Fuel regulator fault diagnosis model acquisition method, equipment, medium and product

Abstract

The present disclosure relates to the field of aviation engine technology, and in particular, provides a method, device, medium and product for obtaining a fuel regulator fault diagnosis model. The method for obtaining a fuel regulator fault diagnosis model comprises: constructing a mathematical model and an initial simulation model of a fuel regulator; performing model tuning on the initial simulation model based on the mathematical model to obtain a target simulation model of the fuel regulator; performing reliability verification on the target simulation model based on a fault injection strategy to obtain a reliability parameter value of the target simulation model; if the reliability parameter value is greater than a preset threshold, simulating multiple fault types using the target simulation model to obtain fault feature data of the fuel regulator under each fault type, and using the fault feature data associated with each fault type to train a fuel regulator fault diagnosis model; the present disclosure can improve the reliability of the obtained fuel regulator fault diagnosis model.

Description

Technical Field

[0001] The present disclosure relates to the field of aviation engines, and in particular to a method, device, medium and product for acquiring a fuel regulator fault diagnosis model. Background Art

[0002] The aircraft engine completes the fuel supply through the fuel regulator, provides fuel to the engine, and then realizes the flight state adjustment. Due to its high failure rate, various failure forms, and hidden failure characteristics, the fault diagnosis of the fuel regulator system is challenging.

[0003] In the related technology, the fuel regulator can be modeled through modeling software, and the fault characteristics of the fuel regulator after failure can be simulated through the fuel regulator simulation model, and a fault diagnosis model that can be used for fuel regulator fault diagnosis can be trained to perform fuel regulator fault diagnosis during the fuel regulator process.

[0004] However, the fault diagnosis solutions provided in the related art usually have the problem of low reliability of the fuel regulator fault diagnosis model constructed, which is easy to misjudge the fault of the fuel regulator. Summary of the invention

[0005] The present disclosure is proposed in view of the above problems. The present disclosure provides a method, device, medium and product for obtaining a fuel regulator fault diagnosis model, which can improve the reliability of the obtained fuel regulator fault diagnosis model.

[0006] According to one aspect of the present disclosure, a method for acquiring a fuel regulator fault diagnosis model is provided, comprising:

[0007] Construct mathematical model and initial simulation model of fuel regulator;

[0008] Performing model tuning on the initial simulation model based on the mathematical model to obtain a target simulation model of the fuel regulator;

[0009] Performing reliability verification on the target simulation model based on a fault injection strategy to obtain a reliability parameter value of the target simulation model;

[0010] If the reliability parameter value is greater than a preset threshold, the target simulation model is used to simulate multiple fault types to obtain fault feature data of the fuel regulator under each fault type, and the fault feature data associated with each fault type is used to train a fuel regulator fault diagnosis model.

[0011] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the above-mentioned method for acquiring a fuel regulator fault diagnosis model.

[0012] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned method for acquiring a fuel regulator fault diagnosis model is implemented.

[0013] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method for acquiring a fuel regulator fault diagnosis model is implemented.

[0014] As will be described in detail below, according to the fuel regulator fault diagnosis model acquisition method, device, medium and product of the embodiment of the present disclosure, the mathematical model of the fuel regulator can be used to tune the initial simulation model, and the reliability of the tuned target simulation model can be verified, so that the fault data characteristics obtained after the target simulation model after reliability verification is used to train the fuel regulator fault diagnosis model. On the one hand, the simulation model can be tuned by the mathematical model of the fuel regulator so that the constructed simulation model of the fuel regulator and the actual situation of the fuel regulator are more matched; on the other hand, after the simulation model of the fuel regulator is constructed, the reliability of the constructed simulation model can be tested by a fault injection strategy, and after determining that the constructed simulation model has achieved the expected goal, the fuel regulator fault diagnosis model can be trained using the fault characteristic data after simulating various faults using the simulation model, so as to improve the reliability of the trained fuel regulator fault diagnosis model.

[0015] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 is a flowchart illustrating a method for obtaining a fuel regulator fault diagnosis model according to an embodiment of the present disclosure.

[0018] Figure 2Schematic diagram showing a partial structure of a fuel regulator according to an embodiment of the present disclosure.

[0019] Figure 3 Schematic diagram of a simulation showing a partial structure of a fuel regulator according to an embodiment of the present disclosure.

[0020] Figure 4 It is a signal status schematic diagram of an embodiment of the present disclosure.

[0021] Figure 5 It is a signal status schematic diagram that further illustrates an embodiment of the present disclosure.

[0022] Figure 6 is a block diagram illustrating a fuel regulator fault diagnosis model acquisition device according to an embodiment of the present disclosure.

[0023] Figure 7 is a hardware block diagram illustrating a chip according to an embodiment of the present disclosure.

[0024] Figure 8 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure.

[0025] Fig. 9 is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0027] In the related art, after the fuel regulator is modeled, different faults of the fuel regulator can be simulated through the fuel regulator simulation model, and the fault characteristics of the fuel regulator under various fault conditions can be obtained to train the fault diagnosis model of the fuel regulator.

[0028] However, the fault diagnosis solutions provided in the related art usually directly perform fault simulation after establishing the fuel regulator to obtain the fault characteristics of the fuel regulator under various fault conditions and train the fuel regulator fault diagnosis model, resulting in low reliability of the constructed fuel regulator fault diagnosis model.

[0029] In order to solve the above problems, an embodiment of the present disclosure provides a fuel regulator fault diagnosis model acquisition solution. Figure 1 A flowchart of a method for acquiring a fuel regulator fault diagnosis model according to an exemplary embodiment of the present disclosure is shown. The method can be applied to a terminal device, which can be a computer, a notebook, or a tablet computer. Figure 1 As shown, the method of the embodiment of the present disclosure may include:

[0030] Step S101, constructing a mathematical model and an initial simulation model of a fuel regulator;

[0031] Step S102, optimizing the initial simulation model based on the simulation model to obtain a target simulation model of the fuel regulator;

[0032] Step S103, performing reliability verification on the target simulation model based on the fault injection strategy to obtain a reliability parameter value of the target simulation model;

[0033] Step S104, if the reliability parameter value is greater than a preset threshold, multiple fault types are simulated using the target simulation model to obtain fault characteristic data of the fuel regulator under each fault type, and the fault characteristic data associated with each fault type is used to train the fuel regulator fault diagnosis model;

[0034] In summary, the method for acquiring a fuel regulator fault diagnosis model provided by the embodiment of the present disclosure can construct a mathematical model and an initial simulation model of a fuel regulator; perform model tuning on the initial simulation model based on the simulation model to obtain a target simulation model of the fuel regulator; perform reliability verification on the target simulation model based on a fault injection strategy to obtain a reliability parameter value of the target simulation model; if the reliability parameter value is greater than a preset threshold, the target simulation model is used to simulate multiple fault types to obtain fault feature data of the fuel regulator under each fault type, and the fault feature data associated with each fault type is used to train the fuel regulator fault diagnosis model. On the one hand, the simulation model can be tuned by the mathematical model of the fuel regulator so that the constructed simulation model of the fuel regulator is more consistent with the actual situation of the fuel regulator; on the other hand, after the simulation model of the fuel regulator is constructed, the reliability of the constructed simulation model can be detected by the fault injection strategy, and after determining that the constructed simulation model reaches the expected goal, the fault feature data after simulating various faults by the simulation model are used to train the fuel regulator fault diagnosis model, so as to improve the reliability of the trained fuel regulator fault diagnosis model.

[0035] The following Figure 1 The specific implementation methods of each step in the embodiment shown are described in detail:

[0036] In step S101, the terminal device may construct a mathematical model and an initial simulation model of the fuel regulator.

[0037] In the embodiment of the present disclosure, the mathematical model of the fuel regulator is used to characterize the internal working principle of the fuel regulator, and the simulation model of the fuel regulator is a semi-physical simulation model of the fuel regulator; it can be understood that the mathematical model and the initial simulation model of the fuel regulator may be different based on the specific structure of the fuel regulator, and the embodiment of the present disclosure does not limit this.

[0038] It should be noted that some structures of the fuel regulator are as follows Figure 2 As shown, it includes a metering valve 201, a flow stabilizer 202, a pressure differential valve pilot stage 203 and a pressure differential valve actuator stage 204. Figure 2 The working principle of the fuel regulator shown in the figure includes: electro-hydraulic position servo ( Figure 2 The first control pressure P outputted by the hydraulic cylinder control chamber is not shown in FIG. c and the second control pressure P s The opening of the metering valve 201 is controlled, and the inlet and outlet pressure difference of the metering valve 201 (that is, the difference between the pressure before metering and the pressure after metering) is controlled to remain constant through the flow stabilizer 202 and the pressure differential valve pilot stage 203. Finally, the pressure differential valve actuator stage 204 outputs stable fuel to achieve fuel flow control. It should be noted that in Figure 2 In the fuel regulator shown, after the control oil output by the electro-hydraulic servo valve enters the spring chamber of the metering valve 201, the area of ​​the metering window can be changed by adjusting the axial displacement of the metering valve valve core. When the opening of the metering window changes according to the prescribed opening law, regular metering of the fuel flow in the metering valve can be achieved.

[0039] In an optional embodiment, the process of constructing the mathematical model of the fuel regulator by the terminal device may include: in response to the mathematical model input instruction of the fuel regulator, obtaining the flow equation of the metering valve in the fuel regulator, the flow continuity equation of the hydraulic cylinder control chamber, and the force balance equation of the piston and the load in the metering valve; then, combining the flow equation of the metering valve, the flow continuity equation of the hydraulic cylinder control chamber, and the force balance equation of the piston and the load in the metering valve to obtain the mathematical model of the fuel regulator, wherein the hydraulic cylinder control chamber is the hydraulic cylinder control chamber of the electro-hydraulic servo valve connected to the metering valve. Based on the working principle of the fuel regulator, a mathematical model for characterizing the flow change of the metering valve and the pressure change of the electro-hydraulic servo valve in the fuel regulator can be determined, so as to facilitate linearization of the simulation model based on the mathematical model of the fuel regulator, and improve the matching degree between the determined simulation model and the actual condition of the fuel regulator.

[0040] Among them, the flow equation of the metering valve is:

[0041] Q1=K q X v -K eP c ; (Formula 1)

[0042] In formula 1, Q1 is the flow rate of the metering valve, K q is the flow coefficient, X v K is the displacement of the metering valve core. e is the pressure coefficient, P c is the first control pressure for the metering valve;

[0043] The flow continuity equation of the hydraulic cylinder control room is:

[0044]

[0045] In Formula 2, C ip is the hydraulic cylinder internal leakage coefficient, P s A is the second control pressure for the metering valve. h is the piston area in the hydraulic cylinder control chamber, V c is the volume of the hydraulic cylinder control chamber, β e is the elastic modulus of the hydraulic oil;

[0046] The force balance equation between the piston and the load in the metering valve is:

[0047]

[0048] In formula 3, A r is the effective area on the piston rod side, m t is the total mass of the piston and the load, B p is the viscous damping coefficient, K is the load spring stiffness, F L is the external load force.

[0049] In an optional implementation, the process of constructing the initial simulation model by the terminal device may include: in response to the fuel regulator model construction operation in the simulation tool, obtaining the initial simulation model of the fuel regulator. The simulation tool may be determined based on actual needs, which is not limited in the embodiment of the present disclosure. For example, the simulation tool may be AMEsim simulation software.

[0050] For example, Figure 2 The initial simulation model of the fuel regulator shown in Figure 1 can be constructed as follows: Figure 3 shown.

[0051] It should be noted that in the embodiment of the present disclosure, in the process of constructing the initial simulation model of the fuel regulator, the actual operating temperature and / or fluid properties of the fuel regulator can be set to make the initial simulation model of the fuel regulator more consistent with the actual working conditions of the fuel regulator.

[0052] In step S102, the terminal device optimizes the initial simulation model based on the mathematical model to obtain a target simulation model of the fuel regulator.

[0053] In the embodiments of the present disclosure, the initial simulation model can usually simply characterize the components included in the fuel regulator and the connection relationship between the components. Therefore, the initial simulation model can be tuned based on a mathematical model to obtain a target simulation model of the fuel regulator, which can truly restore the actual performance of the fuel regulator.

[0054] In an optional embodiment, the process of the terminal device acquiring the target simulation model can be implemented based on the system identification principle, and the terminal device performs model tuning on the initial simulation model based on the mathematical model. The process of obtaining the target simulation model of the fuel regulator may include: inputting a reference signal into the mathematical model and the initial simulation model to obtain a first response of the mathematical model in the time dimension and a second response of the initial simulation model in the time dimension, wherein if the difference between the first response and the second response is less than a response difference threshold, it is determined that the target simulation model of the fuel regulator is obtained; otherwise, the simulation model is tuned and the above process is repeated until the target simulation model is obtained; wherein, the response difference threshold can be determined based on actual needs, and the embodiments of the present disclosure are not limited to this.

[0055] For example, Figure 4 As shown, Figure 4 A schematic diagram of signal states in a process of acquiring a target simulation model provided in an embodiment of the present disclosure, wherein the horizontal axis is time and the vertical axis is a response signal, including a reference signal 401, a first response 402 and a second response 403.

[0056] In step S103, the terminal device performs reliability verification on the target simulation model based on the fault injection strategy to obtain a reliability parameter value of the target simulation model.

[0057] In the disclosed embodiment, the reliability parameter value is used to characterize the reliability of the constructed target simulation model, that is, the reliability of the simulation effect of the actual condition of the fuel regulator; wherein, the higher the reliability parameter value, the more the constructed target simulation model can truly reflect the actual state of fuel regulation.

[0058] In an optional implementation, the terminal device verifies the reliability of the target simulation model based on the fault injection strategy, and the process of obtaining the reliability parameter value of the target simulation model may include: injecting fault parameters associated with multiple fault types into the target simulation model to obtain the steady-state value of the simulation response associated with each fault type, and injecting fault parameters associated with multiple fault types into the mathematical model to obtain the steady-state value of the real response associated with each fault type; then, according to the steady-state value of the simulation response associated with each fault type and the steady-state value of the real response, determine the consistency analysis parameter value of the simulation fault data and the real fault data associated with each fault type; further, according to the consistency analysis parameter value and the consistency prediction parameter value associated with each fault type, determine the reliability parameter value of the target simulation model. The reliability analysis of the constructed target simulation model can be performed by the quantitative analysis results (i.e., consistency analysis parameter value) and qualitative analysis results (i.e., consistency prediction parameter value) of the fuel regulator in the fault state to ensure the reliability of the constructed simulation model.

[0059] Among them, the process of determining the consistency analysis parameter value of the simulated fault data and the real fault data associated with each fault type by the terminal device according to the steady-state value of the simulated response associated with each fault type and the steady-state value of the real response can be implemented based on the first formula, wherein the first formula is:

[0060]

[0061] In Formula 4, C t (+∞) is the steady-state value of the true response, C e (+∞) is the steady-state value of the simulation response, i is the i-th fault type among n fault types, and match_value is the consistency analysis parameter value.

[0062] The process of determining the reliability parameter value of the target simulation model by the terminal device according to the consistency analysis parameter value and the consistency estimation parameter value associated with each fault type can be implemented based on the second formula, which is:

[0063]

[0064] In Formula 5, ω i is the weight of the i-th fault type among n fault types, true_value is the consistency estimation parameter value, and estimate_value is the reliability parameter value.

[0065] In an optional embodiment, after obtaining the steady-state value of the simulated response associated with each fault type and the steady-state value of the real response associated with each fault type, the terminal device can also: filter the steady-state value of the simulated response associated with each fault type to obtain the denoised steady-state value of the simulated response associated with each fault type; and filter the steady-state value of the real response associated with each fault type to obtain the denoised steady-state value of the real response associated with each fault type. The response signal obtained during the fault simulation process can be denoised to prevent the fault simulation from affecting the mathematical model of the fuel regulator and the target simulation model, so as to improve the accuracy of the reliability parameter value of the determined target simulation model.

[0066] Among them, denoising can be performed by using a Kalman filter, such as Figure 5 As shown, Figure 5 A schematic diagram of the signal state of the metering valve core displacement under denoising and non-denoising conditions using a Kalman filter is shown, with the horizontal axis representing time and the vertical axis representing the metering valve core displacement, wherein 501 is the signal response of the metering valve core displacement under non-denoising conditions, and 502 is the signal response of the metering valve core displacement under denoising conditions.

[0067] It can be understood that after denoising the response, the terminal device determines the consistency analysis parameter values ​​of the simulated fault data and the real fault data associated with each fault type based on the steady-state value of the simulated response associated with each fault type and the steady-state value of the real response, which may include: determining the consistency analysis parameter values ​​of the simulated fault data and the real fault data associated with each fault type based on the denoised steady-state value of the simulated response associated with each fault type and the denoised steady-state value of the real response.

[0068] It should be noted that, in the embodiments of the present disclosure, the fault type can be determined based on actual conditions, and the embodiments of the present disclosure do not limit this. For example, as shown in Tables 1 and 2, Table 1 shows common fault types of the metering valve in the fuel regulator, and Table 2 shows the fault types of the pilot stage of the differential pressure valve in the fuel regulator.

[0069] Table 1

[0070]

[0071] Table 2

[0072]

[0073] In step S104, if the reliability parameter value is greater than a preset threshold, the terminal device simulates multiple fault types using the target simulation model to obtain fault characteristic data of the fuel regulator under each fault type, and trains the fuel regulator fault diagnosis model using the fault characteristic data associated with each fault type;

[0074] In an embodiment of the present disclosure, if the reliability parameter value is greater than a preset threshold, the target simulation model constructed on the surface can truly restore the actual state of the fuel regulator; wherein the preset threshold can be determined based on actual needs, and the embodiment of the present disclosure does not limit this; the fault characteristic data may include: pressure differential valve node pressure, throttle valve outlet flow, pressure differential valve valve core displacement, metering valve valve core displacement and / or pressure reduction differential valve pressure, etc.

[0075] In an optional embodiment, in order to further determine the reliability of the target simulation model, when the reliability parameter value is greater than a preset threshold, the terminal device can also: obtain the simulation response characteristic parameter value of the target simulation model, and determine to train the fuel regulator fault diagnosis model when it is determined that the simulation response characteristic parameter value meets the preset requirements, wherein the simulation response characteristic parameters include data fit, steady-state error, rise time, adjustment time and overshoot, wherein the data fit is used to characterize the degree of match between the simulated data and actual fault data of the target simulation model for the fault type.

[0076] The process of determining whether the simulation response characteristic parameter value meets the preset requirements may include: if the data fit is greater than the data fit threshold, the steady-state error is less than the steady-state error threshold, the rise time is less than the first time threshold, the adjustment time is less than the second time threshold, and the overshoot is less than the overshoot threshold, then it is determined that the simulation response characteristic parameter value meets the preset requirements. The data fit threshold, the steady-state error threshold, the first time threshold, the second time threshold and the overshoot threshold can be determined based on actual needs, and the embodiments of the present disclosure do not limit this.

[0077] It can be understood that in the embodiments of the present disclosure, when the reliability parameter value is less than or equal to the preset threshold, or the simulation response characteristic parameter value does not meet the preset requirements, it is necessary to continue to tune the target simulation model until the reliability parameter value is greater than the preset threshold, or the reliability parameter value is greater than the preset threshold and the simulation response characteristic parameter value meets the preset requirements.

[0078] In an optional embodiment, the fault feature data is time series data, and the terminal device uses the fault feature data associated with each fault type to train the fuel regulator fault diagnosis model. The process may include: for the fault feature data associated with each fault type, traverse the fault feature data based on the feature extraction window length value to obtain multiple sub-fault feature data; then, combine the multiple sub-fault feature data and the sample label associated with each sub-fault feature data to obtain a sample data set; further, use the sample data set to train the time series model to obtain the fuel regulator fault diagnosis model, wherein the sample label is the fault type associated with the fault feature data to which the sub-fault feature data belongs. In the process of training the fuel regulator fault diagnosis model, the feature extraction window can be used to extract multiple sub-fault feature data from the fault feature data associated with each fault type to train the fuel regulator fault diagnosis model, thereby enriching the sample data volume, enhancing the sample data's expressiveness of the fuel regulator's fault features, and improving the reliability of the fault diagnosis results of the trained fuel regulator fault diagnosis model.

[0079] It should be noted that in the embodiments of the present disclosure, the type of time series model can be determined based on actual needs, and the embodiments of the present disclosure are not limited to this. For example, the time series model can be a long short-term memory (Long Short-Term Memory, LSTM) network model, or an auto-regressive moving average (Auto-Regressive Moving Average Model, ARMA) model, etc.

[0080] In an optional embodiment, the process in which the terminal device traverses the fault feature data based on the feature extraction window length value to obtain multiple sub-fault feature data may include: starting from the fault feature data of the first unit time in the fault feature data, based on the feature extraction window length value, obtaining sub-fault feature data in the fault feature data; then, determining the moving average and moving standard deviation of the current time step, wherein one sliding of the feature extraction window is one time step; wherein, if the feature extraction window is determined to be a feature extraction window to be updated based on the moving average and the moving standard deviation, then the feature extraction window length value is updated based on a preset rule to obtain an updated feature extraction window length value; further, based on the updated feature extraction window length value and the feature extraction window sliding step size, the above process of obtaining sub-fault feature data is repeated until the fault feature data is traversed. In the process of extracting sub-fault feature data using the feature extraction window, after each sub-fault feature data is obtained, the rationality of the feature extraction window length value can be judged, and if it is determined that the feature extraction window length value is unreasonable, the feature extraction window length value can be updated. Since the moving average and moving fluctuation of the data are considered in the updating process of the feature extraction window length value, the feature differences between the sub-fault feature data obtained each time for characterizing the same type of fault type can be reduced, thereby improving the reliability and rationality of the determined sample data.

[0081] It should be noted that in the embodiments of the present disclosure, the feature extraction window length value is the number of unit time that the feature extraction window can obtain each time. For example, the feature extraction window length value can be 10 unit time, or 20 unit time; the feature extraction window sliding step is used to characterize the number of time units that the feature extraction window moves each time, wherein the feature extraction window sliding step can be determined based on actual needs, and the embodiments of the present disclosure do not limit this.

[0082] The process of determining the moving standard deviation by the terminal device can be implemented based on the third formula, which is:

[0083]

[0084] In Formula 6, MA i is the moving average of the i-th time step, x j is the sub-fault feature data of the jth time step, and n is the window length value.

[0085] The process of determining the moving standard deviation by the terminal device can be implemented based on the fourth formula, wherein the fourth formula is:

[0086]

[0087] In Formula 7, STD iis the moving standard deviation of the ith time step,

[0088] In an optional embodiment, the process of the terminal device determining whether the feature extraction window is a feature extraction window to be updated based on the moving average and the moving standard deviation may include: determining the product of the moving standard deviation and the window adjustment parameter value, and determining the sum of the product and the moving average to obtain the feature extraction window adjustment reference value; wherein, if the sub-fault feature data determined at the current time step is greater than or less than the feature extraction window adjustment reference value, the feature extraction window is determined to be a feature extraction window to be updated. Whether the feature extraction window needs to be adjusted can be determined by the window adjustment parameter value used to characterize the sensitivity of adjusting the window size, the moving average used to characterize the change trend of the sub-fault feature data, and the moving standard deviation used to characterize the discreteness of the sub-fault feature data, so as to improve the adjustment reliability of the feature extraction window.

[0089] The window adjustment parameter value is used to characterize the sensitivity of adjusting the window size, and the window adjustment parameter value can be determined based on the offline characteristic data of various types of fuel regulator faults, which is not limited in the embodiment of the present disclosure. It can be understood that if the sub-fault characteristic data determined at the current time step is greater than or less than the feature extraction window adjustment reference value, it is determined that the feature extraction window does not need to be updated.

[0090] In an optional embodiment, after obtaining the sub-fault characteristic data, the terminal device may also: determine the calculated statistical characteristics of the sub-fault characteristic data, then the terminal device combines multiple sub-fault characteristic data, and the sample label associated with each sub-fault characteristic data, and the process of obtaining a sample data set may include: combining multiple sub-fault characteristic data, and the sample label and calculated statistical characteristics associated with each sub-fault characteristic data to obtain a sample data set; wherein the calculated statistical characteristics may include: measurement indicators of the central tendency, degree of dispersion and distribution form of the sub-fault characteristic data, etc.

[0091] In an optional embodiment, the terminal device can also: read the fuel regulator characteristics of the fuel regulator under various fault types, then the terminal device combines multiple sub-fault characteristic data, and the sample label associated with each sub-fault characteristic data, and the process of obtaining the sample data set may include: combining multiple sub-fault characteristic data, and the sample label associated with each sub-fault characteristic data, calculating statistical features and fuel regulator characteristics, and obtaining the sample data set; wherein the fuel regulator characteristics may be characteristics such as temperature, pressure and / or speed of the fuel regulator.

[0092] It can be understood that the fuel regulator feature associated with the sub-fault feature data is the fuel regulator feature associated with the fault feature data to which the sub-fault feature data belongs.

[0093] An exemplary embodiment of the present disclosure provides a fuel regulator fault diagnosis model acquisition device, which may be a server or a chip applied to a server. Figure 6 FIG. 1 is a schematic block diagram of the functional modules of a fuel regulator fault diagnosis model acquisition device according to an exemplary embodiment of the present disclosure. Figure 6 As shown, the fuel regulator fault diagnosis model acquisition device 600 includes:

[0094] A construction module 601 is configured to construct a mathematical model and an initial simulation model of a fuel regulator;

[0095] A tuning module 602 is configured to perform model tuning on the initial simulation model based on the mathematical model to obtain a target simulation model of the fuel regulator;

[0096] The verification module 603 is configured to perform reliability verification on the target simulation model based on a fault injection strategy to obtain a reliability parameter value of the target simulation model;

[0097] The training module 604 is configured to simulate multiple fault types using the target simulation model if the reliability parameter value is greater than a preset threshold, obtain fault feature data of the fuel regulator under each fault type, and train the fuel regulator fault diagnosis model using the fault feature data associated with each fault type.

[0098] Optionally, building block 601 is configured to:

[0099] In response to the mathematical model input instruction of the fuel regulator, a flow equation of the metering valve in the fuel regulator, a flow continuity equation of the hydraulic cylinder control chamber, and a force balance equation between the piston and the load in the metering valve are obtained, wherein the hydraulic cylinder control chamber is a hydraulic cylinder control chamber of an electro-hydraulic servo valve connected to the metering valve;

[0100] The mathematical model of the fuel regulator is obtained by combining the flow equation of the metering valve, the flow continuity equation of the hydraulic cylinder control chamber, and the force balance equation between the piston and the load in the metering valve.

[0101] Optionally, the verification module 603 is configured to:

[0102] Injecting fault parameters respectively associated with a plurality of fault types into the target simulation model to obtain a steady-state value of a simulation response associated with each fault type;

[0103] Injecting fault parameters respectively associated with a plurality of fault types into the mathematical model to obtain a steady-state value of a real response associated with each fault type;

[0104] Determining consistency analysis parameter values ​​of the simulated fault data and the real fault data associated with each fault type according to the steady-state value of the simulated response and the steady-state value of the real response associated with each fault type;

[0105] The reliability parameter value of the target simulation model is determined according to the consistency analysis parameter value and the consistency estimation parameter value associated with each fault type.

[0106] Optionally, the device further includes a denoising module 605 configured to:

[0107] Performing filtering processing on the steady-state value of the simulation response associated with each of the fault types to obtain a denoised steady-state value of the simulation response associated with each of the fault types;

[0108] The steady-state value of the real response associated with each of the fault types is filtered to obtain a denoised steady-state value of the real response associated with each of the fault types.

[0109] Optionally, the fault feature data is time series data, and the training module 604 is configured to:

[0110] For the fault feature data associated with each fault type, traverse the fault feature data based on the feature extraction window length value to obtain a plurality of sub-fault feature data;

[0111] Combining a plurality of sub-fault feature data and a sample label associated with each sub-fault feature data to obtain a sample data set, wherein the sample label is a fault type associated with the fault feature data to which the sub-fault feature data belongs;

[0112] The sample data set is used to train a time series model to obtain a fuel regulator fault diagnosis model.

[0113] Optionally, the training module 604 is configured to:

[0114] Starting from the first unit time of fault feature data in the fault feature data, based on the feature extraction window length value, obtaining sub-fault feature data in the fault feature data;

[0115] Determine the moving average and moving standard deviation of the current time step, where one sliding of the feature extraction window is one time step;

[0116] If it is determined that the feature extraction window is a feature extraction window to be updated based on the moving average value and the moving standard deviation, then the feature extraction window length value is updated based on a preset rule to obtain an updated feature extraction window length value;

[0117] Based on the updated feature extraction window length value and the feature extraction window sliding step size, the above process of obtaining the sub-fault feature data is repeated until the fault feature data is traversed.

[0118] Optionally, the training module 604 is configured to:

[0119] Determine the product of the moving standard deviation and the window adjustment parameter value, and determine the sum of the product and the moving average value to obtain a feature extraction window adjustment reference value;

[0120] If the sub-fault feature data determined at the current time step is greater than or less than the feature extraction window adjustment reference value, the feature extraction window is determined to be a feature extraction window to be updated.

[0121] Figure 7 Schematic block diagram of a chip according to an exemplary embodiment of the present disclosure is shown. Figure 7 As shown, the chip 700 includes one or more (including two) processors 701 and a communication interface 702. The communication interface 702 can support the terminal device to perform the data sending and receiving steps in the above-mentioned fuel regulator fault diagnosis model acquisition method, and the processor 701 can support the server to perform the data processing steps in the above-mentioned fuel regulator fault diagnosis model acquisition method.

[0122] Optional, such as Figure 7 As shown, the chip 700 also includes a memory 703, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory (NVRAM).

[0123] In some embodiments, Figure 7 As shown, the processor 701 performs corresponding operations by calling the operation instructions stored in the memory (the operation instructions may be stored in the operating system). The processor 701 controls the processing operations of any one of the terminal devices, and the processor may also be called a central processing unit (CPU). The memory 703 may include a read-only memory and a random access memory, and provides instructions and data to the processor 701. A portion of the memory 703 may also include NVRAM. For example, in an application, the memory, the communication interface, and the memory are coupled together through a bus system, wherein the bus system may include a power bus, a control bus, and a status signal bus in addition to a data bus. However, for the sake of clarity, in Figure 7 Various buses are labeled as bus system 704 .

[0124] The method disclosed in the above-mentioned embodiment of the present disclosure can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above-mentioned processor may be a general-purpose processor, a digital signal processor (digital signal processing, DSP), an ASIC, a field-programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiment of the present disclosure can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware.

[0125] The exemplary embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to cause the electronic device to perform the method according to the embodiment of the present disclosure when executed by the at least one processor.

[0126] The exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform the method according to the embodiments of the present disclosure.

[0127] like Figure 8 As shown, the exemplary embodiment of the present disclosure further provides a computer program product 800, including a computer program 801, wherein when the computer program is executed by a processor of a computer, it is used to enable the computer to perform the method according to the embodiment of the present disclosure.

[0128] refer to Fig. 9, a block diagram of an electronic device 900 that can be used as a terminal device of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0129] like Fig. 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0130] A plurality of components in the electronic device 900 are connected to the I / O interface 905, including: an input unit 906, an output unit 907, a storage unit 908, and a communication unit 909. The input unit 906 may be any type of device capable of inputting information to the electronic device 900, and the input unit 906 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 907 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 908 may include, but is not limited to, a disk, an optical disk. The communication unit 909 allows the electronic device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0131] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above. For example, in some embodiments, the method of the exemplary embodiment of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 900 via the ROM 902 and / or the communication unit 909. In some embodiments, the computing unit 901 may be configured to perform the method of the exemplary embodiment of the present disclosure by any other appropriate means (e.g., by means of firmware).

[0132] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0133] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0135] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0136] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0137] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0138] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, a tape; it may also be an optical medium, for example, a digital video disc (DVD); it may also be a semiconductor medium, for example, a solid state drive (SSD).

[0139] Although the present disclosure has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely exemplary illustrations of the present disclosure as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A method for obtaining a fuel regulator fault diagnosis model, characterized in that: include: Construct mathematical model and initial simulation model of fuel regulator; Performing model tuning on the initial simulation model based on the mathematical model to obtain a target simulation model of the fuel regulator; Performing reliability verification on the target simulation model based on a fault injection strategy to obtain a reliability parameter value of the target simulation model; If the reliability parameter value is greater than a preset threshold, simulating multiple fault types using the target simulation model to obtain fault feature data of the fuel regulator under each fault type, and training a fuel regulator fault diagnosis model using the fault feature data associated with each fault type; The reliability verification of the target simulation model based on the fault injection strategy to obtain the reliability parameter value of the target simulation model includes: Injecting fault parameters respectively associated with a plurality of fault types into the target simulation model to obtain a steady-state value of a simulation response associated with each fault type; Injecting fault parameters respectively associated with a plurality of fault types into the mathematical model to obtain a steady-state value of a real response associated with each fault type; Determining consistency analysis parameter values ​​of the simulated fault data and the real fault data associated with each fault type according to the steady-state value of the simulated response and the steady-state value of the real response associated with each fault type; The reliability parameter value of the target simulation model is determined according to the consistency analysis parameter value and the consistency estimation parameter value associated with each fault type.

2. The method for acquiring a fuel regulator fault diagnosis model according to claim 1, characterized in that: The mathematical model of the fuel regulator is constructed, including: In response to the mathematical model input instruction of the fuel regulator, a flow equation of the metering valve in the fuel regulator, a flow continuity equation of the hydraulic cylinder control chamber, and a force balance equation between the piston and the load in the metering valve are obtained, wherein the hydraulic cylinder control chamber is a hydraulic cylinder control chamber of an electro-hydraulic servo valve connected to the metering valve; The mathematical model of the fuel regulator is obtained by combining the flow equation of the metering valve, the flow continuity equation of the hydraulic cylinder control chamber, and the force balance equation between the piston and the load in the metering valve.

3. The method for acquiring a fuel regulator fault diagnosis model according to claim 1, wherein: The method further comprises: Performing filtering processing on the steady-state value of the simulation response associated with each of the fault types to obtain a denoised steady-state value of the simulation response associated with each of the fault types; The steady-state value of the real response associated with each of the fault types is filtered to obtain a denoised steady-state value of the real response associated with each of the fault types.

4. The method for acquiring a fuel regulator fault diagnosis model according to claim 1, wherein: The fault characteristic data is time series data, and the method of using the fault characteristic data associated with each fault type to train the fuel regulator fault diagnosis model includes: For the fault feature data associated with each fault type, traverse the fault feature data based on the feature extraction window length value to obtain a plurality of sub-fault feature data; Combining a plurality of sub-fault feature data and a sample label associated with each sub-fault feature data to obtain a sample data set, wherein the sample label is a fault type associated with the fault feature data to which the sub-fault feature data belongs; The sample data set is used to train a time series model to obtain a fuel regulator fault diagnosis model.

5. The method for acquiring a fuel regulator fault diagnosis model according to claim 4, characterized in that: The fault feature data is traversed based on the feature extraction window length value to obtain a plurality of sub-fault feature data, including: Starting from the first unit time of fault feature data in the fault feature data, based on the feature extraction window length value, obtaining sub-fault feature data in the fault feature data; Determine the moving average and moving standard deviation of the current time step, where one sliding of the feature extraction window is one time step; If it is determined that the feature extraction window is a feature extraction window to be updated based on the moving average value and the moving standard deviation, then the feature extraction window length value is updated based on a preset rule to obtain an updated feature extraction window length value; Based on the updated feature extraction window length value and the feature extraction window sliding step size, the above process of obtaining the sub-fault feature data is repeated until the fault feature data is traversed.

6. The method for acquiring a fuel regulator fault diagnosis model according to claim 5, characterized in that: Determining whether the feature extraction window is a feature extraction window to be updated based on the moving average value and the moving standard deviation includes: Determine the product of the moving standard deviation and the window adjustment parameter value, and determine the sum of the product and the moving average value to obtain a feature extraction window adjustment reference value; If the sub-fault feature data determined at the current time step is greater than or less than the feature extraction window adjustment reference value, the feature extraction window is determined to be a feature extraction window to be updated.

7. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the fuel regulator fault diagnosis model acquisition method of claim 1.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for acquiring a fuel regulator fault diagnosis model according to claim 1 is implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for acquiring a fuel regulator fault diagnosis model according to claim 1 is implemented.

Images