Methods, devices, equipment and storage media for detecting air brake failures in subway vehicles

Abstract

This invention relates to a method, apparatus, equipment, and storage medium for detecting air brake faults in subway vehicles, belonging to the field of fault diagnosis technology. The method involves: acquiring in-stock data of subway vehicles based on in-stock screening rules; setting the inflation / deflation cycle duration T under normal operating conditions for the subway train; extracting and processing in-stock data for duration T to obtain a training dataset; dividing the data in the training dataset into normal data and fault data based on the subway vehicle's operation and maintenance data to establish an air brake fault detection model; acquiring the data to be detected during subway vehicle operation; importing the data to be detected into the air brake fault detection model to obtain the detection results. This method achieves multi-dimensional detection of subway vehicles through multi-dimensional in-stock data, effectively improving the accuracy of fault detection in the air brake system of subway vehicles.

Description

Technical Field

[0001] This invention belongs to the field of fault diagnosis technology, and in particular relates to a method, device, equipment and storage medium for detecting air brake faults in subway vehicles. Background Technology

[0002] Subway vehicle braking systems are mainly divided into two types: electric braking and air braking. When electric braking force is insufficient or the train is running at low speeds, air braking serves as the primary braking force to stop the train. The main principle of air braking is to use high-pressure air to push the brake cylinder piston, causing the brake shoes to press against the wheels and generate braking force. If there is a leak in the components of the air pipeline, the system air pressure will drop, thus affecting the train's braking performance.

[0003] Identifying and detecting air leaks is crucial for troubleshooting. Existing technologies have explored methods for detecting faults in air braking systems. For example, Chinese invention patent CN110293949B provides a method for detecting minor air brake system faults in high-speed trains. This method uses pressure measurement data generated during normal operation of the high-speed train to establish a mathematical model. By comparing the statistical quantities of the data to be tested with those in the mathematical model, it determines whether a fault exists in the braking system during braking application, braking holding, braking release, or traction. Based on the judgment results, it can analyze various fault causes, such as relay valve failure, brake cylinder pressure sensor failure, or minor pipeline leakage. However, this patent requires statistical calculations for both the data to be tested and normal data. The mathematical model application is very cumbersome, and this cumbersome calculation process can easily lead to data calculation errors and incorrect detection results. Furthermore, this patent does not detail the working conditions of the air compressor and the pressure data of the main air pipe during fault detection, resulting in a very limited detection dimension and potentially leading to incorrect judgments about the state of the air braking system by operators.

[0004] Therefore, how to solve the problem of limited detection dimensions in current air braking system fault detection methods is an urgent technical problem that needs to be solved. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method, device, equipment, and storage medium for detecting air brake faults in subway vehicles. By utilizing multi-dimensional in-stock data, it enables multi-dimensional detection of subway vehicles, effectively improving the accuracy of fault detection in the air brake system of subway vehicles.

[0006] In a first aspect, the present invention provides a method for detecting air brake failures in subway vehicles, comprising:

[0007] S1. Obtain the inventory data of subway vehicles according to the inventory screening rules. The inventory data includes the working time data of the air compressor, the working status data of the air compressor, the pressure data of the main air duct, and the idle time data of the relay valve.

[0008] S2, for data in the database, set the inflation / deflation cycle duration T for subway trains under normal operating conditions;

[0009] S3, determine whether the duration of the data in the database is greater than the duration of the inflation / deflation cycle T; if not, return to step S1 to retrieve the data in the database again;

[0010] S4. If the duration of the data in the database is greater than the duration of the inflation / deflation cycle T, then extract the data in the database for the duration of the inflation / deflation cycle T and process it to obtain the training dataset.

[0011] S5. Based on the operation and maintenance data of subway vehicles, the data in the training dataset is divided into normal data and fault data to establish a fault detection model for air brakes of subway vehicles;

[0012] S6: Obtain the test data of the subway vehicle operation, import the test data into the subway vehicle air brake fault detection model, and obtain the test results.

[0013] This technical solution enables multi-dimensional detection of subway vehicles, effectively improving the reliability of the air braking system of subway vehicles, ensuring the safe operation of subway vehicles, and providing passengers with a comfortable and safe travel experience.

[0014] In some embodiments, in step S1, the database filtering rules are determined by database filtering logic, and data that meets all the database filtering criteria is determined to be in-database data; the database filtering logic includes:

[0015] Platform number determination logic: The current platform number is equal to 0, and the next platform number is greater than or equal to the total number of platforms on the subway line or the next platform number is equal to 0;

[0016] Time judgment logic: The time range is within the subway's non-operational hours;

[0017] Vehicle speed determination logic: The vehicle speed is 0, and the duration of the 0 speed exceeds a set time. This technical solution uses the above-mentioned database filtering rules to select accurate data from the database, thereby improving the accuracy of model training.

[0018] In some embodiments, the vehicle speed determination logic is set to a duration of 30 minutes.

[0019] In some embodiments, step S4 includes the following steps:

[0020] S41, calculate the air compressor working time F1, and the duration of the air charging / discharging cycle T.

[0021] S42, divide the air compressor working status data within the air charging / discharging cycle duration T into sub-segments according to whether the air compressor is charging or discharging, obtain the longest sub-segment with the longest duration, and calculate the pressure drop rate F2 of the longest sub-segment;

[0022] S43, extract the first sequence data of the inflation / deflation cycle duration T from the main duct pressure data, copy the first sequence data to obtain the second sequence data, perform a fast Fourier transform on the second sequence data to obtain the third sequence data, and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data.

[0023] S44, the idle time F4 of the relay valve within the duration T of the gas charging / discharging cycle;

[0024] S45. Based on the air compressor working time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idle time of the relay valve F4 obtained in steps S41-S44, the training dataset is obtained.

[0025] In some embodiments, step S43 specifically involves: denoting the total length of the first sequence data as L, copying the first sequence data n times to obtain a second sequence data of length n*L; performing a Fast Fourier Transform on the second data series using L as the sampling frequency to obtain a third sequence data; calculating the amplitude of the third sequence data, and extracting the frequency F3 corresponding to the maximum amplitude of the third sequence data. This technical solution uses the frequency F3 corresponding to the maximum amplitude of the third sequence data as a characteristic parameter of the main duct pressure data, reflecting the variation law of the main duct pressure, which helps in analyzing whether there are any abnormalities in the main duct pressure.

[0026] Secondly, the present invention provides a subway vehicle air brake fault detection device, employing the aforementioned subway vehicle air brake fault detection method, the device comprising:

[0027] The data acquisition unit is used to acquire the inventory data of subway trains;

[0028] The control unit, which is connected to the data acquisition unit, is used to set the inflation / deflation cycle duration T of the subway train under normal operating conditions.

[0029] The judgment unit, which is communicatively connected to the data acquisition unit and the control unit, is used to determine whether the duration of the data in the database is greater than the duration of the inflation / deflation cycle T.

[0030] The data processing unit, which is communicatively connected to the data acquisition unit and the judgment unit, is used to extract and process the data in the database for a duration of T to obtain the training dataset.

[0031] The data analysis unit, which is connected to the data processing unit, is used to divide the data in the training dataset into normal data and fault data based on the operation and maintenance data of the subway vehicles, and to establish a fault detection model for the air brakes of the subway vehicles.

[0032] In some embodiments, in step S5, the subway vehicle air brake fault detection model is established using the random forest algorithm.

[0033] In some embodiments, the subway vehicle air brake fault detection device further includes a data verification unit, which is communicatively connected to the data analysis unit, for importing the data to be detected into the subway vehicle air brake fault detection model to obtain the detection results.

[0034] Thirdly, the present invention provides a subway vehicle air brake fault detection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the subway vehicle air brake fault detection method of the first aspect described above.

[0035] Fourthly, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the subway vehicle air brake fault detection method of the first aspect described above.

[0036] Based on the above solutions, the subway vehicle air brake fault detection method, device, equipment, and storage medium in this embodiment of the invention can achieve multi-dimensional detection of subway vehicles through multi-dimensional in-database data, effectively improving the accuracy of fault detection of the subway vehicle air brake system; it can achieve automatic fault identification by using the subway vehicle air brake fault detection model, improving the fault detection efficiency and accuracy; and it can ensure the safe operation of subway vehicles and provide passengers with a comfortable and safe travel experience.

[0037] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0038] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0039] Figure 1 This is a flowchart of the subway vehicle air brake fault detection method in an embodiment of the present invention;

[0040] Figure 2 This is a structural block diagram of the subway vehicle air brake fault detection device in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the hardware structure of the air brake fault detection device for subway vehicles in an embodiment of the present invention;

[0042] Figure 4 This is a schematic diagram showing the running time of the air compressors in two carriages of a subway train in Embodiment 1 of the present invention;

[0043] Figure 5 This is a schematic diagram of the first sequence data of length L in Embodiment 1 of the present invention;

[0044] Figure 6 This is a schematic diagram of the third sequence data in Embodiment 1 of the present invention;

[0045] Figure 7 This is a schematic diagram of the verification results of the third sequence data corresponding to the data to be detected in Embodiment 1 of the present invention;

[0046] Figure 8 This is a schematic diagram showing the idle time of relay valves in different carriages of a subway train in Embodiment 1 of the present invention.

[0047] In the picture:

[0048] 101. Data acquisition unit; 102. Control unit; 103. Judgment unit; 104. Data processing unit; 105. Data analysis unit; 106. Data verification unit;

[0049] 201. Processor; 202. Memory; 203. Communication interface; 204. Bus. Detailed Implementation

[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0051] In the description of this invention, it should be understood that the terms "center", "lateral", "longitudinal", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0052] The terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first," "second," or "third" may explicitly or implicitly include one or more of that feature.

[0053] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0054] The terms “system,” “unit,” and “module” used in this article are methods for distinguishing different components, elements, parts, sections, or assemblies at different levels. These terms may be replaced by other expressions that achieve the same purpose.

[0055] like Figures 1-8 As shown, in one embodiment of the method, apparatus, equipment, and storage medium for detecting air brake faults in subway vehicles according to the present invention, as follows: Figure 1 As shown, the method for detecting air brake failures in subway vehicles includes the following steps:

[0056] S1. Obtain the inventory data of subway vehicles according to the inventory screening rules. The inventory data includes the working time data of the air compressor, the working status data of the air compressor, the pressure data of the main air duct, and the idle time data of the relay valve.

[0057] S2, for data in the database, set the inflation / deflation cycle duration T for subway trains under normal operating conditions;

[0058] S3, determine whether the duration of the data in the database is greater than the duration of the inflation / deflation cycle T; if not, return to step S1 to retrieve the data in the database again;

[0059] S4. If the duration of the data in the database is greater than the duration of the inflation / deflation cycle T, then extract the data in the database for the duration of the inflation / deflation cycle T and process it to obtain the training dataset.

[0060] S5. Based on the operation and maintenance data of subway vehicles, the data in the training dataset is divided into normal data and fault data to establish a fault detection model for air brakes of subway vehicles;

[0061] S6: Obtain the test data of the subway vehicle operation, import the test data into the subway vehicle air brake fault detection model, and obtain the test results.

[0062] In the above illustrative embodiment, step S1 of the subway vehicle air brake fault detection method reduces interference from vehicle operation data and improves data utilization by utilizing multi-dimensional stored data; step S2 dynamically adjusts the inflation / deflation cycle duration T according to the actual operating conditions of the subway vehicle to avoid data redundancy or insufficiency; step S3 ensures that the stored data meets the working duration within a cycle by judging the duration of the stored data, thus improving data representativeness; step S4 processes the stored data within a cycle to obtain a training dataset, preparing for the establishment of a mathematical model; step S5 provides a reference standard for model training by dividing the data in the training data into normal data and fault data; step S6 verifies the data to be detected using the detection model, determines the cause of the subway vehicle fault based on the detection results, and uses the subway vehicle air brake fault detection model to achieve automatic fault identification, improving fault detection efficiency and accuracy. In summary, the subway vehicle air brake fault detection method in this embodiment can achieve multi-dimensional detection of subway vehicles, effectively improve the reliability of the subway vehicle air brake system, ensure the safe operation of subway vehicles, and provide passengers with a comfortable and safe travel experience.

[0063] It should be noted that the inflation / deflation cycle time T of a subway train under normal operating conditions is set based on the design of the braking equipment or on the experience of engineers.

[0064] In some embodiments, such as Figure 1 As shown, the in-database filtering rules are determined by the in-database filtering logic. Data that meets all the in-database filtering criteria is considered in-database data. The in-database filtering logic includes:

[0065] Platform number determination logic: The current platform number is equal to 0, and the next platform number is greater than or equal to the total number of platforms on the subway line or the next platform number is equal to 0;

[0066] Time judgment logic: The time range is within the subway's non-operational hours;

[0067] Vehicle speed determination logic: The vehicle speed is 0, and the duration of the 0 speed exceeds the set duration.

[0068] By using the above-mentioned in-database filtering rules, accurate in-database data can be selected, thereby improving the accuracy of model training.

[0069] Furthermore, such as Figure 1 As shown, the vehicle speed determination logic is set to a duration of 30 minutes. It should be noted that the duration set in this embodiment can be determined based on the engineer's experience; 30 minutes is only the time used in this embodiment and can be changed to other times.

[0070] In some embodiments, such as Figure 1 As shown, step S4 includes the following steps:

[0071] S41, calculate the air compressor working time F1, and the duration of the air charging / discharging cycle T.

[0072] S42, divide the air compressor working status data within the air charging / discharging cycle duration T into sub-segments according to whether the air compressor is charging or discharging, obtain the longest sub-segment with the longest duration, and calculate the pressure drop rate F2 of the longest sub-segment;

[0073] S43, extract the first sequence data of the inflation / deflation cycle duration T from the main duct pressure data, copy the first sequence data to obtain the second sequence data, perform a fast Fourier transform on the second sequence data to obtain the third sequence data, and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data.

[0074] S44, the idle time F4 of the relay valve within the statistical duration T;

[0075] S45. Based on the air compressor working time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idle time of the relay valve F4 obtained in steps S41-S44, the training dataset is obtained.

[0076] In the above illustrative embodiment, four characteristic parameters—air compressor operating time F1, pressure drop rate of the longest segment F2, frequency corresponding to the maximum amplitude F3, and idle time of the relay valve F4—are used as training datasets. This provides multi-dimensional data for fault detection of the air braking system of subway vehicles, making the fault detection results more accurate. Among them, air compressor operating time F1 reflects the performance of the air compressor, pressure drop rate of the longest segment F2 and frequency corresponding to the maximum amplitude F3 reflect the condition of the main air duct, and idle time of the relay valve F4 reflects the performance of the relay valve.

[0077] It should be noted that, in step S6, when verifying the data to be tested using the detection model, if the air compressor operating time F1 corresponding to the data to be tested is abnormal, it indicates that the air compressor performance of the subway car corresponding to the data to be tested is malfunctioning; if the pressure drop rate F2 of the longest segment or the frequency F3 corresponding to the largest amplitude value in the data to be tested is abnormal, it indicates that the main air duct of the subway car corresponding to the data to be tested is leaking; if the idle time F4 of the relay valve corresponding to the data to be tested is abnormal, it indicates that the relay valve of the subway car corresponding to the data to be tested is stuck. Staff can determine the fault condition of the subway car based on the analysis of the detection results in this embodiment.

[0078] In some embodiments, such as Figure 1As shown, step S43 specifically involves: Let the total length of the first sequence data be L; copy the first sequence data n times to obtain a second sequence data of length n*L; perform a Fast Fourier Transform on the second data series using L as the sampling frequency to obtain a third sequence data; calculate the amplitude of the third sequence data and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data. In this embodiment, by copying the first sequence data and performing a Fast Fourier Transform, the time-domain signal is converted into a frequency-domain signal, thereby eliminating noise and interference in the signal and improving the signal quality and stability; by extracting the frequency F3 corresponding to the maximum amplitude of the third sequence data as a characteristic parameter of the main duct pressure data, the variation law of the main duct pressure is reflected, which helps to analyze whether there are any abnormalities in the main duct pressure.

[0079] In some embodiments, such as Figure 1 As shown, in step S5, the fault detection model for the air brake of the subway vehicle is established using the random forest algorithm.

[0080] It should be noted that the method for establishing a subway vehicle air brake fault detection model using the random forest algorithm is as follows: The air compressor operating time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idle time of the relay valve F4, obtained in steps S41-S44, are used as feature columns. Maintenance data is used as label columns. Normal or abnormal labels are added to the feature columns using the label columns to form a training dataset. By randomly sampling from the training dataset, m different sample datasets are constructed. Based on these sample datasets, m different decision tree models are built to form the subway vehicle air brake fault detection model. The data to be detected is imported into the subway vehicle air brake fault detection model, and the detection results are obtained based on the voting results of the decision tree models.

[0081] like Figure 2 As shown, this embodiment also provides a subway vehicle air brake fault detection device, which employs the above-described subway vehicle air brake fault detection method. The device includes:

[0082] Data acquisition unit 101 is used to acquire the inventory data of subway trains;

[0083] The control unit 102 is communicatively connected to the data acquisition unit 101 and is used to set the cycle duration T of the subway train under normal operating conditions.

[0084] The judgment unit 103 is communicatively connected to the data acquisition unit 101 and the control unit 102, and is used to determine whether the duration of the data in the database is greater than the duration T.

[0085] The data processing unit 104 is communicatively connected to the data acquisition unit 101 and the judgment unit 103, respectively, and is used to extract and process the data in the database for a duration of T to obtain the training dataset.

[0086] The data analysis unit 105, which is connected to the data processing unit 104, is used to divide the data in the training dataset into normal data and fault data based on the operation and maintenance data of the subway vehicles, and to establish a fault detection model for the air brakes of the subway vehicles.

[0087] In some embodiments, such as Figure 2 As shown, the subway vehicle air brake fault detection device also includes a data verification unit 106, which is communicatively connected to the data analysis unit 105, and is used to import the data to be detected into the subway vehicle air brake fault detection model to obtain the detection results.

[0088] In addition, combined Figure 1 The method for detecting air brake failures in subway vehicles described in this application can be implemented using an air brake failure detection device for subway vehicles. Figure 3 This is a schematic diagram of the hardware structure of a subway vehicle air brake fault detection device according to an embodiment of this application.

[0089] The subway vehicle air brake fault detection device includes a memory 202, a processor 201, and a computer program stored in the memory and run on the processor 201. When the processor 201 executes the computer program, it implements the aforementioned subway vehicle air brake fault detection method.

[0090] Specifically, the processor 201 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0091] The memory 202 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 202 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 202 may include removable or non-removable (or fixed) media. Where appropriate, the memory 202 may be internal or external to a data processing device. In a particular embodiment, the memory 202 is non-volatile memory. In a particular embodiment, the memory 202 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0092] The memory 202 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 201.

[0093] The processor 201 reads and executes computer program instructions stored in the memory 202 to implement any of the subway vehicle air brake fault detection methods in the above embodiments.

[0094] In some embodiments, the subway vehicle air brake fault detection equipment may further include a communication interface 203 and a bus 204. For example, Figure 8 As shown, the processor 201, memory 202, and communication interface 203 are connected through bus 204 and complete communication with each other.

[0095] The communication interface 203 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication interface 203 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0096] Bus 204 includes hardware, software, or both, that couples together components of the metro vehicle air brake fault detection equipment. Bus 204 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, and Local Bus. For example, and not as a limitation, bus 204 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 204 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0097] The subway vehicle air brake fault detection equipment can execute the subway vehicle air brake fault detection method in this application embodiment based on the acquired in-store data, thereby achieving a combination of... Figure 1 A method for detecting air brake failures in subway vehicles is described.

[0098] Furthermore, in conjunction with the subway vehicle air brake fault detection method in the above embodiments, this application embodiment can provide a storage medium for implementation. This storage medium is a computer-readable storage medium storing computer program instructions; when these computer program instructions are executed by the processor 201, they implement any of the subway vehicle air brake fault detection methods in the above embodiments.

[0099] Example 1

[0100] Now combined Figures 1-8 Example 1 illustrates the method for detecting air brake failures in subway vehicles provided by the present invention:

[0101] S1. Based on the subway vehicle inventory screening rules, the original data of a certain subway train is screened to obtain the inventory data of the subway vehicle. The inventory data includes the working time data of the air compressor, the working status data of the air compressor, the pressure data of the main air duct, and the idle time data of the relay valve.

[0102] S2, For data in the database, set the inflation / deflation cycle time of subway trains under normal operating conditions to T=2h;

[0103] S3, Determine if the duration of the data in the database is greater than the duration of the inflation / deflation cycle T; if not, return to step S1 to retrieve the data in the database again;

[0104] S4. If the duration of the data in the database is greater than the duration of the inflation / deflation cycle T, then extract the data in the database for the duration of the inflation / deflation cycle T and process it to obtain the training dataset.

[0105] S41, calculate the air compressor operating time F1 of the charging / discharging cycle T, and the air compressor operating time of carriages Tc1 and Tc2 of the subway train as follows: Figure 4 As shown, their working time is all around 150 seconds;

[0106] S42, divide the air compressor working status data within the air charging / discharging cycle duration T into sub-segments according to whether the air compressor is charging or discharging, obtain the longest sub-segment with the longest duration, and calculate the pressure drop rate F2 of the longest sub-segment;

[0107] S43, extract the first sequence of data for the inflation / deflation cycle duration T from the main duct pressure data, such as... Figure 5 As shown, the total length of the first sequence data is denoted as L, where L = 14400. The first sequence data is copied n times to obtain a second sequence data of length n*L. Using L as the sampling frequency, a Fast Fourier Transform is performed on the second data series to obtain a third sequence data, as shown below. Figure 6 As shown, the maximum energy value corresponds to a frequency of 1; calculate the amplitude of the third sequence data, and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data;

[0108] S44, Calculate the idle time F4 of the relay valve within the duration T of the inflation / deflation cycle, such as... Figure 8 As shown, the average empty travel time of the 6 cars of the subway train fluctuates between 0.1s and 0.25s. In the figure, Tc1, Tc2, Mp1, Mp2, M1, and M2 are the car numbers of the 6 cars of the subway train.

[0109] S45. Based on the air compressor working time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idling time of the relay valve F4 obtained in steps S41-S44, the training dataset is obtained.

[0110] S5. Based on the subway vehicle operation and maintenance data, the data in the training dataset is divided into normal data and fault data. The air compressor working time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idle time of the relay valve F4 obtained in steps S41-S44 are used as feature columns, and the operation and maintenance data are used as label columns. Normal or abnormal labels are added to the feature columns through the label columns to form the training dataset. By randomly sampling from the training dataset, 100 different sample datasets are constructed. 100 different decision tree models are built based on the sample datasets to form the subway vehicle air brake fault detection model. The process of constructing the random forest algorithm using the learner is as follows:

[0111] 1) Set the number of learners n_estimators to 100 and construct 100 decision trees;

[0112] 2) Set random_state to 42;

[0113] 3) When boostrp is True, the sample is sampled with replacement to build the tree;

[0114] 4) The maximum depth of the tree is set to 5;

[0115] S6, acquire the detection data of the subway vehicle operation, import the detection data into the subway vehicle air brake fault detection model, and obtain the detection result based on the voting results of the decision tree model; in this embodiment, no abnormalities were detected in the air compressor working time F1, the pressure drop rate of the longest sub-segment F2, and the idle time of the relay valve F4, but an abnormality was found in the frequency F3 corresponding to the maximum amplitude value. Figure 7 As shown, the frequency corresponding to the largest amplitude value in the validation results of the data to be detected is 5, which exceeds the limit. Figure 6 Based on the maximum amplitude frequency, it can be determined that there is an air leakage fault in the main air duct of the train.

[0116] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0117] Through the description of several embodiments of the method, apparatus, equipment, and storage medium for detecting air brake faults in subway vehicles of the present invention, it can be seen that the embodiments of the method, apparatus, equipment, and storage medium for detecting air brake faults in subway vehicles of the present invention have at least one or more of the following advantages:

[0118] 1. The method for detecting air brake failures in subway vehicles provided by this invention enables multi-dimensional detection of subway vehicles through multi-dimensional in-database data, effectively improving the accuracy of fault detection in the air brake system of subway vehicles.

[0119] 2. The subway vehicle air brake fault detection method provided by the present invention utilizes a subway vehicle air brake fault detection model to achieve automatic fault identification, thereby improving the fault detection efficiency and accuracy.

[0120] 3. The subway vehicle air brake fault detection device provided by the present invention can effectively improve the reliability of the subway vehicle air brake system, ensure the safe operation of the subway vehicle, and provide passengers with a comfortable and safe travel experience.

[0121] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0122] 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 preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications and substitutions should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A method for detecting air brake failures in subway vehicles, characterized in that, Includes the following steps: S1. Obtain the inventory data of subway vehicles according to the inventory screening rules. The inventory data includes the working time data of the air compressor, the working status data of the air compressor, the pressure data of the main air duct, and the idle time data of the relay valve. S2, for data in the database, set the inflation / deflation cycle duration T for subway trains under normal operating conditions; S3, determine whether the duration of the data in the database is greater than the duration of the inflation / deflation cycle T; if not, return to step S1 to retrieve the data in the database again; S4, if the duration of the data in the database is longer than the duration of the inflation / deflation cycle T, then extract the data in the database for the duration of the inflation / deflation cycle T and process it to obtain the training dataset; step S4 includes the following sub-steps: S41, calculate the air compressor working time F1, and the duration of the air charging / discharging cycle T. S42, divide the air compressor working status data within the air charging / discharging cycle duration T into sub-segments according to whether the air compressor is charging or discharging, obtain the longest sub-segment with the longest duration, and calculate the pressure drop rate F2 of the longest sub-segment; S43, extract the first sequence data with a charging / discharging cycle duration T from the main duct pressure data, copy the first sequence data to obtain the second sequence data, perform a fast Fourier transform on the second sequence data to obtain the third sequence data, and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data; specifically: denote the total length of the first sequence data as L, copy the first sequence data n times to obtain the second sequence data with a length of n*L; perform a fast Fourier transform on the second sequence data with L as the sampling frequency to obtain the third sequence data; calculate the amplitude of the third sequence data, and extract the frequency F3 corresponding to the maximum amplitude of the third sequence data; S44, the idle time F4 of the relay valve within the duration T of the gas charging / discharging cycle; S45. Based on the air compressor working time F1, the pressure drop rate of the longest segment F2, the frequency corresponding to the largest amplitude F3, and the idling time of the relay valve F4 obtained in steps S41-S44, the training dataset is obtained. S5. Based on the operation and maintenance data of subway vehicles, the data in the training dataset is divided into normal data and fault data to establish a fault detection model for air brakes of subway vehicles; S6: Obtain the test data of the subway vehicle operation, import the test data into the subway vehicle air brake fault detection model, and obtain the test results.

2. The method for detecting air brake failures in subway vehicles according to claim 1, characterized in that, In step S1, the in-database filtering rules are judged by the in-database filtering logic, and data that meets all the in-database filtering logic rules is judged as in-database data; The in-stock filtering logic includes: Platform number determination logic: The current platform number is equal to 0, and the next platform number is greater than or equal to the total number of platforms on the subway line or the next platform number is equal to 0; Time judgment logic: The time range is within the subway's non-operational hours; Vehicle speed determination logic: The vehicle speed is 0, and the duration of the 0 speed exceeds the set duration.

3. The method for detecting air brake failures in subway vehicles according to claim 2, characterized in that, The speed determination logic is set to a duration of 30 minutes.

4. The method for detecting air brake failures in subway vehicles according to claim 1, characterized in that, In step S5, the air brake fault detection model for subway vehicles is established using the random forest algorithm.

5. A fault detection device for air brakes in subway vehicles, characterized in that, The device employing the subway vehicle air brake fault detection method as described in any one of claims 1-4 comprises: The data acquisition unit is used to acquire the inventory data of subway trains; The control unit, which is connected to the data acquisition unit, is used to set the inflation / deflation cycle duration T of the subway train under normal operating conditions. The judgment unit, which is communicatively connected to the data acquisition unit and the control unit, is used to determine whether the duration of the data in the database is greater than the duration of the inflation / deflation cycle T. The data processing unit, which is communicatively connected to the data acquisition unit and the judgment unit, is used to extract and process the data in the database for a duration of T to obtain the training dataset. The data analysis unit, which is connected to the data processing unit, is used to divide the data in the training dataset into normal data and fault data based on the operation and maintenance data of the subway vehicles, and to establish a fault detection model for the air brakes of the subway vehicles.

6. The subway vehicle air brake fault detection device according to claim 5, characterized in that, The subway vehicle air brake fault detection device also includes a data verification unit, which is connected to the data analysis unit to import the data to be detected into the subway vehicle air brake fault detection model and obtain the detection results.

7. A fault detection device for air brakes in subway vehicles, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for detecting air brake failures in subway vehicles as described in any one of claims 1-4.

8. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for detecting air brake failures in subway vehicles as described in any one of claims 1-4.

Images