A fault detection method based on super-resolution and related devices

Abstract

The application discloses a kind of based on super-resolution fault detection method and related device, the described method includes obtaining the vibration signal of rotating structure, and the vibration signal is oversampled to obtain oversampling signal;The phase spectrum of oversampling signal is obtained, and the maximum likelihood period of oversampling signal is determined based on phase spectrum;The phase correction value of the vibration signal is calculated based on maximum likelihood period, and the fault characteristic signal of vibration signal is calculated based on maximum likelihood period, the phase correction value and vibration signal;Rotating structure fault result is determined based on fault characteristic signal.The application is oversampled to vibration signal, then the maximum likelihood period of oversampling signal is obtained, and fault characteristic signal is extracted based on maximum likelihood period, finally, rotating structure fault result is determined based on fault characteristic signal, and fault characteristic signal can comprehensively reflect the running condition of rotating structure, so as to improve the accuracy of fault detection.

Description

Technical Field

[0001] This application relates to the field of data analysis technology, and in particular to a fault detection method and related apparatus based on super-resolution. Background Technology

[0002] In industrial production, it is necessary to monitor the operating status of rotating structures (e.g., rolling bearing equipment). Currently, common methods include analyzing the vibration signal spectrum using Fourier transform to extract fault feature values, or using artificial intelligence algorithms (e.g., neural networks, autoencoders) to extract fault feature values, and then determining whether a fault exists in the rotating structure based on these extracted feature values. However, fault diagnosis based on fault feature values ​​is prone to errors due to inaccuracies in feature value extraction.

[0003] Therefore, the existing technology still needs to be improved and enhanced. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide a fault detection method and related apparatus based on super-resolution, addressing the shortcomings of existing technologies.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a fault detection method based on super-resolution, the method comprising: The vibration signal of the rotating structure is acquired, and the vibration signal is oversampled to obtain an oversampled signal; The phase spectrum of the oversampled signal is obtained, and the maximum likelihood period of the oversampled signal is determined based on the phase spectrum. The phase correction value of the vibration signal is calculated based on the maximum likelihood period, and the fault characteristic signal of the vibration signal is calculated based on the maximum likelihood period, the phase correction value, and the vibration signal. The fault result of the rotating structure is determined based on the fault characteristic signal.

[0006] The fault detection method based on super-resolution, wherein acquiring the phase spectrum of the oversampled signal specifically includes: Obtain several discrete periods corresponding to the oversampled signal, wherein each discrete period in the several discrete periods is different from the others; For each discrete period, the oversampled signal is cyclically sampled and superimposed based on the discrete period to obtain a cyclically sampled signal, and the phase value of the cyclically sampled signal is calculated; The phase spectrum sequence formed by the phase values ​​of each cyclically sampled signal is used as the phase spectrum of the oversampled signal.

[0007] In the super-resolution-based fault detection method, the signal length of the cyclic sampling signal is equal to the discrete period corresponding to the cyclic sampling signal.

[0008] The fault detection method based on super-resolution, wherein calculating the phase value of the cyclically sampled signal specifically includes: Obtain the signal value of each sampling point in the cyclic sampling signal; The phase value of the cyclically sampled signal is calculated based on each signal value.

[0009] The fault detection method based on super-resolution, wherein determining the maximum likelihood period of the oversampled signal based on the phase spectrum specifically includes: Select the largest phase value from all phase values ​​in the phase spectrum; The discrete period corresponding to the largest selected phase value is taken as the maximum likelihood period of the oversampled signal.

[0010] The super-resolution-based fault detection method, wherein calculating the fault characteristic signal of the vibration signal based on the maximum likelihood period specifically includes: The vibration signal is divided into several periodic signals based on the maximum likelihood period; For every two periodic signals in a series of periodic signals, the phase deviation between the two periodic signals is determined based on the cross-correlation function; The phase value corresponding to the largest phase deviation value among all calculated phase deviation values ​​is taken as the phase correction value.

[0011] The super-resolution-based fault detection method, wherein determining the fault result of the rotating structure based on the fault feature signal specifically includes: Obtain the maximum amplitude of the fault characteristic signal; If several of the maximum amplitude values ​​are greater than a preset amplitude threshold, then the failure result of the rotating structure is a failure. If the maximum amplitude value is less than or equal to the preset amplitude threshold, the failure result of the rotating structure is no failure.

[0012] A second aspect of this application provides a fault detection system based on super-resolution, the system comprising: A sampling module is used to acquire the vibration signal of the rotating structure and to oversample the vibration signal to obtain an oversampled signal; An acquisition module is used to acquire the phase spectrum of the oversampled signal and determine the maximum likelihood period of the oversampled signal based on the phase spectrum. The calculation module is used to calculate the phase correction value of the vibration signal based on the maximum likelihood period, and to calculate the fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value, and the vibration signal. The determination module is used to determine the fault result of the rotating structure based on the fault characteristic signal.

[0013] A third aspect of this application provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in any of the super-resolution-based fault detection methods described above.

[0014] A fourth aspect of this application provides a terminal device, which includes: a processor, a memory, and a communication bus; the memory stores a computer-readable program that can be executed by the processor; The communication bus enables communication between the processor and the memory; When the processor executes the computer-readable program, it implements the steps in any of the super-resolution-based fault detection methods described above.

[0015] Beneficial Effects: Compared with existing technologies, this application provides a fault detection method and related apparatus based on super-resolution. The method includes: acquiring a vibration signal of a rotating structure and oversampling the vibration signal to obtain an oversampled signal; acquiring the phase spectrum of the oversampled signal and determining the maximum likelihood period of the oversampled signal based on the phase spectrum; calculating a phase correction value of the vibration signal based on the maximum likelihood period; and calculating a fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value, and the vibration signal; and determining the fault result of the rotating structure based on the fault characteristic signal. This application improves the accuracy of fault detection by oversampling the vibration signal, acquiring the maximum likelihood period of the oversampled signal, extracting the fault characteristic signal based on the maximum likelihood period, and finally determining the fault result of the rotating structure based on the fault characteristic signal. The fault characteristic signal can comprehensively reflect the operating status of the rotating structure, thereby improving the accuracy of fault detection. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1A flowchart of the super-resolution-based fault detection method provided in this application.

[0018] Figure 2 A schematic diagram of the cyclic sampling process in the super-resolution-based fault detection method provided in this application.

[0019] Figure 3 This is a schematic diagram of the phase spectrum.

[0020] Figure 4 This is another schematic diagram of the phase spectrum.

[0021] Figure 5 This is a schematic diagram of a cyclically sampled signal determined using Western Reserve University's public dataset as an example.

[0022] Figure 6 for Figure 5 The corresponding fault signal characteristic waveform without phase correction.

[0023] Figure 7 for Figure 5 The corresponding phase-corrected fault signal characteristic waveform.

[0024] Figure 8 The structural schematic diagram of the super-resolution-based fault detection system provided in this application.

[0025] Figure 9 A schematic diagram of the terminal device provided in this application. Detailed Implementation

[0026] This application provides a fault detection method and related apparatus based on super-resolution. To make the objectives, technical solutions, and effects of this application clearer and more explicit, the following detailed description is provided with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only for explaining this application and are not intended to limit this application.

[0027] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0028] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0029] It should be understood that the sequence number and size of each step in this embodiment do not imply the order of execution. The execution order of each process is determined by its function and internal logic, and should not constitute any limitation on the implementation process of this application embodiment.

[0030] The inventors discovered through research that in industrial production, it is necessary to monitor the operating status of rotating structures (e.g., rolling bearing equipment). Currently, commonly used methods include analyzing the vibration signal spectrum using Fourier transform to extract fault feature values, or using artificial intelligence algorithms (e.g., neural networks, autoencoders) to extract fault feature values, and then determining whether a fault exists in the rotating structure based on these extracted fault feature values. However, fault judgment based on fault feature values ​​is prone to errors in fault feature value extraction, leading to incorrect fault diagnosis.

[0031] To address the aforementioned problems, in this embodiment, a vibration signal of a rotating structure is acquired, and the vibration signal is oversampled to obtain an oversampled signal; the phase spectrum of the oversampled signal is acquired, and the maximum likelihood period of the oversampled signal is determined based on the phase spectrum; a phase correction value of the vibration signal is calculated based on the maximum likelihood period, and a fault characteristic signal of the vibration signal is calculated based on the maximum likelihood period, the phase correction value, and the vibration signal; and the fault result of the rotating structure is determined based on the fault characteristic signal. This application, by oversampling the vibration signal, acquiring the maximum likelihood period of the oversampled signal, extracting the fault characteristic signal based on the maximum likelihood period, and finally determining the fault result of the rotating structure based on the fault characteristic signal, provides a comprehensive reflection of the operating status of the rotating structure, thereby improving the accuracy of fault detection.

[0032] The application content will be further explained below with reference to the accompanying drawings and the description of the embodiments.

[0033] This embodiment provides a fault detection method based on super-resolution, such as... Figure 1 As shown, the method includes: S10. Obtain the vibration signal of the rotating structure and oversample the vibration signal to obtain an oversampled signal.

[0034] Specifically, the vibration signal of a rotating structure refers to the vibration acceleration time-series signal of the rotating structure. This vibration signal can be used for bearing vibration assessment (where the test point is located at the bearing base) and shaft vibration assessment (where the test point is located on both sides of the shaft at the base). When a fault occurs, the vibration signal is unstable and nonlinear. Analyzing and processing the vibration signal facilitates subsequent judgment of the fault outcome in the rotating structure.

[0035] After acquiring the vibration signal, oversampling is performed. This oversampling doesn't physically increase the sampling rate; instead, it uses mathematical methods (such as linear interpolation or cubic spline interpolation) to oversample the signal. This avoids introducing extra detail into the vibration signal and prevents the problem of determining the maximum likelihood period when the vibration signal's period is a non-integer multiple of the sampling rate. This is because when the vibration signal's period is a non-integer multiple of the sampling rate, large periodic spectra are likely to appear under the large period, making it difficult to determine the maximum likelihood period under the small period. Therefore, in this embodiment, after acquiring the vibration signal, oversampling is performed to adjust the sampling rate, making the vibration signal's period much larger than the sampling rate (e.g., the vibration signal's period is 100 times the sampling rate), thus facilitating the extraction of the maximum likelihood period.

[0036] In one implementation, the vibration signal is represented as: ；

[0037]

[0038] in, Indicates the sampling time. Indicates the sampling rate. Indicates the sampling interval. Indicates the sampling length.

[0039] Vibration signals By expanding the super-resolution sampling, we can obtain:

[0040]

[0041]

[0042]

[0043]

[0044]

[0045] Among them, the sampling multiple is ,For example, , 200, etc.; Interpolation functions can be implemented using MATLAB's `interp1.m` function, third-party libraries in Python, or linear interpolation. In a typical implementation, Spline interpolation is used.

[0046] S20. Obtain the phase spectrum of the oversampled signal and determine the maximum likelihood period of the oversampled signal based on the phase spectrum.

[0047] Specifically, the phase spectrum reflects the sequence of phase changes with frequency. It can be understood as a phase sequence composed of several phase values. The maximum likelihood period is the sampling frequency corresponding to the maximum phase value; in other words, the maximum likelihood period is the sampling period corresponding to the maximum phase value. The phase spectrum of an oversampled signal can be determined through phase spectrum analysis or Fourier transform, etc.

[0048] In a typical implementation, obtaining the phase spectrum of the oversampled signal specifically includes: Obtain several discrete periods corresponding to the oversampled signal, wherein each discrete period in the several discrete periods is different from the others; For each discrete period, the oversampled signal is cyclically sampled and superimposed based on the discrete period to obtain a cyclically sampled signal, and the phase value of the cyclically sampled signal is calculated; The phase spectrum sequence formed by the phase values ​​of each cyclically sampled signal is used as the phase spectrum of the oversampled signal.

[0049] Specifically, the discrete periods can be pre-set or determined based on the signal length of the oversampled signal. For example, the number of discrete periods may equal the signal length, or the number of discrete periods may equal half the signal length. Furthermore, each discrete period in the discrete period is distinct, and the largest discrete period is less than or equal to the signal length of the oversampled signal. For example, the discrete periods may be denoted as... So there is. Furthermore, the signal length of each cyclically sampled signal is equal to its corresponding discrete period. For example, the discrete period of the cyclically sampled signal is... Then the signal length of the cyclically sampled signal is .

[0050] Furthermore, performing cyclic sampling and superposition on the oversampled signal based on the discrete period to obtain a cyclically sampled signal refers to cyclically sampling the oversampled signal with the discrete period as the sampling period to obtain several signal sequences of length equal to the discrete period, and then linearly superimposing these several signal sequences to obtain the cyclically sampled signal. Specifically, as shown... Figure 2 As shown, the discrete period is denoted as First, the sampling length in the oversampled signal is... The first signal sequence, and then the remaining oversampled signal with a sampling length of The second signal sequence is then repeated, and so on, until the oversampled signal is cyclically sampled to obtain K signal sequences. Then, the signal values ​​at corresponding sampling times in the K signal sequences are superimposed to obtain the signal value at that sampling time, thus obtaining the cyclically sampled signal. Therefore, the cyclically sampled signal can be expressed as:

[0051] in, express The floor value, i.e. The number of effective segments, Indicates discrete period, Indicates the first In the nth signal sequence The signal value at the sampling point, Indicates the number of signal sequences.

[0052] In one implementation, calculating the phase value of the cyclically sampled signal specifically includes: Obtain the signal value of each sampling point in the cyclic sampling signal; The phase value of the cyclically sampled signal is calculated based on each signal value.

[0053] Specifically, after acquiring each cyclically sampled signal, the phase value of each cyclically sampled signal can be calculated. The phase value of a cyclically sampled signal is equal to the standard deviation of the signal values ​​in its corresponding cyclically sampled signal. Accordingly, the phase value of a cyclically sampled signal can be expressed as: =

[0054] in, Represents discrete period The corresponding phase value of the cyclically sampled signal, Represented based on discrete period Determine the cyclic sampling signal. The standard deviation is expressed as: .

[0055] in, Represents a sequence, express The first in One element, express The mean of all elements in the matrix. express The number of elements.

[0056] In one implementation, determining the maximum likelihood period of the oversampled signal based on the phase spectrum specifically includes: Select the largest phase value from all phase values ​​in the phase spectrum; The discrete period corresponding to the largest selected phase value is taken as the maximum likelihood period of the oversampled signal.

[0057] Specifically, the phase spectrum is a sequence of phase values ​​formed by various phase values. This can be understood as the phase spectrum... This can be understood as, for a given sequence Calculate all discrete periods corresponding Value, to obtain signal Different discrete periods Below The sequence is composed of the standard deviations of the phase spectrum. Furthermore, since the maximum likelihood period is the discrete period that maximizes the phase value, after obtaining the phase spectrum, the maximum phase value in the phase spectrum can be selected, and the discrete period corresponding to the maximum phase value can be obtained and used as the maximum likelihood period. Based on this, the expression for the maximum likelihood period can be:

[0058] in, Indicates the maximum likelihood period. Indicates an oversampled signal. Indicates the first i A discrete period.

[0059] For example: Suppose a vibration signal At 100,000 data sampling points, when , At that time, the phase spectrum is as follows Figure 3 As shown, when , At that time, the phase spectrum is as follows Figure 4 As shown. By Figure 3 and Figure 4 It can be seen that the peak values ​​in the periodic spectrum correspond to the signal. The maximum likelihood period, and simultaneously, by Figure 4It is known that when the vibration signal period is a non-integer multiple of the sampling rate, a larger period is more likely to result in a large period spectrum value, which can lead to the problem that the minimum period estimation is difficult to reflect. Therefore, this embodiment avoids the problem of the minimum period estimation being difficult to reflect when the vibration signal period is a non-integer multiple of the sampling rate by oversampling the vibration signal.

[0060] S30. Calculate the phase correction value of the vibration signal based on the maximum likelihood period, and calculate the fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value, and the vibration signal.

[0061] Specifically, the fault characteristic signal is a time-series waveform, and the phase correction value is used to reflect the local phase deviation of the vibration signal. The phase correction value can be used to determine the fluctuation value between different periods of the rotating structure, thereby detecting the stability of the rotating structure. In other words, after obtaining the phase correction value, the stability of the rotating structure can be judged based on the phase correction value. For example, when the phase correction value is greater than a correction threshold, the rotating structure is determined to be unstable; conversely, when the phase correction value is less than or equal to the correction threshold, the rotating structure is determined to be stable. Therefore, the super-resolution-based fault detection method provided in this embodiment can detect whether a rotating structure has a fault, and can also detect the stability of the rotating structure based on the phase correction value, improving the comprehensiveness of rotating structure detection and providing assurance for the operation of the rotating structure.

[0062] In one implementation of this embodiment, calculating the phase correction value of the vibration signal based on the maximum likelihood period specifically includes: The vibration signal is divided into several periodic signals based on the maximum likelihood period; For every two periodic signals in a series of periodic signals, the phase deviation between the two periodic signals is calculated using a cross-correlation function; The phase value corresponding to the largest phase deviation value among all calculated phase deviation values ​​is taken as the phase correction value.

[0063] Specifically, the signal period of each of the several periodic signals is equal to the maximum likelihood period. The several periodic signals can be determined through the cyclic sampling method described above, which will not be elaborated further here. After acquiring the several periodic signals, for every two periodic signals in the sequence, the phase deviation between these two signals is calculated. The phase deviation is determined using a cross-correlation function. Based on this, the periodic signals... and periodic signals These are two periodic signals out of a set of periodic signals. and The cross-correlation function can be expressed as:

[0064] in, This indicates the signal phase value.

[0065] Furthermore, after obtaining the phase deviation value of every two cycles of signal, a phase correction value is determined based on the phase deviation value, wherein the phase correction value... The expression can be: 。

[0066] After obtaining the phase correction value, the fault characteristic signal can be calculated based on the phase correction value, the maximum likelihood period, and the vibration signal. The expression for the fault characteristic signal can be:

[0067] in, Indicates vibration signal, Indicates the maximum likelihood period. This represents the phase correction value.

[0068] S40. Determine the fault result of the rotating structure based on the fault characteristic signal.

[0069] Specifically, the fault result includes the presence or absence of a fault. That is, when determining the fault result of the rotating structure based on the fault characteristic signal, it can be determined that the rotating structure has a fault, or that the rotating structure does not have a fault.

[0070] In one implementation, determining the fault result of the rotating structure based on the fault characteristic signal specifically includes: Obtain the maximum amplitude of the fault characteristic signal; If several of the maximum amplitude values ​​are greater than a preset amplitude threshold, then the failure result of the rotating structure is a failure. If the maximum amplitude value is less than or equal to the preset amplitude threshold, the failure result of the rotating structure is no failure.

[0071] Specifically, the preset amplitude threshold is a pre-set criterion used to determine whether a fault has occurred in the rotating structure. When the maximum amplitude value is greater than the preset threshold, it indicates a fault in the rotating structure; conversely, when the maximum amplitude value is less than or equal to the preset threshold, it indicates that the rotating structure has not failed. Of course, in practical applications, after obtaining the fault characteristic signal, the fault result can also be determined based on other methods, such as determining the amplitude range where the maximum amplitude value is located, and determining whether a fault has occurred based on the amplitude range.

[0072] Furthermore, to further illustrate the super-resolution-based fault detection method provided in this embodiment, the following test is conducted using a publicly available dataset from Western Reserve University. The cyclic sampling of the original vibration signal is as follows: Figure 5 As shown, the characteristic waveform of the fault signal without phase correction is as follows: Figure 6 As shown, the characteristic waveform of the fault signal after phase correction is as follows: Figure 7 As shown. By Figure 6 and Figure 7 As can be seen, the fault detection method based on super-resolution provided in this embodiment extracts the fault feature signal of the faulty bearing and can perform fault detection based on the fault feature signal. In addition, the fault detection method based on super-resolution provided in this embodiment can also determine the periodic fluctuation deviation of the rotational speed fluctuation rate of the rotating mechanism at 0.12ms, thereby determining the stability of the rotating mechanism based on the rotational speed fluctuation rate.

[0073] In summary, this embodiment provides a fault detection method based on super-resolution. The method includes acquiring the vibration signal of a rotating structure and oversampling the vibration signal to obtain an oversampled signal; acquiring the phase spectrum of the oversampled signal and determining the maximum likelihood period of the oversampled signal based on the phase spectrum; calculating the phase correction value of the vibration signal based on the maximum likelihood period; and calculating the fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value, and the vibration signal; and determining the fault result of the rotating structure based on the fault characteristic signal. This application, by oversampling the vibration signal, obtaining the maximum likelihood period of the oversampled signal, extracting the fault characteristic signal based on the maximum likelihood period, and finally determining the fault result of the rotating structure based on the fault characteristic signal, can comprehensively reflect the operating status of the rotating structure, thereby improving the accuracy of fault detection.

[0074] Based on the above-described super-resolution-based fault detection method, this embodiment provides a super-resolution-based fault detection system, such as... Figure 8 As shown, the system includes: The sampling module 100 is used to acquire the vibration signal of the rotating structure and to oversample the vibration signal to obtain an oversampled signal. The acquisition module 200 is used to acquire the phase spectrum of the oversampled signal and determine the maximum likelihood period of the oversampled signal based on the phase spectrum. The calculation module 300 is used to calculate the phase correction value of the vibration signal based on the maximum likelihood period, and to calculate the fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value and the vibration signal. The determination module 400 is used to determine the fault result of the rotating structure based on the fault characteristic signal.

[0075] Based on the above-described super-resolution-based fault detection method, this embodiment provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the super-resolution-based fault detection method described in the above embodiment.

[0076] Based on the above-described super-resolution-based fault detection method, this application also provides a terminal device, such as... Figure 9 As shown, it includes at least one processor 20; a display screen 21; and a memory 22, and may also include a communications interface 23 and a bus 24. The processor 20, display screen 21, memory 22, and communications interface 23 can communicate with each other via the bus 24. The display screen 21 is configured to display a preset user guide interface in the initial setup mode. The communications interface 23 can transmit information. The processor 20 can invoke logical instructions in the memory 22 to execute the methods described in the above embodiments.

[0077] Furthermore, the logical instructions in the aforementioned memory 22 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0078] The memory 22, as a computer-readable storage medium, can be configured to store software programs, computer-executable programs, such as program instructions or modules corresponding to the methods in the embodiments of this disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions, or modules stored in the memory 22, thereby implementing the methods in the above embodiments.

[0079] The memory 22 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 22 may include high-speed random access memory (RAM) and non-volatile memory. Examples include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, as well as transient storage media.

[0080] Furthermore, the specific process of loading and executing multiple instruction processors in the aforementioned storage medium and terminal device has been described in detail in the above method, and will not be repeated here.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A fault detection method based on super-resolution, characterized in that, The method includes: The vibration signal of the rotating structure is acquired, and the vibration signal is oversampled to obtain an oversampled signal; The phase spectrum of the oversampled signal is obtained, and the maximum likelihood period of the oversampled signal is determined based on the phase spectrum, wherein the maximum likelihood period is the discrete period corresponding to the maximum phase value; The phase correction value of the vibration signal is calculated based on the maximum likelihood period, and the fault characteristic signal of the vibration signal is calculated based on the maximum likelihood period, the phase correction value, and the vibration signal. The phase correction value is used to reflect the fluctuation value between different periods of the rotating structure to detect the stability of the rotating structure. The fault result of the rotating structure is determined based on the fault characteristic signal; The expression for the fault characteristic signal is as follows: ， in, Indicates vibration signal, Indicates the maximum likelihood period. Indicates the phase correction value; Indicates the number of signal sequences; The calculation of the phase correction value of the vibration signal based on the maximum likelihood period specifically includes: The vibration signal is divided into several periodic signals based on the maximum likelihood period; For every two periodic signals in a series of periodic signals, the phase deviation between the two periodic signals is calculated using a cross-correlation function; The phase value corresponding to the largest phase deviation value among all calculated phase deviation values ​​is taken as the phase correction value; The cross-correlation function is: ， in, Indicates the signal phase value. Represents the cross-correlation function. and It represents two periodic signals out of a set of periodic signals.

2. The fault detection method based on super-resolution according to claim 1, characterized in that, The acquisition of the phase spectrum of the oversampled signal specifically includes: Obtain several discrete periods corresponding to the oversampled signal, wherein each discrete period in the several discrete periods is different from the others; For each discrete period, the oversampled signal is cyclically sampled and superimposed based on the discrete period to obtain a cyclically sampled signal, and the phase value of the cyclically sampled signal is calculated; The phase spectrum sequence formed by the phase values ​​of each cyclically sampled signal is used as the phase spectrum of the oversampled signal.

3. The fault detection method based on super-resolution according to claim 2, characterized in that, The signal length of the cyclic sampling signal is equal to the discrete period corresponding to the cyclic sampling signal.

4. The fault detection method based on super-resolution according to claim 2, characterized in that, The calculation of the phase value of the cyclically sampled signal specifically includes: Obtain the signal value of each sampling point in the cyclic sampling signal; The phase value of the cyclically sampled signal is calculated based on each signal value.

5. The fault detection method based on super-resolution according to claim 2, characterized in that, The determination of the maximum likelihood period of the oversampled signal based on the phase spectrum specifically includes: Select the largest phase value from all phase values ​​in the phase spectrum; The discrete period corresponding to the largest selected phase value is taken as the maximum likelihood period of the oversampled signal.

6. The fault detection method based on super-resolution according to claim 1, characterized in that, The determination of the fault result of the rotating structure based on the fault characteristic signal specifically includes: Obtain the maximum amplitude of the fault characteristic signal; If the maximum amplitude value is greater than the preset amplitude threshold, the failure result of the rotating structure is a failure. If the maximum amplitude value is less than or equal to the preset amplitude threshold, the failure result of the rotating structure is no failure.

7. A fault detection system based on super-resolution, characterized in that, The system includes: A sampling module is used to acquire the vibration signal of the rotating structure and to oversample the vibration signal to obtain an oversampled signal; The acquisition module is used to acquire the phase spectrum of the oversampled signal and determine the maximum likelihood period of the oversampled signal based on the phase spectrum, wherein the maximum likelihood period is the discrete period corresponding to the maximum phase value; The calculation module is used to calculate the phase correction value of the vibration signal based on the maximum likelihood period, and to calculate the fault characteristic signal of the vibration signal based on the maximum likelihood period, the phase correction value and the vibration signal, wherein the phase correction value is used to reflect the fluctuation value between different periods of the rotating structure to detect the stability of the rotating structure. The determination module is used to determine the fault result of the rotating structure based on the fault characteristic signal; The expression for the fault characteristic signal is as follows: ， in, Indicates vibration signal, Indicates the maximum likelihood period. Indicates the phase correction value. Indicates the number of signal sequences; The calculation of the phase correction value of the vibration signal based on the maximum likelihood period specifically includes: The vibration signal is divided into several periodic signals based on the maximum likelihood period; For every two periodic signals in a series of periodic signals, the phase deviation between the two periodic signals is calculated using a cross-correlation function; The phase value corresponding to the largest phase deviation value among all calculated phase deviation values ​​is taken as the phase correction value; The cross-correlation function is: ， in, Indicates the signal phase value. Represents the cross-correlation function. and It represents two periodic signals out of a set of periodic signals.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps in the super-resolution-based fault detection method as described in any one of claims 1-6.

9. A terminal device, characterized in that, include: Processor, memory, and communication bus; the memory stores a computer-readable program that can be executed by the processor; The communication bus enables communication between the processor and the memory; When the processor executes the computer-readable program, it implements the steps in the super-resolution-based fault detection method as described in any one of claims 1-6.

Images