Fault diagnosis model training and fault diagnosis method, equipment and medium

Abstract

The invention relates to the technical field of fault diagnosis, and particularly provides a fault diagnosis model training and fault diagnosis method and device, and a medium, and the method comprises the steps: obtaining a sample data set, inputting the sample feature data into a first sub-model of a fault diagnosis model, obtaining a sample prediction fault mode, and obtaining a second sub-model of the fault diagnosis model; inputting the sample prediction fault mode into a second sub-model of the fault diagnosis model to obtain a sample motor internal and external leakage coefficient of the hydraulic winch, and inputting the sample motor internal and external leakage coefficient and the sample control state signal into a system model of the hydraulic winch to obtain a sample operation parameter prediction value of the hydraulic winch; and on the basis of the fault mode label, the sample prediction fault mode, the sample operation parameter value and the sample operation parameter prediction value, a trained fault diagnosis model is obtained under the condition that convergence of the fault diagnosis model is determined. The fault diagnosis accuracy of the hydraulic winch can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of fault diagnosis, and in particular to a fault diagnosis model training and a fault diagnosis method, device and medium. Background Art

[0002] Hydraulic winches are widely used for lifting or towing materials in marine engineering, construction, water conservancy projects, forestry, mining, docks and other scenarios. Since hydraulic winches usually work in harsh environments and have complex and changeable working conditions, they are prone to failure. In order to reduce the property and manpower losses caused by hydraulic winch failures, accurate fault diagnosis is crucial to improving system reliability.

[0003] In the related art, fault diagnosis of the hydraulic winch can be performed by constructing a physical model of the hydraulic winch, or by analyzing the signal characteristics of the hydraulic winch.

[0004] However, the fault diagnosis solutions for hydraulic winches provided in the related art usually have the problems of great difficulty in diagnosis and inaccurate diagnosis results. Summary of the invention

[0005] The present disclosure is proposed in view of the above problems. The present disclosure provides a fault diagnosis model training and a fault diagnosis method, device and medium, which can improve the fault diagnosis accuracy of a hydraulic winch.

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

[0007] Acquire a sample data set, wherein the sample data set includes sample operating parameter values ​​of the hydraulic winch, fault mode labels associated with the sample operating parameter values, and sample control state signals of the hydraulic winch;

[0008] Inputting sample characteristic data into a first sub-model of a fault diagnosis model to obtain a sample predicted fault mode, and inputting the sample predicted fault mode into a second sub-model of the fault diagnosis model to obtain a sample motor internal and external leakage coefficient of the hydraulic winch, wherein the sample characteristic data is determined based on the sample operating parameter value;

[0009] Input the internal and external leakage coefficients of the sample motor and the sample control state signal into the system model of the hydraulic winch to obtain the predicted values ​​of the sample operating parameters of the hydraulic winch;

[0010] When it is determined that the fault diagnosis model has converged based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter predicted value, a trained fault diagnosis model is obtained.

[0011] According to another aspect of the present disclosure, a fault diagnosis method is provided, comprising:

[0012] Obtaining the operating parameter values ​​of the hydraulic winch to be diagnosed;

[0013] The operating parameter value is input into the first sub-model in the fault diagnosis model to obtain the fault mode diagnosis result of the hydraulic winch to be diagnosed, wherein the fault diagnosis model is obtained based on the above-mentioned fault diagnosis model training.

[0014] 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 steps of the above method.

[0015] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0016] The fault diagnosis model training and fault diagnosis method, device and medium provided by the embodiments of the present disclosure can introduce the system model of the hydraulic winch during the fault diagnosis model training process to train a fault diagnosis model that can take into account the system laws and operating parameter characteristics of the hydraulic winch for fault diagnosis, so as to improve the accuracy of the fault diagnosis results of the hydraulic winch determined by the trained fault diagnosis model.

[0017] 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

[0018] 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.

[0019] Figure 1 is a flowchart illustrating the application of the fault diagnosis model training method according to an embodiment of the present disclosure.

[0020] Figure 2 It is a schematic diagram illustrating the structure of a fault diagnosis model according to an embodiment of the present disclosure.

[0021] Figure 3 It is a schematic diagram illustrating the fault diagnosis accuracy of the fault diagnosis model obtained by training based on different weight combinations according to an embodiment of the present disclosure.

[0022] Figure 4 is a flow chart of a fault diagnosis method according to an embodiment of the present disclosure.

[0023] Figure 5 It is a block diagram of a fault diagnosis model training device according to an embodiment of the present disclosure.

[0024] Figure 6 It is a block diagram of a fault diagnosis device according to an embodiment of the present disclosure.

[0025] Figure 7 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure.

[0026] Figure 8 is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] 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.

[0028] In the related art, in the process of diagnosing hydraulic winch faults by constructing a physical model of the hydraulic winch, not only a large amount of system knowledge is required, but it is also difficult to ensure the accuracy of the constructed physical model, resulting in great difficulty and low accuracy in diagnosing hydraulic winch faults.

[0029] At the same time, in the process of hydraulic winch fault diagnosis by analyzing the signal characteristics of the operating parameter values ​​of the hydraulic winch, since only the signal characteristics of the operating parameter values ​​of the hydraulic winch are paid attention to, less information is paid attention to in the fault analysis process of the hydraulic winch, resulting in inaccurate diagnosis results.

[0030] In order to solve the above problems, the present disclosure provides a fault diagnosis model training method, which can be applied to a terminal device, which can be an electronic device such as a computer, a notebook or a server. Figure 1 As shown, the fault diagnosis model training method includes:

[0031] Step S101, obtaining a sample data set;

[0032] The sample data set includes sample operating parameter values ​​of the hydraulic winch, fault mode labels associated with the sample operating parameter values, and sample control state signals of the hydraulic winch;

[0033] Step S102, inputting the sample characteristic data into the first sub-model of the fault diagnosis model to obtain a sample predicted fault mode, and inputting the sample predicted fault mode into the second sub-model of the fault diagnosis model to obtain the internal and external leakage coefficient of the sample motor of the hydraulic winch;

[0034] Wherein, the sample characteristic data is determined based on the sample operation parameter value;

[0035] Step S103, inputting the internal and external leakage coefficients of the sample motor and the sample control state signal into the system model of the hydraulic winch to obtain the predicted values ​​of the sample operating parameters of the hydraulic winch;

[0036] Step S104, when it is determined that the fault diagnosis model has converged based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter predicted value, a trained fault diagnosis model is obtained.

[0037] In summary, the fault diagnosis model training provided by the example of the present disclosure can obtain a sample data set, input the sample feature data into the first sub-model of the fault diagnosis model to obtain a sample predicted fault mode, and input the sample predicted fault mode into the second sub-model of the fault diagnosis model to obtain the sample motor internal and external leakage coefficients of the hydraulic winch, and input the sample motor internal and external leakage coefficients and the sample control state signal into the system model of the hydraulic winch to obtain the sample operating parameter prediction values ​​of the hydraulic winch; and, when it is determined that the fault diagnosis model converges based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter prediction value, a trained fault diagnosis model is obtained; in the process of fault diagnosis model training, the system model of the hydraulic winch can be introduced to train a fault diagnosis model that can take into account the system laws and operating parameter characteristics of the hydraulic winch for fault diagnosis, so as to improve the accuracy of the fault diagnosis results of the hydraulic winch determined by the trained fault diagnosis model.

[0038] The following Figure 1 The specific implementation methods of each step in the embodiment shown are described in detail:

[0039] In step S101, the terminal device obtains a sample data set.

[0040] In the embodiment of the present disclosure, the sample data set includes sample operating parameter values ​​of the hydraulic winch, fault mode labels associated with the sample operating parameter values, and sample control status signals of the hydraulic winch; it can be understood that in the embodiment of the present disclosure, the sample data set may include multiple groups of sample operating parameter values, and fault mode labels and sample control status signals associated with each group of sample operating parameter values.

[0041] It should be noted that, in the embodiment of the present disclosure, the operating parameters of the hydraulic winch may include the tension of the hydraulic winch and the speed of the steel cable collected by the sensor, wherein the control state may include reaping, hovering or releasing the cable.

[0042] In an optional implementation, the process of the terminal device acquiring the sample data set may include: in response to detecting the fault diagnosis model training operation, reading the sample data set pre-stored in the terminal device.

[0043] In step S102, the terminal device inputs the sample characteristic data into the first sub-model of the fault diagnosis model to obtain a sample predicted fault mode, and inputs the sample predicted fault mode into the second sub-model of the fault diagnosis model to obtain the internal and external leakage coefficient of the sample motor of the hydraulic winch.

[0044] In the disclosed embodiment, the sample characteristic data is determined based on the sample operation parameter value; Figure 2 As stated, Figure 2 A structural schematic diagram of a fault diagnosis model provided by an embodiment of the present disclosure is shown, wherein the fault diagnosis model 200 includes a first sub-model 201 and a second sub-model 202, wherein the first sub-model 201 is used to predict the fault mode of the hydraulic winch according to the operating parameter value of the hydraulic winch, and the second sub-model 202 is used to predict the internal and external leakage coefficients of the motor of the hydraulic winch according to the fault mode of the hydraulic winch, so as to input the internal and external leakage coefficients of the motor and the control state signal of the hydraulic winch into the system model of the hydraulic winch to determine whether the operating condition of the hydraulic winch conforms to the physical laws during the operation of the hydraulic winch.

[0045] It should be noted that, in the embodiment of the present disclosure, the first sub-model and the second sub-model can be neural network models, and the specific model structure can be determined based on actual needs, which is not limited in the embodiment of the present disclosure; optionally, the first sub-model can be a deep convolutional network model, which can capture the operating parameter values ​​of the hydraulic winch and the nonlinear mapping relationship between the failure modes of the hydraulic winch without a complex network architecture; the second sub-model can be a network model based on the attention mechanism, which can more accurately characterize the nonlinear mapping relationship between the failure mode of the hydraulic winch and the internal and external leakage coefficients of the motor.

[0046] It is understandable that the first sub-model and the second sub-model may generally include an input layer, a hidden layer including a plurality of nodes, and an output layer. The number of nodes in the hidden layer may be determined based on actual needs, and the embodiment of the present disclosure does not limit this. For example, the hidden layer may include 100 nodes.

[0047] In an optional embodiment, the process of the terminal device determining the sample characteristic data based on the sample operation parameter value may include: performing noise reduction processing on the sample operation parameter value to obtain the noise-reduced sample operation parameter value; then, decomposing the noise-reduced sample operation parameter value based on the local mean decomposition algorithm of the empirical optimal envelope to obtain the sample fault signal component; further, performing feature extraction on the sample fault signal component to obtain the sample characteristic data. The sample operation parameter value of the hydraulic winch can be denoised and decomposed to obtain the sample characteristic data of the sample fault signal component for model training. Since the denoising and decomposition process of the sample operation parameter value can remove useless signals in the sample operation parameter value, the sample characteristic data can contain more fault features, which not only reduces the amount of data processing in the model training process, but also improves the reliability of the fault diagnosis model obtained by training.

[0048] The terminal device decomposes the noise reduction sample operation parameter value based on the empirical optimal envelope local mean decomposition (EOE_LMD) algorithm to obtain the sample fault signal component. The process may include: for the signal x(t) of the noise reduction sample operation parameter value, let the counting variable h=1; then, if h=1, use the cubic spline function (CS) as the interpolation function, if h>1, then use the piecewise cubic Hermite interpolation polynomial (PCHIP) as the interpolation function to estimate the upper and lower envelopes of the signal, wherein the local mean function is:

[0049]

[0050] The local envelope function is:

[0051]

[0052] Furthermore, the frequency modulation signal y is determined by formula 3 11 (t):

[0053]

[0054] At this time, let h = h + 1. 11 (t) as the original signal data, calculate g 12 (t). If g 12 (t) = 1, y 11 (t) is a pure normalized frequency modulation signal, which is a product function, thus PF1(t) is obtained. 12 (t)≠1, then repeat the above process until y 1m (t) is a pure frequency modulated signal, that is, it satisfies g 1m (t)=1.

[0055] Next, determine the product of the envelope functions calculated by the above process to obtain the comprehensive envelope signal:

[0056]

[0057] Then, the comprehensive envelope signal g1(t) and y 1m (t) to calculate the PF1(t) of the signal x(t):

[0058] PF1(t)=g1(t)y 1m (t); (Formula 5)

[0059] Finally, PF1 is subtracted from the original signal x(t) to obtain the residual signal s1(t), which is regarded as the new original signal. The above process is repeated j times until s j (t) is a constant or monotonic, the final signal x(t) is decomposed into j PF components and a residual signal s j (t), that is:

[0060]

[0061] Among them, the PF component is the sample fault signal component.

[0062] In an optional implementation, the terminal device extracts features from the sample fault signal component to obtain the sample feature data, which may include: determining the sample feature data based on the sample fault signal component and the time-frequency feature solution function. The time-frequency feature may be a mean, a kurtosis scale, a peak-to-peak value, a frequency variance, a mean difference, a variance, a peak index, and a mean square frequency, etc., which are not limited in the embodiments of the present disclosure.

[0063] In an optional embodiment, the terminal device can input the sample characteristic data into the first sub-model of the fault diagnosis model to obtain a sample predicted fault mode, and input the sample predicted fault mode into the second sub-model of the fault diagnosis model to obtain the sample motor internal and external leakage coefficient of the hydraulic winch.

[0064] In step S103, the terminal device inputs the sample motor internal and external leakage coefficients and the sample control state signal into the system model of the hydraulic winch to obtain the sample operation parameter prediction value of the hydraulic winch.

[0065] In the disclosed embodiment, during the operation of the hydraulic motor of the hydraulic winch, the high load causes a large interaction force between the two components constituting the relative motion, and wear itself is caused by the friction between the moving components, and once wear occurs, it will affect its working performance and cause the hydraulic motor to leak. Therefore, in order to perform fault diagnosis more accurately, the system model of the hydraulic winch can include the internal and external leakage coefficients of the motor.

[0066] In an optional embodiment, the process of constructing a system model of a hydraulic winch by a terminal device may include: based on the operating characteristics of the hydraulic winch, constructing a relationship model between the pump outlet flow of the hydraulic winch and the internal and external leakage coefficients of the motor, the rotational displacement of the motor in the hydraulic winch, the motor inlet pressure and outlet pressure, and the control state signal, to obtain the flow equation of the motor in the hydraulic winch; further, determining the flow equation of the motor in the hydraulic winch and the dynamic equation of the hydraulic winch as the system model of the hydraulic winch. A system model of a hydraulic winch including the internal and external leakage coefficients of the motor can be constructed to more accurately characterize the system characteristics of the hydraulic winch in the presence of device friction in the hydraulic winch.

[0067] It should be noted that, in the embodiment of the present disclosure, the process of the terminal device constructing the system model of the hydraulic winch may be implemented in response to obtaining the system model construction operation of the hydraulic winch.

[0068] Among them, the flow equation of the motor in the hydraulic winch is:

[0069]

[0070] In Formula 7, s c is the control state signal, where s c =1, means acquisition, s c =1, indicating hovering, s c =-1, indicating cable release, D indicating motor displacement, Cix and Cox indicating motor internal leakage coefficient and motor external leakage coefficient respectively, Vm indicating load chamber volume, β e represents the elastic modulus of the oil, θ represents the rotational displacement of the motor, wherein, when the cable is reeled in, Pm=Pa-Pb, Pa and Pb represent the pressure at the inlet and outlet of the motor respectively.

[0071] The pump outlet flow rate is Pconstant is the power of the pump.

[0072] The dynamic equation of the winch is:

[0073]

[0074] In Formula 8, F represents the tension of the cable, J m represents the equivalent moment of inertia, B represents the equivalent damping coefficient of the motor, R represents the radius of the drum, and i represents the reduction ratio of the hydraulic motor to the drum. Usually i=4.

[0075] In an optional embodiment, the terminal device can input the sample motor internal and external leakage coefficients and the sample control state signal into the system model of the hydraulic winch to obtain sample operating parameter prediction values ​​of the hydraulic winch, wherein the sample operating parameter prediction values ​​can include sample tension prediction values ​​and sample steel cable speed prediction values ​​of the hydraulic winch.

[0076] In step S104, the terminal device obtains a trained fault diagnosis model when determining that the fault diagnosis model has converged based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter predicted value.

[0077] In an embodiment of the present disclosure, the terminal device can determine whether the fault diagnosis model converges through a loss function, and the loss function can include a first loss function and a second loss function, wherein the result of the first loss function is used to characterize the fault mode label associated with the sample operating parameter value, and the degree of difference between the fault mode predicted by the first sub-model; the result of the second loss function is used to characterize the sample operating parameter value of the hydraulic winch, and the degree of conformity with the laws of the system model of the hydraulic winch, so that the fault diagnosis model can perform fault diagnosis based on the operating parameter characteristics and system laws of the hydraulic winch.

[0078] In an optional implementation manner, the terminal device determines whether the fault diagnosis model converges based on the fault mode label, the sample predicted fault mode, the sample operating parameter value, and the sample operating parameter predicted value, including:

[0079] The fault mode label and the sample predicted fault mode are input into a first loss function to obtain a first loss function value; then, the sample operating parameter value and the sample operating parameter predicted value are input into a second loss function to obtain a second loss function value; and the sum of the first loss function value and the second loss function value is determined as the loss function value to be evaluated; further, if the loss function value to be evaluated meets the model convergence condition, the fault diagnosis model is determined to be converged; wherein, the first loss function value is used to characterize the fault mode label associated with the sample operating parameter value, and the degree of difference between the fault mode predicted by the first sub-model, and the second loss function value is used to characterize the sample operating parameter value of the hydraulic winch, and the degree of conformity with the system law of the hydraulic winch, wherein the system law of the hydraulic winch is characterized by the system model of the hydraulic winch. The fault diagnosis model can be trained based on the matching degree between the hydraulic winch operating parameters and the fault mode, as well as the conformity degree between the hydraulic winch operating parameters and the system laws represented by the system model, so that the fault diagnosis model can perform fault diagnosis based on the operating parameter characteristics and system laws of the hydraulic winch, thereby improving the accuracy of the fault diagnosis results determined by the trained fault diagnosis model.

[0080] It should be noted that in the embodiment of the present disclosure, the process of the terminal device determining whether the loss function value to be evaluated meets the model convergence condition can be determined based on actual needs, and the embodiment of the present disclosure does not limit this.

[0081] For example, the process of the terminal device determining whether the loss function value to be evaluated meets the model convergence condition may include: if the loss function value to be evaluated is less than or equal to the loss function threshold, then determining that the loss function value to be evaluated meets the model convergence condition; or, if the difference in quality inspection of the loss function value to be evaluated obtained after multiple consecutive iterative training is less than or equal to the loss function difference threshold, then determining that the loss function value to be evaluated meets the model convergence condition; wherein, the loss function threshold, or the loss function difference threshold can be determined based on actual needs, and the embodiments of the present disclosure are not limited to this.

[0082] It is understandable that in the embodiment of the present disclosure, if the loss function value to be evaluated does not meet the model convergence condition, the iterative training process of the above fault diagnosis model is repeated starting from step S102 until it is determined that the fault diagnosis model converges.

[0083] Among them, the first loss function is:

[0084]

[0085] In formula 9, δ iw is the failure mode label, For the sample prediction failure mode, n is the size of the sample dataset used for training and C is the number of failure modes.

[0086] In an optional embodiment, the sample operation parameter value includes the sample tension and sample cable speed of the hydraulic winch, and the sample operation parameter prediction value includes the sample tension prediction value and sample cable speed prediction value of the hydraulic winch. The terminal device inputs the sample operation parameter value and the sample operation parameter prediction value into the second loss function to obtain the second loss function value, and the process includes: inputting the sample tension and the sample tension prediction value into the tension loss function of the second loss function to obtain the tension loss function value; then, inputting the sample cable speed and the sample cable speed prediction value into the speed loss function of the second loss function to obtain the speed loss function value; further, inputting the tension loss function value and the speed loss function value to obtain the second loss function value. The tension and cable speed of the hydraulic winch can be combined to analyze the matching degree between the operation parameters of the hydraulic winch during operation and the system laws represented by the system model, and further improve the reliability of the fault diagnosis model obtained by training.

[0087] Among them, the second loss function is loss sys =loss F +loss v , loss F is the tension loss function, loss v is the speed loss function; the tension loss function is:

[0088]

[0089] In Formula 10, F oi is the sample tension, F i is the predicted value of sample tension.

[0090] The speed loss function is:

[0091]

[0092] In formula 11, v oi is the sample cable speed, v i is the predicted value of sample cable speed.

[0093] In an optional embodiment, the process in which the terminal device determines the sum of the first loss function value and the second loss function value as the loss function value to be evaluated may include: determining the product of the first loss function value and the first weight value to obtain the first weighted loss function value, and determining the product of the second loss function value and the second weight value to obtain the second weighted loss function value; then, determining the sum of the first weighted loss function value and the second weighted loss function value as the loss function value to be evaluated. During the training of the fault diagnosis model, the fault diagnosis model can be adjusted to emphasize the fault mode prediction and the compliance with the physical laws, so as to improve the matching degree between the trained fault diagnosis model and the actual needs.

[0094] It should be noted that in the embodiment of the present disclosure, the sum of the first weight value and the second weight value is 1, and the specific values ​​of the first weight value and the second weight value can be determined based on actual needs, and the embodiment of the present disclosure does not limit this.

[0095] The process of the terminal device determining the value of the loss function to be evaluated by combining the first weight value and the second weight value may be:

[0096] Loss = κ F loss Data +κ v loss sys ;(Formula 12)

[0097] In Formula 12, κ F is the first weight value, κ v is the second weight value.

[0098] like Figure 3 As shown, Figure 3 A schematic diagram showing the fault diagnosis accuracy of the fault diagnosis model trained based on different weight combinations is shown, where when the weights of the two loss functions reach κ F =0.5,κ v When =0.5, the diagnostic accuracy of the fault diagnosis model reaches the optimal level.

[0099] In an optional implementation, the process in which the terminal device determines the sum of the first loss function value and the second loss function value as the loss function value to be evaluated may include: determining the sum of the first loss function value and the second loss function value to obtain the loss function value to be evaluated. Fault diagnosis model training can be performed directly based on the first loss function value and the second loss function value to improve model training efficiency.

[0100] The present disclosure provides a fault diagnosis method, which can be applied to a terminal device, such as Figure 4 As shown, the fault diagnosis method includes:

[0101] Step S401, obtaining the operating parameter value of the hydraulic winch to be diagnosed;

[0102] Step S402, inputting the operating parameter value into the first sub-model in the fault diagnosis model to obtain the fault mode diagnosis result of the hydraulic winch to be diagnosed;

[0103] The fault diagnosis model is obtained by training based on the fault diagnosis model in the above embodiment.

[0104] To sum up, the fault diagnosis method provided by the embodiment of the present invention, since the system model of the hydraulic winch is introduced in the fault diagnosis model training process, can train a fault diagnosis model that takes into account the system laws and operating parameter characteristics of the hydraulic winch for fault diagnosis, thereby improving the accuracy of the fault diagnosis results of the hydraulic winch to be diagnosed determined based on the fault diagnosis model.

[0105] In an optional embodiment, after obtaining the fault mode diagnosis result of the hydraulic winch to be diagnosed, the terminal device can also: input the fault mode diagnosis result into the second sub-model in the fault diagnosis model to obtain the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed; then, based on the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed, the control state signal, and the system model of the hydraulic winch, obtain the predicted value of the operating parameter of the hydraulic winch; further, if the difference between the predicted value of the operating parameter and the value of the operating parameter is less than a difference threshold, it is determined that the credibility of the fault mode diagnosis result is at a high level, wherein the difference threshold can be determined based on actual needs, and the embodiment of the present disclosure is not limited to this. After determining the fault mode diagnosis result of the hydraulic winch to be diagnosed, the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed can be predicted based on the fault mode diagnosis result, and the internal and external leakage coefficients of the motor and the control state signal can be input into the system model of the hydraulic winch to obtain the predicted value of the operating parameters of the hydraulic winch, so as to determine the credibility of the fault mode diagnosis result based on the comparison result of the difference between the predicted value of the operating parameter of the winch and the operating parameter value and the difference threshold, and realize the evaluation of the fault diagnosis result in combination with the system model of the hydraulic winch, so as to further improve the reliability of the determined fault mode diagnosis result.

[0106] Among them, the operating parameter values ​​of the hydraulic winch to be diagnosed may include: the tension and cable speed of the hydraulic winch to be diagnosed, and the process of the terminal device determining whether the difference between the predicted operating parameter value and the operating parameter value is less than the difference threshold may include: if the difference between the tension of the hydraulic winch to be diagnosed and the tension predicted value is less than the tension difference threshold, and the difference between the cable speed of the hydraulic winch to be diagnosed and the cable speed predicted value is less than the cable speed difference threshold, then determining that the difference between the predicted operating parameter value and the operating parameter value is less than the difference threshold.

[0107] It can be understood that if the difference between the predicted value of the operating parameter and the value of the operating parameter is greater than or equal to the difference threshold, the credibility of the fault mode diagnosis result is determined to be low.

[0108] An exemplary embodiment of the present disclosure provides a fault diagnosis model training device, which may be a terminal device or a chip applied to the terminal device. Figure 5 FIG. 1 shows a schematic block diagram of functional modules of a fault diagnosis model training device according to an exemplary embodiment of the present disclosure. Figure 5 As shown, the fault diagnosis model training device 500 includes:

[0109] A first acquisition module 501 is configured to acquire a sample data set, wherein the sample data set includes sample operating parameter values ​​of the hydraulic winch, fault mode labels associated with the sample operating parameter values, and a sample control state signal of the hydraulic winch;

[0110] The training module 502 is configured to input the sample feature data into a first sub-model of the fault diagnosis model to obtain a sample predicted fault mode, and input the sample predicted fault mode into a second sub-model of the fault diagnosis model to obtain a sample motor internal and external leakage coefficient of the hydraulic winch, wherein the sample feature data is determined based on the sample operating parameter value;

[0111] An input module 503 is configured to input the sample motor internal and external leakage coefficients and the sample control state signal into the system model of the hydraulic winch to obtain a sample operating parameter prediction value of the hydraulic winch;

[0112] The determination module 504 is configured to obtain a trained fault diagnosis model when it is determined that the fault diagnosis model converges based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter predicted value.

[0113] Optionally, the device further includes a construction module 505 configured to:

[0114] Based on the operating characteristics of the hydraulic winch, a relationship model is constructed between the pump outlet flow rate of the hydraulic winch and the internal and external leakage coefficients of the motor, the rotational displacement of the motor in the hydraulic winch, the motor inlet pressure and outlet pressure, and the control state signal to obtain the flow equation of the motor in the hydraulic winch;

[0115] The flow equation of the motor in the hydraulic winch and the dynamic equation of the hydraulic winch are determined as the system model of the hydraulic winch.

[0116] Optionally, the determination module 504 is configured to:

[0117] Inputting the fault mode label and the sample predicted fault mode into a first loss function to obtain a first loss function value, wherein the first loss function value is used to characterize the fault mode label associated with the sample operating parameter value and the degree of difference between the fault modes predicted by the first sub-model;

[0118] Inputting the sample operating parameter value and the sample operating parameter prediction value into a second loss function to obtain a second loss function value, wherein the second loss function value is used to characterize the degree of conformity of the sample operating parameter value of the hydraulic winch with the system law of the hydraulic winch;

[0119] Determine the sum of the first loss function value and the second loss function value as the loss function value to be evaluated;

[0120] If the loss function value to be evaluated meets the model convergence condition, it is determined that the fault diagnosis model converges.

[0121] Optionally, the determining module 504 is configured to:

[0122] Determine the product of the first loss function value and the first weight value to obtain a first weighted loss function value, and determine the product of the second loss function value and the second weight value to obtain a second weighted loss function value;

[0123] The sum of the first weighted loss function value and the second weighted loss function value is determined as the loss function value to be evaluated.

[0124] Optionally, the sample operating parameter value includes a sample tension and a sample steel cable speed of the hydraulic winch, and the sample operating parameter prediction value includes a sample tension prediction value and a sample steel cable speed prediction value of the hydraulic winch.

[0125] The determining module 504 is configured to:

[0126] Inputting the sample tension and the sample tension prediction value into the tension loss function of the second loss function to obtain a tension loss function value;

[0127] Inputting the sample steel cable speed and the predicted value of the sample steel cable speed into the speed loss function of the second loss function to obtain a speed loss function value;

[0128] The tension loss function value and the speed loss function value are added to obtain the second loss function value.

[0129] Optionally, the training module 502 is further configured to:

[0130] Performing noise reduction processing on the sample operating parameter value to obtain a noise-reduced sample operating parameter value;

[0131] Decomposing the noise reduction sample operation parameter value based on the local mean decomposition algorithm of the empirical optimal envelope to obtain the sample fault signal component;

[0132] Feature extraction is performed on the sample fault signal component to obtain the sample feature data.

[0133] An exemplary embodiment of the present disclosure provides a fault diagnosis apparatus, which may be a terminal device or a chip applied to the terminal device. Figure 6 FIG. 1 shows a schematic block diagram of functional modules of a fault diagnosis device according to an exemplary embodiment of the present disclosure. Figure 6 As shown, the fault diagnosis device 600 includes:

[0134] The second acquisition module 601 is configured to acquire the operating parameter value of the hydraulic winch to be diagnosed;

[0135] The diagnosis module 602 is configured to input the operating parameter value into the first sub-model in the fault diagnosis model to obtain the fault mode diagnosis result of the hydraulic winch to be diagnosed, wherein the fault diagnosis model is obtained by training based on the fault diagnosis model described in the above embodiment.

[0136] Optionally, the diagnosis module 602 is further configured to:

[0137] Inputting the fault mode diagnosis result into the second sub-model in the fault diagnosis model to obtain the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed;

[0138] Based on the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed, the control state signal, and the system model of the hydraulic winch, a predicted value of the operating parameter of the hydraulic winch is obtained;

[0139] If the difference between the predicted value of the operating parameter and the value of the operating parameter is less than a difference threshold, it is determined that the credibility of the fault mode diagnosis result is at a high level.

[0140] 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.

[0141] 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.

[0142] like Figure 7 As shown, the exemplary embodiment of the present disclosure further provides a computer program product 700, including a computer program 701, 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.

[0143] refer to Figure 8 , a block diagram of an electronic device 800 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.

[0144] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0145] A plurality of components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 may be any type of device capable of inputting information to the electronic device 800, and the input unit 806 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 807 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 808 may include, but is not limited to, a disk, an optical disk. The communication unit 809 allows the electronic device 800 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.

[0146] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 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 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. In some embodiments, the computing unit 801 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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 fault diagnosis model training method, characterized in that: include: Acquire a sample data set, wherein the sample data set includes sample operating parameter values ​​of the hydraulic winch, fault mode labels associated with the sample operating parameter values, and sample control state signals of the hydraulic winch; Inputting sample characteristic data into a first sub-model of a fault diagnosis model to obtain a sample predicted fault mode, and inputting the sample predicted fault mode into a second sub-model of the fault diagnosis model to obtain a sample motor internal and external leakage coefficient of the hydraulic winch, wherein the sample characteristic data is determined based on the sample operating parameter value; Input the internal and external leakage coefficients of the sample motor and the sample control state signal into the system model of the hydraulic winch to obtain the predicted values ​​of the sample operating parameters of the hydraulic winch; When it is determined that the fault diagnosis model has converged based on the fault mode label, the sample predicted fault mode, the sample operating parameter value and the sample operating parameter predicted value, a trained fault diagnosis model is obtained.

2. The fault diagnosis model training as claimed in claim 1, characterized in that: The method further comprises: Based on the operating characteristics of the hydraulic winch, a relationship model is constructed between the pump outlet flow rate of the hydraulic winch and the internal and external leakage coefficients of the motor, the rotational displacement of the motor in the hydraulic winch, the motor inlet pressure and outlet pressure, and the control state signal to obtain the flow equation of the motor in the hydraulic winch; The flow equation of the motor in the hydraulic winch and the dynamic equation of the hydraulic winch are determined as the system model of the hydraulic winch.

3. The fault diagnosis model training method according to claim 1, characterized in that: Determining whether the fault diagnosis model converges based on the fault mode label, the sample predicted fault mode, the sample operating parameter value, and the sample operating parameter predicted value includes: Inputting the fault mode label and the sample predicted fault mode into a first loss function to obtain a first loss function value, wherein the first loss function value is used to characterize the fault mode label associated with the sample operating parameter value and the degree of difference between the fault modes predicted by the first sub-model; Inputting the sample operating parameter value and the sample operating parameter prediction value into a second loss function to obtain a second loss function value, wherein the second loss function value is used to characterize the degree of conformity of the sample operating parameter value of the hydraulic winch with the system law of the hydraulic winch; Determine the sum of the first loss function value and the second loss function value as the loss function value to be evaluated; If the loss function value to be evaluated meets the model convergence condition, it is determined that the fault diagnosis model converges.

4. The fault diagnosis model training method according to claim 3, characterized in that: The step of determining the sum of the first loss function value and the second loss function value as the loss function value to be evaluated includes: Determine the product of the first loss function value and the first weight value to obtain a first weighted loss function value, and determine the product of the second loss function value and the second weight value to obtain a second weighted loss function value; The sum of the first weighted loss function value and the second weighted loss function value is determined as the loss function value to be evaluated.

5. The fault diagnosis model training method according to claim 3, characterized in that: The sample operating parameter values ​​include the sample tension and sample wire rope speed of the hydraulic winch, and the sample operating parameter prediction values ​​include the sample tension prediction value and sample wire rope speed prediction value of the hydraulic winch. The step of inputting the sample operation parameter value and the sample operation parameter prediction value into a second loss function to obtain a second loss function value includes: Inputting the sample tension and the sample tension prediction value into the tension loss function of the second loss function to obtain a tension loss function value; Inputting the sample steel cable speed and the predicted value of the sample steel cable speed into the speed loss function of the second loss function to obtain a speed loss function value; The tension loss function value and the speed loss function value are added to obtain the second loss function value.

6. The fault diagnosis model training method according to claim 1, characterized in that: Determining the sample characteristic data based on the sample operation parameter value includes: Performing noise reduction processing on the sample operating parameter value to obtain a noise-reduced sample operating parameter value; Decomposing the noise reduction sample operation parameter value based on the local mean decomposition algorithm of the empirical optimal envelope to obtain the sample fault signal component; Feature extraction is performed on the sample fault signal component to obtain the sample feature data.

7. A fault diagnosis method, characterized in that: include: Obtaining the operating parameter values ​​of the hydraulic winch to be diagnosed; The operating parameter value is input into the first sub-model in the fault diagnosis model to obtain the fault mode diagnosis result of the hydraulic winch to be diagnosed, wherein the fault diagnosis model is trained based on the fault diagnosis model described in any one of claims 1-6.

8. The fault diagnosis method according to claim 7, characterized in that: The method further comprises: Inputting the fault mode diagnosis result into the second sub-model in the fault diagnosis model to obtain the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed; Based on the internal and external leakage coefficients of the motor of the hydraulic winch to be diagnosed, the control state signal, and the system model of the hydraulic winch, a predicted value of the operating parameter of the hydraulic winch is obtained; If the difference between the predicted value of the operating parameter and the value of the operating parameter is less than a difference threshold, it is determined that the credibility of the fault mode diagnosis result is at a high level.

9. 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 steps of any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images