Fault diagnosis method and device, storage medium and equipment

Abstract

The invention provides a fault diagnosis method and device, a storage medium and equipment, and the method comprises the steps: obtaining an original vibration signal of target mechanical equipment, carrying out the filtering of the original vibration signal through an initial filter, obtaining an original filtering signal, and obtaining a fault diagnosis result according to the original vibration signal, the discrete degree of the original filtering signal, and the system response of the initial filter. An initial search direction and an initial update step are determined. And iteratively updating the initial filter for multiple times by taking the minimum discrete degree as a target according to the initial updating step length in the initial search direction until a preset shutdown criterion is met, so as to obtain a target filter. In the multi-time iteration updating, the target filter is iteratively updated in the direction that the dispersion degree of the original filtering signal is decreased progressively, the target filter filters the original vibration signal to obtain the target filtering signal, from the dimension of the dispersion degree, interference of periodic noise is avoided, and the accuracy of fault diagnosis is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and particularly relates to a fault diagnosis method, device, storage medium and equipment. Background Art

[0002] Mechanical equipment is widely used in many fields such as industry, transportation, and energy. It contains many key components inside, such as rotating parts, transmission devices, bearings, etc. During long-term operation, these components are prone to failures due to working environment factors such as wear and corrosion. The failures of mechanical equipment not only cause equipment downtime, affect production efficiency, but even lead to safety accidents. Therefore, it is crucial to perform fault diagnosis on mechanical equipment.

[0003] Currently, the commonly used fault diagnosis method is mainly to collect the vibration signals of mechanical equipment, and then extract the fault signals of periodic pulses, so as to perform fault diagnosis on mechanical equipment according to the extracted fault signals. However, in actual application scenarios, due to the existence of various interference sources such as vibrations from other equipment and environmental white noise, these noises contain high-energy components with strong periodicity, making it extremely difficult to directly extract fault signals and resulting in low accuracy of fault diagnosis.

[0004] Based on this, there is an urgent need for a mechanical equipment fault diagnosis scheme with high accuracy in a low signal-to-noise ratio environment. Summary of the Invention

[0005] The present application provides a fault diagnosis method, device, storage medium and equipment to partially solve the above problems existing in the prior art.

[0006] The present application adopts the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a fault diagnosis method, including:

[0008] Obtain the original vibration signal corresponding to the target mechanical equipment;

[0009] Filter the original vibration signal through a preset initial filter to obtain an original filtered signal;

[0010] Determine an initial search direction and an initial update step size according to the discrete degree of the original vibration signal, the original filtered signal, and the system response of the initial filter;

[0011] Along the initial search direction, according to the initial update step size, with the goal of minimizing the discrete degree, iteratively update the initial filter multiple times until a preset stop criterion is met, to obtain a target filter, where the initial search direction represents the iterative direction in which the discrete degree decreases;

[0012] Filter the original vibration signal through the target filter to obtain a target filtered signal;

[0013] Perform fault diagnosis on the target mechanical equipment according to the target filtered signal.

[0014] In some embodiments, before determining the initial search direction and the initial update step size according to the original vibration signal, the discrete degree of the original filtered signal, and the system response of the initial filter, the method further includes:

[0015] Determine the signal mean of the original filtered signal;

[0016] Determine the signal variance of the original filtered signal according to the original filtered signal and the signal mean;

[0017] Use the signal variance as the discrete degree.

[0018] In some embodiments, determining the initial search direction and the initial update step size according to the original vibration signal, the discrete degree of the original filtered signal, and the system response of the initial filter specifically includes:

[0019] Determine the partial derivative of the discrete degree with respect to the system response of the initial filter as the discrete gradient;

[0020] Convert the original vibration signal into a Hankel matrix to obtain an original vibration matrix;

[0021] Determine the initial search direction and the initial update step size according to the original vibration matrix, the discrete gradient, and the system response of the initial filter.

[0022] In some embodiments, the step of determining the initial search direction and the initial update step size according to the original vibration matrix, the discrete gradient, and the system response of the initial filter specifically includes:

[0023] Determine a coefficient matrix according to the original vibration matrix and the transpose matrix of the original vibration matrix;

[0024] Determine the initial search direction according to the original vibration matrix, the discrete gradient, and the coefficient matrix;

[0025] Determine the initial update step size according to the coefficient matrix.

[0026] In some embodiments, the step of iteratively updating the initial filter multiple times along the initial search direction according to the initial update step size with the goal of minimizing the discrete degree until a preset stopping criterion is met to obtain the target filter specifically includes:

[0027] Perform the first iterative update on the initial filter along the initial search direction according to the initial update step size;

[0028] Determine the initial residual vector;

[0029] Perform multiple iterative updates on the initial filter after the first iterative update based on the original vibration signal and the initial residual vector with the goal of minimizing the dispersion until the preset stopping criterion is met, and obtain the target filter.

[0030] In some embodiments, the step of performing multiple iterative updates on the initial filter after the first iterative update based on the original vibration signal with the goal of minimizing the dispersion until the preset stopping criterion is met to obtain the target filter specifically includes:

[0031] For each iterative update in the multiple iterative updates, adjust the search direction in the previous iterative update and adjust the update step size in the previous iterative update;

[0032] For each iterative update in the multiple iterative updates, perform this iterative update on the initial filter after the previous iterative update along the adjusted search direction in this iterative update according to the adjusted update step size in this iterative update;

[0033] For each iterative update in the multiple iterative updates, determine whether the initial filter after this iterative update meets the preset stopping criterion;

[0034] If so, stop the iteration and obtain the target filter;

[0035] If not, continue to perform the next iterative update on the initial filter after this iterative update.

[0036] In some embodiments, the step of adjusting the search direction in the previous iterative update and adjusting the update step size in the previous iterative update specifically includes:

[0037] Adjust the residual vector in the previous iterative update according to the update step size in the previous iterative update and the search direction in the previous iterative update;

[0038] Determine the adjustment parameter corresponding to the search direction in this iterative update according to the adjusted residual vector in this iterative update, and the adjustment parameter is used to constrain the search direction in this iterative update and the search direction in the previous iterative update to be orthogonally conjugate;

[0039] Adjust the search direction in the previous iterative update according to the adjusted residual vector in this iterative update and the adjustment parameter;

[0040] Adjust the update step size of the previous iteration update according to the adjusted residual vector in this iteration update and the adjusted search direction in this iteration update.

[0041] In some embodiments, the step of determining whether the initial filter after this iteration update meets a preset stopping criterion specifically includes:

[0042] Determine the norm of the adjusted search direction in this iteration update;

[0043] Determine whether the norm is less than a preset threshold.

[0044] In some embodiments, the step of performing fault diagnosis on the target mechanical equipment according to the target filtered signal specifically includes:

[0045] Determine the envelope spectrum of the target filtered signal;

[0046] Extract the fault signal that conforms to the preset probability distribution from the envelope spectrum.

[0047] In a second aspect, an embodiment of the present application provides a fault diagnosis device, including:

[0048] An acquisition module, configured to acquire an original vibration signal corresponding to a target mechanical equipment;

[0049] An original filtering module, configured to filter the original vibration signal through a preset initial filter to obtain an original filtered signal;

[0050] An iteration parameter module, configured to determine an initial search direction and an initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter;

[0051] An iteration update module, configured to iteratively update the initial filter multiple times along the initial search direction according to the initial update step size with the goal of minimizing the dispersion degree until a preset stopping criterion is met, to obtain a target filter, where the initial search direction represents the iteration direction in which the dispersion degree decreases;

[0052] A target filtering module, configured to filter the original vibration signal through the target filter to obtain a target filtered signal;

[0053] A fault diagnosis module, configured to perform fault diagnosis on the target mechanical equipment according to the target filtered signal.

[0054] In a third aspect, an embodiment of the present application provides an electronic device, which includes: a memory and a program or instruction stored on the memory and executable on a processor, and when the program or instruction is executed by the processor, it implements a fault diagnosis method provided in any one of the above aspects of the embodiments of the present application.

[0055] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, it implements a fault diagnosis method provided in any one of the above aspects of the embodiments of the present application.

[0056] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute a fault diagnosis method provided in any one of the above aspects of the embodiments of the present application.

[0057] The technical solutions provided by the embodiments of the present application at least bring the following beneficial effects:

[0058] The technical solution provided by the embodiment of the present application can filter the original vibration signal of the target mechanical equipment based on the target filter to obtain a target filtered signal, and then perform fault diagnosis on the target mechanical equipment based on the target filtered signal. The initial search direction and the initial update step size determined based on the dispersion degree of the original vibration signal, the original filtered signal, and the system response of the initial filter are used to iteratively update the target filter with the goal of minimizing the dispersion degree, and the fault signal has the characteristic of small dispersion degree. Therefore, the target filter obtained by iteratively updating with the goal of minimizing the dispersion degree can be used to filter the original vibration signal to obtain a target filtered signal, so as to realize the fault diagnosis of the target mechanical equipment based on the analysis of the target filtered signal.

[0059] In addition, the initial search direction represents the iterative direction of decreasing dispersion degree, that is, the process of performing multiple iterative updates based on the initial search direction and the initial update step size is the process of iteratively updating the initial filter along the direction of decreasing dispersion degree of the original filtered signal. Therefore, the target filter can filter the original vibration signal to obtain a target filtered signal from the dimension of minimizing the dispersion degree, so as to realize fault diagnosis based on the target filtered signal, and from the dimension of the dispersion degree, it can avoid the interference of periodic noise, thus ensuring the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0061] Figure 1 is a schematic flowchart of a fault diagnosis method provided by an embodiment of the present application;

[0062] Figure 2 is a schematic flowchart of obtaining a target filter by iteratively updating an initial filter multiple times provided by an embodiment of the present application;

[0063] Figure 3 is a schematic structural diagram of a train test bench provided by an embodiment of the present application;

[0064] Figure 4 is a schematic diagram of an outer race fault signal provided by an embodiment of the present application;

[0065] Figure 5 is a schematic diagram of an inner race fault signal provided by an embodiment of the present application;

[0066] Figure 6 is obtained by using the Figure 1 schematic diagram of the target filtered signal obtained by the fault diagnosis method shown;

[0067] Figure 7 is a schematic diagram of the envelope spectrum of the target filtered signal provided by the present application;

[0068] Figure 8 is a schematic diagram of the filtered signal obtained by using IMCKD provided by the present application;

[0069] Figure 9 is a schematic diagram of the envelope spectrum corresponding to the filtered signal obtained by using IMCKD provided by the present application;

[0070] Figure 10 is a schematic diagram of the filtered signal obtained by using ACYCBD provided by the present application;

[0071] Figure 11 is a schematic diagram of the envelope spectrum corresponding to the filtered signal obtained by using ACYCBD provided by the present application;

[0072] Figure 12 is a schematic structural diagram of a fault diagnosis device provided by an embodiment of the present application;

[0073] Figure 13 is a schematic structural diagram of a fault diagnosis device provided by an embodiment of the present application. Detailed implementation manners

[0074] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application and not to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0075] It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

[0076] It should also be noted that the acquisition, storage, use, processing, etc. of data in the present application all comply with the relevant regulations of national laws and regulations. In the embodiments of the present application, certain industry-existing solutions such as software, components, models, etc. may be mentioned, and they should be considered exemplary. The purpose is only to illustrate the feasibility in the embodiments of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0077] Mechanical equipment has a wide range of applications in many fields such as industry, transportation, and energy. It contains many key components inside, such as rotating parts, transmission devices, bearings, etc. During long-term operation, these components are prone to failures due to the influence of working environment factors such as wear and corrosion. Therefore, it is crucial to diagnose the faults of mechanical equipment.

[0078] Currently, the commonly used fault diagnosis method is mainly to collect the vibration signals of mechanical equipment, and then extract the fault signals of periodic pulses, so as to diagnose the faults of mechanical equipment based on the extracted fault signals. However, in actual application scenarios, due to the existence of various interference sources such as vibrations from other equipment and environmental white noise, these noises contain high-energy components with strong periodicity, making it extremely difficult to directly extract fault signals and resulting in low accuracy of fault diagnosis.

[0079] Based on the technical problems mentioned above, embodiments of the present application provide a fault diagnosis method, apparatus, storage medium, and device. The technical solution provided by the present application can filter the original vibration signal of the target mechanical equipment based on the target filter to obtain the target filtered signal, and then perform fault diagnosis on the target mechanical equipment based on the target filtered signal. The initial search direction and the initial update step size are determined based on the discrete degrees of the original vibration signal, the original filtered signal, and the system response of the initial filter. The target filter is obtained by iterative updating with the goal of minimizing the discrete degree, and the fault signal has the characteristic of small discrete degree. Therefore, the target filter obtained by iterative updating with the goal of minimizing the discrete degree can be used to filter the original vibration signal to obtain the target filtered signal, and thus, based on the analysis of the target filtered signal, the fault diagnosis of the target mechanical equipment can be realized.

[0080] In addition, the initial search direction represents the iterative direction of decreasing discrete degree, that is, the process of performing multiple iterative updates based on the initial search direction and the initial update step size is the process of iteratively updating the initial filter along the direction of decreasing discrete degree of the original filtered signal. Therefore, the target filter can start from the dimension of minimizing the discrete degree, filter the original vibration signal to obtain the target filtered signal, and then perform fault diagnosis based on the target filtered signal. Fault diagnosis is carried out from the dimension of discrete degree, thereby avoiding the interference of periodic noise and ensuring the accuracy of fault diagnosis.

[0081] Among them, regarding the execution entity adopted in the embodiments of the present application, specifically, it can be a terminal device capable of data processing and filter iterative update processes, such as a desktop computer, a laptop computer, etc., or a server, etc. In addition, the execution entity adopted in the embodiments of the present application can also be an execution entity in the form of software, such as a client installed in a terminal device, a software program, etc. For the sake of convenience of description, in the following embodiments of the present application, the server is used as the execution entity to illustrate a fault diagnosis method provided by the present application.

[0082] In the technical solution of the present application, the specific application scenarios of the fault diagnosis method, apparatus, storage medium, and device provided by the embodiments are not strictly limited, and can be flexibly selected according to actual needs. For the sake of facilitating the understanding of the actual application scenarios of the technical solution provided by the embodiments of the present application, the application scenarios of the fault diagnosis method, apparatus, storage medium, and device provided by the present application are illustrated by examples below.

[0083] Taking the fault detection of a rotating part as an example, a rotating part refers to a component in a mechanical device that rotates around a fixed axis. In actual application scenarios, due to the existence of various interference sources such as vibrations from other devices and environmental white noise, these noises will cause the vibration signal to contain high-energy components with strong periodicity, interfering with the extraction of the true fault signal and resulting in low accuracy of fault diagnosis.

[0084] Therefore, in the fault detection of a rotating part, by using the method provided in the embodiments of the present application, the original vibration signal corresponding to the target rotating part is obtained, and the original vibration signal is filtered through a preset initial filter to obtain an original filtered signal. According to the original vibration signal, the discrete degree of the original filtered signal, and the system response of the initial filter, an initial search direction and an initial update step size are determined. Then, along the determined initial search direction, according to the determined initial update step size, with the goal of minimizing the discrete degree, the initial filter is iteratively updated multiple times until a preset stopping criterion is met, and a target filter is obtained, where the initial search direction represents the iterative direction in which the discrete degree decreases. The original vibration signal is filtered through the target filter to obtain a target filtered signal, and then the target rotating part is diagnosed for faults based on the target filtered signal.

[0085] It should be noted that the application scenarios described above for the present application are only for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the present application. Those of ordinary skill in the art can know that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems. The fault diagnosis method provided by the embodiments of the present application can be applied to various application scenarios that require fault diagnosis based on vibration signals.

[0086] The following will describe in detail the technical solutions provided by each embodiment of the present application with reference to the accompanying drawings.

[0087] Figure 1 The flowchart of a fault diagnosis method provided in the present application includes the following steps:

[0088] S100: Obtain the original vibration signal corresponding to the target mechanical device.

[0089] In one or more embodiments of the present application, in order to determine the original filtered signal through the initial filter in subsequent steps. In this step, the server needs to obtain the original vibration signal corresponding to the target mechanical device.

[0090] Specifically, the server can obtain the original vibration signal corresponding to the target mechanical equipment. In this application, the acquisition method of the original vibration signal is not limited and can be set according to requirements. For example, by fixing a contact vibration sensor on the housing near the target mechanical equipment to ensure that the contact vibration sensor accurately captures the vibration of the parts; or by a non-contact vibration sensor to measure the vibration of the target mechanical equipment; or based on vision or acoustic methods.

[0091] S101: Filter the original vibration signal through a preset initial filter to obtain an original filtered signal.

[0092] In one or more embodiments of this application, in order to determine the search direction and update step size for updating the initial filter in subsequent steps. In this step, the server can filter the original vibration signal obtained in step S100 through a preset initial filter, thereby obtaining an original filtered signal.

[0093] Specifically, the server inputs the original vibration signal obtained in step S100 into the initial filter, and filters the original vibration signal through the initial filter to obtain the output original filtered signal.

[0094] It should be noted that since the initial filter needs to be iteratively updated in subsequent steps to obtain the required target filter, therefore, in this application, the system response of the initial filter can be set according to actual needs. For example, the initial filter f = [0, 0…1…0, 0] T ∈R k . In addition, during the convolution process of the original vibration signal and the system response of the initial filter, the values at the signal edges may be lost or distorted due to the convolution of the initial filter, resulting in boundary effects. Therefore, in one or more embodiments of this application, the server can perform zero-padding operations on the original vibration signal, that is, add zeros at both ends of the original vibration signal to expand the length of the original vibration signal and avoid boundary effects. Continuing with the above example, add (k - 1) / 2 zeros at both ends of the original vibration signal x0∈R N to obtain a new sequence x∈R N+k-1 .

[0095] S102: Determine an initial search direction and an initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter.

[0096] In one or more embodiments of the present application, in order to iteratively update the initial filter multiple times in subsequent steps to obtain a target filter aiming to minimize the dispersion degree. In this step, the server needs to determine the initial search direction and the initial update step size according to the acquired original vibration signal, the dispersion degree of the original filtered signal obtained by filtering the original vibration signal, and the system response of the initial filter.

[0097] Specifically, the server can determine the initial search direction and the initial update step size according to the original vibration signal acquired in step S100, the dispersion degree of the original filtered signal obtained by filtering in step S101, and the system response of the initial filter.

[0098] It should be noted that in the present application, there is no limitation on the specific manner of determining the dispersion degree of the original filtered signal, which can be set according to actual needs. For example, the dispersion degree can be the signal variance, standard deviation, etc. of the original filtered signal. In one or more embodiments of the present application, the server can determine the signal variance of the original filtered signal as the dispersion degree, specifically as follows:

[0099] First, the server can determine the signal mean of the original filtered signal. Secondly, the server can determine the signal variance of the original filtered signal based on the original filtered signal and the signal mean. Finally, the server can use the signal variance as the dispersion degree of the original filtered signal.

[0100] In addition, in the present application, there is no limitation on the specific manner of determining the initial search direction and the initial update step size based on the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter, which can be set according to actual needs. In one or more embodiments of this specification, the server can convert the convolution operation of the initial filter on the original vibration signal into a matrix form, and then convert it into the form of a linear equation system, and determine the initial search direction and the initial update step size with the constraint of solving the extreme value of the dispersion degree, specifically as follows:

[0101] First, the server can determine the partial derivative of the dispersion degree with respect to the system response of the initial filter as the discrete gradient. Secondly, the server can convert the original vibration signal into a Hankel Matrix to obtain the original vibration matrix. Finally, the server can determine the initial search direction and the initial update step size according to the original vibration matrix, the discrete gradient, and the system response of the initial filter.

[0102] In one or more embodiments of the present application, first, the server can determine the coefficient matrix according to the original vibration matrix and the transposed matrix of the original vibration matrix. Secondly, the server can determine the initial search direction according to the original vibration matrix, the discrete gradient, and the coefficient matrix. Finally, the server can determine the initial update step size according to the coefficient matrix.

[0103] The process of converting the convolution operation in matrix form (y = X * f) into a system of linear equations (A * f = 0 = b) is as follows:

[0104]

[0105]

[0106]

[0107] In the above formula, x0 is the original vibration signal, x ∈ R N+k-1 is the signal after zero-padding the original vibration signal, X ∈ R N×k is the original vibration matrix obtained by converting the original vibration signal into a Hankel matrix, X T is the transpose matrix of the original vibration matrix; y is the original filtered signal obtained by filtering the original vibration signal with the initial filter, is the signal mean of the original filtered signal; var is the signal variance (degree of dispersion) of the original filtered signal, f0 ∈ R k represents the system response of the initial filter, is the discrete gradient; [T1, T2…T1] T represents the vector formed by the sum of the elements in each row of the original filtered matrix X, A is the coefficient matrix, referring to formula (7); p1 is the initial search direction, and a1 is the initial update step size.

[0108] S103: Along the initial search direction, according to the initial update step size, with the goal of minimizing the degree of dispersion, iteratively update the initial filter multiple times until a preset stopping criterion is met, to obtain the target filter, where the initial search direction represents the iterative direction in which the degree of dispersion decreases.

[0109] In one or more embodiments of the present application, in order to filter the original vibration signal in subsequent steps to obtain the target filtered signal for fault diagnosis. In this step, the server needs to iteratively update the initial filter multiple times based on the initial search direction and the initial update step size determined in step S102, with the goal of minimizing the degree of dispersion, until a preset stopping criterion is met, to obtain the target filter after multiple iterative updates.

[0110] Specifically, the server needs to follow the initial search direction determined in step S102, according to the initial update step size determined in step S102, with the goal of minimizing the degree of dispersion, iteratively update the initial filter multiple times until a preset stopping criterion is met, to obtain the target filter, where the search direction represents the iterative direction in which the degree of dispersion decreases.

[0111] It should be noted that in this application, the specific content of the stopping criterion is not restricted and can be set according to requirements, such as a preset maximum number of iterations. Meanwhile, in the process of iteratively updating the initial filter based on the initial search direction and the initial update step size under the constraint that the partial derivative of the dispersion degree with respect to the system response of the initial filter is an extreme value in step S102, that is, along the initial search direction and according to the initial update step size, to find the system response that minimizes the dispersion degree, so as to obtain the target filter corresponding to the system response that meets the constraint.

[0112] S104: Filter the original vibration signal through the target filter to obtain a target filtered signal.

[0113] In one or more embodiments of this application, in order to perform fault diagnosis on the target mechanical equipment in subsequent steps. In this step, the server needs to filter the original vibration signal obtained in step S100 through the target filter iteratively updated in step S103 to filter out interference noise and enhance the fault characteristic frequency, so as to obtain a target filtered signal.

[0114] Specifically, the server can filter the original vibration signal obtained in step S100 through the target filter after multiple iterative updates in step S103 to obtain a target filtered signal.

[0115] S105: Perform fault diagnosis on the target mechanical equipment according to the target filtered signal.

[0116] Specifically, the server can perform fault diagnosis on the target mechanical equipment based on the target filtered signal obtained in step S104 to analyze the components that generate fault signals in the target mechanical equipment.

[0117] It should be noted that in addition to analyzing based on the target filtered signal, the server can also perform fault diagnosis on the target mechanical equipment from the spectral dimension. In one or more embodiments of this application, the server can determine the envelope spectrum of the target filtered signal and extract the fault signals that conform to the preset probability distribution from the envelope spectrum. In the fault detection of rotating parts, the fault signals have the characteristics of sub-Gaussian distribution. Therefore, the preset probability distribution can be sub-Gaussian distribution.

[0118] In the above method, first, the server needs to obtain the original vibration signal corresponding to the target mechanical equipment, filter the original vibration signal through a preset initial filter to obtain the original filtered signal, and determine the initial search direction and the initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter. Secondly, the server iteratively updates the initial filter multiple times along the determined initial search direction and according to the determined initial update step size with the goal of minimizing the dispersion degree until the preset stopping criterion is met to obtain the target filter. Finally, the server filters the original vibration signal through the target filter to obtain the target filtered signal, and then performs fault diagnosis on the target mechanical equipment based on the target filtered signal.

[0119] Among them, the initial search direction represents the iterative direction in which the dispersion degree decreases. That is, the process of performing multiple iterative updates based on the initial search direction and the initial update step size is the process of iteratively updating the initial filter along the direction in which the dispersion degree of the original filtered signal decreases. Therefore, the target filter can start from the dimension of minimizing the dispersion degree, utilize the characteristic that the fault signal conforms to the sub-Gaussian distribution (small dispersion degree), and indirectly extract the fault signal. That is, starting from the dimension of the dispersion degree, it avoids the interference of periodic noise and ensures the accuracy of fault diagnosis. At the same time, matrix operations are adopted in step S102, with less computational amount and data storage amount, thus making the fault diagnosis efficient.

[0120] In step S103, in addition to iteratively updating the initial filter based on the initial search direction and the initial update step size, in one or more embodiments of the present application, the server can adjust the search direction and the update step size used in each iterative update during the process of performing multiple iterative updates on the initial filter, so as to improve the search for the target filter corresponding to the system response that "meets the constraint of minimizing the dispersion degree", specifically as follows:

[0121] First, the server needs to perform the first iterative update on the initial filter along the initial search direction determined in step S102 and according to the initial update step size determined in step S102.

[0122] Continuing with the representation of each parameter in step S102, after the first iterative update, the parameter transformation of the initial filter is as follows:

[0123] f1 = f0 + a1p1 (11)

[0124] In the above formula, f0 is the system response of the initial filter, f1 is the system response of the initial filter after the first iterative update, and other parameters can refer to the description in step S102 and will not be elaborated here.

[0125] Secondly, the server can determine the initial residual vector.

[0126] Finally, based on the initial residual vector and the original vibration signal, the server iteratively updates the initial filter after the first iteration update multiple times with the goal of minimizing the discrete degree until a preset stopping criterion is met, and a target filter is obtained. Among them, based on the initial residual vector, the initial search direction, and the initial update step size, the initial residual vector, the initial search direction, and the initial update step size used in each iterative update need to be iteratively adjusted, and then based on the dynamically adjusted initial search direction and the dynamically adjusted initial update step size, with the goal of minimizing the discrete degree, the system response of the initial filter is optimized.

[0127] In one or more embodiments of the present application, first, for each iterative update among multiple iterative updates, the server can respectively adjust the residual vector, the search direction, and the update step size in the previous iterative update.

[0128] Second, for each iterative update among multiple iterative updates, the server can perform the iterative update of the initial filter after the previous iterative update along the adjusted search direction in this iterative update according to the adjusted update step size in this iterative update.

[0129] Finally, for each iterative update among multiple iterative updates, the server can determine whether the initial filter after this iterative update meets the preset stopping criterion. If the preset stopping criterion is met, the iteration is stopped to obtain the target filter. If the preset stopping criterion is not met, the initial filter after this iterative update continues to be iteratively updated for the next iteration.

[0130] As Figure 2 shown, it is a schematic flowchart of obtaining a target filter by iteratively updating the initial filter provided by the embodiment of the present application.

[0131] In addition, in one or more embodiments of the present application, the process of the server iteratively adjusting the residual vector, the search direction, and the update step size is specifically as follows:

[0132] For each iterative update among multiple iterative updates, first, the server can adjust the residual vector in the previous iterative update according to the update step size in the previous iterative update and the search direction in the previous iterative update.

[0133] Second, the server determines the adjustment parameter corresponding to the search direction in this iterative update according to the adjusted residual vector in this iterative update. The server can adjust the search direction in the previous iterative update according to the adjusted residual vector in this iterative update and the adjustment parameter. Among them, the adjustment parameter is used to constrain that the search direction in this iterative update and the search direction in the previous iterative update are orthogonally conjugate.

[0134] Finally, the server can adjust the update step size of the previous iteration update according to the adjusted residual vector and the adjusted search direction in the current iteration update.

[0135] Continuing with the representations of the parameters in step S102, the process of iteratively adjusting the residual vector, search direction, and update step size is as follows with reference to the following formula:

[0136] r0 = b - A * f0 (12)

[0137] r h-1 = r h-2 - a h-1 (Ap h-1 ), h > 1 (13)

[0138]

[0139] f h = f h-1 + a h p h (16)

[0140] In the above formula, h is the number of iteration updates, and h = 1 for the first iteration update. r0 is the initial residual vector, b is the ideal value (which can be set to 0 or a very small value); p h-1 is the search direction of the (h - 1)-th iteration update, a h-1 is the update step size of the (h - 1)-th iteration update, r h-1 is the residual vector of the h-th iteration update; β h is the adjustment parameter of the h-th iteration update, p h is the search direction of the h-th iteration update; a h is the update step size of the h-th iteration update, is the transpose of the residual vector corresponding to the h-th iteration update, is the transpose of the search direction corresponding to the h-th iteration update; f h is the system response of the initial filter after the h-th iteration update. Other parameters can be referred to the description in step S102 and will not be elaborated here.

[0141] In step S102, the stopping criterion can be a preset maximum number of iterations. And in the above, the search direction is adjusted in each iteration update. Therefore, in one or more embodiments of the present application, the server can determine whether to stop the iteration based on the adjusted search direction, specifically as follows:

[0142] Specifically, for each iteration update among multiple iteration updates, the server can determine the norm of the adjusted search direction in this iteration update, and determine whether this norm is less than a preset threshold. In the case where this norm is less than the preset threshold, stop the iteration and obtain the target filter. In the case where this norm is not less than the preset threshold, continue the next iteration update. Among them, the preset threshold can be set according to actual requirements. For example, the preset threshold can be 10 -3 、10 -4 or 10 -5 。

[0143] Such as Figure 3 shown, this application provides an embodiment for fault detection with a train test bench as the target mechanical equipment. In Figure 3 it, the train test bench consists of a drive motor, an acceleration sensor, a faulty bearing, a train axle, and a drive wheel. The working principle is that the drive motor drives the drive wheel to rotate, and the drive wheel drives the train axle to rotate, thereby simulating the scenario when the train is running. The acceleration sensor is used to measure and collect the vibration signal of the faulty bearing, specifically as follows:

[0144] First, the server needs to obtain the original vibration signal of the bearing to be tested.

[0145] It should be noted that the acceleration sensor can be adsorbed on the shell near the bearing to be tested to collect the original vibration signal. The outer ring fault signal is as Figure 4 shown. During the experiment, the rotational speed of the inner ring of the bearing is 256 rpm, the sampling frequency of the acceleration sensor is 76800 Hz, and the length of the tested original vibration signal is 2.5 s; the inner ring fault signal is as Figure 5 shown. During the experiment, the rotational speed of the inner ring of the bearing is 257 rpm, the sampling frequency of the acceleration sensor is 76800 Hz, and the length of the tested original vibration signal is 2.5 s. In the attached figure, f r is the bearing rotation inclination, and f is the fault characteristic frequency corresponding to the fault signal.

[0146] Secondly, the server adopts steps S101 - S103 in the above fault diagnosis method to obtain the target filter, and then through this target filter, filter the original vibration signal of the bearing to be tested to obtain the target filtered signal.

[0147] Finally, the server can perform fault diagnosis on the bearing to be tested based on the target filtered signal of this bearing to be tested.

[0148] This application provides experimental schematic diagrams of the above fault diagnosis method, IMCKD, and ACYCBD for fault diagnosis respectively based on the original vibration signal of the outer ring of the bearing to be tested. Figure 6 is the target filtered signal obtained by using the fault diagnosis method provided by this application, Figure 7is the envelope spectrum of the target filtered signal. From Figure 7 it can be obtained that based on the fault diagnosis method provided in this application, the fault characteristic frequency of the inner ring (f = 42.1 Hz) is successfully extracted; the filtered signal obtained by using IMCKD is as shown in Figure 8 , and the envelope spectrum is as shown in Figure 9 . Based on Figure 8 and Figure 9 it can be obtained that in the scenario of low signal-to-noise ratio of this embodiment, IMCKD has periodic interference signals, which affect the extraction effect; the filtered signal obtained by using ACYCBD is as shown in Figure 10 , and the envelope spectrum is as shown in Figure 11 . Based on Figure 10 and Figure 11 it can be concluded that ACYCBD still only extracts periodic harmonic interference and runout, and does not extract the fault characteristic frequency.

[0149] Through the comparison of Figures 6 to 11 , the fault diagnosis method provided in this application shows the robustness of fault diagnosis under white noise and harmonic interference compared with other methods such as IMCKD and ACYCBD.

[0150] The above is a fault diagnosis method provided in one or more embodiments of this application. Based on the same idea, this application also provides a corresponding fault diagnosis device, as shown in Figure 12 .

[0151] An acquisition module 1200, configured to acquire an original vibration signal corresponding to a target mechanical device;

[0152] An original filtering module 1201, configured to filter the original vibration signal through a preset initial filter to obtain an original filtered signal;

[0153] An iteration parameter module 1202, configured to determine an initial search direction and an initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter;

[0154] An iteration update module 1203, configured to iteratively update the initial filter along the initial search direction according to the initial update step size with the goal of minimizing the dispersion degree until a preset stop criterion is met, so as to obtain a target filter, where the initial search direction represents the iteration direction in which the dispersion degree decreases;

[0155] A target filtering module 1204, configured to filter the original vibration signal through the target filter to obtain a target filtered signal;

[0156] A fault diagnosis module 1205, configured to perform fault diagnosis on the target mechanical equipment according to the target filtered signal.

[0157] In one embodiment, the above iterative parameter module 1202 is further configured to determine the signal mean of the original filtered signal; determine the signal variance of the original filtered signal according to the original filtered signal and the signal mean; and use the signal variance as the degree of dispersion.

[0158] In one embodiment, the above iterative parameter module 1202 is specifically configured to determine the partial derivative of the degree of dispersion with respect to the system response of the initial filter as the discrete gradient; convert the original vibration signal into a Hankel matrix to obtain an original vibration matrix; and determine an initial search direction and an initial update step size according to the original vibration matrix, the discrete gradient, and the system response of the initial filter.

[0159] In one embodiment, the above iterative parameter module 1202 is further configured to determine a coefficient matrix according to the original vibration matrix and the transpose matrix of the original vibration matrix; determine the initial search direction according to the original vibration matrix, the discrete gradient, and the coefficient matrix; and determine the initial update step size according to the coefficient matrix.

[0160] In one embodiment, the above iterative update module 1203 is specifically configured to perform a first iterative update on the initial filter along the initial search direction according to the initial update step size; determine an initial residual vector; and perform multiple iterative updates on the initial filter after the first iterative update with the goal of minimizing the degree of dispersion according to the original vibration signal and the initial residual vector until a preset stopping criterion is met, thereby obtaining a target filter.

[0161] In one embodiment, the above iterative update module 1203 is further configured to, for each iterative update in the multiple iterative updates, adjust the residual vector, the search direction, and the update step size in the previous iterative update respectively; for each iterative update in the multiple iterative updates, perform the iterative update on the initial filter after the previous iterative update along the adjusted search direction in this iterative update according to the adjusted update step size in this iterative update; for each iterative update in the multiple iterative updates, determine whether the initial filter after this iterative update meets the preset stopping criterion; if so, stop the iteration to obtain the target filter; if not, continue to perform the next iterative update on the initial filter after this iterative update.

[0162] In one embodiment, the iterative update module 1203 is further configured to adjust the residual vector in the previous iterative update according to the update step size and the search direction in the previous iterative update; determine an adjustment parameter corresponding to the search direction in the current iterative update according to the adjusted residual vector in the current iterative update, where the adjustment parameter is used to constrain the search direction in the current iterative update and the search direction in the previous iterative update to be orthogonally conjugate; adjust the search direction in the previous iterative update according to the adjusted residual vector and the adjustment parameter in the current iterative update; and adjust the update step size in the previous iterative update according to the adjusted residual vector and the adjusted search direction in the current iterative update.

[0163] In one embodiment, the iterative update module 1203 is further configured to determine the norm of the adjusted search direction in the current iterative update; and determine whether the norm is less than a preset threshold.

[0164] In one embodiment, the fault diagnosis module 1205 is specifically configured to determine the envelope spectrum of the target filtered signal; and extract a fault signal conforming to a preset probability distribution from the envelope spectrum.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working processes of the units and modules in the above system can refer to the corresponding processes of fault diagnosis in the foregoing method embodiments and will not be elaborated herein.

[0166] Based on Figure 1 A fault diagnosis method as shown. Correspondingly, the present application also provides a specific embodiment of a fault diagnosis device.

[0167] Figure 13 FIG. is a schematic hardware structure diagram of a fault diagnosis device provided in an embodiment of the present application.

[0168] A fault diagnosis device may include a processor 1301 and a memory 1302 storing computer program instructions.

[0169] Exemplarily, the program can be divided into one or more modules / units, and one or more modules / units are stored in the memory 1302 and executed by the processor 1301 to complete a fault diagnosis method provided in this application. One or more modules / units can be a series of program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the program in the device.

[0170] Specifically, the above-mentioned processor 1301 can include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0171] The memory 1302 can include a mass storage for data or instructions. By way of example and not limitation, the memory 1302 can include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 1302 can include removable or non-removable (or fixed) media. In a suitable case, the memory 1302 can be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1302 is a non-volatile solid-state memory.

[0172] The processor 1301 reads and executes the computer program instructions stored in the memory 1302 to implement any one of the fault diagnosis methods in the above embodiments.

[0173] In one example, a fault diagnosis device may further include a communication interface 1303 and a bus 1310. Among them, as Figure 13 shown, the processor 1301, the memory 1302, and the communication interface 1303 are connected through the bus 710 to complete communication with each other.

[0174] The communication interface 1303 is mainly used to implement communication between the modules, devices, units, and / or devices in the embodiments of this application.

[0175] Bus 1310 includes hardware, software, or both, and couples components of a fault diagnosis device to each other. By way of example and not limitation, the bus can include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, bus 710 can include one or more buses. Although embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0176] In addition, in combination with a fault diagnosis method in the above embodiments, embodiments of the present application can be implemented by providing a computer storage medium. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any of the fault diagnosis methods in the above embodiments is implemented.

[0177] In addition, in combination with a fault diagnosis method in the above embodiments, embodiments of the present application can be implemented by providing a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute a fault diagnosis method provided in any aspect of the embodiments of the present application as described above.

[0178] It should be clear that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0179] The functional blocks shown in the above-described structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments for performing the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via a data signal carried in a carrier wave. A "machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0180] It should also be noted that in the exemplary embodiments mentioned in the present application, some methods or systems are described based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or can be different from the order in the embodiments, or several steps can be executed simultaneously.

[0181] Aspects disclosed in the present application have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments disclosed in the present application. It should be understood that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / actions specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0182] As described above, this is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A fault diagnosis method, characterized in that, Including: Obtain the original vibration signal corresponding to the target mechanical equipment; Filter the original vibration signal through a preset initial filter to obtain an original filtered signal; Determine an initial search direction and an initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter; Along the initial search direction, according to the initial update step size, with the goal of minimizing the dispersion degree, iteratively update the initial filter multiple times until a preset stopping criterion is met, to obtain a target filter, where the initial search direction represents the iterative direction in which the dispersion degree decreases; Filter the original vibration signal through the target filter to obtain a target filtered signal; Perform fault diagnosis on the target mechanical equipment according to the target filtered signal.

2. The method according to claim 1, wherein Before determining the initial search direction and the initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter, the method further includes: Determine the signal mean value of the original filtered signal; Determine the signal variance of the original filtered signal according to the original filtered signal and the signal mean value; Use the signal variance as the dispersion degree.

3. The method according to claim 1, wherein The step of determining the initial search direction and the initial update step size according to the original vibration signal, the dispersion degree of the original filtered signal, and the system response of the initial filter specifically includes: Determine the partial derivative of the dispersion degree with respect to the system response of the initial filter as the dispersion gradient; Convert the original vibration signal into a Hankel matrix to obtain an original vibration matrix; Determine the initial search direction and the initial update step size according to the original vibration matrix, the dispersion gradient, and the system response of the initial filter.

4. The method according to claim 3, wherein The step of determining the initial search direction and the initial update step size according to the original vibration matrix, the dispersion gradient, and the system response of the initial filter specifically includes: Determine a coefficient matrix according to the original vibration matrix and the transpose matrix of the original vibration matrix; Determine the initial search direction according to the original vibration matrix, the dispersion gradient, and the coefficient matrix; Determine the initial update step size according to the coefficient matrix.

5. The method according to claim 1, wherein The step of iteratively updating the initial filter multiple times along the initial search direction, according to the initial update step size, with the goal of minimizing the dispersion degree until a preset stopping criterion is met to obtain a target filter specifically includes: Perform the first iterative update on the initial filter along the initial search direction according to the initial update step size; Determine an initial residual vector; According to the original vibration signal and the initial residual vector, with the goal of minimizing the dispersion degree, perform multiple iterative updates on the initial filter after the first iterative update until a preset stopping criterion is met to obtain a target filter.

6. The method according to claim 5, characterized in that, The step of performing multiple iterative updates on the initial filter after the first iterative update with the aim of minimizing the degree of discreteness based on the original vibration signal until a preset stopping criterion is met to obtain the target filter specifically includes: For each iterative update in the multiple iterative updates, adjust the residual vector, search direction, and update step size in the previous iterative update respectively; For each iterative update in the multiple iterative updates, along the adjusted search direction in this iterative update, according to the adjusted update step size in this iterative update, perform this iterative update on the initial filter after the previous iterative update; For each iterative update in the multiple iterative updates, determine whether the initial filter after this iterative update meets the preset stopping criterion; If so, stop the iteration and obtain the target filter; If not, continue to perform the next iterative update on the initial filter after this iterative update.

7. The method according to claim 6, wherein The step of, for each iterative update in the multiple iterative updates, adjusting the residual vector, search direction, and update step size in the previous iterative update respectively specifically includes: Adjust the residual vector in the previous iterative update according to the update step size in the previous iterative update and the search direction in the previous iterative update; Determine the adjustment parameter corresponding to the search direction in this iterative update according to the adjusted residual vector in this iterative update, where the adjustment parameter is used to constrain the search direction in this iterative update and the search direction in the previous iterative update to be orthogonally conjugate; Adjust the search direction in the previous iterative update according to the adjusted residual vector in this iterative update and the adjustment parameter; Adjust the update step size in the previous iterative update according to the adjusted residual vector in this iterative update and the adjusted search direction in this iterative update.

8. The method according to claim 6, wherein The step of determining whether the initial filter after this iterative update meets the preset stopping criterion specifically includes: Determine the norm of the adjusted search direction in this iterative update; Judge whether the norm is less than a preset threshold.

9. The method according to claim 1, wherein The step of performing fault diagnosis on the target mechanical equipment according to the target filtering signal specifically includes: Determine the envelope spectrum of the target filtering signal; Extract the fault signal that conforms to the preset probability distribution from the envelope spectrum.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is caused to execute the method according to any one of claims 1-9.

11. A machine-readable storage medium, characterized in that, The program or instructions are stored on the machine-readable storage medium, and when the program or instructions are executed by the processor, the method according to any one of claims 1-9 is implemented.

12. An electronic device, characterized in that, The device includes: a processor and a memory storing the program or instructions; When the processor executes the program or instructions, the method according to any one of claims 1-9 is implemented.

Images