Fault detection method, device and equipment and computer storage medium

Abstract

The invention provides a fault detection method, device and equipment and a computer storage medium, and the method comprises the steps: carrying out the filtering processing of an initial vibration signal through an initial filter, and determining an initial iteration gradient and an initial iteration step size according to an initial filtering variance and the initial vibration signal; and on the basis of the initial iteration gradient and the initial iteration step length, performing multiple iterations on the filter by taking the minimum filtering variance as a target. The iterated filter can perform filtering processing on the initial vibration signal to determine a target filtering signal. And performing fault detection on the target mechanical equipment according to the target filtering signal. The filter is iterated by taking variance minimization as a target, so that the filter accurately filters the fault signal in the vibration signal, and the filtering precision of the noise signal and the detection precision and efficiency of the fault signal are effectively improved. Fault problems in the mechanical equipment can be detected more accurately and efficiently based on the filtered signals, and powerful safety guarantee is provided for normal operation of the mechanical equipment.

Description

Technical Field

[0001] This application belongs to the field of signal analysis, and particularly relates to a fault detection method, device, equipment, and computer storage medium. Background Art

[0002] Currently, most of the running fault detections for mechanical equipment are carried out by analyzing faults through data such as vibration signals during the operation of the equipment. For example, through the Deconvolution Algorithm (DA), by continuously optimizing and iterating the filter, the fault signal is accurately filtered out from the vibration signal during the operation of the equipment.

[0003] However, at the present stage, most of the deconvolution algorithms for filtering fault signals use kurtosis and signal periodicity as the objective functions. Such methods rely relatively heavily on vibration signals with high signal-to-noise ratios. In low signal-to-noise ratio vibration signals, the true fault signals and noises are intertwined and complex. Traditional algorithms cannot accurately distinguish various signal types in low signal-to-noise ratio vibration signals, resulting in a serious impact on the detection accuracy and detection efficiency. Noise signals in low signal-to-noise ratio vibration signals may also have periodicity. Based on the above algorithms, it is easy to misjudge periodic noise as a fault signal, with relatively low detection accuracy and poor robustness in the detection process. Summary of the Invention

[0004] Embodiments of this application provide a fault detection method, device, equipment, and computer storage medium, which can accurately and efficiently detect faults in mechanical equipment.

[0005] In a first aspect, embodiments of this application provide a fault detection method, including:

[0006] Obtain an initial vibration signal corresponding to a target mechanical equipment;

[0007] Perform filtering processing on the initial vibration signal through a preset initial filter to obtain an initial filtered signal;

[0008] Determine an initial iteration gradient and an initial iteration step size corresponding to the initial filter according to the initial filtered variance corresponding to the initial filtered signal and the initial vibration signal;

[0009] Based on the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filtered variance, perform multiple parameter iterations on the initial filter to determine the iterated filter, where the filtered variance is the filtered variance corresponding to the filtered signal obtained by performing filtering processing on the initial vibration signal;

[0010] Perform filtering processing on the initial vibration signal through the iterated filter to obtain a target filtered signal;

[0011] Perform fault detection on the target mechanical equipment according to the target filtered signal.

[0012] In some embodiments, determining an initial iteration gradient and an initial iteration step size corresponding to an initial filter according to an initial filtering variance corresponding to an initial filtering signal and an initial vibration signal includes:

[0013] Determining a partial derivative of the initial filtering variance with respect to filter parameters corresponding to the initial filter according to the initial filtering variance and the initial vibration signal as the initial iteration gradient;

[0014] Determining the initial iteration step size according to the initial iteration gradient, the initial filtering signal, and the initial vibration signal.

[0015] In some embodiments, determining the initial iteration step size according to the initial iteration gradient, the initial filtering signal, and the initial vibration signal includes:

[0016] Determining an inner product value of the initial iteration gradient and the initial vibration signal, and determining a difference between the initial filtering signal and a mean value corresponding to the initial filtering signal;

[0017] Determining the initial iteration step size according to the inner product value and the difference.

[0018] In some embodiments, based on the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filtering variance, performing multiple parameter iterations on the initial filter to determine the iterated filter includes:

[0019] According to the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filtering variance of the filtering signal obtained by filtering the initial vibration signal with the filter after the first iteration, performing a first iteration on the initial parameters of the initial filter to obtain the filter after the first iteration;

[0020] According to the initial vibration signal, with the goal of minimizing the filtering variance of the filtering signal obtained by filtering the initial vibration signal with the iterated filter, performing multiple iterations on the filter after the first iteration to determine the iterated filter.

[0021] In some embodiments, according to the initial vibration signal, with the goal of minimizing the filtering variance of the filtering signal obtained by filtering the initial vibration signal with the iterated filter, performing multiple iterations on the filter after the first iteration includes:

[0022] For each round of iteration, filtering the initial vibration signal through the filter after the previous round of iteration corresponding to this round of iteration to obtain the filtering signal corresponding to the filter after the previous round of iteration;

[0023] Determining the iteration gradient and the iteration step size corresponding to this round of iteration according to the filtering variance of the filtering signal corresponding to the filter after the previous round of iteration and the initial vibration signal;

[0024] Based on the iteration gradient and iteration step corresponding to this round of iteration, with the goal of minimizing the filtering variance of the filtered signal obtained by filtering the initial vibration signal with the filter after this round of iteration, iterate on the parameters of the filter after the previous round of iteration.

[0025] In some embodiments, perform multiple iterations on the filter after the initial iteration to determine the filter after iteration, including:

[0026] For each round of iteration, determine whether the iteration gradient corresponding to this round of iteration is greater than a preset iteration gradient threshold;

[0027] If so, continue the iteration;

[0028] If not, based on the iteration gradient and iteration step corresponding to this round of iteration, with the goal of minimizing the filtering variance of the filtered signal obtained by filtering the initial vibration signal with the filter after this round of iteration, iterate on the parameters of the filter after the previous round of iteration, and use the filter after this round of iteration as the filter after iteration.

[0029] In some embodiments, perform fault detection on the target mechanical equipment according to the target filtered signal, including:

[0030] Determine the envelope spectrum data corresponding to the target filtered signal;

[0031] According to the envelope spectrum data, determine the fault signal of the target mechanical equipment during operation.

[0032] In some embodiments, obtain the initial vibration signal corresponding to the target mechanical equipment, including:

[0033] Collect the vibration data generated by the target mechanical equipment at a preset acquisition interval through a preset vibration sensor as the initial vibration signal.

[0034] In a second aspect, an embodiment of the present application provides a fault detection device, including:

[0035] A signal acquisition unit for acquiring the initial vibration signal corresponding to the target mechanical equipment;

[0036] An initial filtering unit for filtering the initial vibration signal through a preset initial filter to obtain an initial filtered signal;

[0037] An iteration information determination unit for determining the initial iteration gradient and initial iteration step corresponding to the initial filter according to the initial filtering variance corresponding to the initial filtered signal and the initial vibration signal;

[0038] An iterative unit, configured to perform multiple parameter iterations on an initial filter with the aim of minimizing the filtering variance based on an initial iterative gradient and an initial iterative step size, and determine the iterated filter, where the filtering variance is the filtering variance corresponding to the filtered signal obtained by filtering the initial vibration signal;

[0039] A filtering unit, configured to filter the initial vibration signal through the iterated filter to obtain a target filtered signal;

[0040] A fault detection unit, configured to perform fault detection on a target mechanical device according to the target filtered signal.

[0041] In a third aspect, an embodiment of the present application provides a fault detection device, which includes:

[0042] A processor and a memory storing programs or instructions;

[0043] When the processor executes the programs or instructions, the above-mentioned method is implemented.

[0044] In a fourth aspect, an embodiment of the present application provides a machine-readable storage medium, on which programs or instructions are stored, and when the programs or instructions are executed by a processor, the above-mentioned method is implemented.

[0045] 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 enabled to execute the above-mentioned method.

[0046] The technical solutions provided by the embodiments of the present application at least bring the following beneficial effects:

[0047] The embodiments of the present application provide a fault detection method, device, equipment, and computer storage medium. The initial vibration signal obtained can be filtered through an initial filter. According to the variance of the initial filtered signal and the initial vibration signal, an initial iterative gradient and an initial iterative step size are determined. Based on the initial iterative gradient and the initial iterative step size, multiple iterations are performed on the initial filter with the aim of minimizing the filtering variance. The iterated filter can be used to filter the initial vibration signal to determine a target filtered signal.

[0048] Finally, fault detection can be performed on the target mechanical device according to the target filtered signal obtained by filtering. Iterating the filter in a way of minimizing the variance can enable the filter to accurately filter out the fault signals in the vibration signals of the mechanical device, effectively improving the filtering accuracy of the noise signals and the detection efficiency of the fault signals. Based on the filtered signal, the fault problems in the mechanical device can be detected more accurately and efficiently, thus providing a strong safety guarantee for the normal operation of the mechanical device. Description of the Drawings

[0049] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a schematic flowchart of a fault detection method provided by an embodiment of the present application;

[0051] Figure 2(a) is one of the schematic diagrams of the process of collecting an initial vibration signal provided by an embodiment of the present application;

[0052] Figure 2(b) is another schematic diagram of the process of collecting an initial vibration signal provided by an embodiment of the present application;

[0053] Figure 2(c) is yet another schematic diagram of the process of collecting an initial vibration signal provided by an embodiment of the present application;

[0054] Figure 3(a) is a waveform schematic diagram of a target filtered signal provided by an embodiment of the present application;

[0055] Figure 3(b) is a waveform schematic diagram of envelope spectrum data provided by an embodiment of the present application;

[0056] Figure 4 It is a schematic diagram of the overall framework of a fault detection method provided by an embodiment of the present application;

[0057] Figure 5 It is a schematic structural diagram of a fault detection device provided by another embodiment of the present application;

[0058] Figure 6 It is a schematic hardware structure diagram of an electronic device provided by yet another embodiment of the present application. Detailed implementation manners

[0059] The following will describe in detail the features and exemplary embodiments of various aspects of the present application. To make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than limiting 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.

[0060] It should be noted that in this article, 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 terms "include", "comprise" or any other variant thereof are 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 elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0061] At present, the fault detection of mechanical equipment is mostly realized through the deconvolution algorithm (DA). However, the traditional deconvolution algorithm mainly takes kurtosis and signal periodicity as the objective function. The core principle is to separate fault features from vibration signals by optimizing filters.

[0062] However, this method has significant limitations. In a low signal-to-noise ratio environment, real fault signals are highly intertwined with noise, and the noise itself may have periodic characteristics. This makes it difficult for traditional algorithms to accurately distinguish fault signals from interference noise during the operation of mechanical equipment, and it is very easy to misjudge periodic noise as fault signals, resulting in poor robustness and significantly reducing the detection accuracy and efficiency of fault problems in mechanical equipment.

[0063] In addition, even if there are detection methods that can effectively identify low signal-to-noise ratio and periodic noise, most of them require prior period data of the noise signal, and the limitation problem is relatively serious, which greatly restricts the application effect in complex working conditions and when prior period of noise cannot be obtained.

[0064] Based on the technical problems mentioned above, embodiments of the present application provide a fault detection method, device, equipment and computer storage medium. Specifically, an initial filter can be used to filter the acquired initial vibration signal. According to the variance of the initial filtered signal and the initial vibration signal, the initial iterative gradient and the initial iterative step size are determined.

[0065] Then, based on the initial iterative gradient and the initial iterative step size, the initial filter is iterated multiple times with the goal of minimizing the filtering variance. The iterated filter can be used to filter the initial vibration signal to determine the target filtered signal. Finally, based on the target filtered signal obtained by filtering, fault detection can be performed on the target mechanical equipment.

[0066] The technical solution provided by the embodiments of the present application can iteratively optimize the filter in a way that minimizes variance, effectively enabling the iterated filter to accurately filter out fault signals from the vibration signals of the target mechanical equipment, and effectively improving the filtering accuracy of noise signals and the detection accuracy and efficiency of fault signals. Based on the filtered signals obtained from the technical solution of the present application, the fault problems in the target mechanical equipment can be detected more accurately and efficiently, thus providing a strong safety guarantee for the normal operation of the target mechanical equipment.

[0067] Among them, regarding the execution entity adopted in the embodiments of the present application, specifically, it can be a terminal device, such as a desktop computer, a laptop computer, etc., or a remote device, such as 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. Here, the execution entity of the fault detection method, device, equipment, and computer storage medium provided by the embodiments of the present application is not specifically limited, and can be flexibly selected according to the application scenario and actual requirements.

[0068] It should be noted that in the embodiments provided by the present application, the specific application scenarios corresponding to the above-mentioned fault detection methods, devices, equipment, and computer storage media are not strictly limited, and can be flexibly applied according to actual requirements.

[0069] For example, in the scenario of fault detection for an epicyclic gearbox in a wind turbine, the technical solution provided by the embodiments of the present application can filter the vibration signals collected from the epicyclic gearbox during the operation of the wind turbine through an initial filter. Based on the filtering variance corresponding to the initial filtered signal and the vibration signals of the epicyclic gearbox, the initial iteration gradient and the initial iteration step size are determined.

[0070] Based on the initial iteration gradient and the initial iteration step size, the parameters of the filter are iteratively adjusted in multiple rounds with the goal of minimizing the filtering variance. The filtered filter can filter the vibration signals of the epicyclic gearbox, thereby accurately obtaining the target filtered signal. Further, based on the target filtered signal, the fault signals in the epicyclic gearbox can be accurately detected.

[0071] Through the technical solution provided by the embodiments of the present application, the possible fault signals in the epicyclic gearbox of the wind turbine can be filtered out efficiently and accurately, and the interference of invalid signals such as noise signals can be accurately excluded. Based on the detected fault problems, the processing efficiency and effectiveness in subsequent quality control and risk assessment can be effectively improved, providing a strong safety guarantee for the normal operation of the wind turbine.

[0072] It should be noted that the application scenarios described in the above embodiments of the present application are 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 embodiments of 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 detection method provided by the embodiments of the present application can be applied to various application scenarios that require detecting the operating faults of mechanical equipment, such as motors, generators, industrial gearboxes, gearboxes, centrifuges, and so on.

[0073] Figure 1 It is a schematic flow chart of a fault detection method provided by an embodiment of the present application.

[0074] As Figure 1 shown, the fault detection method provided by the embodiment of the present application includes steps S101 to S105.

[0075] S101: Obtain the initial vibration signal corresponding to the target mechanical equipment.

[0076] In step S101, the technical solution provided by the embodiment of the present application can obtain the initial vibration signal of the target mechanical equipment during operation through a preset signal acquisition method.

[0077] Among them, the initial vibration signal can be vibration data collected for the target mechanical equipment within a preset sampling time according to a preset sampling frequency. Specifically, it can be expressed as x0 ∈ R N , where x0 represents the initial vibration signal, R represents that the initial vibration signal x0 is a real number set, N represents the data dimension corresponding to the initial vibration signal x0, and can be determined by calculating the product of the sampling frequency and the sampling time.

[0078] In the embodiment of the present application, the specific content of the signal acquisition method for obtaining the initial vibration signal is not strictly limited. In an embodiment provided by the present application, vibration sensors can be added to the target mechanical equipment to accurately collect the vibration data corresponding to the target mechanical equipment within the sampling time according to the preset sampling frequency as the initial vibration signal.

[0079] To facilitate understanding of the process of obtaining the initial vibration signal, taking the planetary gearbox in the above-mentioned wind turbine as an example of the target mechanical equipment, a detailed description will be given below, and specifically, reference can be made to Figures 2(a), 2(b), and 2(c).

[0080] Figures 2(a), 2(b), and 2(c) are schematic diagrams of a process for collecting an initial vibration signal provided by an embodiment of the present application.

[0081] Figure 2(a) is a schematic structural diagram of a wind turbine. Among them, 201 is the drive motor of the wind turbine, and 202 is a tachometer. 203 is the planetary gearbox of the wind turbine, and 204 is a vibration sensor adsorbed on the surface of the housing of the planetary gearbox 203. 205 is a parallel-axis gearbox, and 206 is a brake.

[0082] The working principle of the wind turbine shown in Figure 2(a) is that the drive motor 201 provides power to make the planetary gearbox 203 and the parallel-axis gearbox 205 operate. The tachometer 202 records and feeds back the rotational speed information of the device to reasonably control the motor speed, while the brake 206 is used to apply a load. The vibration data during the operation of the wind turbine can be accurately collected through the vibration sensor 204 outside the planetary gearbox 203, so as to obtain the initial vibration signal.

[0083] Figure 2(b) is a schematic diagram of the signal waveform of the initial vibration signal corresponding to the planetary gearbox 20 under the preset sampling conditions that the motor rotation frequency of the drive motor 201 is 50 Hz, the sampling frequency of the vibration sensor 204 is 48000 Hz, and the sampling time interval is 0.8 s. Figure 2(c) is a schematic diagram of the envelope spectrum corresponding to the initial vibration signal determined based on Figure 2(b).

[0084] The technical solution provided by the embodiment of the present application can be based on the initial vibration signal shown in Figure 2(b) to perform subsequent filter iteration and parameter optimization. The fault signal in the initial vibration signal can be accurately identified through the iterated filter, improving the fault detection accuracy and detection efficiency.

[0085] S102: Filter the initial vibration signal through a preset initial filter to obtain an initial filtered signal.

[0086] In step S102, the technical solution provided by the embodiment of the present application can first filter the initial vibration signal obtained in the above steps through an initial filter without parameter optimization to determine the initial filtered signal corresponding to the initial vibration signal.

[0087] Among them, the filtering parameter corresponding to the initial filter can be f = [0, 0…1…0, 0] T ∈R k , f represents the filtering parameter corresponding to the initial filter, [0, 0…1…0, 0] represents the specific initial parameter vector corresponding to the initial filter, T represents the transpose symbol, and R kIt is indicated that the filtering parameters corresponding to the initial filter are real vectors in k dimensions. It can be clearly seen that among the filtering parameters before iterative optimization, there is only one non-zero element. In the subsequent multiple rounds of iteration, each element in the filtering parameters can be iteratively optimized one by one, so that the finally iterated filter can accurately filter out the fault signal in the initial vibration signal.

[0088] Regarding the specific determination process of the initial filtered signal, in an embodiment provided by the present application, for the initial vibration signal x0 obtained through step S101, (k - 1) / 2 zero-valued elements can be filled at both ends of the initial vibration signal x0. Then, for the initial vibration signal X ∈ R after padding N*k a matrix transformation is performed to obtain the Hankel Matrix corresponding to the initial vibration signal x0. The Hankel Matrix corresponding to the initial vibration signal x0 can specifically refer to that shown in formula (1):

[0089]

[0090] where X is used to represent the Hankel Matrix corresponding to the initial vibration signal x0. It can be seen that the elements on each sub-diagonal inside this matrix are equal. Through matrix transformation, the signal characteristics in the initial vibration signal can be effectively enhanced, greatly improving the signal feature extraction accuracy and efficiency of the initial vibration signal in the subsequent filter iteration process and the process of determining the target filtered signal, enhancing the filtering effect, and further improving the fault detection accuracy and detection efficiency.

[0091] Furthermore, inputting the determined Hankel Matrix corresponding to the initial vibration signal x0 into the initial filter, the initial filtered signal can be determined through the initial filter. The determination process can refer to that shown in formula (2):

[0092]

[0093] where y can be used to represent the initial filtered signal, and f is the filtering parameter corresponding to the initial filter. Through the calculation process of formula (2), the initial filtered signal y corresponding to the initial vibration signal x0 can be determined.

[0094] S103: Determine the initial iteration gradient and initial iteration step length corresponding to the initial filter according to the initial filter variance corresponding to the initial filtered signal and the initial vibration signal.

[0095] In step S103, the technical solution provided by the embodiment of the present application can determine the corresponding initial filter variance according to the initial filtered signal determined in the above steps. Then, further based on the initial filter variance and the initial vibration signal, the initial iteration gradient and initial iteration step length corresponding to the initial filter are calculated.

[0096] Among them, the specific meaning of the initial iteration gradient is the same as the meaning of the gradient in the current filter-related technology, that is, it can be used to represent the rate of change of the objective function with respect to each parameter under the current parameters of the filter. In the embodiments of the present application, the initial iteration gradient can be used to represent the rate of change of the filtering variance with respect to each parameter corresponding to the initial filter.

[0097] Similarly, the specific meaning of the initial iteration step size is the same as the meaning of the step size (Step Size / Learning Rate) in the current filter-related technology, that is, it represents the update amplitude of the parameters of the filter during the iteration process. In the embodiments of the present application, the initial iteration step size can be used to represent the update amplitude of the parameters of the initial filter during the first iteration process.

[0098] Regarding the specific determination process of the initial iteration gradient, in an embodiment provided by the present application, according to the initial filtering variance corresponding to the initial filtering signal and the initial vibration signal, the partial derivative of the initial filtering variance with respect to the filter parameters corresponding to the initial filter can be accurately calculated.

[0099] To enable the filter to accurately filter out the filtering signal with the minimum variance, in this embodiment, the partial derivative of the initial filtering variance with respect to the filter parameters corresponding to the initial filter can be used as the initial iteration gradient corresponding to the initial filter.

[0100] The specific determination process of the initial iteration gradient can be referred to as shown in formula (3):

[0101]

[0102] Among them, var is used to represent the initial filtering variance corresponding to the initial filtering signal, y is used to represent the initial filtering signal, and is used to represent the mean value corresponding to the initial filtering signal y. Through the calculation and derivation process of the above formula (3), the initial iteration gradient corresponding to the initial filter can be accurately calculated as:

[0103]

[0104] X T is the transposed matrix of the Hankel matrix corresponding to the initial vibration signal x0 determined in the above embodiment, y is the initial filtering signal, and N is the sampling data dimension size of the initial vibration signal x0.

[0105] It should be noted that the above determination process of the initial iteration gradient is almost exactly the same as the determination process of the iteration gradient corresponding to each iteration process in the subsequent multiple rounds of iteration processes, only the filtering signal in the formula changes correspondingly.

[0106] Regarding the reason for selecting the filtering variance corresponding to the filtered signal as the objective function during the filter iteration process, the fault signals generated by mechanical equipment during operation are usually regular impact signals. For example, a faulty gear generates a slight vibration every time it rotates one full circle. The periodicity makes the distribution of the fault signals more concentrated, and the tail of the signal decays faster, similar to a uniform distribution, forming a "thin tail" sub-Gaussian characteristic.

[0107] The tail probability distribution of a sub-Gaussian signal is lower than that of a normal Gaussian signal. Therefore, the fault signal is closer to a sub-Gaussian signal, while most noise signals belong to Gaussian signals. Due to the special probability distribution characteristics of sub-Gaussian signals, the data points in similar signals tend to be closer to the signal mean, resulting in a smaller variance for the overall signal. Therefore, it can be concluded that the variance value corresponding to the fault signal similar to a sub-Gaussian signal in the vibration signal of mechanical equipment is also low.

[0108] For the above reasons, in the embodiments provided in this application, the vibration signal during the operation of the target mechanical equipment can be filtered with the goal of minimizing the variance to filter out the sub-Gaussian signal with a smaller variance, and thus the fault signal in the vibration signal can be accurately determined.

[0109] By using the variance as the objective function to determine the filter iteration gradient, the Gaussian-distributed noise signals in the vibration signal can be accurately filtered out, and the filtering accuracy will not be affected by periodic problems. The fault signal can also be accurately filtered out in vibration signals with a low signal-to-noise ratio. This effectively improves the detection efficiency and accuracy of fault detection for mechanical equipment, providing a strong safety guarantee for the normal operation of mechanical equipment.

[0110] The above is an introduction to the determination process and principle of the initial iteration gradient and the iteration gradients corresponding to subsequent rounds. Regarding the specific determination process of the initial iteration step corresponding to the initial filter, in an embodiment provided in this application, based on the inner product value between the determined initial iteration gradient and the previously obtained initial vibration signal, and the difference between the initial filtered signal and the signal mean corresponding to the initial filtered signal, the initial iteration step for the first iteration of the initial filter can be calculated.

[0111] Similarly, during the subsequent multiple rounds of iteration, the calculation method of the iteration step corresponding to each round of iteration can be exactly the same as the calculation process of the initial iteration step.

[0112] Specifically, the determination process of the initial iteration step size will be introduced in detail based on formula derivation in turn below. To maximize the iteration rate of the filter, it should be ensured that during each round of iteration, the filter parameters can be optimized in the direction where the filtering variance decreases fastest. Therefore, it can be concluded that when the filter performs parameter iteration in each round, the optimal step size should make the change rate of the objective function (i.e., the filtering variance in the embodiments of the present application) in the direction of this step size zero, that is, the partial derivative of the filtering variance in the embodiments of the present application with respect to the step size is zero, as shown in formula (4):

[0113]

[0114] It should be specifically noted that for the first iteration of the initial filter, var shown in formula (4) does not represent the initial filtering variance corresponding to the first filtering signal, but the filtering variance corresponding to the filtering signal after the filter after the first iteration filters the initial vibration signal. α represents the first iteration step size corresponding to the first iteration process.

[0115] The parameter optimization formula based on which the filter in the embodiments of the present application performs each round of iteration can specifically refer to that shown in formula (5):

[0116]

[0117] Among them, is the filtering parameter after each round of iteration of the filter, f is the filtering parameter before iteration, is the iteration gradient corresponding to each round of iteration process, and α is the iteration step size. The first iteration and subsequent iteration processes can both perform iteration of the filter parameters based on formula (5).

[0118] Assume that the filtering signal obtained after the filter after the first iteration filters the initial vibration signal is Based on the above formulas, the following formula (6) and the corresponding derivation process can be calculated:[[]]END]]

[0119]

[0120] Based on formula (6) and the above formula (4), formula (7) can be derived:[[]]END]]

[0121]

[0122] Among them, for the first iteration process, can represent the inner product value of the initial vibration signal and the initial iteration gradient, and can represent the signal mean value corresponding to the initial filtering signal. Based on formula (7), the following formula (8) and formula (9) are set:[[]]END]]

[0123]

[0124] Based on Equation (8) and Equation (9), Equation (7) can be further derived, calculated, and simplified to obtain the following Equation (10):

[0125]

[0126] Based on Equation (10), the expression formula corresponding to the initial iteration step size can be determined, as specifically shown in Equation (11):

[0127]

[0128] Among them, for the first iteration process of the initial filter, α is the initial iteration step size, W is the arithmetic matrix calculated from the inner product value of the initial vibration signal and the initial iteration gradient as shown in Equation (8) above, and r is the difference matrix between the initial filter signal and the signal mean corresponding to the initial filter signal as shown in Equation (9).

[0129] It can be seen that the initial iteration step size calculated by Equation (11) is specifically a negative value. Therefore, in the filter parameter optimization function shown in Equation (5), the filter parameters after the first iteration are the sum of the filter parameter f before iteration and the product of the initial iteration gradient and the initial iteration step size α. Since the initial iteration step size itself is negative, through the parameter iteration in Equation (5), it can be ensured that whether it is the first iteration or each subsequent round of parameter iteration, the filter parameters can be rapidly iterated in the direction of minimizing the variance.

[0130] Moreover, in the embodiments of the present application, the steepest descent method can be used to determine the steepest descent step size for each iteration process, so that the objective function, specifically the filtering variance, can converge rapidly, greatly accelerating the iteration rate of the filter, and thus to a certain extent, also significantly improving the subsequent fault detection efficiency and detection accuracy for mechanical equipment.

[0131] Based on the above Equation (11), the iteration step size corresponding to each iteration of the filter can be calculated. The above embodiments are only illustrative examples for easy understanding with the first iteration as an example.

[0132] S104: Based on the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filtering variance, perform multiple parameter iterations on the initial filter to determine the iterated filter.

[0133] In step 104, the technical solution provided by the embodiment of the present application can be based on the above process for determining the initial iteration gradient and the initial iteration step size, and aim to minimize the filtering variance of the filtered signal corresponding to the filtered signal obtained by filtering the initial vibration signal by the filter after each round of iteration, and perform multiple rounds of filter parameter iteration on the initial filter. The filter after multiple rounds of iteration can be used for subsequent detection of fault problems of the target mechanical equipment.

[0134] In an embodiment provided by the present application, according to the above steps, the initial iteration gradient and the initial iteration step size are determined, and the parameters corresponding to the filter after the first iteration can be accurately calculated through formula (5) in the above embodiment.

[0135] Then, the initial vibration signal is filtered by the filter after the first iteration to obtain the filtered signal corresponding to the second iteration process. Then, through formula (3) and formula (11) in the above embodiment, the iteration gradient and the iteration step size corresponding to the second iteration process are respectively calculated, and parameter adjustment and optimization are performed through formula (5). This process is repeatedly executed to obtain the filter after the iteration is completed.

[0136] Specifically, in an embodiment, for each round of iteration process, the technical solution provided by the embodiment of the present application can determine the iteration gradient and the iteration step size corresponding to the current round of iteration process according to the filtered signal obtained by filtering the initial vibration signal by the filter with optimized parameters after the previous round of iteration is completed.

[0137] Then, according to the iteration gradient and the iteration step size corresponding to the current round of iteration process, with the aim of minimizing the filtering variance of the filtered signal obtained by filtering the initial vibration signal by the filter after the current round of iteration, the parameters corresponding to the filter after the previous round of iteration are optimized and adjusted. The specific parameter optimization process can refer to that shown in formula (5) above.

[0138] The filter after multiple parameter iterations can be officially used for the subsequent fault detection link of the target mechanical equipment, and can accurately filter out the noise signals with a Gaussian distribution and a high variance in the initial vibration signal, so as to accurately retain the fault signals in the initial vibration signal. By means of the steepest descent method for filter parameter iteration, the iteration rate and the signal recognition ability of the filter are effectively improved, and the detection efficiency and detection accuracy in the subsequent fault signal detection process are greatly improved.

[0139] Regarding the specific judgment conditions for determining the filter after the iteration is completed in the above multiple rounds of iteration process, no strict limitation is imposed in the embodiment of the present application. For example, in an embodiment provided by the present application, a stop criterion can be set for the iteration gradient corresponding to each round of iteration process to obtain the filter after the parameters are fully iterated.

[0140] Specifically, for each round of parameter iteration process, before optimizing the filter parameters, it can be determined whether the iteration gradient corresponding to this iteration round determined by the above formula (3) is greater than a preset iteration gradient threshold.

[0141] When it is determined that the iteration gradient corresponding to this iteration round is greater than the preset iteration gradient threshold, it means that the gradient of the current iteration round has not dropped to the ideal situation, and the filtering effect of the filter on the low-variance signals in the initial vibration signal still needs to be optimized. In this case, the filter after the previous round of iteration is iterated again according to the iteration gradient corresponding to this iteration round and the iteration step determined by formula (11). After this round of iteration, the iteration gradient and iteration step corresponding to the next round are continued to be determined.

[0142] When it is determined that the iteration gradient corresponding to the iteration round is not greater than the preset iteration gradient threshold, it indicates that the gradient of the current iteration round already meets the stopping criterion. The change relationship between the filtering variance of the filtered signal after filtering the initial vibration signal by the filter after this round of iteration and the filter parameters is no longer obvious, and the filtering variance corresponding to this round of iteration can be nearly close to the vibration signal with the smallest variance in the initial vibration signal, and the objective function corresponding to the filter obtains a minimum value.

[0143] In this case, the filter after the previous round of iteration is iterated again according to the iteration gradient and iteration step corresponding to this iteration round. The filter after this round of iteration can be used as the filter processed by the overall multi-round parameter iteration process.

[0144] Through the above processing process of determining the completed iteration of the filter according to the iteration gradient, the iteration efficiency of the filter can be effectively improved, excessive rounds of useless iteration can be avoided, and the iteration time consumption and resource occupation can be saved to a great extent. At the same time, it can also ensure the accurate convergence of the iterated filter, accurately identify the fault signals with smaller variances for the initial vibration signal, and thus effectively improve the detection efficiency and detection accuracy of the subsequent fault detection process.

[0145] In addition to the above determination of the completed iteration of the filter according to the iteration gradient and the preset threshold, it can also be other ways to determine the completed iteration of the filter. For example, in some other embodiments provided in this application, it can also be determined whether the filter iteration is completed by setting the maximum number of iteration rounds, determining the convergence situation of the filtering variance according to the filtered signal, etc., and can be flexibly adjusted specifically according to the application scenario and actual requirements.

[0146] S105: Filter the initial vibration signal through the iterated filter to obtain the target filtered signal.

[0147] In step S105, the technical solution provided by the embodiment of the present application can use the filter obtained by iterating through the above steps S101 to S104 to filter the initial vibration signal again, so as to accurately filter out the target filtered signal that can represent the fault signal in the initial vibration signal.

[0148] The specific filtering process is almost the same as determining the corresponding filtered signal in each round of the above iterative process, that is, as shown in formula (2) in the above embodiment. The difference is that there is no need to calculate the iterative gradient and iterative step length again. The filtering process can directly refer to the above corresponding content and formula, and will not be elaborated here too much.

[0149] S106: Perform fault detection on the target mechanical equipment according to the target filtered signal.

[0150] In step S106, the technical solution provided by the embodiment of the present application can identify the fault problems of the target mechanical equipment based on the target filtered signal determined in step S105, so as to accurately judge the possible fault problems of the target mechanical equipment within the sampling interval time.

[0151] In an embodiment provided by the present application, according to the determined target filtered signal, the envelope spectrum data corresponding to the target filtered signal can be determined.

[0152] Among them, the envelope spectrum data can represent the characteristic frequency corresponding to the fault signal in the envelope spectrum number target filtered signal, the signal energy distribution, and the non-stationary signal distribution, etc.

[0153] The specific method for determining the envelope spectrum data corresponding to the target filtered signal is not strictly limited in the present application. For example, in an embodiment provided by the present application, the envelope signal corresponding to the target filtered signal can be determined first. Then, perform frequency domain conversion on the envelope signal, which can be achieved by means such as Fast Fourier Transform (FFT), and finally obtain the envelope spectrum data corresponding to the target filtered signal. Of course, it can also be other feasible ways to determine the envelope spectrum data, which can be flexibly selected according to the application scenario and signal type.

[0154] Furthermore, according to the envelope spectrum data corresponding to the target filtered signal, the operation fault problems of the target mechanical equipment can be accurately detected. The specific detection method of the fault problems is not strictly limited in the embodiment of the present application. In one embodiment, it can be based on a preset fault signal frequency threshold to detect different types of fault problems, or other feasible fault problem detection methods, which can be flexibly selected according to the application scenario and the actual signal type.

[0155] To facilitate the understanding of the specific forms of the target filtering signal and the envelope spectrum data, based on Fig. 2(b) shown in the above embodiment, a schematic diagram of a target filtering signal and the corresponding envelope spectrum data is used for illustration. Specifically, reference can be made to Fig. 3(a) and Fig. 3(b).

[0156] Fig. 3(a) is a waveform schematic diagram of a target filtering signal provided by an embodiment of the present application.

[0157] Fig. 3(b) is a waveform schematic diagram of an envelope spectrum data provided by an embodiment of the present application.

[0158] As shown in Fig. 3(a) and Fig. 3(b), through the parameter iteration of the above steps, the filter can accurately filter out the target filtering signal shown in Fig. 3(a) from the initial vibration signal shown in Fig. 2(b). Then, based on the target filtering signal shown in Fig. 3(a), the envelope spectrum data shown in Fig. 3(b) can be determined. During the subsequent fault detection process, the possible fault problems in the operation of the target mechanical equipment can be accurately detected based on the envelope spectrum data.

[0159] Through the above fault detection process, according to the target filtering signal determined by the above steps, the fault problems of the target mechanical equipment within the sampling time can be accurately detected. The target filtering signal determined by the filter iteratively obtained with the minimum filtering variance as the optimization target can accurately represent the fault problems in the initial vibration signal, effectively improving the detection accuracy and detection efficiency of the fault detection process, avoiding the problems of false fault judgment or missed fault judgment, and thus providing a strong safety guarantee for the normal operation and rotation of the target mechanical equipment.

[0160] The above are the specific operation contents of each step corresponding to the fault detection method provided by the embodiment of the present application. To facilitate the understanding of the implementation process of the overall fault detection method, the following uses a schematic diagram of the overall framework of a fault detection method for overall introduction. Specifically, reference can be made to Figure 4 as shown in

[0161] Figure 4 Fig. is a schematic diagram of the overall framework of a fault detection method provided by an embodiment of the present application, including steps S401 to S408.

[0162] S401: Obtain the initial vibration signal corresponding to the envelope spectrum data.

[0163] Through step S401, the vibration data of the target mechanical equipment within the sampling time interval can be accurately collected by methods such as vibration sensors.

[0164] S402: Filter the initial vibration signal through an initial filter to determine the initial filtering signal.

[0165] S403: Determine the iterative gradient.

[0166] S404: Determine the iterative step size.

[0167] Through steps S402 to S404, the initial vibration signal can be filtered by the filter. According to the filtering variance corresponding to the determined filtered signal and the initial vibration signal, the iterative gradient (such as the above formula (3)) and the gradient step size (such as the above formula (11)) can be determined respectively.

[0168] S405: Optimize the filter parameters according to the iterative gradient and the iterative step size.

[0169] Through step S405, the filter in each round of iteration can be optimized with the goal of minimizing the filtering variance according to the iterative gradient and the iterative step size, effectively improving the filter's ability to identify fault signals.

[0170] S406: Determine whether the iteration is completed according to the iterative gradient.

[0171] Through the judgment process of step S406, the timing of stopping the iteration can be accurately judged, effectively improving the iteration rate and the filter's ability to detect fault signals. When the iterative gradient does not meet the preset threshold, the parameter iteration is repeated to calculate the iterative gradient and the iterative step size, ensuring that the parameters of the filter after iteration can achieve precise convergence for variance minimization.

[0172] S407: Filter the initial vibration signal through the filter after iteration to determine the target filtered signal.

[0173] S408: Perform fault detection on the target mechanical equipment according to the envelope spectrum data corresponding to the target filtered signal.

[0174] Through steps S407 to S408, the target filtered signal corresponding to the initial vibration signal can be accurately determined by the filter after iteration, and fault detection can be performed on the target mechanical equipment based on the envelope spectrum data corresponding to the target filtered signal. The fault signal of the initial vibration signal can be accurately identified, improving the fault detection efficiency and detection accuracy, and providing a strong safety guarantee for the normal operation of the target mechanical equipment.

[0175] The above is the specific implementation method of the fault detection method provided by this application embodiment. Through the technical solution provided by this application embodiment, the filter can be iterated in a way of minimizing the variance, effectively enabling the filter after iteration to accurately filter out the fault signal from the vibration signal of the target mechanical equipment, and improving the filtering accuracy of the noise signal and the detection accuracy and efficiency of the fault signal.

[0176] For the problem that the current technology cannot accurately identify faults in vibration signals with low signal-to-noise ratio, this application can effectively solve this problem. Whether it is a vibration signal with high signal-to-noise ratio or low signal-to-noise ratio, the filter iteratively obtained based on the technical solution of this application can accurately filter out the target filtered signal that can accurately represent the fault problem of the target mechanical equipment, effectively improving the applicable range of the overall detection process and the adaptability to different types of vibration signals, and enhancing the robustness of the detection process.

[0177] The filtered signal obtained based on the technical solution of this application can more accurately and efficiently detect the fault problems in mechanical equipment, thus providing a strong safety guarantee for the normal operation of mechanical equipment.

[0178] Based on the fault detection method provided in the above embodiments, this application also provides an embodiment of a fault detection device.

[0179] Figure 5 FIG. is a schematic structural diagram of a fault detection device provided in another embodiment of this application. The fault detection device 500 includes:

[0180] A signal acquisition unit 501, configured to acquire an initial vibration signal corresponding to a target mechanical equipment;

[0181] An initial filtering unit 502, configured to perform filtering processing on the initial vibration signal through a preset initial filter to obtain an initial filtered signal;

[0182] An iteration information determination unit 503, configured to determine an initial iteration gradient and an initial iteration step corresponding to the initial filter according to the initial filtering variance corresponding to the initial filtered signal and the initial vibration signal;

[0183] An iteration unit 504, configured to perform multiple parameter iterations on the initial filter with the goal of minimizing the filtering variance based on the initial iteration gradient and the initial iteration step, and determine the iterated filter, where the filtering variance is the filtering variance corresponding to the filtered signal obtained by filtering the initial vibration signal;

[0184] A filtering unit 505, configured to perform filtering processing on the initial vibration signal through the iterated filter to obtain a target filtered signal;

[0185] A fault detection unit 506, configured to perform fault detection on the target mechanical equipment according to the target filtered signal.

[0186] In some embodiments, the above iteration information determination unit 503 is specifically configured to:

[0187] Determine the partial derivative of the initial filtering variance with respect to the filter parameters corresponding to the initial filter according to the initial filtering variance and the initial vibration signal, and use it as the initial iteration gradient;

[0188] Determine an initial iteration step size based on an initial iteration gradient, an initial filtered signal, and an initial vibration signal.

[0189] In some embodiments, the above-mentioned iteration information determination unit 503 is specifically configured to:

[0190] Determine the inner product value of the initial iteration gradient and the initial vibration signal, and determine the difference between the initial filtered signal and the mean value corresponding to the initial filtered signal;

[0191] Determine the initial iteration step size according to the inner product value and the difference.

[0192] In some embodiments, the above-mentioned iteration unit 504 is specifically configured to:

[0193] Taking the filtering variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the filter after the first iteration to be minimized as the target, perform a first iteration on the initial parameters of the initial filter according to the initial iteration gradient and the initial iteration step size, and obtain the filter after the first iteration;

[0194] Taking the filtering variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the filter after iteration to be minimized as the target, perform multiple iterations on the filter after the first iteration according to the initial vibration signal, and determine the filter after iteration.

[0195] In some embodiments, the above-mentioned iteration unit 504 is specifically configured to:

[0196] For each round of iteration, filter the initial vibration signal through the filter after the previous round of iteration corresponding to this round of iteration to obtain the filtered signal corresponding to the filter after the previous round of iteration;

[0197] Determine the iteration gradient and iteration step size corresponding to this round of iteration according to the filtering variance of the filtered signal corresponding to the filter after the previous round of iteration and the initial vibration signal;

[0198] Taking the filtering variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the filter after this round of iteration to be minimized as the target, perform iteration on the parameters of the filter after the previous round of iteration according to the iteration gradient and iteration step size corresponding to this round of iteration.

[0199] In some embodiments, the above-mentioned iteration unit 504 is specifically configured to:

[0200] For each round of iteration, determine whether the iteration gradient corresponding to this round of iteration is greater than a preset iteration gradient threshold;

[0201] If so, continue the iteration;

[0202] Otherwise, based on the iteration gradient and iteration step size corresponding to this round of iteration, with the goal of minimizing the filtering variance of the filtered signal obtained by filtering the initial vibration signal using the filter after this round of iteration, iterate on the parameters of the filter after the previous round of iteration, and use the filter after this round of iteration as the iterated filter.

[0203] In some embodiments, the above-mentioned fault detection unit 506 is specifically configured to:

[0204] Determine the envelope spectrum data corresponding to the target filtered signal;

[0205] Based on the envelope spectrum data, determine the fault signal during the operation of the target mechanical equipment.

[0206] In some embodiments, the above-mentioned signal acquisition unit 501 is specifically configured to:

[0207] Collect vibration data generated by the target mechanical equipment at a preset acquisition interval through a preset vibration sensor as the initial vibration signal.

[0208] It should be noted that the information interaction, execution process, etc. between the above-mentioned device / units are based on the same concept as the method embodiments of this application, and are devices corresponding to the above-mentioned fault detection method. All implementation manners in the above method embodiments are applicable to the embodiments of this device. For the specific functions and the technical effects brought by them, please refer to the method embodiment part for details, and will not be elaborated here.

[0209] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module 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 is 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 each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0210] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided by another embodiment of this application.

[0211] The device may include a processor 601 and a memory 602 storing programs or instructions.

[0212] When the processor 601 executes a program, it implements the steps in any of the above method embodiments.

[0213] Exemplarily, the program may be divided into one or more modules / units, and one or more modules / units are stored in the memory 602 and executed by the processor 601 to complete this application. One or more modules / units may be a series of program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the program in the device.

[0214] Specifically, the above-mentioned processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be an integrated circuit configured to implement one or more embodiments of this application.

[0215] The memory 602 may include a mass storage for data or instructions. By way of example and not limitation, the memory 602 may 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 602 may include removable or non-removable (or fixed) media. In a suitable case, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0216] The memory may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) machine-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

[0217] The processor 601 reads and executes the program or instructions stored in the memory 602 to implement any one of the above methods.

[0218] In one example, the electronic device may further include a communication interface 603 and a bus 604. Among them, the processor 601, the memory 602, and the communication interface 603 are connected through the bus 604 to complete communication with each other.

[0219] The communication interface 603 is mainly used to implement the communication between various modules, devices, units, and / or apparatuses in the embodiments of the present application.

[0220] The bus 604 includes hardware, software, or both, and couples the components of the online data flow meter charging device to each other. By way of example and not limitation, the bus may 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 buses or a combination of two or more of these. In a suitable case, the bus 604 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0221] In addition, in combination with the method in the above embodiments, the embodiments of the present application may be implemented by providing a machine-readable storage medium. A program or instruction is stored on the machine-readable storage medium; when the program or instruction is executed by a processor, any one of the methods in the above embodiments is implemented. The machine-readable storage medium can be read by a machine such as a computer.

[0222] The embodiments of the present application further provide a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run a program or instruction, implement each process of the above method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described here again.

[0223] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip.

[0224] The embodiments of the present application provide a computer program product, the program product is stored in a machine-readable storage medium, and the program product is executed by at least one processor to implement each process of the above method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described here again.

[0225] It should be clear that the present application is not limited to the specific configurations and processes described above and shown 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 shown as examples. However, the method process of the present application is not limited to the specific steps described and shown. 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.

[0226] The functional modules 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 used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), 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.

[0227] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems 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 different from the order in the embodiments, or several steps can be executed simultaneously.

[0228] The aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and program products according to embodiments of the present disclosure. It should be understood that each block in the flowchart and / or block diagram, and the combinations of blocks in the flowchart and / or block diagram, can be implemented by computer programs or instructions. These programs or instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing devices to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing devices 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 is also understood that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions.

[0229] 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 be covered within the protection scope of the present application.

Claims

1. A fault detection method, characterized in that Including: Obtain an initial vibration signal corresponding to a target mechanical device; Perform filtering processing on the initial vibration signal through a preset initial filter to obtain an initial filtered signal; Determine an initial iteration gradient and an initial iteration step size corresponding to the initial filter according to the initial filter variance corresponding to the initial filtered signal and the initial vibration signal; Based on the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filter variance, perform multiple parameter iterations on the initial filter to determine the iterated filter, where the filter variance is the filter variance corresponding to the filtered signal obtained by filtering the initial vibration signal; Perform filtering processing on the initial vibration signal through the iterated filter to obtain a target filtered signal; Perform fault detection on the target mechanical device according to the target filtered signal.

2. The method according to claim 1, wherein Determine an initial iteration gradient and an initial iteration step size corresponding to the initial filter according to the initial filter variance corresponding to the initial filtered signal and the initial vibration signal, including: Determine the partial derivative of the initial filter variance with respect to the filter parameters corresponding to the initial filter according to the initial filter variance and the initial vibration signal as the initial iteration gradient; Determine the initial iteration step size according to the initial iteration gradient, the initial filtered signal, and the initial vibration signal.

3. The method according to claim 2, characterized in that Determine the initial iteration step size according to the initial iteration gradient, the initial filtered signal, and the initial vibration signal, including: Determine the inner product value of the initial iteration gradient and the initial vibration signal, and determine the difference between the initial filtered signal and the mean value corresponding to the initial filtered signal; Determine the initial iteration step size according to the inner product value and the difference.

4. The method according to claim 1, characterized in that, Based on the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filter variance, perform multiple parameter iterations on the initial filter to determine the iterated filter, including: According to the initial iteration gradient and the initial iteration step size, with the goal of minimizing the filter variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the filter after the first iteration, perform the first iteration on the initial parameters of the initial filter to obtain the filter after the first iteration; According to the initial vibration signal, with the goal of minimizing the filter variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the iterated filter, perform multiple iterations on the filter after the first iteration to determine the iterated filter.

5. The method according to claim 4, wherein According to the initial vibration signal, with the goal of minimizing the filter variance corresponding to the filtered signal obtained by filtering the initial vibration signal by the iterated filter, perform multiple iterations on the filter after the first iteration, including: For each round of iteration, perform filtering processing on the initial vibration signal through the filter after the previous round of iteration corresponding to this round of iteration to obtain the filtered signal corresponding to the filter after the previous round of iteration; Determine the iteration gradient and iteration step corresponding to this round of iteration according to the filtering variance of the filtering signal corresponding to the filter after the previous round of iteration and the initial vibration signal; With the iteration gradient and iteration step corresponding to this round of iteration, and aiming to minimize the filtering variance of the filtering signal obtained by filtering the initial vibration signal with the filter after this round of iteration, iterate the parameters of the filter after the previous round of iteration.

6. The method according to claim 4, wherein Perform multiple iterations on the filter after the initial iteration to determine the iterated filter, including: For each round of iteration, determine whether the iteration gradient corresponding to this round of iteration is greater than a preset iteration gradient threshold; If so, continue the iteration; If not, with the iteration gradient and iteration step corresponding to this round of iteration, and aiming to minimize the filtering variance of the filtering signal obtained by filtering the initial vibration signal with the filter after this round of iteration, iterate the parameters of the filter after the previous round of iteration, and the filter after this round of iteration is used as the iterated filter.

7. The method according to claim 1, characterized in that Perform fault detection on the target mechanical equipment according to the target filtering signal, including: Determine the envelope spectrum data corresponding to the target filtering signal; Determine the fault signal of the target mechanical equipment during operation according to the envelope spectrum data.

8. The method according to claim 1, wherein Obtain the initial vibration signal corresponding to the target mechanical equipment, including: Collect the vibration data generated by the target mechanical equipment at a preset acquisition interval through a preset vibration sensor as the initial vibration signal.

9. An electronic device, characterized in that, The device includes: a processor and a memory storing programs or instructions; When the processor executes the programs or instructions, the method described in any one of claims 1-8 is implemented.

10. A machine-readable storage medium, characterized in that, Programs or instructions are stored on the machine-readable storage medium, and when the programs or instructions are executed by the processor, the method described in any one of claims 1-8 is implemented.

11. 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 described in any one of claims 1-8.

Images