the fault. This fault location method based on time series analysis can effectively identify the propagation path and causal relationship of the fault, not only can quickly locate the root cause of the fault, but also can predict other modules that may be affected by the fault, providing a basis for taking timely preventive measures and effectively reducing the risk of fault spread. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a schematic flow chart of an intelligent maintenance method for train control equipment in an embodiment of the present application; Figure 2 is another schematic flow chart of an intelligent maintenance method for train control equipment in an embodiment of the present application; Figure 3 is a schematic structural diagram of an entity device of the maintenance system in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The terms used in the following embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application, the singular forms "a", "an", "above-mentioned", "the", and "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations including one or more of the listed items.

[0029] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and should not be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0030] The following describes the process of the method provided in this embodiment. Please refer to Figure 1 , which is a schematic flowchart of a method for intelligent maintenance of train control equipment in an embodiment of this application.

[0031] S101. Collect the working temperature, working voltage, and working current of preset electronic components in the train control equipment within a preset time window; Among them, the preset time window refers to a preset continuous time interval, which can usually be 10 minutes, 30 minutes, 1 hour, etc.; the train control equipment refers to the key equipment for controlling train operation, including on-vehicle control units, ground control units, etc.; the preset electronic components refer to the key electronic devices that need to be monitored in the train control equipment in advance, such as processors, memories, communication modules, etc.; the working temperature refers to the real-time temperature value of the preset electronic components during actual operation, with the unit of degree Celsius; the working voltage refers to the power supply voltage value of the preset electronic components during actual operation, with the unit of volt; the working current refers to the consumed current value of the preset electronic components during actual operation, with the unit of ampere.

[0032] Specifically, first, the maintenance system determines the preset electronic components to be monitored. Then, within each preset time window, the maintenance system continuously collects the working parameters of the preset electronic components through temperature sensors, voltage sensors, and current sensors, including working temperature, working voltage, and working current. The maintenance system performs preliminary filtering and preprocessing on the collected data, eliminates obvious abnormal data points, and stores the processed data in the database in chronological order for subsequent analysis. The sampling frequency is adjusted according to the change characteristics of different parameters. The working temperature is usually sampled once per minute, while the working voltage and working current may require a higher sampling frequency, such as sampling multiple times per second.

[0033] S102. Based on the operating temperature, the operating voltage, and the operating current, determine the actual operating temperature change curve, the actual operating voltage change curve, and the actual operating current change curve of the preset electronic components in the train control equipment within the preset time window; Among them, the actual operating temperature change curve refers to the function curve of the operating temperature of the preset electronic components changing with time, which is used to reflect the dynamic change of the operating temperature; the actual operating voltage change curve refers to the function curve of the operating voltage of the preset electronic components changing with time, which is used to reflect the fluctuation of the operating voltage; the actual operating current change curve refers to the function curve of the operating current of the preset electronic components changing with time, which is used to reflect the dynamic characteristics of the operating current.

[0034] Specifically, first, the maintenance system arranges the collected discrete data points in time sequence. Then, the maintenance system uses a data smoothing algorithm to eliminate sampling noise. Next, the maintenance system uses mathematical methods such as cubic spline interpolation to fit the data points to generate a continuous change curve. The maintenance system will consider the time correlation of the data and select an appropriate curve fitting method to ensure that the generated change curve can accurately reflect the change trend of the parameters over time. For data with mutation points, the maintenance system will specifically mark these positions and retain them when generating the change curve for subsequent analysis.

[0035] S103. Compare the actual operating temperature change curve with the preset operating temperature change curve, the actual operating voltage change curve with the preset operating voltage change curve, and the actual operating current change curve with the preset operating current change curve respectively to obtain the temperature curve deviation, the voltage curve deviation, and the current curve deviation; Among them, the preset operating temperature change curve refers to the standard temperature change curve of the preset electronic components when they are operating normally and stored in advance; the preset operating voltage change curve refers to the standard voltage change curve of the preset electronic components when they are operating normally and stored in advance; the preset operating current change curve refers to the standard current change curve of the preset electronic components when they are operating normally and stored in advance; the curve deviation refers to the degree of difference between the actual parameter change curve and the preset parameter change curve, which can be measured by indicators such as the Euclidean distance and the correlation coefficient.

[0036] Specifically, first, the maintenance system performs time alignment and amplitude normalization processing on the actual parameter change curve and the preset parameter change curve. Then, the maintenance system uses the Fourier transform to convert the time-domain curve into a frequency-domain curve and extracts the spectral features. The maintenance system calculates the Euclidean distance between the actual parameter change curve and the preset parameter change curve in terms of frequency-domain features as a quantitative index of the curve deviation. At the same time, the maintenance system will also analyze the deviation characteristics of the actual parameter change curve and the preset parameter change curve on different time scales, including short-term fluctuation deviation, medium-term trend deviation, and long-term accumulation deviation.

[0037] Optionally, generally, the actual working temperature change curve is compared with the preset working temperature change curve, the actual working voltage change curve is compared with the preset working voltage change curve, and the actual working current change curve is compared with the preset working current change curve respectively to obtain the temperature curve deviation, voltage curve deviation, and current curve deviation. This can be achieved in the following ways, which are not limited herein: Perform Fourier transforms on the actual working temperature change curve, the actual working voltage change curve, and the actual working current change curve respectively to obtain the corresponding spectral features; perform Fourier transforms on the preset working temperature change curve, the preset working voltage change curve, and the preset working current change curve respectively to obtain the corresponding standard spectral features; calculate the Euclidean distance between the spectral features and the corresponding standard spectral features to obtain the temperature curve deviation, voltage curve deviation, and current curve deviation.

[0038] S104. When the temperature curve deviation exceeds the preset temperature deviation, the voltage curve deviation exceeds the preset voltage deviation, and / or the current curve deviation exceeds the preset current deviation, determine the abnormal type of the train control equipment. The abnormal type includes the working temperature, the working voltage, and / or the working current. Among them, the preset temperature deviation refers to the maximum range value that is preset to allow deviation from the preset working temperature change curve, usually determined based on the thermal performance requirements of the equipment; the preset voltage deviation refers to the maximum range value that is preset to allow deviation from the preset voltage temperature change curve, usually determined based on the voltage tolerance of the equipment; the preset current deviation refers to the maximum range value that is preset to allow deviation from the preset working voltage change curve, usually determined based on the rated power of the equipment; the abnormal type refers to the specific abnormal parameter category, which can be a single parameter abnormality or a multi-parameter combination abnormality.

[0039] Specifically, the maintenance system compares the temperature curve deviation with the preset temperature deviation, compares the voltage curve deviation with the preset voltage deviation, and compares the current curve deviation with the preset current deviation. When the temperature curve deviation exceeds the preset temperature deviation, determine that the abnormal type is the working temperature; when the voltage curve deviation exceeds the preset voltage deviation, determine that the abnormal type is the working voltage; when the current curve deviation exceeds the preset current deviation, determine that the abnormal type is the working current. The abnormal type can be one or more.

[0040] S105. Retrieve multiple fault prediction results corresponding to the abnormal type in the preset fault mode library. The preset fault mode library includes the corresponding relationship between the abnormal type and the fault prediction results. Among them, the preset fault mode library refers to a pre-established database containing various fault mode information; the fault prediction result refers to the possible causes of faults determined based on the abnormal type; the corresponding relationship refers to the mapping rules between the abnormal type and the fault prediction result, including various relationship modes such as one-to-one and one-to-many.

[0041] The following lists an example of a preset fault mode library: The maintenance system searches in the preset fault mode library according to the specific abnormal type and obtains multiple fault prediction results corresponding to the abnormal type. For example, if the abnormal type is the working temperature, the fault prediction results may include various situations such as processor overload, abnormal ambient temperature, decreased efficiency of the cooling fan, temperature sensor failure, and aging of the thermal conductive material.

[0042] S106. Based on the multiple fault prediction results, determine the maintenance strategy for the train control equipment.

[0043] Among them, the maintenance strategy refers to the maintenance plan formulated for the fault prediction result, including specific contents such as the maintenance time, maintenance method, and maintenance components.

[0044] Specifically, first, the maintenance system generates a corresponding maintenance plan according to the fault prediction result and in combination with historical data. Other ways of generating the maintenance plan are not limited here. Then, the maintenance system integrates all the fault prediction results and the corresponding maintenance plans to generate the maintenance strategy for the train control equipment. Continuing with the example in step S105: 1. Maintenance plan for processor overload: Maintenance time: Immediate maintenance; Maintenance method: Analyze the CPU usage rate; check the running status of processes; restart the system if necessary; Maintenance components: Processor and related control circuits; Required tools: System diagnostic tools, performance monitoring software; Priority: High; 2. Maintenance plan for abnormal ambient temperature: Maintenance time: Within 24 hours; Maintenance method: Adjust the ventilation facilities; Maintenance components: Ventilation equipment; Required tools: Thermometer, anemometer; Priority: Medium; 3. Maintenance plan for decreased efficiency of the cooling fan: Maintenance time: Within 48 hours; Maintenance method: Clean the cooling fan and the heat sink; test the rotation speed of the cooling fan; replace the cooling fan if necessary; Maintenance parts: Cooling fan, heat sink; Required tools: Cleaning tools, tachometer, spare fan; Priority: Medium; 4. Maintenance plan for temperature sensor failure: Maintenance timing: Immediate maintenance; Maintenance method: Test temperature sensor data; Check signal transmission; Replace temperature sensor; Maintenance parts: Temperature sensor, signal wire; Required tools: Multimeter, temperature calibrator; Priority: High; 5. Maintenance plan for aging thermal conductive material: Maintenance timing: Within one week; Maintenance method: Disassemble the cooling system; Remove the old thermal conductive material; Reapply thermal grease; Maintenance parts: Thermal grease, heat sink; Required tools: Cleaner, thermal grease, screwdriver set; Priority: Low; 6. Comprehensive maintenance strategy: First, execute high-priority maintenance items (processor overload, temperature sensor detection), then handle medium-priority maintenance items (ambient temperature, cooling fan), and finally arrange low-priority maintenance items (thermal conductive material replacement).

[0045] By adopting the above technical solution, the maintenance system can collect the working temperature, working voltage, and working current of the preset electronic components in the train control equipment in real time to generate the actual parameter change curve, and compare and analyze it with the preset parameter change curve, so as to timely detect the abnormal operation of the train control equipment, automatically identify the type of abnormality, and retrieve the corresponding fault prediction result in the preset fault mode library, thereby formulating a targeted maintenance strategy. This method based on multi-dimensional parameter monitoring and intelligent analysis can detect potential faults earlier than the traditional regular maintenance method, improve the accuracy of fault prediction, achieve preventive maintenance, effectively reduce the equipment failure rate, and enhance the reliability and safety of the train control equipment operation.

[0046] The following further describes the more specific process of the method provided in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of the intelligent maintenance method for train control equipment in the embodiment of the present application.

[0047] S201. Collect the working temperature, working voltage, and working current of the preset electronic components in the train control equipment within the preset time window; Specifically, reference can be made to step S101, which will not be elaborated here.

[0048] S202. Record the system startup information, system stop information, function call information, and error prompt information of the train control equipment in real time; Among them, the system startup information refers to various information generated during the startup process of the train control equipment, including startup time, startup sequence, module loading status, etc.; the system stop information refers to various information generated when the train control equipment shuts down or stops running, including stop time, stop reason, stop process, etc.; the function call information refers to the function call records of each module during the operation of the train control equipment, including call time, call parameters, return results, etc.; the error prompt information refers to various abnormal information and error information that occur during the operation of the train control equipment, including error code, error description, error level, etc.

[0049] Specifically, the maintenance system monitors the operation status of the train control equipment throughout the process through the log recording module. For the startup process of the train control equipment, record the initialization sequence, loading time, and startup result of each module; for the operation process of the train control equipment, record the call situation of each module, including call timestamp, caller, callee, call parameters, execution duration, return result, etc.; for the stop process of the train control equipment, record the trigger reason for the stop, stop time, module shutdown sequence, etc.

[0050] S203. Generate the software operation log information flow of the train control equipment based on the system startup information, system stop information, function call information, and error prompt information; Among them, the software operation log information flow refers to the record flow of the operation status of the train control equipment organized in chronological order, which is used to reflect the complete process of the train control equipment operation.

[0051] Specifically, first, the maintenance system standardizes all the collected information and unifies the format. Then, the maintenance system integrates the information from different sources into a unified information flow in chronological order and establishes a multi-dimensional index to support querying in multiple dimensions such as time, type, and module. The maintenance system analyzes the information flow, identifies the key event sequences, and establishes the association relationships between events.

[0052] S204. If the occurrence frequency of the target error prompt information of the target module within the preset time period exceeds the preset frequency threshold, mark the target module as an abnormal module; Among them, the preset time period refers to the predefined statistical analysis time interval, which can be at the minute, hour, or day level; the target module refers to the specific module being monitored; the target error prompt information refers to the error prompt information of the target module; the preset frequency threshold refers to the maximum frequency allowed for the error prompt information to appear; the occurrence frequency refers to the number of times the target error prompt information appears; marking as an abnormal module refers to the special identification of the problem module by the maintenance system.

[0053] Specifically, first, the maintenance system classifies and counts the error prompt messages by module, and calculates the occurrence frequency of the error prompt messages of each module within a preset time period. When counting, the severity of the error prompt messages is considered, and different weight calculations are used for error prompt messages of different levels. The maintenance system compares the calculated occurrence frequency of the error prompt messages with a preset frequency threshold, and the setting of the preset frequency threshold takes into account the importance of the module and historical operation experience. When the occurrence frequency of the target error prompt message of the target module exceeds the preset frequency threshold, the maintenance system immediately marks the target module as an abnormal module.

[0054] S205. According to the timestamp information of the target error prompt message, perform a timing analysis on the target error prompt message to establish a fault propagation chain; according to the fault propagation chain, determine the root cause of the fault; Among them, the timestamp information refers to the precise time point when the target error prompt message occurs, including detailed information such as year, month, day, hour, minute, second, and millisecond; the timing analysis refers to the correlation analysis of the target error prompt message in chronological order; the fault propagation chain refers to the causal relationship chain that describes how the fault spreads from one module to other modules; the root cause of the fault refers to the initial cause or trigger point that causes a series of faults; the causal relationship refers to the influence and dependency relationship between faults.

[0055] Specifically, first, the maintenance system extracts the timestamp information of all target error prompt messages and establishes an error event sequence in chronological order. The maintenance system uses a time series data mining algorithm to analyze the time correlation between error events and identify error sequences with significant time series patterns. Based on the time series association rules, the maintenance system constructs a directed graph of fault propagation, where the nodes represent error events and the edges represent propagation relationships. The maintenance system calculates the time delay and conditional probability between error events to determine the possible paths of fault propagation. Through backtracking analysis, the maintenance system locates the earliest independent fault event and verifies its possibility as the root cause of the fault. The maintenance system also considers the dependency relationship and data flow direction between modules to assist in judging the reasonableness of fault propagation.

[0056] S206. Establish a data flow diagram between the abnormal module and other modules. The data flow diagram includes the sender, sending time, receiver, receiving time, and transmission path of the data packet; detect the packet loss rate, retransmission rate, and data error rate of the data packet during the transmission process; based on the packet loss rate, the retransmission rate, and the data error rate, judge the communication quality between the abnormal module and the other modules; optimize the network nodes with communication quality lower than the preset quality threshold; Among them, a data flow diagram refers to a network topology diagram that describes the data transmission relationship between modules; a data packet refers to an information unit transmitted between modules; a packet loss rate refers to the ratio of the number of lost data packets to the total number of transmitted data packets during the transmission process; a retransmission rate refers to the ratio of the number of data packets that need to be retransmitted to the total number of transmitted data packets; a data error rate refers to the ratio of the number of data packets with errors during the transmission process to the total number of received data packets; communication quality refers to the reliability and efficiency of data transmission between modules; a preset quality threshold refers to a predefined minimum communication quality standard; network node optimization refers to adjustment measures to improve communication performance.

[0057] Specifically, first, the maintenance system collects the communication data between each module through the network monitoring module, including the detailed transmission records of data packets. The maintenance system constructs a complete data flow diagram and records the complete transmission process of each data packet, including information such as the sending time, receiving time, and transmission path. The maintenance system calculates the performance indicators of each communication link in real time, including the average transmission delay, instantaneous packet loss rate, cumulative retransmission rate, etc. When it is found that the performance indicator of a certain communication link is lower than the preset performance indicator threshold, the maintenance system will start an adaptive optimization strategy, such as adjusting the size of the transmission buffer, updating the routing strategy, adjusting the size of the data packet, etc. The maintenance system continuously monitors the optimization effect and makes dynamic adjustments as needed.

[0058] S207. Based on the operating temperature, the operating voltage, and the operating current, determine the actual operating temperature change curve, the actual operating voltage change curve, and the actual operating current change curve of the preset electronic components in the train control equipment within the preset time window; Specifically, reference can be made to step S102, which will not be elaborated here.

[0059] S208. Extract the temperature curve slope, temperature fluctuation characteristics, and temperature mutation characteristics of the actual operating temperature change curve, extract the voltage curve slope, voltage fluctuation characteristics, and voltage mutation characteristics of the actual operating voltage change curve, and extract the current curve slope, current fluctuation characteristics, and current mutation characteristics of the actual operating current change curve; Among them, the curve slope refers to the change rate of the parameter; the fluctuation characteristics refer to the oscillation of the parameter near the mean value, including the fluctuation amplitude, fluctuation period, and fluctuation law; the mutation characteristics refer to the characteristics of the parameter changing rapidly and significantly, including the mutation amplitude, mutation duration, and mutation frequency.

[0060] Specifically, for the curve slope, the maintenance system preprocesses the curve, including denoising, smoothing, and normalization. Then, the maintenance system uses the difference method to calculate the slope of the curve at different time points and obtains the parameter change trend. For the fluctuation characteristics, the maintenance system uses the sliding window method to calculate local statistical characteristics, including variance, peak factor, waveform factor, etc., and uses the fast Fourier transform to analyze the spectral characteristics of the fluctuation. For the mutation characteristics, the maintenance system uses the wavelet transform method to locate the mutation points and calculate the amplitude and duration of the mutation.

[0061] S209. Determine the temperature change pattern of the preset electronic component according to the temperature curve slope, the temperature fluctuation characteristics, and the temperature mutation characteristics; Among them, the temperature change pattern refers to the typical law of the working temperature changing with time.

[0062] Specifically, the maintenance system matches the temperature curve slope, the temperature fluctuation characteristics, and the temperature mutation characteristics with the standard temperature change patterns in the typical pattern library and calculates the similarity scores. The maintenance system sorts the similarity scores from high to low and determines the most matching temperature change pattern.

[0063] S210. Determine the voltage change pattern of the preset electronic component according to the voltage curve slope, the voltage fluctuation characteristics, and the voltage mutation characteristics; Among them, the voltage change pattern refers to the typical law of the working voltage changing with time.

[0064] Specifically, the maintenance system matches the voltage curve slope, the voltage fluctuation characteristics, and the voltage mutation characteristics with the standard voltage change patterns in the typical pattern library and calculates the similarity scores. The maintenance system sorts the similarity scores from high to low and determines the most matching voltage change pattern.

[0065] S211. Determine the current change pattern of the preset electronic component according to the current curve slope, the current fluctuation characteristics, and the current mutation characteristics; Among them, the current change pattern refers to the typical law of the working current changing with time.

[0066] Specifically, the maintenance system matches the current curve slope, the current fluctuation characteristics, and the current mutation characteristics with the standard current change patterns in the typical pattern library and calculates the similarity scores. The maintenance system sorts the similarity scores from high to low and determines the most matching current change pattern.

[0067] S212. Establish a health state evaluation model for the preset electronic component based on the temperature change pattern, the voltage change pattern, and the current change pattern; Among them, the health state evaluation model refers to a mathematical model used to evaluate the operating state of a preset electronic component.

[0068] Specifically, first, the maintenance system constructs a multi-dimensional feature space and maps the temperature change pattern, voltage change pattern, and current change pattern into the feature space. The maintenance system uses machine learning methods, such as support vector machines or deep neural networks, to establish the mapping relationship between parameter features and health status. During the model training process, the maintenance system uses historical operation data and expert knowledge to optimize the parameters and ensures the generalization ability of the model through cross-validation. The maintenance system considers the coupling effect between parameters and establishes a parameter correlation matrix. The model outputs include evaluation results in multiple dimensions such as health index, failure risk level, and remaining service life. The maintenance system also establishes an adaptive update mechanism for the model to dynamically adjust the model parameters according to new operation data.

[0069] S213. Compare the actual working temperature change curve with the preset working temperature change curve, the actual working voltage change curve with the preset working voltage change curve, and the actual working current change curve with the preset working current change curve respectively to obtain the temperature curve deviation, voltage curve deviation, and current curve deviation. Specifically, reference can be made to step S103, which will not be elaborated here.

[0070] S214. When the temperature curve deviation exceeds the preset temperature deviation, the voltage curve deviation exceeds the preset voltage deviation, and / or the current curve deviation exceeds the preset current deviation, determine the abnormal type of the train control equipment, where the abnormal type includes the working temperature, the working voltage, and / or the working current. Specifically, reference can be made to step S104, which will not be elaborated here.

[0071] S215. According to the abnormal type, determine the corresponding abnormal curve slope, abnormal fluctuation characteristics, and abnormal mutation characteristics; retrieve the fault prediction results in the preset fault mode library whose relevance to the abnormal curve slope, the abnormal fluctuation characteristics, and the abnormal mutation characteristics exceeds the preset relevance threshold. Among them, the abnormal curve slope refers to the curve slope of the abnormal type; the abnormal fluctuation characteristics refer to the fluctuation characteristics of the abnormal type; the abnormal mutation characteristics refer to the mutation characteristics of the abnormal type; the preset relevance threshold is used to represent the standard value for judging the feature matching degree.

[0072] Specifically, first, the maintenance system uses the multi-dimensional feature analysis method to calculate the relevance between the abnormal features and each fault mode in the fault mode library. The relevance calculation uses various measurement methods such as cosine similarity and Euclidean distance, and the comprehensive relevance is obtained through weighted combination. The maintenance system sorts the fault modes whose relevance exceeds the preset relevance threshold to generate a list of possible fault prediction results. For each matching fault prediction result, the maintenance system analyzes its development trend and influence degree and provides a detailed feature matching analysis report.

[0073] S216. Retrieve multiple fault prediction results corresponding to this abnormal type in the preset fault mode library, where the preset fault mode library includes the correspondence between the abnormal type and the fault prediction results; Specifically, refer to step S105 for details and no further elaboration will be provided here.

[0074] S217. Determine the maintenance strategy of the train control equipment based on the multiple fault prediction results.

[0075] Specifically, refer to step S106 for details and no further elaboration will be provided here.

[0076] The maintenance system in the embodiment of the present invention application will be described from the perspective of hardware processing. Please refer to Figure 3 , which is a schematic structural diagram of an entity device of the maintenance system in the embodiment of the present application.

[0077] It should be noted that Figure 3 The structure of the maintenance system shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention.

[0078] As Figure 3 shown, the maintenance system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) 302 or the program loaded from the storage section 308 into the Random Access Memory (RAM) 303, such as executing the methods described in the above embodiments. In the RAM 303, various programs and data required for system operation are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. The Input / Output (I / O) interface 305 is also connected to the bus 304.

[0079] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD), an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface 305 as required. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 310 as required so that a computer program read from it can be installed into the storage section 308 as required.

[0080] Specifically, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are executed.

[0081] It should be noted that specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, device, or component.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block may occur in a different order from that marked in the accompanying drawings.

[0083] Specifically, the maintenance system of this embodiment includes a processor and a memory. A computer program is stored on the memory. When the computer program is executed by the processor, it implements the intelligent maintenance method for train control equipment provided in the above-mentioned embodiment.

[0084] On the other hand, the present invention also provides a computer-readable storage medium. This storage medium may be included in the maintenance system described in the above-mentioned embodiment; or it may exist separately without being assembled into the maintenance system. The above storage medium carries one or more computer programs. When the above one or more computer programs are executed by a processor of the maintenance system, the maintenance system is enabled to implement the intelligent maintenance method for train control equipment provided in the above-mentioned embodiment.

[0085] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application.

[0086] As used in the above embodiments, depending on the context, the term "when..." can be interpreted to mean "if...", or "after...", or "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining...", or "in response to determining...", or "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0087] Those of ordinary skill in the art can understand all or part of the processes in the methods of the above embodiments. These processes can be completed by relevant hardware instructed by a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the above method embodiments. The foregoing storage medium includes: various media such as ROM or random access memory RAM, magnetic disk, or optical disc that can store program codes.

Claims

1. A train control equipment intelligent maintenance method, characterized in that: Applied to a maintenance system, the method comprises: Collect the operating temperature, operating voltage and operating current of the preset electronic components in the train control equipment within the preset time window; Based on the operating temperature, the operating voltage and the operating current, determining an actual operating temperature change curve, an actual operating voltage change curve and an actual operating current change curve of a preset electronic component in the train control device within the preset time window; Respectively comparing the actual working temperature change curve with the preset working temperature change curve, the actual working voltage change curve with the preset working voltage change curve, and the actual working current change curve with the preset working current change curve to obtain a temperature curve deviation, a voltage curve deviation, and a current curve deviation; When the temperature curve deviation exceeds a preset temperature deviation, the voltage curve deviation exceeds a preset voltage deviation, and / or the current curve deviation exceeds a preset current deviation, determining an abnormality type of the train control device, the abnormality type including the operating temperature, the operating voltage, and / or the operating current; Retrieving a plurality of fault prediction results corresponding to the abnormal type in a preset fault mode library, wherein the preset fault mode library includes a correspondence between the abnormal type and the fault prediction results; Based on the multiple fault prediction results, a maintenance strategy for the train control device is determined.

2. The method according to claim 1, characterized in that The actual working temperature change curve is compared with the preset working temperature change curve, the actual working voltage change curve is compared with the preset working voltage change curve, and the actual working current change curve is compared with the preset working current change curve to obtain the temperature curve deviation, the voltage curve deviation and the current curve deviation, specifically including: Performing Fourier transformation on the actual working temperature change curve, the actual working voltage change curve, and the actual working current change curve respectively to obtain corresponding frequency spectrum characteristics; Performing Fourier transformation on the preset working temperature change curve, the preset working voltage change curve, and the preset working current change curve respectively to obtain corresponding standard frequency spectrum characteristics; The Euclidean distance between the frequency spectrum feature and the corresponding standard frequency spectrum feature is calculated to obtain the temperature curve deviation, the voltage curve deviation and the current curve deviation.

3. The method according to claim 1, characterized in that After the step of determining, based on the operating temperature, the operating voltage, and the operating current, an actual operating temperature change curve, an actual operating voltage change curve, and an actual operating current change curve of a preset electronic component in the train control device within the preset time window, the method further includes: Extracting the temperature curve slope, temperature fluctuation characteristics and temperature mutation characteristics of the actual working temperature change curve, extracting the voltage curve slope, voltage fluctuation characteristics and voltage mutation characteristics of the actual working voltage change curve, and extracting the current curve slope, current fluctuation characteristics and current mutation characteristics of the actual working current change curve; Determining a temperature change mode of the preset electronic component according to the temperature curve slope, the temperature fluctuation characteristics, and the temperature mutation characteristics; Determining a voltage variation mode of the preset electronic component according to the voltage curve slope, the voltage fluctuation characteristics, and the voltage mutation characteristics; Determining a current change mode of the preset electronic component according to the current curve slope, the current fluctuation characteristics, and the current mutation characteristics; A health status assessment model of the preset electronic component is established based on the temperature change pattern, the voltage change pattern and the current change pattern.

4. The method according to claim 3, characterized in that After the step of determining the abnormality type of the train control device when the temperature curve deviation exceeds a preset temperature deviation, the voltage curve deviation exceeds a preset voltage deviation, and / or the current curve deviation exceeds a preset current deviation, the method further includes: According to the abnormal type, determine the corresponding abnormal curve slope, abnormal fluctuation characteristics and abnormal mutation characteristics; The fault prediction results whose correlation with the abnormal curve slope, the abnormal fluctuation feature and the abnormal mutation feature exceeds a preset correlation threshold are retrieved from the preset fault mode library.

5. The method according to claim 1, characterized in that After the step of collecting the operating temperature, the operating voltage and the operating current of the preset electronic components in the train control device within the preset time window, the method further includes: Recording system startup information, system stop information, function call information and error prompt information of the train control device in real time; Based on the system startup information, the system stop information, the function call information and the error prompt information, a software operation log information flow of the train control device is generated.

6. The method according to claim 5, characterized in that After the step of recording the system startup information, system stop information, function call information and error prompt information of the train control device in real time, the method further includes: If the frequency of occurrence of target error prompt information of the target module within a preset time period exceeds a preset frequency threshold, the target module is marked as an abnormal module; According to the timestamp information of the target error prompt information, performing a timing analysis on the target error prompt information to establish a fault propagation chain; According to the fault propagation chain, the root cause of the fault is determined.

7. The method according to claim 6, characterized in that After the step of marking the target module as an abnormal module if the frequency of occurrence of the target error prompt information of the target module within the preset time period exceeds a preset frequency threshold, the method further includes: Establishing a data flow diagram of the abnormal module and other modules, wherein the data flow diagram includes a sender, a sending time, a receiver, a receiving time, and a transmission path of a data packet; Detecting the packet loss rate, retransmission rate and data error rate of the data packet during transmission; Based on the packet loss rate, the retransmission rate and the data error rate, determining the communication quality between the abnormal module and the other modules; The network nodes whose communication quality is lower than a preset quality threshold are optimized.

8. A maintenance system, characterized in that: The maintenance system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the maintenance system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the maintenance system, the maintenance system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a maintenance system, the maintenance system is caused to execute the method according to any one of claims 1 to 7.

Images