WO2021036663A1 - Method for detecting anomaly of fixed screw for device, and related products - Google Patents

Abstract

A method for detecting anomaly of a fixed screw for a device. The method comprises: obtaining a photographing video for a fixed screw disposed in a preset component on a device to be detected (101); processing the photographing video according to a preset motion amplification algorithm to obtain an amplification video (102); extracting vibration data of a plurality of test points for the fixed screw from the amplification video (103); and determining at least one target test point whose vibration data does not satisfy a preset condition in the plurality of test points according to the vibration data, marking the at least one target test point as an abnormal test point, and displaying a target video region corresponding to the at least one target test point in the amplification video (104). According to the method, the vibration data can be extracted by means of the photographing video of the fixed screw, and the test points with abnormal vibration near the fixed screw are determined according to the vibration data, so that the anomaly of the fixed screw of the device can be detected more accurately. The present invention further provides an apparatus and device for detecting the anomaly of the fixed screw of the device.

Description

Detection method and related products for equipment fixing screw abnormality Technical field

This application relates to the technical field of vibration detection, and specifically relates to a detection method for abnormality of a fixing screw of a device and related products.

Background technique

All machinery and motion systems produce various vibrations, some of which reflect the normal motion state of the system, while others reflect the abnormal motion state of the system (internal failure, unbalanced shaft connection, etc.). Therefore, to predictively maintain system equipment, vibration detection is an important part. For example, when the equipment is running, if the fixing screws on the equipment are abnormal, the equipment may be unstable. Therefore, it is necessary to correct the equipment when it is unstable. The vibration of the equipment is detected to provide a reference for the maintenance of the equipment.

At present, most of the vibration detection uses accelerometer equipment. Although more accurate and reliable, the accelerometer requires a long preparation and installation time, requires physical contact with the system under test during the test (therefore, it will change the vibration response of the system under test), and can only test a limited number of discrete points, so In order to better maintain the equipment, it is necessary to detect the vibration of the equipment caused by the abnormal screw more accurately and reliably.

Summary of the invention

The embodiment of the present application provides a method for detecting an abnormality of a fixing screw of a device and related products, which can extract the vibration data of the fixing screw through a shooting video of the fixing screw on the device, so as to detect the abnormality of the fixing screw of the device more accurately.

The first aspect of the embodiments of the present application provides a method for detecting abnormality of a fixing screw of a device, which is applied to a vibration detection device, and the method includes:

Obtain a shooting video for the fixing screws set on the preset component on the device to be tested;

Processing the shooting video according to a preset motion zoom algorithm to obtain a zoomed video;

Extracting vibration data of multiple test points for the fixing screw from the enlarged video;

According to the vibration data, determine at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the The target video area corresponding to at least one target test point is displayed.

A second aspect of the embodiments of the present application provides a device for detecting an abnormality of a fixing screw of a device, which is applied to a vibration detection device, and the device includes:

An acquiring unit, configured to acquire a shooting video for a fixing screw set on a preset component on the device to be tested;

A processing unit, configured to process the shot video according to a preset motion amplification algorithm to obtain an enlarged video; and extract vibration data of a plurality of test points for the fixed screw from the enlarged video;

A determining unit, configured to determine, according to the vibration data, at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, and mark the at least one target test point as an abnormal test point;

The display unit is configured to display the target video area corresponding to the at least one target test point in the enlarged video.

A third aspect of the embodiments of the present application provides a vibration detection device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured Executed by the foregoing processor, the foregoing program includes instructions for executing the steps in the method described in the first aspect of the embodiments of the present application.

The fourth aspect of the embodiments of the present application provides a computer-readable storage medium. The above-mentioned computer-readable storage medium is used to store a computer program, and the above-mentioned computer program is executed by a processor to implement the method described in the first aspect of the embodiments of the present application. Part or all of the steps described in the method.

The fifth aspect of the embodiments of the present application provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to execute Part or all of the steps described in the method described in one aspect.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1A is a system architecture diagram of a method for detecting abnormality of a fixing screw of a device according to an embodiment of the application;

FIG. 1B is a schematic flowchart of a method for detecting abnormality of a fixing screw of a device according to an embodiment of the application;

2 is a schematic flowchart of another method for detecting abnormality of a fixed screw of a device provided by an embodiment of the application;

FIG. 3 is a schematic flowchart of another method for detecting abnormality of a fixing screw of a device provided by an embodiment of the application;

4 is a schematic structural diagram of a vibration detection device provided by an embodiment of the application;

FIG. 5 is a schematic structural diagram of a device for detecting abnormality of a fixing screw of a device according to an embodiment of the application.

detailed description

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The terms "first" and "second" in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific sequence. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

The reference to "embodiments" in this application means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described in this application can be combined with other embodiments.

Please refer to FIG. 1A. FIG. 1A is a schematic structural diagram of a detection system for an abnormality of a fixed screw of a device according to an embodiment of the present application. The detection system includes: a device to be detected and a vibration detection device, wherein the device to be detected is provided with Fix the screws.

Among them, the vibration detection devices involved in the embodiments of the present application may include various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to wireless modems, as well as various forms of users. Equipment (user equipment, UE), mobile station (mobile station, MS), terminal device (terminal device), and so on. For ease of description, the devices mentioned above are collectively referred to as vibration detection devices.

Among them, the vibration involved in the embodiments of the present application refers to the reciprocating motion of an object relative to a stationary reference object or an object in a balanced state. The vibration generated by the device to be tested during operation may include mechanical vibration generated by the internal interaction of the device to be tested, for example, engine vibration or gear vibration, or mechanical vibration due to external force. Under normal conditions, the equipment to be tested will mechanically vibrate at a fixed frequency during operation, and when the equipment to be tested fails, the vibration frequency of the equipment to be tested will also change, for example, when the fixed screws on the equipment to be tested Looseness may cause changes in the vibration of the equipment to be tested during operation. Therefore, the vibration detection equipment can be used to perform vibration testing on the equipment to be tested, and the abnormality of the fixing screws can be estimated, so as to facilitate the maintenance of the equipment to be tested.

The following describes the embodiments of the present application in detail.

Please refer to FIG. 1B. FIG. 1B is a schematic flowchart of a method for detecting abnormality of a fixing screw of a device according to an embodiment of the present application. As shown in FIG. 1B, the method for detecting an abnormality of a fixing screw of a device provided by an embodiment of the present application is applied to a vibration detection device, and the method for detecting an abnormality of a fixing screw of the device may include the following steps:

101. Obtain a shooting video of a fixing screw set on a preset component on a device to be tested.

Wherein, the above-mentioned preset component is a component provided with fixing screws on the equipment to be tested, and the preset component may be, for example, a base of the equipment to be tested.

In the embodiment of the present application, the vibration detection device can obtain the shooting video for the fixed screw on the device to be detected through the camera. In specific implementation, when the device to be tested is running, the inspector can aim the camera of the vibration detection device at the fixing screw on the device to be tested, and the vibration detection device can take a video of the device to be tested containing vibration and the fixing screw.

Optionally, the vibration detection device may receive the shooting video transmitted by other devices, and the other device refers to an electronic device that stores the shooting video.

102. Process the shooting video according to a preset motion amplification algorithm to obtain an enlarged video.

The preset motion amplification algorithm may include at least one of the following: Lagrangian motion amplification algorithm, Euler motion amplification algorithm, complex phase motion amplification algorithm, RIESZ pyramid motion amplification algorithm.

In the embodiment of the present application, the motion amplification algorithm can be used to amplify the fixed screw and the minute vibration near the fixed screw in the shooting video to obtain an enlarged video.

Optionally, in the foregoing step 102, processing the captured video according to a preset motion zoom algorithm to obtain the zoomed video may include the following steps:

21. Split the shooting video into multiple frames of video images;

22. Convert the multi-frame video image from the RGB color space to the YIQ color space to obtain a multi-frame reference image, and the pixel of each reference image in the multi-frame reference image contains luminance information and chrominance information;

23. Perform Fourier transform FFT processing on the brightness information in the multi-frame reference image to obtain a multi-frame target image;

24. Process the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image;

25. Synthesize the multiple frames of enlarged images to obtain the enlarged video.

Among them, after the shooting video is divided into multiple frames of video images, the pixels in each frame of the multiple frames of video images contain RGB color information. RGB is a color standard in the industry, and each pixel contains red (R). The brightness components corresponding to the three color channels of, green (G) and blue (B).

Among them, YIQ is the television system standard of the National Television Standards Committee (NTSC). Y is the brightness component that provides black-and-white TV and color TV, I represents the chromaticity component of the color from orange to cyan, and Q represents the chromaticity component of the color from purple to yellow-green.

In the embodiment of this application, a multi-frame video image can be converted from the RGB color space to the YIQ color space to obtain a multi-frame reference image. The pixels of each reference image in the multi-frame reference image include luminance component Y, chrominance component I, and Chrominance component Q. In specific implementation, the RGB color information of each pixel of each video image in the multi-frame video image can be converted by the following conversion formula to obtain the YIQ color information of each pixel:

Y＝0.299*R+0.587*G+0.114*B;

I=0.596*R–0.275*G–0.321*B;

Q=0.212*R-0.523*G+0.311*B.

Among them, the brightness information in the multiple frames of reference images may be subjected to Fourier transform (fast fourier transform, FFT) processing to obtain multiple frames of target images. In specific implementation, FFT processing can be performed on the brightness information of each pixel of each reference image in the multi-frame reference image, and the brightness change in the time domain corresponding to the same pixel in the multi-frame reference image can be converted into the phase change in the frequency domain. .

Among them, the multi-frame target image can be processed according to any one of the Lagrangian motion amplification algorithm, Euler motion amplification algorithm, complex phase motion amplification algorithm, and RIESZ pyramid motion amplification algorithm to obtain multi-frame zoomed images.

Optionally, taking the Lagrangian motion magnification algorithm as an example, in the above step 24, processing the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image may include the following steps:

Perform the following steps for each frame of the target image in the multi-frame target image:

2401. Calibrate each frame of target image to obtain a plurality of stable motion feature points;

2402. Tracking the plurality of motion feature points to obtain trajectory vectors of the plurality of motion feature points;

2403. Use a clustering algorithm to cluster the trajectory vectors of the multiple motion feature points to obtain K-type motion layers;

2404. Obtain a target motion layer that needs to be amplified from the K-type motion layer;

2405. Multiply the offset distance of the movement feature point in the target movement layer by a magnification to obtain an enlarged movement layer.

2406. Render the enlarged motion layer to obtain an enlarged image.

First, each frame of the target image can be calibrated to obtain stable multiple motion feature points. Specifically, multiple motion feature points refer to feature points whose motion amplitude is less than a preset range, so as to be consistent with the stillness in the target video. The point (background point) is distinguished from the point of violent movement, thereby preventing zooming in motion caused by camera shake when shooting video. Then, track multiple motion feature points to obtain their corresponding trajectory vector. The trajectory vector uses numerical values to describe the motion direction, motion distance, and brightness change of the motion feature point; then clustering algorithm is used to analyze the multiple motion feature points. The trajectory vector is clustered to obtain the K-type motion layer, and the K-type motion layer is divided according to the correlation and similarity of the trajectory vector, so that different motion layers can contain different types of motion, so as to select the small motion in the K-type motion layer The corresponding motion layer is enlarged to obtain an enlarged motion layer. Finally, because the enlargement of the motion layer causes some blank areas in the target image, rendering needs to be performed to fill the target image with texture, and the motion amplitude of the motion layer is increased to obtain an enlarged image. Therefore, the multi-frame target image can be magnified by the Lagrangian motion magnification algorithm to obtain a multi-frame magnified image.

Optionally, taking the Euler motion magnification algorithm as an example, in the above step 24, processing the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image may include the following steps:

2407. Perform spatial pyramid decomposition on the multi-frame target image to obtain a pyramid structure composed of multiple sub-images with different spatial resolutions.

2408. Perform time-domain band-pass filtering processing on each of the multiple sub-images in the pyramid structure to obtain a transformed signal corresponding to the target frequency band;

2409. Amplify the displacement corresponding to the transformed signal by A times to obtain the amplified signal, where the value range of A is (4, Amax), and the value of Amax is determined by the target frequency band and the displacement function of the transformed signal;

2410. Perform pyramid reconstruction in combination with the amplified signal and the pyramid structure to obtain the multi-frame enlarged image.

Specifically, to use Euler motion magnification to amplify a multi-frame target image, it is first necessary to convert the pixels in the multi-frame target image into a function of time and space, that is, to decompose the multi-frame target image into multiple different spaces through image pyramid transformation The sub-images of different resolutions and sizes form a pyramid structure. For example, a Gaussian pyramid is used to decompose a multi-frame target image, that is, a set of multi-frame target images whose size is halved layer by layer constitutes a pyramid structure. Each level of image in the structure is the result of low-pass filtering of the previous level of image and interlaced sampling.

Pyramid decomposition is to perform spatial filtering on multiple frames of target images, decompose to obtain frequency bands of different spatial frequencies, and amplify these frequency bands respectively. Because frequency bands at different spatial frequencies correspond to different signal-to-noise ratios, the lower the spatial frequency, the less image noise and the higher the signal-to-noise ratio. Therefore, different amplification factors can be set for each layer of spatial frequency bands. For example, a linearly variable magnification factor can be used to amplify frequency bands of different frequencies. In the pyramid structure, from the top to the bottom, the magnifications are sequentially reduced.

After the frequency bands of different spatial frequencies are obtained through pyramid processing, time-domain band-pass filtering can be performed on each frequency band to obtain the transformed signal of interest, that is, the transformed signal corresponding to the target frequency band, and only the transformation corresponding to the target frequency band The signal is amplified. When performing band-pass filtering, ideal band-pass filters, Butterworth band-pass filters, second-order infinite impulse response filters, etc. can be used.

After obtaining the transformed signal corresponding to the target frequency band, let I(x,t) be the gray value of point x at time t, and the initial value is f(x), then:

Where δ(t) represents the displacement signal.

Amplify I(x,t) by α times, that is, amplify the displacement signal δ(t), and the amplified signal is:

It is meaningless if the magnification is too small when zooming in on small movements, so the minimum value of A is greater than 4. In addition, the magnification is related to the spatial frequency and satisfies the following relationship:

Among them, the spatial frequency is ω, the spatial wavelength of the target frequency band is λ, and λ=2π/ω, the maximum value of α can be determined by the displacement function of the target frequency band and the transformed signal. A _max ≤α.

After the amplified signal is obtained, it is combined with the original frequency band again, and then pyramid reconstruction, such as Laplace pyramid transformation reconstruction, is used to obtain multiple frames of enlarged images.

103. Extract vibration data of multiple test points for the fixed screw from the enlarged video.

In the embodiment of the present application, phase correlation calculation, interpolation filtering, and inverse Fourier transform processing DFFT processing can be performed on the enlarged image in the enlarged video to obtain the vibration data of the pixels in the enlarged image.

Optionally, in the foregoing step 103, extracting vibration data of multiple test points for the fixing screw from the enlarged video may include the following steps:

31. Calculate the first cross cross power spectrum between the multiple frames of zoomed-in images in the zoomed-in video according to a preset phase correlation algorithm;

32. Perform interpolation filtering according to the first cross cross power spectrum to obtain a second cross cross power spectrum after interpolation filtering;

33. Perform inverse Fourier transform DFFT processing on the second cross cross power spectrum to obtain vibration data of all pixels in the amplified video;

34. From the vibration data of all pixels in the enlarged video, select vibration data of pixels corresponding to multiple test points within a preset distance range from the fixing screw.

Wherein, the first cross cross power spectrum between the multiple frames of the zoomed-in images in the zoomed-in video may be calculated according to a preset phase correlation algorithm. In a specific implementation, the following formula may be used to calculate the first cross cross power spectrum.

Wherein, R is a first cross crosspower, F. To _a frame image of a Fourier transform, F ^{* _'b} of the b-th frame image signal of the conjugated Fourier transform, in addition to two lower Fourier formula The modulus of the correlation product of the transformed signal.

Wherein, the filter bank can be adaptively selected for filtering according to the position of the correlation peak of the first cross cross power spectrum R to obtain the filtered second cross cross power spectrum R′.

Optionally, in the foregoing step 32, performing interpolation filtering according to the first cross cross power spectrum to obtain the second cross cross power spectrum after interpolation filtering may include the following steps:

3201. Acquire a plurality of state change signals corresponding to the first cross power spectrum in the amplified video, where the state change signals are time-domain signals;

3202. Extract a target state change signal segment of a preset length from the plurality of state change signals to obtain a plurality of target state change signal segments, and obtain each target state change signal segment of the plurality of target state change signal segments The target frequency of, get multiple target frequencies;

3203. Set the corresponding sliding window according to the target frequency corresponding to each state change signal in the multiple state change signals to obtain multiple sliding windows, and send each state change signal in the multiple state change signals to the corresponding Sliding window

3204. Use the state change signal of the plurality of state change signals that cannot pass through the corresponding sliding window as an aperiodic signal to obtain at least one aperiodic signal;

3205. Remove the at least one non-periodic signal from the multiple state change signals to obtain a second cross cross power spectrum after frequency domain noise is filtered out.

Wherein, the first cross cross power spectrum R is a frequency domain signal, which includes one or more correlation peaks. After performing the inverse Fourier transform on the first cross cross power spectrum R, the state change signal corresponding to each correlation peak can be obtained. Each state change signal can reflect the state change of a certain position in the amplified video. Therefore, a predetermined length of the target state change signal segment can be extracted from the multiple state change signals to obtain multiple target state change signal segments . The state change information includes vibration data and other noise information. For example, changes in illumination can also cause state changes in the video screen, and the vibration data can reflect the operating conditions of the object to be vibrated. The vibration of the equipment to be tested is periodic when it is running, and the state change caused by the vibration is also periodic. Although a lot of noise information will cause the state of each pixel in the amplified video to change, the state change caused by noise is often not periodic, and when the operating condition of the device to be tested is analyzed according to the vibration of the device to be tested, it shows periodic vibration. It can be used to reflect the operating conditions of the device to be tested, because the non-periodic vibration is often caused by the external environment, not by the device to be tested itself, and this part of the non-periodic signal cannot be used to analyze the device to be tested. Health status. Acquire noise signals that are not caused by self-vibration by acquiring non-periodic signals in the state change signals. Since aperiodic signals are often signals that have little effect or no effect or even interference in analyzing the operating conditions of the device to be tested, this part of the aperiodic signal can be removed, so that the state change signal obtained from the amplified video, More useful information.

Among them, after obtaining multiple state change signals, it can be judged whether each state change signal is a periodic signal. Specifically, a target state change signal segment with a preset length can be extracted first, the target frequency of the target change signal segment can be obtained, and then the state The frequencies of other parts in the change signal are compared with the target frequency. If the frequencies of other parts in the state change signal are not consistent with the target frequency, the state change signal can be regarded as a non-periodic signal. The preset length can be set by a user to a certain value, or it can be self-adapted according to the length of the signal during signal processing. For example, the preset length can be set to 1/10 of the length of the state change signal. After obtaining the target frequency of the target state transition signal segment, the window size of the sliding window can be set according to the target frequency. For example, the window size of the sliding window can be set to be consistent with the target frequency, so that only signals with the same frequency as the target frequency can pass through the sliding window. However, signals that are inconsistent with the target frequency cannot pass through the sliding window. If the state change signal cannot pass through the corresponding sliding window, it means that there is a signal segment whose frequency is inconsistent with the target frequency in the state change signal, that is, the state change signal is a non-periodic signal. In this way, by judging whether the frequencies of other parts of the state change signal are consistent with the target frequency by means of sliding windows, conclusions can be obtained conveniently and quickly, and the amount of calculation is smaller.

Further, the filtered second cross cross power spectrum R'can be subjected to inverse Fourier transform, and phase comparison (phase-by-phase comparison) can be performed. In this case, the sliding window adaptive matching method can be used to extract the distance fixation screw preset Vibration data of pixels corresponding to multiple test points within the distance range. The calculation formula is as follows:

r=F ^-1 {R'}

Among them, F ^-1 {R'} is the inverse Fourier transform of the second cross cross power spectrum R', r is the vibration data of the pixels in the zoomed-in video, so that the vibrations of all the pixels in the zoomed-in video can be obtained data.

Finally, the target position of the fixing screw can be obtained, and then the vibration data of the pixel points corresponding to the multiple test points within the preset distance range from the target position can be determined.

104. Determine, according to the vibration data, at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the results in the enlarged video The target video area corresponding to the at least one target test point is displayed.

Wherein, the vibration data includes at least one of the following: vibration amplitude, frequency, phase, and time-domain waveform.

In the embodiment of the present application, the vibration data of the pixels corresponding to the multiple test points within the preset distance range near the fixed screw in the enlarged video can be selected to obtain multiple sets of vibration data. Therefore, each of the multiple sets of vibration data can be further selected based on the vibration data. The group of vibration data determines whether the corresponding test point is an abnormal test point.

Optionally, in the foregoing step 104, determining at least one target test point whose vibration data does not satisfy a preset condition among the plurality of test points according to the vibration data may include the following steps:

41. Determine whether the vibration data corresponding to the pixel point corresponding to each test point in the plurality of test points meets the following conditions:

The vibration amplitude is in the preset vibration amplitude range; the frequency is in the preset frequency range; the phase is in the preset phase range; the time domain waveform is matched with the preset reference time domain waveform to obtain A matching value, the matching value being in a preset matching value range;

42. Determine the test point corresponding to the pixel point that does not meet any of the above conditions as the target test point, and obtain at least one target test point.

In the embodiment of the present application, for each test point of the multiple test points, determining whether the test point is a target test point according to the vibration data corresponding to the test point may include: determining whether the vibration data corresponding to the test point meets the aforementioned requirements. Condition, if the vibration amplitude is in the preset vibration amplitude range; the frequency is in the preset frequency range; the phase is in the preset phase range; the time domain waveform is matched with the preset reference time domain waveform to obtain the matching value, matching If the value is within the preset matching value range, the test point is not the target test point. If the vibration data corresponding to the test point does not meet any of the above conditions, the test point can be determined as the target test point. And mark the test point as an abnormal test point.

Thus, at least one target test point and non-target test points other than the target test point among the plurality of test points can be determined, and the target test point can be marked as an abnormal test point.

Further, the target video area corresponding to at least one target test point in the zoomed-in video may be displayed, specifically, the target video area corresponding to at least one target test point in the zoomed-in video may be displayed.

Optionally, the preset component is the base of the device to be tested. In the embodiment of the present application, it may further include the following steps:

A1. Obtain the position of each target test point in the base in the at least one target test point to obtain at least one position;

A2. Determine a shock reduction strategy according to the at least one location and the vibration data of each target test point in the at least one target test point.

Wherein, the position of each target test point on the base can be determined, and if there is a target position in the first position area in at least one position, the vibration reduction strategy can be further determined according to the vibration data of the target test point at the target position.

Optionally, in the above step A2, determining a vibration reduction strategy according to the at least one location and the vibration data of each target test point in the at least one target test point may include the following steps:

A22. For the vibration data of each target test point in the at least one target test point, determine a vibration amplitude deviation value according to the vibration amplitude and a preset vibration amplitude threshold; determine the frequency according to the frequency and the preset frequency threshold Deviation value; determining a frequency deviation value according to the phase and a preset phase threshold; determining a time-domain waveform deviation value according to the matching value and the preset matching value threshold;

A23. If there is a target position in the first position area in the at least one position, and the vibration data of the target test point corresponding to the target position meets at least one of the following, determine the shock absorption strategy and the anti-vibration plate strategy: the vibration The amplitude deviation value is greater than the first preset deviation value; the frequency deviation value is greater than the second preset deviation value; the frequency deviation value is greater than the third preset deviation value; the time domain waveform deviation value is greater than the fourth preset deviation value.

In the embodiment of the present application, the vibration amplitude threshold corresponding to the vibration amplitude, the frequency threshold corresponding to the frequency, the phase threshold corresponding to the phase, and the matching value threshold corresponding to the matching value can be preset. Therefore, for the vibration data of each target test point in at least one target test point, the vibration amplitude and the preset vibration amplitude threshold value can be determined to determine the vibration amplitude deviation value; the frequency deviation value is determined according to the frequency and the preset frequency threshold value; and the frequency deviation value is determined according to the phase Determine the frequency deviation value with the preset phase threshold; determine the time-domain waveform deviation value according to the matching value and the preset matching value threshold. If there is a target location in the first location area in at least one location, and the vibration data of the target test point corresponding to the target location meets at least one of the following, determine the shock absorber strategy: the vibration amplitude deviation value is greater than the first preset Deviation value; the frequency deviation value is greater than the second preset deviation value; the frequency deviation value is greater than the third preset deviation value; the time domain waveform deviation value is greater than the fourth preset deviation value.

Among them, the anti-vibration plate strategy is the strategy of adding anti-vibration plates to the base. The effect of shock absorption can be achieved by the anti-vibration plate.

It can be seen that, in this embodiment of the application, the vibration detection device can obtain the shooting video for the fixing screws set on the preset component on the device to be detected, and process the shooting video according to the preset motion amplification algorithm to obtain the enlarged video, from Extract the vibration data of multiple test points for the fixed screw from the enlarged video, determine at least one target test point whose vibration data does not meet the preset conditions among the multiple test points according to the vibration data, and mark the at least one target test point as an abnormal test point , And display the target video area corresponding to at least one target test point in the enlarged video. In this way, the vibration data of the fixed screw can be extracted from the video of the fixed screw on the device, and the test point with abnormal vibration near the fixed screw can be determined based on the vibration data Therefore, the abnormality of the fixing screw of the device can be detected more accurately.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of another method for detecting abnormality of a fixed screw of a device provided by an embodiment of the present application. The method for detecting abnormality of a fixed screw of a device provided by the embodiment of the present application is applied to a vibration detection device , The detection method for the abnormality of the fixed screw of the device includes:

201. Obtain a shooting video for a fixing screw set on a preset component on a device to be tested.

202. Split the captured video into multiple frames of video images.

203. Convert the multi-frame video image from the RGB color space to the YIQ color space to obtain a multi-frame reference image, where the pixel of each reference image in the multi-frame reference image includes luminance information and chrominance information.

204. Perform Fourier transform FFT processing on the brightness information in the multi-frame reference image to obtain a multi-frame target image.

205. Process the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image.

206. Synthesize the multiple frames of enlarged images to obtain the enlarged video.

207. Extract vibration data of multiple test points for the fixed screw from the enlarged video.

208. Determine, according to the vibration data, at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the results in the enlarged video The target video area corresponding to the at least one target test point is displayed.

For the specific implementation process of 201-208, please refer to the corresponding description in the method shown in FIG. 1B, which is not repeated here.

It can be seen that in this embodiment of the application, the vibration detection device can obtain the shooting video for the fixing screws set on the preset component on the device to be detected, divide the shooting video into multiple frames of video images, and divide the multiple frames of video images from RGB colors. The space is converted to YIQ color space to obtain a multi-frame reference image, Fourier transform FFT processing is performed on the brightness information in the multi-frame reference image, and a multi-frame target image is obtained. The multi-frame target image is processed according to the motion amplification algorithm to obtain a multi-frame target image. Frame magnified images, combine multiple magnified images to obtain a magnified video, extract vibration data of multiple test points for the fixed screw from the magnified video, and determine the vibration data of multiple test points that do not meet the preset conditions according to the vibration data At least one target test point, at least one target test point is marked as an abnormal test point, and the target video area corresponding to at least one target test point in the zoomed-in video is displayed. In this way, the vibration data of the fixed screw can be extracted by the motion zoom algorithm, And according to the vibration data, determine the test point of abnormal vibration near the fixing screw, so that the abnormality of the fixing screw of the device can be detected more accurately.

Please refer to FIG. 3. FIG. 3 is a schematic flowchart of a method for detecting abnormality of a fixing screw of a device according to an embodiment of the present application. As shown in FIG. 3, the method for detecting abnormality of a fixed screw of a device provided by an embodiment of the present application is applied to a vibration detection device, and the method for detecting abnormality of a fixed screw of the device may include the following steps:

301. Obtain a shooting video for a fixing screw set on a preset component on a device to be tested.

302. Process the captured video according to a preset motion zoom algorithm to obtain an enlarged video.

303. Extract vibration data of multiple test points for the fixed screw from the enlarged video.

304. Determine, according to the vibration data, at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the results in the enlarged video The target video area corresponding to the at least one target test point is displayed.

305. Obtain the position of each target test point on the base in the at least one target test point to obtain at least one position.

306. Determine a shock reduction strategy according to the at least one location and the vibration data of each target test point in the at least one target test point.

Among them, the specific implementation process of 301-306 can refer to the corresponding description in the method shown in FIG. 1B, which will not be repeated here.

It can be seen that through this embodiment, the vibration detection device can obtain the shooting video for the fixing screws set on the preset component on the device to be detected, and process the shooting video according to the preset motion zoom algorithm to obtain the zoomed video. The video extracts the vibration data of multiple test points for the fixed screw, determines at least one target test point whose vibration data does not meet the preset condition among the multiple test points according to the vibration data, and marks the at least one target test point as an abnormal test point, The target video area corresponding to at least one target test point in the zoomed-in video is displayed, and the position of each target test point in the at least one target test point on the base is obtained, and at least one position is obtained. According to the at least one position and the at least one target The vibration data of each target test point in the test point determines the vibration reduction strategy. In this way, the vibration data of the fixed screw can be extracted from the video of the fixed screw on the device, and the test point with abnormal vibration near the fixed screw can be determined based on the vibration data, so that, It can detect the abnormality of the fixed screw of the equipment more accurately. In addition, it can also provide the corresponding shock absorption strategy for the abnormal test point, which is conducive to the maintenance of the equipment to be tested.

The foregoing mainly introduces the solution of the embodiment of the present application from the perspective of the execution process on the method side. It can be understood that, in order to realize the above-mentioned functions, the image information determining apparatus includes hardware structures and/or software modules corresponding to each function. Those skilled in the art should easily realize that in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

The embodiment of the present application may divide the image information determining apparatus into functional units according to the foregoing method examples. For example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.

Please refer to FIG. 4, which is a schematic structural diagram of a vibration detection device disclosed in an embodiment of the present application. As shown in the figure, the vibration detection device includes a processor, a memory, a communication interface, and one or more programs. Or multiple programs are stored in the above-mentioned memory and configured to be executed by the above-mentioned processor, and the above-mentioned programs include instructions for executing the following steps:

Obtain a shooting video for the fixing screws set on the preset component on the device to be tested;

Processing the shooting video according to a preset motion zoom algorithm to obtain a zoomed video;

Extracting vibration data of multiple test points for the fixing screw from the enlarged video;

According to the vibration data, determine at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the The target video area corresponding to at least one target test point is displayed.

In a possible example, in terms of processing the captured video according to the preset motion zoom algorithm to obtain the zoomed video, the foregoing program includes instructions for executing the following steps:

Dividing the shooting video into multiple frames of video images;

Converting the multi-frame video image from the RGB color space to the YIQ color space to obtain a multi-frame reference image, where the pixel of each reference image in the multi-frame reference image contains luminance information and chrominance information;

Performing Fourier transform FFT processing on the brightness information in the multi-frame reference image to obtain a multi-frame target image;

Processing the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image;

The multiple frames of enlarged images are synthesized to obtain the enlarged video.

In a possible example, the motion amplification algorithm may include at least one of the following: Lagrangian motion amplification algorithm, Euler motion amplification algorithm, complex phase motion amplification algorithm, RIESZ pyramid motion amplification algorithm.

In a possible example, in terms of extracting vibration data of multiple test points for the fixing screw from the enlarged video, the above program includes instructions for executing the following steps:

Calculating the first cross cross power spectrum between the multiple frames of enlarged images in the enlarged video according to a preset phase correlation algorithm;

Performing interpolation filtering according to the first cross cross power spectrum to obtain a second cross cross power spectrum after interpolation filtering;

Performing inverse Fourier transform DFFT processing on the second cross cross power spectrum to obtain vibration data of all pixels in the amplified video;

From the vibration data of all pixels in the enlarged video, vibration data of pixels corresponding to a plurality of test points within a preset distance from the fixing screw are selected.

In a possible example, the vibration data includes at least one of the following: vibration amplitude, frequency, phase, and time-domain waveform. It is determined according to the vibration data that the vibration data does not satisfy a preset value among the multiple test points. Regarding at least one target test point of the condition, the above-mentioned program includes instructions for performing the following steps:

Determine whether the vibration data corresponding to the pixel point corresponding to each test point in the plurality of test points meets the following conditions:

The vibration amplitude is in the preset vibration amplitude range; the frequency is in the preset frequency range; the phase is in the preset phase range; the time domain waveform is matched with the preset reference time domain waveform to obtain A matching value, the matching value being in a preset matching value range;

It is determined that a test point corresponding to a pixel point that does not meet any of the foregoing conditions is the target test point, and at least one target test point is obtained.

In a possible example, the preset component is the base of the device to be tested, and the above program further includes instructions for executing the following steps:

Acquiring the position of each target test point of the at least one target test point on the base to obtain at least one position;

A shock reduction strategy is determined according to the at least one location and the vibration data of each target test point in the at least one target test point.

In a possible example, in the aspect of determining a shock absorption strategy based on the at least one location and the vibration data of each target test point in the at least one target test point, the program further includes instructions for executing the following steps :

For the vibration data of each target test point in the at least one target test point, determine a vibration amplitude deviation value according to the vibration amplitude and a preset vibration amplitude threshold; determine a frequency deviation value according to the frequency and the preset frequency threshold Determine the frequency deviation value according to the phase and the preset phase threshold; determine the time-domain waveform deviation value according to the matching value and the preset matching value threshold;

If there is a target position in the first position area in the at least one position, and the vibration data of the target test point corresponding to the target position meets at least one of the following, determine the shock absorber strategy of the shock absorption strategy: the vibration amplitude deviation The value is greater than the first preset deviation value; the frequency deviation value is greater than the second preset deviation value; the frequency deviation value is greater than the third preset deviation value; the time domain waveform deviation value is greater than the fourth preset deviation value.

Please refer to FIG. 5. FIG. 5 is a schematic structural diagram of a device for detecting an abnormality of a fixing screw of a device disclosed in an embodiment of the present application, which is applied to a vibration detection device. The device for detecting an abnormality of a fixing screw of the device includes an acquiring unit 501 , The processing unit 502, the determining unit 503, and the display unit 504, wherein:

The acquiring unit 501 is configured to acquire a shooting video of a fixing screw set on a preset component on the device to be tested;

The processing unit 502 is configured to process the shooting video according to a preset motion amplification algorithm to obtain an enlarged video; and extract vibration data for multiple test points of the fixed screw from the enlarged video;

The determining unit 503 is configured to determine at least one target test point whose vibration data does not meet a preset condition among the plurality of test points according to the vibration data, and mark the at least one target test point as an abnormal test point;

The display unit 504 is configured to display the target video area corresponding to the at least one target test point in the zoomed-in video.

Optionally, in the aspect of processing the captured video according to a preset motion amplification algorithm to obtain an enlarged video, the processing unit 502 is specifically configured to:

Dividing the shooting video into multiple frames of video images;

Converting the multi-frame video image from the RGB color space to the YIQ color space to obtain a multi-frame reference image, where the pixel of each reference image in the multi-frame reference image contains luminance information and chrominance information;

Performing Fourier transform FFT processing on the brightness information in the multi-frame reference image to obtain a multi-frame target image;

Processing the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image;

The multiple frames of enlarged images are synthesized to obtain the enlarged video.

Optionally, the motion amplification algorithm may include at least one of the following: Lagrangian motion amplification algorithm, Euler motion amplification algorithm, complex phase motion amplification algorithm, RIESZ pyramid motion amplification algorithm.

Optionally, in terms of extracting vibration data of multiple test points for the fixing screw from the enlarged video, the processing unit 502 is specifically configured to:

Calculating the first cross cross power spectrum between the multiple frames of enlarged images in the enlarged video according to a preset phase correlation algorithm;

Performing interpolation filtering according to the first cross cross power spectrum to obtain a second cross cross power spectrum after interpolation filtering;

Performing inverse Fourier transform DFFT processing on the second cross cross power spectrum to obtain vibration data of all pixels in the amplified video;

From the vibration data of all pixels in the enlarged video, vibration data of pixels corresponding to a plurality of test points within a preset distance from the fixing screw are selected.

Optionally, the vibration data includes at least one of the following: vibration amplitude, frequency, phase, and time-domain waveform, and it is determined according to the vibration data that the vibration data does not meet a preset condition at least A target test point, the determining unit 503 is specifically configured to:

Determine whether the vibration data corresponding to the pixel point corresponding to each test point in the plurality of test points meets the following conditions:

The vibration amplitude is in the preset vibration amplitude range; the frequency is in the preset frequency range; the phase is in the preset phase range; the time domain waveform is matched with the preset reference time domain waveform to obtain A matching value, the matching value being in a preset matching value range;

It is determined that a test point corresponding to a pixel point that does not meet any of the foregoing conditions is the target test point, and at least one target test point is obtained.

Optionally, the preset component is a base of the device to be tested,

The acquiring unit 501 is further configured to acquire the position of each target test point in the base in the at least one target test point to obtain at least one position;

The determining unit 503 is further configured to determine a vibration reduction strategy according to the at least one location and the vibration data of each target test point in the at least one target test point.

Optionally, in terms of determining a shock absorption strategy based on the at least one location and the vibration data of each target test point in the at least one target test point, the determining unit 503 is specifically configured to:

For the vibration data of each target test point in the at least one target test point, determine a vibration amplitude deviation value according to the vibration amplitude and a preset vibration amplitude threshold; determine a frequency deviation value according to the frequency and the preset frequency threshold Determine the frequency deviation value according to the phase and the preset phase threshold; determine the time-domain waveform deviation value according to the matching value and the preset matching value threshold;

If there is a target position in the first position area in the at least one position, and the vibration data of the target test point corresponding to the target position meets at least one of the following, determine the shock absorber strategy of the shock absorption strategy: the vibration amplitude deviation The value is greater than the first preset deviation value; the frequency deviation value is greater than the second preset deviation value; the frequency deviation value is greater than the third preset deviation value; the time domain waveform deviation value is greater than the fourth preset deviation value.

It can be seen that through the embodiments of the present application, the vibration detection device can obtain the shooting video of the fixed screw set on the preset component on the device to be detected, and process the shooting video according to the preset motion amplification algorithm to obtain the enlarged video , Extract the vibration data of multiple test points for the fixed screw from the enlarged video, determine at least one target test point whose vibration data does not meet the preset condition among the multiple test points according to the vibration data, and mark the at least one target test point as abnormal Test points, and display the target video area corresponding to at least one target test point in the enlarged video. In this way, the vibration data of the fixed screw can be extracted from the video of the fixed screw on the device, and the vibration data near the fixed screw can be determined according to the vibration data. The test point can detect the abnormality of the fixing screw of the device more accurately.

An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes the computer to execute any of the fixing screws for the device as described in the above method embodiments. Part or all of the steps of the abnormal detection method.

The embodiments of the present application also provide a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program. The computer program causes a computer to execute any of the methods described in the above-mentioned method embodiments. Part or all of the steps of the method of detecting abnormality of the fixing screws of the equipment.

It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that this application is not limited by the described sequence of actions. Because according to this application, some steps can be performed in other order or at the same time. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

In the above-mentioned embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in an embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in this application, it should be understood that the disclosed device may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, it is stated in the application that each functional unit in each embodiment may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be realized in the form of hardware or software program module.

If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable memory. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory. A number of instructions are included to enable a computer device (which may be a personal computer, a vibration detection device, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), mobile hard disk, magnetic disk, or optical disk and other media that can store program codes.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory, random access device, magnetic or optical disk, etc.

The embodiments of the application are described in detail above, and specific examples are used in this article to illustrate the principles and implementation of the application. The descriptions of the above embodiments are only used to help understand the methods and core ideas of the application; at the same time, for Those of ordinary skill in the art, based on the ideas of the application, will have changes in the specific implementation and the scope of application. In summary, the content of this specification should not be construed as limiting the application.

Claims (10)

1. A detection method for an abnormality of a fixing screw of a device is characterized in that it is applied to a vibration detection device, and the method includes:

   Obtain a shooting video for the fixing screws set on the preset component on the device to be tested;

   Processing the shooting video according to a preset motion zoom algorithm to obtain a zoomed video;

   Extracting vibration data of multiple test points for the fixing screw from the enlarged video;

   According to the vibration data, determine at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, mark the at least one target test point as an abnormal test point, and compare the The target video area corresponding to at least one target test point is displayed.
2. The method according to claim 1, wherein the processing the captured video according to a preset motion zoom algorithm to obtain the zoomed video comprises:

   Dividing the shooting video into multiple frames of video images;

   Converting the multi-frame video image from the RGB color space to the YIQ color space to obtain a multi-frame reference image, where the pixel of each reference image in the multi-frame reference image contains luminance information and chrominance information;

   Performing Fourier transform FFT processing on the brightness information in the multi-frame reference image to obtain a multi-frame target image;

   Processing the multi-frame target image according to the motion magnification algorithm to obtain a multi-frame magnified image;

   The multiple frames of enlarged images are synthesized to obtain the enlarged video.
3. The method according to claim 1 or 2, wherein the motion amplification algorithm comprises at least one of the following: Lagrangian motion amplification algorithm, Euler motion amplification algorithm, complex phase motion amplification algorithm, RIESZ pyramid motion amplification algorithm.
4. The method according to any one of claims 1 to 3, wherein the extracting vibration data of a plurality of test points of the fixing screw from the enlarged video comprises:

   Calculating the first cross cross power spectrum between the multiple frames of enlarged images in the enlarged video according to a preset phase correlation algorithm;

   Performing interpolation filtering according to the first cross cross power spectrum to obtain a second cross cross power spectrum after interpolation filtering;

   Performing inverse Fourier transform DFFT processing on the second cross cross power spectrum to obtain vibration data of all pixels in the amplified video;

   From the vibration data of all pixels in the enlarged video, vibration data of pixels corresponding to a plurality of test points within a preset distance from the fixing screw are selected.
5. The method according to claim 4, wherein the vibration data includes at least one of the following: vibration amplitude, frequency, phase, and time-domain waveform, and the vibration data in the multiple test points are determined according to the vibration data. At least one target test point whose data does not meet the preset conditions, including:

   It is determined whether the vibration data corresponding to the pixel point corresponding to each test point in the plurality of test points meets the following conditions:

   The vibration amplitude is in the preset vibration amplitude range; the frequency is in the preset frequency range; the phase is in the preset phase range; the time domain waveform is matched with the preset reference time domain waveform to obtain A matching value, the matching value being in a preset matching value range;

   It is determined that a test point corresponding to a pixel point that does not meet any of the foregoing conditions is the target test point, and at least one target test point is obtained.
6. The method according to claim 5, wherein the preset component is a base of the device to be tested, and the method further comprises:

   Acquiring the position of each target test point in the base in the at least one target test point to obtain at least one position;

   A shock reduction strategy is determined according to the at least one location and the vibration data of each target test point in the at least one target test point.
7. The method according to claim 6, wherein determining a vibration reduction strategy according to the at least one location and the vibration data of each target test point in the at least one target test point comprises:

   For the vibration data of each target test point in the at least one target test point, determine a vibration amplitude deviation value according to the vibration amplitude and a preset vibration amplitude threshold; determine a frequency deviation value according to the frequency and the preset frequency threshold Determine the frequency deviation value according to the phase and the preset phase threshold; determine the time-domain waveform deviation value according to the matching value and the preset matching value threshold;

   If there is a target position in the first position area in the at least one position, and the vibration data of the target test point corresponding to the target position meets at least one of the following, determine the shock absorber strategy: the vibration amplitude deviation The value is greater than the first preset deviation value; the frequency deviation value is greater than the second preset deviation value; the frequency deviation value is greater than the third preset deviation value; the time domain waveform deviation value is greater than the fourth preset deviation value.
8. A device for detecting abnormality of fixing screws of equipment is characterized in that it is applied to vibration detection equipment, and the device includes:

   An acquiring unit, configured to acquire a shooting video for a fixing screw set on a preset component on the device to be tested;

   A processing unit, configured to process the shot video according to a preset motion amplification algorithm to obtain an enlarged video; and extract vibration data of a plurality of test points for the fixed screw from the enlarged video;

   A determining unit, configured to determine, according to the vibration data, at least one target test point whose vibration data does not meet a preset condition among the plurality of test points, and mark the at least one target test point as an abnormal test point;

   The display unit is configured to display the target video area corresponding to the at least one target test point in the enlarged video.
9. A vibration detection device, characterized by comprising a processor, a memory, a communication interface, and one or more programs, the one or more programs are stored in the memory and configured to be executed by the processor The program includes instructions for executing the steps in the method according to any one of claims 1-7.
10. A computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1-7.

Images