A fault injection method and injector for EP valve of train air brake system

Abstract

The present invention relates to the technical field of fault injection, and discloses a train air brake system EP valve fault injection method and injector, comprising: building a brake system simulation model according to the principle of the train air brake system, the brake system simulation model including an EP valve normal model; setting the fault type, fault injection position and fault degree of the EP valve, and generating an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model; generating fault information based on a preset injection method and the EP valve fault model, the preset injection method including a specified fault injection method and a random fault injection method; and performing fault injection based on the fault information.

Description

Technical Field

[0001] The invention relates to the technical field of fault injection, and in particular to a method and an injector for injecting faults of an EP valve of a train air brake system. Background Art

[0002] With the development of economy and the progress of social science and technology, trains have begun to develop steadily in the direction of high speed, large capacity and high safety. Now the speed of trains is getting faster and faster. In order to ensure the safety of trains in high-speed driving state and ensure that trains can brake stably during driving, more reliable braking performance is needed. At present, the braking system of trains mostly adopts electric-pneumatic composite braking method, and EP valve, as a key component in air brake system, can convert braking electrical signal command into corresponding braking pressure command. If the EP valve fails, it will lead to insufficient air braking force of the braking system and the braking cannot be relieved, resulting in damage to brake shoes, scratches on treads, and the train cannot stop smoothly. However, due to the complex structure of EP valve, it is difficult to determine the failure mechanism. At the same time, the cost of EP valve is high, and the research on EP valve is relatively small. At present, the research on EP valve fault inspection and diagnosis technology is difficult to obtain reliable verification data and simulation environment support. Summary of the invention

[0003] The invention provides a train air brake system EP valve fault injection method and an injector to solve the problems existing in the prior art.

[0004] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0005] In a first aspect, the present invention provides a fault injection method for an EP valve of a train air brake system, comprising:

[0006] Building a braking system simulation model according to the principle of the train air braking system, wherein the braking system simulation model includes a normal model of the EP valve;

[0007] Setting a fault type, a fault injection position and a fault degree of the EP valve, and generating an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model;

[0008] Generate fault information based on a preset injection method and the EP valve fault model, wherein the preset injection method includes a specified fault injection method and a random fault injection method;

[0009] Fault injection is performed based on the fault information.

[0010] In a second aspect, an embodiment of the present application provides a fault injector for an EP valve of a train air brake system, comprising: a user setting interface, a fault injection control unit, and an EP valve model library, wherein the user setting interface is connected to the fault injection control unit and the EP valve model library respectively;

[0011] The user setting interface is used to build a braking system simulation model according to the principle of the train air braking system, and the braking system simulation model includes an EP valve normal model; set the fault type, fault injection position and fault degree of the EP valve, and generate an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model; generate fault information based on a preset injection method and the EP valve fault model, and the preset injection method includes a specified fault injection method and a random fault injection method;

[0012] The fault injection control unit is used to perform fault injection based on the fault information;

[0013] The EP valve model library is used to store the EP valve fault model.

[0014] Beneficial effects:

[0015] The train air brake system EP valve fault injection method provided by the present invention builds a brake system simulation model and an EP valve normal model, and generates an EP valve fault model according to research needs, and simulates and studies the EP valve fault by replacing the EP valve fault model with the EP valve normal model, thereby injecting the EP valve fault model into the brake system simulation model, so as to obtain various data of the train air brake system when the EP valve fails by studying the brake system fault model injected with the EP valve fault model. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 One of the flow charts of the fault injection method of the EP valve of the train air brake system according to the preferred embodiment of the present invention;

[0017] Figure 2 This is the second flow chart of the fault injection method of the EP valve of the train air brake system according to the preferred embodiment of the present invention;

[0018] Figure 3 A schematic structural diagram of an air brake system according to a preferred embodiment of the present invention;

[0019] Figure 4 A schematic diagram of the structure of an EP valve in an air brake system in a preferred embodiment of the present invention;

[0020] Figure 5 This is a schematic diagram of the structure of a fault injector for an EP valve of a train air brake system according to a preferred embodiment of the present invention;

[0021] Figure 6 A schematic diagram of a user-specified fault injection setting interface of an EP valve fault injector built in a GUI according to a preferred embodiment of the present invention;

[0022] Figure 7 A schematic diagram of the results of user-specified fault injection of an EP valve fault injector built in a GUI according to a preferred embodiment of the present invention;

[0023] Figure 8 A schematic diagram of a user random fault injection setting interface of an EP valve fault injector built in a GUI according to a preferred embodiment of the present invention;

[0024] Fig. 9 This is a schematic diagram of the results of random fault injection by a user of an EP valve fault injector built in a GUI according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the usual meanings understood by persons with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "one" do not indicate quantity restrictions, but indicate the existence of at least one. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship also changes accordingly.

[0027] See also Figure 1-Figure 2 The present application embodiment provides a fault injection method for an EP valve of a train air brake system, comprising:

[0028] According to the principle of train air brake system, a brake system simulation model is built, which includes a normal model of EP valve;

[0029] Among them, the normal model can be recorded as M0.

[0030] The fault type, fault injection position and fault degree of the EP valve are set, and the EP valve fault model is generated according to the fault type, fault injection position and fault degree and the EP valve normal model;

[0031] Among them, the EP valve fault model can be recorded as M i (i=1, 2, ..., n), stored in the EP valve model library.

[0032] Generate fault information based on a preset injection method and an EP valve fault model, wherein the preset injection method includes a specified fault injection method and a random fault injection method;

[0033] Perform fault injection based on the fault information.

[0034] It should be noted that, in this embodiment, the fault model is generated by building a suitable simulation model to simulate the faults that occur in reality.

[0035] The above-mentioned fault injection method of the EP valve of the train air brake system builds a brake system simulation model and an EP valve normal model, and generates an EP valve fault model according to the set EP valve fault type, fault injection position and fault degree. The fault type, fault injection position and fault degree can be manually input into a specified fault injection method and randomly generated into a random fault injection method according to different research requirements. The EP valve fault model and the EP valve normal model are replaced to realize the simulation and study of the EP valve fault, so that the EP valve fault model is injected into the brake system simulation model. By studying the brake system fault model injected with the EP valve fault model, various data of the train air brake system when the EP valve fails can be obtained.

[0036] See also Figure 3 and Figure 4 The embodiment of the present application provides a fault injection method for the EP valve of a train air brake system, wherein the fault type is determined according to the solenoid valve relationship of the EP valve, and the fault type includes a spring damage fault, a solenoid valve leakage fault, or an EP valve pipeline blockage fault.

[0037] First of all, it should be noted that when simulating the possible failures of the EP valve in the application, it is necessary to understand the mechanism of the EP valve, so as to explore the relationship between the possible EP valve failures in the actual application and its mechanism parameters. In this embodiment, the intake valve of the EP valve is taken as an example to deduce the relationship of the solenoid valve of the EP valve, and the outlet pressure of the intake valve satisfies the following relationship:

[0038]

[0039] Where P is the outlet pressure of the intake valve, f0 is the spring preload, and f jet represents the airflow force, fBCU Indicates the force after the brake control unit signal is converted into equal amounts, f prs Indicates the pressure difference between the upper and lower parts of the valve core. represents the second-order derivative of the displacement of the valve core, m represents the mass of the valve core, d spool Indicates the shaft diameter of the valve core, d rod Indicates the stem diameter of the valve core;

[0040] At the same time, the following relationship is also satisfied in the formula:

[0041] f k =k(x+x s0 );

[0042]

[0043] In the formula, f k represents the spring force, k represents the spring stiffness, x represents the displacement of the valve core, and x s0 Indicates the compression of the spring at zero displacement, P prs Indicates the pressure difference between the upper and lower parts of the valve core, d p Indicates the piston diameter, d r Indicates the rod diameter;

[0044] According to the continuity equation of gas, the transient mass flow rate of compressed air flowing out of the switch solenoid valve through the throttle hole satisfies the following relationship:

[0045]

[0046] In the formula, A represents the restricted area, represents the transient mass flow rate, C q Indicates the flow coefficient, C m Represents the mass flow parameter, P i Indicates the inlet pressure, R gas is the air gas constant, T air Indicates the inlet temperature;

[0047] Substituting the data obtained from the intake valve outlet pressure relationship into the inlet pressure, the transient mass flow rate of the intake valve output air flowing through the throttle hole can be obtained; similarly, the transient mass flow rate of the exhaust valve output air flowing through the throttle hole can be obtained.

[0048] The position of the pre-control volume chamber is after the intake valve and before the exhaust valve. The net total flow of the pre-control volume chamber satisfies the following relationship:

[0049]

[0050] According to the ideal gas state equation, the output pressure satisfies the following relationship:

[0051]

[0052] In the formula, It represents the total net flow of the pre-control volume chamber, Indicates the total flow into the pre-control volume chamber, Represents the total flow out of the pre-control volume chamber, V ch Indicates the volume of the pre-control volume chamber, P ch Indicates output pressure;

[0053] Through the above derivation, it can be obtained that factors such as spring pressure and the transient mass flow rate of compressed air flowing through the throttle hole will affect the output pressure. Through the intake valve outlet pressure relationship, it can be obtained that the spring damage failure can be described by the spring stiffness. Through the transient mass flow rate relationship of the throttle hole, it can be obtained that the design gas flow change failure can be described by the restricted area or restricted diameter, thereby providing a theoretical basis for the establishment of the EP fault model.

[0054] Specifically, when setting different types of faults, it can be achieved in the following ways:

[0055] First, for the failure of the pneumatic piston spring characteristics degradation or damage (spring damage failure) in the intake valve and the exhaust valve in the EP valve, the degree of spring damage is simulated by modifying the stiffness coefficient of the spring.

[0056] Secondly, for the solenoid valve leakage failure in the EP valve, it is divided into two situations according to the location of the fault injection point.

[0057] Case 1: The solenoid valve core has structural defects or fatigue wear, and there are problems such as clearance fit deviation, which will cause the solenoid valve to leak. At this time, a new pipe is added between the air inlet and exhaust port of the switch solenoid valve to simulate leakage, and a throttle hole is used to simulate the leakage area.

[0058] Case 2: The sealing gasket at the solenoid valve interface will form irreversible sealing performance degradation over a long period of use, eventually causing the solenoid valve to leak into the atmosphere. At this time, a new pipe is added behind the exhaust port of the switch solenoid valve to simulate leakage, and a throttle hole is used to simulate the leakage area.

[0059] Thirdly, there are many reasons for the EP valve pipeline blockage failure. For example, the screw plug of the switch solenoid valve is prone to rust, and the rust will block the pipeline with a small inner diameter; it may also be that the rubber pad on the top of the valve core is aging, and some rubber pad debris falls off, causing the channel to be blocked. At this time, the diameter of the pipeline is modified to simulate the degree of pipeline blockage.

[0060] Optionally, when the fault type is a spring damage fault, the fault injection position includes a spring in an intake valve or a spring in an exhaust valve, and the fault model satisfies the following relationship:

[0061] f(·) k =a k ×k;

[0062] In the formula, f(·) k represents the specific fault degree signal generated according to the stiffness change characteristics of different springs of different objects, k represents the specific spring stiffness, a k Indicates the degree of spring damage.

[0063] Optionally, when the fault type is a solenoid valve leakage fault, the fault injection position includes a position between an air inlet and an exhaust port of the switch solenoid valve, or an outlet position of the exhaust port of the switch solenoid valve, and the fault model satisfies the following relationship:

[0064] f(·) o =a o ×o;

[0065] In the formula, f(·) o represents the specific fault degree signal generated according to the different leakage degrees at different leakage locations, o represents the restricted area, a o Indicates the degree of failure of pipeline leakage.

[0066] Optionally, when the fault type is an EP valve pipeline blockage fault, the fault injection position includes a pipeline position between an intake valve and an exhaust valve, or a pipeline position leading to a brake cylinder, and the fault model satisfies the following relationship:

[0067] f(·) d =a d ×d;

[0068] In the formula, f(·) d represents the specific fault degree signal generated according to the different blockage degrees at different blockage locations, d represents the pipe diameter, a d Indicates the degree of failure of pipeline blockage.

[0069] Optionally, when the preset injection method includes a random fault injection method, the generating fault information based on the preset injection method and the EP valve fault model includes:

[0070] The random faults are divided into three layers, namely the first layer, the second layer and the third layer, wherein the first layer corresponds to the fault type, the second layer corresponds to the fault injection position, and the third layer corresponds to the fault degree;

[0071] Simulating a first probability distribution corresponding to the fault type in the first layer, and randomly generating a target fault type based on the first probability distribution;

[0072] In combination with the target fault type, simulating a second probability distribution corresponding to the fault injection position in the second layer, and randomly generating a target fault injection position based on the second probability distribution;

[0073] In combination with the target fault injection position, simulating a third probability distribution corresponding to the fault degree in the third layer, and randomly generating a target fault degree based on the third probability distribution;

[0074] Random fault injection information is determined based on the target fault type, the target fault injection location, and the target fault degree.

[0075] In this way, designated fault injection can simulate specific faults in a targeted manner, while random fault injection can more closely simulate the real scenario of EP valve failure, providing a diverse test environment for subsequent fault detection and test evaluation.

[0076] Optionally, the first probability distribution, the second probability distribution, and the third probability distribution satisfy the following relationship:

[0077] The first probability distribution, the second probability distribution, and the third probability distribution are the same; or,

[0078] The first probability distribution, the second probability distribution, and the third probability distribution are different from each other; or,

[0079] The first probability distribution is the same as the second probability distribution, and the first probability distribution is different from the third probability distribution; or,

[0080] The first probability distribution is the same as the third probability distribution, and the first probability distribution is different from the second probability distribution; or,

[0081] The second probability distribution is the same as the third probability distribution, and the first probability distribution is different from the second probability distribution.

[0082] The preset injection methods of this method are divided into two types: specified fault injection method and random fault injection method to meet different research needs. When the specified fault injection method is used, the fault information is injected through data input; when the random fault injection method is used, it is necessary to distribute random fault information according to the fault probability, and divide the fault information into three layers corresponding to the fault type, fault injection position and fault degree in a hierarchical manner, and obey the uniform distribution U(a, b), normal distribution N(μ, σ 2 ), chi-square distribution χ 2 One of (ξ);

[0083] For the case of uniform distribution U(a, b), where a and b are the lower and upper boundaries of the random variable respectively, the Y distribution is established as Y~U(0, 1), then the uniform distribution can be simply transformed and represented by a+(ba)Y, and then one is randomly generated from the above simulated distribution; in this way, although the probability distributions are various and cannot be described uniformly, the amount of calculation can be reduced through simple transformation.

[0084] For N(μ,σ 2 ), where μ is the mean of the probability distribution, σ 2 is the variance of the probability distribution, and the Y distribution is established as Y~N(0,1). Then the normal distribution can be simply transformed and represented by μ+σY. Then, one is randomly generated from the above simulated distribution;

[0085] For a chi-square distribution χ 2 (ξ), where ξ is the degree of freedom of the probability distribution, establish Y i ~N(0,1), i=1,2,...,ξ, then the chi-square distribution can be simply transformed to After that, one is randomly generated from the above simulated distribution; the details of other random situations can be described by the probability distribution of specific faults, which will not be listed here one by one.

[0086] In summary, first, a simulation model is built based on the principle and composition of the train air brake system. The EP valve in the simulation model is used as a normal model, denoted as M0, which is the basis for the subsequent generation of fault models; then, for the EP valve, different fault simulation methods are used to build the model according to its different fault conditions. Then, a specific fault model is generated according to the specific fault injection location and the specific fault degree. Each fault model is denoted as M0. i (i=1,2...n); n is the nth model. After that, two fault injection methods, designated fault injection and random fault injection, are provided according to different needs of users. Specified fault injection is to obtain fault information according to user input, while random fault injection is to randomly generate fault information according to the probability distribution of fault. Finally, according to the acquired specific fault information, the normal model is switched to the specific fault model to complete the EP valve fault injection. It can provide real and reliable verification data and simulation environment for technical research such as detection and diagnosis of EP valve faults.

[0087] See also Figure 5 , the embodiment of the present application also provides a fault injector for an EP valve of a train air brake system, comprising: a user setting interface, a fault injection control unit and an EP valve model library, wherein the user setting interface is connected to the fault injection control unit and the EP valve model library respectively;

[0088] The user setting interface is used to build a braking system simulation model according to the principle of the train air braking system, and the braking system simulation model includes an EP valve normal model; set the fault type, fault injection position and fault degree of the EP valve, and generate an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model; generate fault information based on a preset injection method and the EP valve fault model, and the preset injection method includes a specified fault injection method and a random fault injection method;

[0089] The fault injection control unit is used to perform fault injection based on the fault information;

[0090] The EP valve model library is used to store the EP valve fault model.

[0091] In one example, the user setting interface is built in the Matlab GUI. Its function is to allow users to set the fault injection information of the EP valve through the selection drop-down menu and slider on the interface. Users can selectively inject specified faults or random faults in this interface. When injecting specified faults, users need to set fault parameters, including fault type, fault injection location, and corresponding fault severity parameters; when injecting random faults, there is no need to set fault parameters by themselves.

[0092] Fault injection control unit: Its function is to pass the fault injection information set by the user to each module in Simulink, including the preloading module, random fault generation module, and model switching module. The preloading module preloads a specific fault model according to a specific fault parameter signal, and puts the remaining fault models in a disconnected state to save simulation resources; the random fault generation module works only after receiving a random fault control signal, and randomly generates fault parameters according to the probability distribution of each fault parameter; the model switching module switches the model according to the model switching control signal, completing the switch from the EP valve normal model to each fault model.

[0093] EP valve model library: The above-generated EP valve normal model and various types of EP valve fault models are built and stored in the Amesim software to form an EP valve model library for model switching.

[0094] Now, a fault type of solenoid valve leakage, a fault injection position of between the air inlet and the exhaust port of the solenoid valve, and a solenoid valve leakage degree of 20% are taken as an example for designated fault injection.

[0095] like Figure 6-Figure 7As shown: First, the user selects the fault injection mode as specified fault injection on the user setting interface, and then sets the parameters according to the above fault information. The specific operations are as follows: select the drop-down menu to set the fault type to solenoid valve leakage; set the fault injection position to position ①; pull the slider to set the solenoid valve leakage degree to 20%.

[0096] Then, the fault injection control unit will preload the fault model corresponding to the solenoid valve leakage fault in the model library according to the fault information set by the user, and put other fault models in a disconnected state; the model switching module switches the model according to the model switching control signal; after receiving the model switching signal, the switch is switched from the normal model to the corresponding fault model to complete the injection of the solenoid valve fault; and finally obtain Figure 7 The resulting graph for the specified fault signal is shown.

[0097] Take a random fault injection as an example. Figure 8-Figure 9 As shown: the user selects random fault injection as the fault injection method on the user setting interface. At the same time, the specified fault parameter settings at the bottom of the interface will automatically change to the default values. When the user presses the Start button, the random fault generation module in the fault injection control unit begins to automatically generate random faults. The specific process is divided into three layers.

[0098] In the first layer, the probability distribution of the fault type is simulated. The probability distribution can be any distribution that is suitable for the instance. In this instance, the fault type is considered to be uniformly distributed, that is, the probability of each fault type occurring is the same, which is 1 / 3. Then, the fault type is randomly generated under the above probability distribution, and one of the three fault types is selected;

[0099] On this basis, we proceed to the second layer to simulate the probability distribution of the fault injection location. The probability distribution can be any distribution that is suitable for the instance. In this instance, the fault injection location is considered to conform to the uniform distribution, that is, the probability of failure at each location is the same, which is 1 / 2. Then, the fault injection location is randomly generated under the above probability distribution, and one of the two fault injection locations is selected;

[0100] Finally, we enter the third layer to simulate the probability distribution of the fault degree. Its probability distribution can be any distribution that is suitable for the instance. In this instance, the fault degree is considered to conform to the normal distribution, that is, the probability of finding a minor fault is greater than the probability of a major fault. The fault degrees of the three fault types all conform to the normal distribution. i = 1, 2, 3, where μ i is the mean of the probability distribution of the fault degree corresponding to the three fault types, is the variance of the probability distribution of the fault degree corresponding to the three fault types. Let Y i~N(0,1), then the probability distribution of the fault degree corresponding to the three fault types can be expressed as μ i +σ i Y is simulated. Afterwards, a fault level is randomly generated from the probability distribution of the above simulation.

[0101] The random fault generation module in the fault injection control unit serves as the fault information source for random fault injection. It randomly generates the fault type, fault injection location, and fault degree to form the fault information for random fault injection, providing fault information for subsequent specific fault injection. Then, the fault injection control unit will preload the fault model corresponding to the above fault in the model library according to the fault information randomly generated by the random fault generation module, and put other fault models in the disconnected state; the model switching module switches the model according to the model switching control signal; after receiving the model switching signal, the switch is switched from the normal model to the corresponding fault model above to complete the injection of random faults; and finally obtain Figure 7 The resulting graph for the specified fault signal is shown.

[0102] In another example, a braking system simulation model is built according to the principle of a train air braking system, and a preset injection method is selected through a user setting interface to determine the injection method of fault information. When the preset injection method is selected as a specified fault injection method, the fault type, fault injection position and fault degree of the EP valve can be set through the user setting interface, and the set fault type, fault injection position and fault degree are used to generate an EP valve fault model based on the EP valve normal model, and then the EP valve fault model is injected into the braking system simulation model through the model switching module in the fault injection control unit; when the preset injection method is selected as a random fault injection method, the corresponding fault type, fault injection position and fault degree are randomly generated through the random fault generation module in the fault injection control unit, and the corresponding EP valve fault model is generated based on the randomly generated fault type, fault injection position and fault degree and the EP valve normal model, and then the EP valve fault model is injected into the braking system simulation model through the model switching module in the fault injection control unit; the EP valve fault models generated in the above process can be stored in the EP valve model library for subsequent research and call at any time.

[0103] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A fault injection method for an EP valve of a train air brake system, characterized in that: include: Building a braking system simulation model according to the principle of the train air braking system, wherein the braking system simulation model includes a normal model of the EP valve; Setting a fault type, a fault injection position and a fault degree of the EP valve, and generating an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model; Generate fault information based on a preset injection method and the EP valve fault model, wherein the preset injection method includes a specified fault injection method and a random fault injection method; performing fault injection based on the fault information; The fault type is determined according to the solenoid valve relationship of the EP valve, and the fault type includes a spring damage fault, a solenoid valve leakage fault, or an EP valve pipeline blockage fault; In the case where the fault type is a spring damage fault, the fault injection position includes a spring in an intake valve or a spring in an exhaust valve, and the fault model satisfies the following relationship: ； In the formula, It indicates the specific fault degree signal generated according to the stiffness change characteristics of different springs of different objects. represents a specific spring stiffness, Indicates the degree of spring damage; In the case where the fault type is a solenoid valve leakage fault, the fault injection position includes a position between the air inlet and the exhaust port of the switch solenoid valve, or an outlet position of the exhaust port of the switch solenoid valve, and the fault model satisfies the following relationship: ； In the formula, Indicates the specific fault degree signal generated according to the different leakage degrees at different leakage locations, Represents the restricted area, Indicates the degree of failure of pipeline leakage; In the case where the fault type is an EP valve pipeline blockage fault, the fault injection position includes the pipeline position between the intake valve and the exhaust valve, or the pipeline position leading to the brake cylinder, and the fault model satisfies the following relationship: ； In the formula, Indicates the specific fault degree signal generated according to the different blockage degrees at different blockage locations, Indicates the pipe diameter, Indicates the degree of failure of pipeline blockage.

2. The fault injection method for the EP valve of the train air brake system according to claim 1, characterized in that: In the case where the preset injection method includes a random fault injection method, the generating fault information based on the preset injection method and the EP valve fault model includes: The random faults are divided into three layers, namely the first layer, the second layer and the third layer, wherein the first layer corresponds to the fault type, the second layer corresponds to the fault injection position, and the third layer corresponds to the fault degree; Simulating a first probability distribution corresponding to the fault type in the first layer, and randomly generating a target fault type based on the first probability distribution; In combination with the target fault type, simulating a second probability distribution corresponding to the fault injection position in the second layer, and randomly generating a target fault injection position based on the second probability distribution; In combination with the target fault injection position, simulating a third probability distribution corresponding to the fault degree in the third layer, and randomly generating a target fault degree based on the third probability distribution; Random fault injection information is determined based on the target fault type, the target fault injection location, and the target fault degree.

3. The fault injection method for the EP valve of the train air brake system according to claim 2, characterized in that: The first probability distribution, the second probability distribution, and the third probability distribution satisfy the following relationship: The first probability distribution, the second probability distribution, and the third probability distribution are the same; or, The first probability distribution, the second probability distribution, and the third probability distribution are different from each other; or, The first probability distribution is the same as the second probability distribution, and the first probability distribution is different from the third probability distribution; or, The first probability distribution is the same as the third probability distribution, and the first probability distribution is different from the second probability distribution; or, The second probability distribution is the same as the third probability distribution, and the first probability distribution is different from the second probability distribution.

4. A fault injector for an EP valve of a train air brake system, used to implement a fault injection method for an EP valve of a train air brake system as claimed in any one of claims 1 to 3, characterized in that: The fault injector comprises: a user setting interface, a fault injection control unit and an EP valve model library, wherein the user setting interface is connected to the fault injection control unit and the EP valve model library respectively; The user setting interface is used to build a braking system simulation model according to the principle of the train air braking system, and the braking system simulation model includes an EP valve normal model; set the fault type, fault injection position and fault degree of the EP valve, and generate an EP valve fault model according to the fault type, the fault injection position and the fault degree and the EP valve normal model; generate fault information based on a preset injection method and the EP valve fault model, and the preset injection method includes a specified fault injection method and a random fault injection method; The fault injection control unit is used to perform fault injection based on the fault information; The EP valve model library is used to store the EP valve fault model.

Images