Rail vehicle air supply system fault detection method and device

Abstract

The present invention is applicable to the technical field of rail vehicles, and provides a method and device for detecting faults in an air supply system of a rail vehicle. The method comprises: obtaining the working condition of the air supply system, which includes the use status of the air supply equipment and the air-using equipment; inputting the working condition of the air supply system as an input into a pre-trained first prediction model, outputting a predicted value of the total wind pressure change, and judging whether the air supply system has a fault based on the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system; if the air supply system has a fault, obtaining the abnormal characteristic quantity of the air supply system under the current working condition; inputting the working condition of the air supply system and the abnormal characteristic quantity of the air supply system under the current working condition into a pre-trained second prediction model, and outputting the fault location of the air supply system. The present invention can accurately and timely detect fault conditions of the air supply system.

Description

Technical Field

[0001] The present invention belongs to the technical field of rail vehicles, and in particular relates to a method and a device for detecting faults in an air supply system of a rail vehicle. Background Art

[0002] As more and more Fuxing EMUs are put into operation, the safe operation and daily inspection and maintenance of my country's high-speed rail will face huge challenges.

[0003] Rail vehicles are equipped with an air supply system, which is used to provide compressed air at a certain pressure to meet the air demand during train operation. During the operation of the train, the train air supply system needs to be monitored to ensure the safety of train operation. For example, when the air supply equipment and air use equipment fail, insufficient air supply and increased air consumption will occur, resulting in abnormal rates of increase and decrease of total air pressure. How to accurately and timely detect air supply system anomalies and leaks is an urgent problem that needs to be solved. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for detecting faults in an air supply system of a rail vehicle, so as to accurately and timely detect faults in the air supply system and ensure safe operation of the train.

[0005] A first aspect of an embodiment of the present invention provides a method for detecting a fault in an air supply system of a rail vehicle, comprising:

[0006] Obtain the working conditions of the air supply system, including the use status of the air supply equipment and the air-using equipment;

[0007] Input the working condition of the air supply system as an input into the pre-trained first prediction model, output a predicted value of the total wind pressure change, and determine whether the air supply system has a fault based on the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system;

[0008] If there is a fault in the air supply system, obtain the abnormal characteristic quantity of the air supply system under the current working condition;

[0009] The operating conditions of the air supply system and the abnormal feature quantities of the air supply system under the current operating conditions are input into the pre-trained second prediction model, and the fault location of the air supply system is output.

[0010] A second aspect of an embodiment of the present invention provides a rail vehicle air supply system fault detection device, comprising:

[0011] A first acquisition module is used to acquire the working condition of the air supply system, the working condition including the use status of the air supply equipment and the air use equipment;

[0012] A judgment module, used to input the working condition of the air supply system as an input into the pre-trained first prediction model, output a predicted value of the total wind pressure change, and judge whether the air supply system has a fault according to the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system;

[0013] The second acquisition module is used to acquire the characteristic quantity of the air supply system under the current working condition if there is a fault in the air supply system;

[0014] The diagnosis module is used to input the working condition of the air supply system and the characteristic quantity of the air supply system under the current working condition into the pre-trained second prediction model, and output the fault location of the air supply system.

[0015] A third aspect of an embodiment of the present invention provides a terminal 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, the steps of the rail vehicle air supply system fault detection method of the first aspect described above are implemented.

[0016] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the rail vehicle air supply system fault detection method as described in the first aspect above are implemented.

[0017] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0018] The embodiment of the present invention predicts the normal total air pressure change of the air supply system under the current operating conditions through a pre-trained first prediction model, and compares it with the actual total air pressure change of the air supply system. It can accurately determine whether the total air pressure change of the air supply system is abnormal, and then judge whether the air supply system has faults such as insufficient air supply and air leakage, thereby realizing timely and accurate early warning of air supply system faults; further, according to the operating conditions of the air supply system and the abnormal characteristic quantities of the air supply system under the current operating conditions, the pre-trained second prediction model is used to locate the fault, which is conducive to early processing of the fault and ensuring the safety of train operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a schematic diagram of the implementation flow of a rail vehicle air supply system fault detection method provided by an embodiment of the present invention;

[0021] Figure 2 It is a schematic diagram of the construction process of the database provided by the embodiment of the present invention;

[0022] Figure 3 is a schematic diagram of a process for determining a fault location provided by an embodiment of the present invention;

[0023] Figure 4 is a schematic diagram of a process for determining a fault degree provided by an embodiment of the present invention;

[0024] Figure 5 is a schematic diagram of a rail vehicle air supply system fault detection device provided by an embodiment of the present invention;

[0025] Figure 6 It is a schematic diagram of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0027] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0028] The existing technology has a method of using parameters such as the number of air compressor working cycles and the pressure deviation threshold to determine whether the air supply system is abnormal. However, when the high voltage electricity and the air supply system are normal, the total air pressure continues to be lower than the set threshold and shows a downward trend, making it impossible to accurately detect the fault.

[0029] The embodiment of the present invention provides a method for detecting faults in a rail vehicle air supply system. Figure 1 As shown, the method comprises the following steps:

[0030] Step S101, obtaining the working conditions of the air supply system, including the use status of the air supply equipment and the air using equipment.

[0031] In an embodiment of the present invention, the air supply system includes air supply equipment and air-using equipment. The air supply equipment is generally an air compressor, and the air-using equipment includes a pantograph, a door, a parking brake device, an air brake device, an air spring, a toilet, etc. The air supply equipment can supply air when it is turned on, and the air-using equipment consumes air in the following states: the pantograph is raised, the door state changes, the parking brake is applied, the air brake force command increases, the air spring pressure increases, and the toilet and main circuit breaker are in use. Changes in the states of the vehicle's air supply equipment and air-consuming equipment affect changes in the total air pressure variation. When the air supply equipment and the air-consuming equipment fail, insufficient air supply and increased air consumption will occur, resulting in an abnormal total air pressure variation.

[0032] In step S102, the operating condition of the air supply system is input as an input into a pre-trained first prediction model, a predicted value of the total wind pressure change is output, and based on the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system, it is determined whether the air supply system has a fault.

[0033] In an embodiment of the present invention, the total wind pressure change can be a change compared with the previous working condition, or a change compared with the initial working condition. The theoretical total wind pressure change of the air supply system is predicted according to the first prediction model, so as to determine whether the total wind pressure change is abnormal, and then detect the failure of the air supply system. The input of the first prediction model needs to be strongly related to the change of the total wind pressure, and the state of the wind-using equipment needs to be processed. For example, the pantograph consumes wind only in the process of raising the pantograph, so the pantograph input data is input as 1 only when the pantograph state is changed from lowering the pantograph to raising the pantograph. For example, the door state consumes wind only in the process of opening and closing the door, so the door state data is input as 1 only when the door changes. The data after the above processing is used as input data, for example, a group of input data includes 2 groups of pantograph state data, 1 group of door state data, 1 group of parking brake application state data, 2 groups of air compressor state data, 8 groups of air brake force set value change data, 16 groups of air spring pressure change data, toilet cesspool wind consumption signal data, etc., which are input into the first prediction model, and the output data is the predicted value of the total wind pressure change.

[0034] Step S103: if there is a fault in the air supply system, obtain the abnormal characteristic quantity of the air supply system in the current working condition.

[0035] Step S104, inputting the working condition of the air supply system and the abnormal characteristic quantity of the air supply system under the current working condition into the pre-trained second prediction model, and outputting the fault location of the air supply system.

[0036] In an embodiment of the present invention, under current operating conditions, when an air supply device or an air-using device fails, different equipment failures will have different impacts on the characteristic quantities of the air supply system. The faulty equipment can be located based on the current operating conditions and the abnormal characteristic quantities under the current operating conditions.

[0037] For example:

[0038] The total air pressure remains unchanged when the air compressor is not running. When the air compressor is running, the rising speed of the total air pressure of the actual vehicle is lower than that of the model. With the same pressure change, the air compressor running time becomes longer, and air leakage is located in the air compressor.

[0039] The total air pressure decreases, the rising time of the brake cylinder pressure becomes longer, and the brake air consumption increases, indicating a brake module fault.

[0040] The total air pressure is reduced and the air spring air cylinder pressure is low, indicating a failure in the air spring module.

[0041] The total air pressure is reduced and the toilet air cylinder pressure is low, indicating a toilet module failure.

[0042] The total air pressure is reduced and the bow lifting air cylinder pressure is low, indicating a bow lifting module failure.

[0043] It can be seen that the embodiment of the present invention predicts the normal total air pressure change of the air supply system under the current operating conditions through the pre-trained first prediction model, and compares it with the actual total air pressure change of the air supply system. It can accurately determine whether the total air pressure change of the air supply system is abnormal, and then judge whether the air supply system has faults such as insufficient air supply and air leakage, thereby realizing timely and accurate early warning of air supply system faults; further, according to the operating conditions of the air supply system and the abnormal characteristic quantities of the air supply system under the current operating conditions, the pre-trained second prediction model is used to locate the fault, which is conducive to early processing of the fault and ensuring the safety of train operation.

[0044] As a possible implementation, in step S102, the training process of the first prediction model can be described in detail as follows:

[0045] Obtain the total wind pressure change of the air supply system under different working conditions to obtain the first training set;

[0046] Various working conditions in the first training set are used as inputs of the first prediction model, and the total wind pressure change of the air supply system under the corresponding working conditions is used as the theoretical output of the first prediction model. The model parameters of the first prediction model are trained to obtain the trained first prediction model.

[0047] In an embodiment of the present invention, relevant historical input and output data can be downloaded through the operation and maintenance data platform, and after data processing, training and verification can be performed through the BP neural network. The first prediction model can be a BP neural network model or other types of prediction models, which is not limited in this application.

[0048] As a possible implementation, in step S102, judging whether the air supply system has a fault according to the predicted value of the total air pressure change and the actual value of the total air pressure change of the air supply system can be described in detail as follows:

[0049] If the difference between the predicted value of the total wind pressure change and the actual value of the total wind pressure change is greater than a preset value and lasts for a preset time, it is determined that the air supply system has a fault.

[0050] In an embodiment of the present invention, a suitable threshold value can be set according to actual conditions to issue an early warning for abnormalities and leakages. For example, the following standard can be set: when the difference between the predicted value of the total wind pressure change and the actual value of the total wind pressure change is greater than 0.15 bar and lasts for more than 10 minutes, an abnormality and leakage early warning is issued.

[0051] As a possible implementation, in step S104, the training process of the second prediction model can be described in detail as follows:

[0052] Establishing a simulation model of the air supply system, simulating different working conditions through the simulation model, and simulating different types of faults under each working condition, determining the abnormal characteristic quantity of the air supply system when each fault occurs under each working condition, and obtaining a second training set;

[0053] Each group of operating conditions and their abnormal characteristic quantities in the second training set are used as inputs of the second prediction model, and the corresponding fault types are used as theoretical outputs of the second prediction model. The model parameters of the second prediction model are trained to obtain the trained second prediction model.

[0054] In the embodiments of the present invention, see Figure 2 As shown in the figure, the AMESim simulation model of the air supply system of the whole train can be established, and the model can be calibrated using the actual vehicle data. Different working conditions can be obtained by combining the following equipment states: whether the pantograph is raised, whether the brake is applied, whether the toilet is used, whether the air compressor is turned on, etc. Under each working condition, the AMESim simulation model is injected with air leakage faults of different functional modules, and the abnormal characteristic quantities when different faults occur under different working conditions are determined, such as the number of air compressor blows and time, etc., to form a fault database corresponding to the working condition, abnormal characteristic quantity and fault. Each data in the database consists of working condition, abnormal characteristic quantity and fault, such as "pantograph raised, common brake command 3.1 bar, toilet in car 1 is used, ... toilet in car 8 is not used, main air compressor is turned on, auxiliary air compressor is turned off, total air pressure is low by 0.3 bar (abnormal characteristic quantity), air cylinder pressure in toilet in car 1 is low by 0.1 bar (abnormal characteristic quantity), toilet in car 1 is leaking (fault)".

[0055] See also Figure 3As shown, the second prediction model can be a BP neural network model or other types of prediction models, which is not limited in this application. When training the second prediction model, a training set is generated according to the data in the database. The working conditions and abnormal feature quantities in the database are used as input, and the state quantity of the equipment in the working condition is represented by 0 or 1, such as the main air compressor is turned on with 1, and closed with 0, and the abnormal feature quantity is directly represented by a floating point number, such as the total air pressure is 0.3 bar lower, represented by -0.3; the corresponding fault is used as output, and the output is represented by a number converted from an n-bit binary number, n represents the number of possible faults, and each bit on the binary number represents whether a specific fault occurs, 0 represents no occurrence, and 1 represents occurrence, such as the output format can be defined from low to high as: air compressor leakage, 1 car toilet leakage, 2 car toilet leakage, ... 8 car toilet leakage, 1 car brake cylinder leakage, ... 8 car brake cylinder leakage, training to obtain a fault location model. During the operation of the actual vehicle, a simulation model can be established, and the parameters output by the simulation model can be compared with the actual sensor data of the actual vehicle to determine the abnormal characteristic quantity. The abnormal characteristic quantity and the actual vehicle control instructions (operating conditions) are input into the fault location model, and the model output is converted into binary. It can then be determined that the fault represented by the position of 1 in the binary number has occurred, thereby achieving fault location.

[0056] As a possible implementation manner, after step S104, the following may also be included:

[0057] Step S105, inputting the working condition of the air supply system, the abnormal characteristic quantity of the air supply system under the current working condition, and the fault location into the pre-trained third prediction model, and outputting the fault degree of the air supply system;

[0058] Among them, the fault degree is the air leakage rate.

[0059] In the embodiment of the present invention, the third prediction model may be a BP neural network model, which is not limited in the present application. Figure 4As shown in the figure, the working condition, abnormal characteristic quantity and fault location (such as toilet leakage in car 1) in the database are used as input. The state quantity in the working condition is represented by 0 or 1, such as 1 for the main air compressor to be turned on and 0 for being turned off. The abnormal characteristic quantity is directly represented by a floating point number, such as -0.3 for the total air pressure to be 0.3 bar lower. The fault is represented by an integer, and each integer represents a specific fault. The fault degree (such as 5L / min) in the database is used as the theoretical output to train the fault degree model. During the operation of the actual vehicle, the parameters output by the simulation model are compared with the actual sensor data of the actual vehicle to determine the abnormal characteristic quantity, and the abnormal characteristic quantity and the actual vehicle control instruction (working condition) are input into the fault location model. The model output is converted into binary, and then it can be determined that the fault represented by the position of 1 in the binary number has occurred, and the fault location is realized. Then the abnormal characteristic quantity, the actual vehicle control instruction (working condition) and the fault integer code are input into the fault degree model to obtain the degree of the fault.

[0060] As a possible implementation manner, after step S105, the following may also be included:

[0061] Step S106, establishing a continuous air-charging simulation model of the air supply system under the current fault according to the fault location and fault degree; wherein, in the continuous air-charging simulation model, the air supply device is continuously turned on.

[0062] Step S107, using a continuous air charging simulation model to simulate and determine the total wind pressure stability value of the air supply system when the air-using equipment is in use under the current working condition. If the total wind pressure stability value is less than the preset safety limit, it is determined whether the equipment at the fault location is an important equipment.

[0063] Step S108, if the equipment at the fault location is not important equipment, the equipment will be cut off; if the equipment at the fault location is important equipment, the non-important equipment in the air supply system will be cut off in order of importance from small to large until the total air pressure stable value is not less than the preset safety limit.

[0064] As a possible implementation method, if the total wind pressure stability value is still less than the preset safety limit after all non-important equipment is removed, a prompt is given to stop the vehicle for maintenance.

[0065] In an embodiment of the present invention, simulation is used to determine whether the total air pressure of the air supply system can be maintained within a safe range under continuous air supply. If so, the air supply equipment is controlled to be continuously turned on, and no fault processing is performed during operation, and the fault is processed when entering the station for maintenance. If not, it is determined whether the leaking equipment is an important equipment based on whether the leaking equipment at the fault location affects safety (for example, air-consuming equipment with empty springs and air supply equipment affect safety and are important equipment; toilet air-consuming equipment does not affect safety and is non-important equipment). If it is a non-important equipment, air will no longer be supplied to the leaking equipment, that is, the faulty equipment will be cut off; if the leaking equipment affects safe operation, some equipment with low importance will be cut off based on the importance of all air-consuming equipment; if after all non-important equipment is cut off, the stable value of the total air pressure is still less than the preset safety limit, it is necessary to stop the vehicle for maintenance. The control strategy of steps S106-S108 can be found in Figure 4 shown.

[0066] Based on the above content, the embodiment of the present invention realizes the warning of abnormal total wind pressure and leakage by establishing a BP neural network model between the status data of the air supply and air use equipment and the change of the total wind pressure; by building an AMESim simulation model to simulate the fault situation and find the fault characteristic quantity, a database corresponding to the working condition, fault characteristic quantity and fault is formed, and the BP neural network is trained with the database to establish a fault location model, the fault location model is used to locate the current fault of the train, the BP neural network is trained with the fault degree in the database as the output, a fault degree model is established, and the degree of the located fault is determined by the fault degree model, and the model is continuously updated and optimized according to the actual vehicle operation data; after determining the fault location and fault degree, the stable response value of the total wind pressure is predicted, and hierarchical adaptive control is performed according to the predicted value and the degree of influence of the faulty equipment on safety. The present invention realizes the warning and preventive maintenance of abnormal leakage faults of the total wind pressure, and improves the operation quality, operation efficiency and operation safety of the vehicle.

[0067] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0068] The present invention provides a rail vehicle air supply system fault detection device, see Figure 5 As shown, the device 50 comprises:

[0069] The first acquisition module 51 is used to acquire the working condition of the air supply system, and the working condition includes the use status of the air supply equipment and the air using equipment.

[0070] The judgment module 52 is used to input the working condition of the air supply system as an input into the pre-trained first prediction model, output the predicted value of the total wind pressure change, and judge whether there is a fault in the air supply system based on the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system.

[0071] The second acquisition module 53 is used to acquire characteristic quantities of the air supply system under current working conditions if there is a fault in the air supply system.

[0072] The diagnosis module 54 is used to input the working condition of the air supply system and the characteristic quantity of the air supply system under the current working condition into the pre-trained second prediction model, and output the fault location of the air supply system.

[0073] As a possible implementation method, the training process of the first prediction model includes:

[0074] Obtain the total wind pressure change of the air supply system under different working conditions to obtain the first training set;

[0075] Various working conditions in the first training set are used as inputs of the first prediction model, and the total wind pressure change of the air supply system under the corresponding working conditions is used as the theoretical output of the first prediction model. The model parameters of the first prediction model are trained to obtain the trained first prediction model.

[0076] As a possible implementation manner, the determination module 52 is specifically configured to:

[0077] If the difference between the predicted value of the total wind pressure change and the actual value of the total wind pressure change is greater than the preset value, and the duration reaches the preset duration, it is determined that the air supply system has a fault.

[0078] As a possible implementation method, the training process of the second prediction model includes:

[0079] Establishing a simulation model of the air supply system, simulating different working conditions through the simulation model, and simulating different types of faults under each working condition, determining the abnormal characteristic quantity of the air supply system when each fault occurs under each working condition, and obtaining a second training set;

[0080] Each group of operating conditions and their abnormal characteristic quantities in the second training set are used as inputs of the second prediction model, and the corresponding fault types are used as theoretical outputs of the second prediction model. The model parameters of the second prediction model are trained to obtain the trained second prediction model.

[0081] As a possible implementation, after determining the fault location of the air supply system, the diagnosis module 54 is further used to:

[0082] Input the working condition of the air supply system, the abnormal characteristic quantity of the air supply system under the current working condition, and the fault location into the pre-trained third prediction model, and output the fault degree of the air supply system;

[0083] Among them, the fault degree is the air leakage rate.

[0084] As a possible implementation, after determining the fault degree of the air supply system, the diagnosis module 54 is further used to:

[0085] According to the fault location and fault degree, a continuous air-charging simulation model of the air supply system under the current fault is established; wherein, in the continuous air-charging simulation model, the air supply equipment is continuously turned on;

[0086] The continuous air charging simulation model is used to simulate and determine the total air pressure stability value of the air supply system under the current working condition of the air-using equipment. If the total air pressure stability value is less than the preset safety limit, it is determined whether the equipment at the fault location is an important equipment;

[0087] If the device at the fault location is not an important device, cut off the device.

[0088] As a possible implementation, if the device at the fault location is an important device, the diagnosis module 54 is further configured to:

[0089] In order of importance, cut off the non-important equipment in the air supply system in sequence until the total air pressure stable value is not less than the preset safety limit;

[0090] If the total wind pressure stability value is still less than the preset safety limit after all non-important equipment is removed, a prompt will be given to stop the vehicle for maintenance.

[0091] Figure 6 FIG. 6 is a schematic diagram of a terminal device 60 provided in an embodiment of the present invention. Figure 6 As shown, the terminal device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61, such as a rail vehicle air supply system fault detection program. When the processor 61 executes the computer program 63, the steps in the above-mentioned rail vehicle air supply system fault detection method embodiments are implemented, such as Figure 1 Alternatively, when the processor 61 executes the computer program 63, the functions of each module in the above-mentioned device embodiments are realized, for example Figure 5 The functions of the modules 51 to 54 are shown.

[0092] Exemplarily, the computer program 63 may be divided into one or more modules / units, one or more modules / units are stored in the memory 62, and executed by the processor 61 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 63 in the terminal device 60. For example, the computer program 63 may be divided into a first acquisition module 51, a judgment module 52, a second acquisition module 53, and a diagnosis module 54 (modules in the virtual device), and the specific functions of each module are as follows:

[0093] The first acquisition module 51 is used to acquire the working condition of the air supply system, and the working condition includes the use status of the air supply equipment and the air using equipment.

[0094] The judgment module 52 is used to input the working condition of the air supply system as an input into the pre-trained first prediction model, output the predicted value of the total wind pressure change, and judge whether there is a fault in the air supply system based on the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system.

[0095] The second acquisition module 53 is used to acquire characteristic quantities of the air supply system under current working conditions if there is a fault in the air supply system.

[0096] The diagnosis module 54 is used to input the working condition of the air supply system and the characteristic quantity of the air supply system under the current working condition into the pre-trained second prediction model, and output the fault location of the air supply system.

[0097] The terminal device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 6 It is only an example of the terminal device 60 and does not constitute a limitation of the terminal device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 60 may also include input and output devices, network access devices, buses, etc.

[0098] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] The memory 62 may be an internal storage unit of the terminal device 60, such as a hard disk or memory of the terminal device 60. The memory 62 may also be an external storage device of the terminal device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 60. Further, the memory 62 may also include both an internal storage unit of the terminal device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the terminal device 60. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0100] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0101] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0102] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0103] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0106] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for detecting faults in a rail vehicle air supply system, characterized in that: include: Acquire the working condition of the air supply system, wherein the working condition includes the use status of the air supply equipment and the air using equipment; Inputting the working condition of the air supply system as an input into a pre-trained first prediction model, outputting a predicted value of the total wind pressure change, and judging whether the air supply system has a fault according to the predicted value of the total wind pressure change and the actual value of the total wind pressure change of the air supply system; If there is a fault in the air supply system, obtaining an abnormal characteristic quantity of the air supply system under the current working condition; The operating condition of the air supply system and the abnormal feature quantity of the air supply system under the current operating condition are input into a pre-trained second prediction model, and the fault location of the air supply system is output.

2. The rail vehicle air supply system fault detection method according to claim 1, characterized in that: The training process of the first prediction model includes: Obtaining the total wind pressure change of the air supply system under different working conditions to obtain a first training set; The various working conditions in the first training set are respectively used as the input of the first prediction model, the total wind pressure change of the air supply system under the corresponding working conditions is used as the theoretical output of the first prediction model, the model parameters of the first prediction model are trained to obtain the trained first prediction model.

3. The rail vehicle air supply system fault detection method according to claim 1, characterized in that: Judging whether the air supply system has a fault according to the predicted value of the total air pressure change and the actual value of the total air pressure change of the air supply system includes: If the difference between the predicted value of the total wind pressure change and the actual value of the total wind pressure change is greater than a preset value and lasts for a preset time, it is determined that a fault has occurred in the air supply system.

4. The rail vehicle air supply system fault detection method according to claim 1, characterized in that: The training process of the second prediction model includes: Establishing a simulation model of the air supply system, simulating different working conditions through the simulation model, and simulating different types of faults under each working condition, determining the abnormal characteristic quantity of the air supply system when each fault occurs under each working condition, and obtaining a second training set; Each group of operating conditions and their abnormal characteristic quantities in the second training set are used as the input of the second prediction model, and the corresponding fault type is used as the theoretical output of the second prediction model. The model parameters of the second prediction model are trained to obtain the trained second prediction model.

5. The rail vehicle air supply system fault detection method according to any one of claims 1 to 4, characterized in that: After determining the fault location of the air supply system, the method further includes: Inputting the working condition of the air supply system, the abnormal characteristic quantity of the air supply system under the current working condition, and the fault location into a pre-trained third prediction model, and outputting the fault degree of the air supply system; The fault degree is the air leakage rate.

6. The rail vehicle air supply system fault detection method according to claim 5, characterized in that: After determining the degree of failure of the air supply system, the method further includes: According to the fault location and fault degree, a continuous air-charging simulation model of the air supply system under the current fault is established; wherein, in the continuous air-charging simulation model, the air supply device is continuously turned on; Determine the total wind pressure stability value of the air supply system under the use state of the air-using equipment in the current working condition by simulating the continuous air charging simulation model; if the total wind pressure stability value is less than the preset safety limit, determine whether the equipment at the fault location is an important equipment; If the device at the fault location is not an important device, the device is removed.

7. The rail vehicle air supply system fault detection method according to claim 6, characterized in that: If the device at the fault location is an important device, then: In order of importance, non-important equipment in the air supply system is removed in sequence until the total air pressure stable value is not less than a preset safety limit value; If the total wind pressure stability value is still less than the preset safety limit after all non-important equipment is removed, a prompt will be given to stop the vehicle for maintenance.

8. A rail vehicle air supply system fault detection device, characterized in that: include: A first acquisition module is used to acquire the working condition of the air supply system, wherein the working condition includes the use status of the air supply equipment and the air using equipment; A judgment module, used for inputting the working condition of the air supply system as an input into a pre-trained first prediction model, outputting a predicted value of the total wind pressure change, and judging whether the air supply system has a fault according to the predicted value of the total wind pressure change and an actual value of the total wind pressure change of the air supply system; A second acquisition module is used to acquire an abnormal characteristic quantity of the air supply system under a current working condition if there is a fault in the air supply system; The diagnosis module is used to input the working condition of the air supply system and the abnormal characteristic quantity of the air supply system under the current working condition into the pre-trained second prediction model, and output the fault location of the air supply system.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images