WO2021052025A1 - Procédé et appareil de détection de défaut de vibration de ventilateur électrique - Google Patents

Procédé et appareil de détection de défaut de vibration de ventilateur électrique Download PDF

Info

Publication number
WO2021052025A1
WO2021052025A1 PCT/CN2020/105853 CN2020105853W WO2021052025A1 WO 2021052025 A1 WO2021052025 A1 WO 2021052025A1 CN 2020105853 W CN2020105853 W CN 2020105853W WO 2021052025 A1 WO2021052025 A1 WO 2021052025A1
Authority
WO
WIPO (PCT)
Prior art keywords
vibration
target
video
target video
electric fan
Prior art date
Application number
PCT/CN2020/105853
Other languages
English (en)
Chinese (zh)
Inventor
高风波
Original Assignee
深圳市豪视智能科技有限公司
深圳市广宁股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市豪视智能科技有限公司, 深圳市广宁股份有限公司 filed Critical 深圳市豪视智能科技有限公司
Publication of WO2021052025A1 publication Critical patent/WO2021052025A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Definitions

  • the invention relates to the field of machine learning, in particular to a method and device for detecting vibration faults of an electric fan.
  • the Internet belongs to the field of media, also known as the international network. It is a huge network connected between networks and networks. These networks are connected by a set of common protocols to form a logically single huge international network. This method of connecting computer networks to each other can be called “network interconnection”. On this basis, a global Internet that covers the whole world has been developed, called the Internet, which is a network structure connected to each other. "Internet+" is a new business form of Internet development under Innovation 2.0, and it is the evolution of the Internet form driven by Innovation 2.0 in the Knowledge Society and the new form of economic and social development that it has spawned.
  • Internet+ is a further practical result of Internet thinking, which promotes the continuous evolution of economic forms, thereby driving the vitality of social economic entities, and providing a broad network platform for reform, innovation, and development.
  • Internet + means “Internet + various traditional industries", but this is not a simple addition of the two, but the use of information and communication technology and Internet platforms to deepen the integration of the Internet and traditional industries to create new Develop ecology. It represents a new social form, that is, to give full play to the optimization and integration role of the Internet in the allocation of social resources, to deeply integrate the innovative achievements of the Internet into economic and social domains, to enhance the innovation and productivity of the entire society, and to form A broader new form of economic development using the Internet as an infrastructure and realization tool.
  • the traditional fault monitoring mechanism generally uses localized detection equipment, such as arranging laser Doppler vibrometer LDVs in a dedicated room, through which localized vibration detection and failure prediction are performed.
  • LDVs are expensive and use environment Restrictions (environmental influences such as temperature and light in the test environment will seriously deteriorate the measurement results), small test areas, and difficulty in remote monitoring, making it difficult to meet the needs of intelligent vibration detection in an increasing number of scenarios.
  • vibration can reflect the operating conditions of certain mechanical structures. For example, for electric fans, when they continue to vibrate during operation, you can take a video of the vibration device during operation, and then extract the vibration signal from the video, and then according to the vibration The signal obtains the operating status of the electric fan, and then finds whether the electric fan is malfunctioning.
  • the vibration process is very subtle, many vibration situations are difficult to observe with the naked eye. It is necessary to use an effective method to amplify the vibration video to facilitate the extraction of vibration information for further analysis.
  • the purpose of the present invention is to provide an electric fan vibration fault detection method and device, by adopting the Euler motion amplification method to amplify the small motion in the video, and then extract the vibration information in the video, which improves the information extraction. Accuracy, which in turn improves the reliability of vibration analysis.
  • the first aspect of the embodiments of the present application provides a method for detecting vibration failure of an electric fan.
  • the method includes:
  • the vibration detection entrance provides a vibration detection position option, and the vibration detection position includes a base and a fan;
  • the motion amplification effect refers to the movement of the vibrating object's reciprocating motion area.
  • the target video is amplified in the target video. of;
  • the vibration information is matched with the vibration information corresponding to the standard vibration mode, and the vibration failure of the vibrating object is determined according to the matching result.
  • a second aspect of the embodiments of the present application provides an electric fan vibration fault detection device, which includes:
  • a receiving unit configured to receive an instruction from a user to activate a device detection function, and present a vibration detection entrance of the target electric fan according to the instruction, the vibration detection entrance provides a vibration detection position option, and the vibration detection position includes a base and a fan;
  • the selection unit is configured to receive the vibration detection position option selected by the user, and determine the standard vibration mode according to the vibration detection position option;
  • An obtaining unit configured to locate the electric fan as a vibrating object, and obtain a target video corresponding to the electric fan
  • the amplification unit uses the Euler motion amplification method to amplify the target video to obtain an amplified output video with a motion amplification effect of the vibrating object.
  • the motion amplification effect refers to the movement of the vibrating object in the area where the reciprocating motion occurs in the target video.
  • the calculation unit is used to obtain the frame sequence corresponding to the amplified output video, and use the phase correlation algorithm for the frame sequence to calculate the cross cross power spectrum between the frame sequences;
  • the output unit is used to perform inverse Fourier transform on the cross cross power spectrum to obtain the vibration information of the pixels in the target video;
  • the determining unit is configured to match the vibration information with the vibration information corresponding to the standard vibration mode, and determine the vibration fault of the vibrating object according to the matching result.
  • the third aspect of the embodiments of the present application discloses an electronic device, including a processor, a memory, a communication interface, and one or more programs.
  • the one or more programs are stored in the memory and configured by the Executed by a processor, and the program includes instructions for executing the steps of any one of the methods in the first aspect.
  • the fourth aspect of the embodiments of the present application provides a storage medium for storing a computer program for electronic data exchange, where the computer program causes a computer to execute instructions for the steps of the method corresponding to the first aspect.
  • the embodiment of the present application discloses a method and device for detecting vibration failure of an electric fan.
  • the electric fan vibration detection entrance is obtained, and then a standard vibration mode is provided to the user according to the vibration detection location option selected by the user;
  • This method can amplify the small motions in the video by adopting the Lagrangian motion amplification method, and then extract the vibration information in the video, which improves the accuracy of information extraction and thus the reliability of vibration analysis. Finally, the vibration fault is determined by comparing the standard vibration mode and the vibration information, which improves the accuracy and effectiveness of vibration detection.
  • FIG. 1A is a schematic flowchart of a method for detecting vibration failure of an electric fan according to an embodiment of the application.
  • FIG. 1B is a schematic diagram of an electric fan provided by an embodiment of the application.
  • FIG. 1C is a schematic diagram of a gear position of an electric fan according to an embodiment of the application.
  • FIG. 1D is a schematic diagram of a vibration information display provided by an embodiment of this application.
  • FIG. 2 is a schematic flowchart of another method for detecting vibration failure of an electric fan according to an embodiment of the application.
  • FIG. 3 is a schematic flowchart of a video enlargement processing method provided by an embodiment of the application.
  • FIG. 4 is a schematic flowchart of another method for detecting vibration failure of an electric fan according to an embodiment of the application.
  • FIG. 5 is a schematic structural diagram of an electric fan vibration fault detection device provided by an embodiment of the application.
  • FIG. 1A is a schematic flow chart of an electric fan vibration fault detection method provided by an embodiment of the application. As shown in FIG. 1A, an electric fan vibration fault detection method Including the following steps:
  • the vibration detection portal provides a vibration detection position option, and the vibration detection position includes a base and a fan surface.
  • Vibrating objects include objects that generate mechanical vibration through internal interaction, including engine vibration, transmitter vibration, or gear vibration, or the physics of mechanical vibration due to external forces, including wire vibration or bridge vibration.
  • the vibrating object will mechanically vibrate at a fixed frequency under normal conditions, and when the vibrating object fails, the vibration frequency will also change. Therefore, the target video corresponding to the vibrating object can be obtained and analyzed to determine the fault condition of the vibrating object.
  • Electric fans include ceiling fans, table fans, floor fans, wall fans, ceiling fans, ventilating fans, turning fans, air-conditioning fans, etc.
  • the electric fans discussed in the embodiments of this application are table fans, floor fans, or wall fans, etc., including a base Fan and fan, in which the base includes an engine, which can control the gear position and operation of the fan, and the fan includes fan blades and nets, which can rotate to generate wind.
  • the vibration detection sensor device is connected with the user interface through the interface. After the device detection function is activated, the user interface provides the user with a vibration detection position option. The vibration data of different positions of the electric fan is different.
  • the vibration intensity of the fan is higher than The base therefore needs to receive the vibration detection position options selected by the user, and each vibration detection position corresponds to at least one standard vibration mode, and the standard vibration mode is determined according to the vibration detection position selected by the user, so as to be used in the subsequent vibration fault discovery process.
  • FIG. 1B is a schematic diagram of an electric fan provided by an embodiment of the application.
  • the main detection positions include the sector 110 and the base 120.
  • the vibration intensity of the sector is greater than the vibration intensity of the base, so the two positions should be tested separately and the standard vibration mode should be obtained.
  • the fan 110 some fans can shake their heads, and some fans cannot shake their heads. The vibration situation when shaking the head is different from the vibration situation when the head is not shaking. Therefore, you can also obtain the shaking and non-head shaking conditions.
  • the standard vibration mode is used for the fan 110.
  • the standard vibration mode refers to obtaining the vibration data of the electric fan under the condition of ensuring the normal operation of the electric fan, including the vibration amplitude, the peak and valley of the vibration amplitude, the vibration frequency, the vibration amplitude and the frequency distribution, etc., and the establishment of the standard vibration mode correspondence Related data.
  • the electric fan in the positioning vibration process is a vibrating object, that is, if the electric fan does not vibrate, or the vibrating object is not an electric fan, it will not be used as a vibrating object for target video capture. This can prevent the captured video from being an invalid video, or capturing videos of other vibrating objects as the target video. Improve the efficiency and accuracy of target video capture.
  • obtaining the target video corresponding to the electric fan includes: obtaining the gear position information of the electric fan, the gear position information includes the number of gear positions and the gear mode; prompting the user to input the gear mode, and obtaining the gear corresponding to the gear mode Video:
  • the obtained multiple gear videos are used as the target video corresponding to the electric fan, and the multiple is the number of gears.
  • FIG. 1C is a schematic diagram of an electric fan gear position provided by an embodiment of the application.
  • gears 2, 3, and 4 correspond to different wind speeds
  • gear 0 means that the electric fan is turned off.
  • the corresponding gear video should be obtained, and then all the gear videos form the target video corresponding to the electric fan.
  • the gear video corresponding to gear 0 can be obtained or not.
  • the standard vibration mode includes head shaking or non-head shaking mode
  • all gear videos corresponding to the head shaking mode and non-head shaking mode should also be obtained separately.
  • obtain the target video corresponding to the electric fan obtain a first video and a second video, where the first video and the second video are different source videos shot at the same time for the same target; obtain the corresponding first video The first frame image and the second frame image corresponding to the second video; overlap the first frame image and the second frame image, and remove the pixels that cannot overlap the first frame image and the second frame image; obtain an electric fan The corresponding target video.
  • Bit different source video obtain the first video and the second video, and overlap the first frame image corresponding to the first video and the second frame image corresponding to the second video.
  • the two frame images Corresponding pixels should be completely overlapped, then the pixels that cannot be overlapped between the first frame of image and the second frame of image are removed, that is, to remove the shooting deviation pixels of the two cameras, and the obtained frame image is less noisy.
  • the Euler motion amplification method uses the Euler motion amplification method to amplify the target video to obtain an amplified output video with a motion amplification effect of the vibrating object.
  • the motion amplification effect refers to the movement of the vibrating object in the reciprocating motion area in the target video. Enlarged.
  • the target video corresponding to the vibrating object contains the motion process of the vibrating object. This motion process is very small and needs to be amplified for subsequent extraction of vibration information.
  • the relationship between the brightness value of the pixels in the entire scene image and the change of time can be analyzed by considering the pixels in the video as a function of time and space, so as to realize the amplification of small motions.
  • the method before using the Euler motion amplification method to amplify the target video, includes: converting the target video sequence frame from the RGB color space to the YIQ color space; using the Euler motion amplification method to amplify the target video, Including: using Euler motion zoom method to zoom in on the target video in Y phase.
  • Euler motion amplification method for Y-phase signal to amplify the target video, including: performing fast Fourier transform FFT on the Y-phase signal, converting the brightness change in the time domain into the phase change in the frequency domain;
  • the frequency space uses Euler motion amplification algorithm to enlarge the target video.
  • the Y component represents the brightness information of the image
  • the I and Q components carry color information. It is quite time-consuming to process all three color channels when performing motion amplification. And only in the Y-phase space to perform the zoom processing of the target video, it can effectively reduce the amount of calculation and complete the process of motion zoom at the same time.
  • the input video is RGB color space. After the RGB color space is converted into YIQ color space, the brightness information and chroma information of the video frame are separated. The conversion relationship between RGB and YIQ is:
  • using the Euler zoom method to amplify the target video to obtain the amplified output video including: performing spatial pyramid decomposition on a frame sequence composed of multiple frames of each gear video in the target video to obtain multiple Pyramid structure composed of sub-images with different spatial resolutions; time-domain band-pass filtering is performed on each of the multiple sub-images in the pyramid structure to obtain the transformed signal corresponding to the target frequency band; the displacement corresponding to the transformed signal is performed A Amplify to obtain the amplified signal, where the value range of A is (4, A max ), where the value of A max is determined by the target frequency band and the displacement function of the transformed signal; combine the amplified signal and the pyramid structure to reconstruct the pyramid , The amplified output video corresponding to the gear video is obtained; the amplified output videos corresponding to the multiple gear videos constitute the amplified output video of the vibrating object.
  • the frame sequence composed of multiple frames of the target video is decomposed into multiple Sub-images of different spatial resolutions and different scale sizes form a pyramid structure.
  • a Gaussian pyramid is used to decompose the multi-frame image of the target video, that is, a pyramid structure is composed of a set of image sequences that are halved in size.
  • Each level of image in the sequence is the result of low-pass filtering of the previous level of image and sampling every other row and every column.
  • Pyramid decomposition is to perform spatial filtering on the frame sequence, and decompose to obtain different spatial frequencies
  • Frequency bands and amplify these frequency bands separately. 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.
  • 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.
  • ideal band-pass filters, Butterworth band-pass filters, second-order infinite impulse response filters, etc. can be used.
  • ⁇ (t) represents the displacement signal
  • Amplify I(x,t) by ⁇ times, that is, amplify the displacement signal ⁇ (t), and the amplified signal is:
  • magnification is related to the spatial frequency and satisfies the following relationship:
  • the spatial frequency is ⁇
  • the spatial wavelength of the target frequency band is ⁇
  • ⁇ 2 ⁇ / ⁇
  • the maximum value of ⁇ can be determined by the displacement function of the target frequency band and the transformed signal. A max ⁇ .
  • the performing time-domain band-pass filtering processing on each sub-image in the plurality of sub-images in the pyramid structure to obtain a transformed signal corresponding to the target frequency band includes: acquiring each sub-image from the bottom to the top according to the pyramid structure.
  • the frequency band of the spatial frequency where the bottom layer of the pyramid structure is the layer corresponding to the sub-image with the lowest resolution; the acquired frequency bands of different spatial frequencies are matched with the standard frequency band according to the acquisition order, and the frequency band is determined to be the same as the standard frequency band. Whether the standard frequency band is successfully matched; when the frequency band and the standard frequency band are successfully matched, the frequency band is determined to be the target frequency band; the sub-image corresponding to the frequency domain is acquired as the transformed signal corresponding to the target frequency band.
  • a pyramid structure is obtained.
  • the pyramid structure includes multiple layers of sub-images, and the image resolution from top to bottom is sequentially reduced, and the spatial frequency is sequentially reduced.
  • Time-domain band-pass filtering is performed on each layer of image in order to obtain the target frequency band, so that the sub-image resolution of the target frequency band can clearly express the motion characteristics of the image, and at the same time, it will not cause too much calculation due to the high resolution. Therefore, according to the pyramid structure, the frequency bands of each sub-image at different spatial frequencies are obtained from bottom to top, and the acquisition sequence is compared with the standard frequency band.
  • the frequency band acquisition and matching of the spatial frequency of one or more sub-images above this sub-image improves the efficiency of time-domain loan-pass filtering.
  • the maximum number of pyramid decomposition levels is determined: log2(min(xres,yres)), where xres is the width pixel value of the image, and yres is the height pixel value of the image.
  • the performing time-domain band-pass filtering processing on each of the multiple sub-images in the pyramid structure to obtain the transformed signal corresponding to the target frequency band includes:
  • the first group of sub-images are processed by the first processor to perform temporal band-pass filtering according to the number of layers from small to large
  • the second group of sub-images are processed by the second processor to perform temporal band-pass filtering according to the number of layers from small to large.
  • the time-domain band-pass filtering process is to match frequency bands of different spatial frequencies corresponding to the sub-images with a standard frequency band, and the first processor and the second processor are independently operating processors;
  • the first processor or the second processor determines that the frequency band is successfully matched with the standard frequency band, determining that the frequency band is the target frequency band;
  • the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band.
  • the base array uses the first processor to perform time-domain band-pass filtering in the order of 1,3,5...2n+1, and the even array uses the second processor. Perform the time-domain band-pass filter processing in the order of 2,4,6,...2(n+1).
  • the two processors can start running at the same time or have a certain processing time interval.
  • the obtaining method may be to match the frequency bands of different spatial frequencies corresponding to the sub-images with the standard frequency bands.
  • the first processor or the second processor determines that the frequency band is successfully matched with the standard frequency band, it is determined that the frequency band is the target frequency band.
  • the target frequency band represents the spatial frequency of the lowest resolution sub-image that can reflect the vibration information of the image
  • the sub-image corresponding to the target frequency band is determined as the first target sub-image, and then the sub-image corresponding to the target frequency band in the upper layer of the sub-image is obtained as the second
  • the target sub-image, the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band, and subsequent amplification and transformation are performed.
  • the frame image corresponding to the target video can be enlarged more accurately, and more accurate motion information can be obtained, and at the same time, the amount of calculation that needs to be increased for amplifying a higher resolution image is avoided.
  • the sub-images corresponding to the pyramid structure are grouped, and then the sub-images of different groups are subjected to time-domain band-pass filtering through two independently operating processors, which can improve the efficiency of filtering processing, and at the same time obtain
  • the sub-image of the layer corresponding to the target frequency band is used as the first target sub-image
  • the sub-image of the upper layer is obtained as the second target sub-image
  • the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band
  • the method before performing spatial pyramid decomposition of the frame sequence composed of multiple frames of the target video, the method further includes: obtaining multiple frames of to-be-processed images of the target video, and partitioning the to-be-processed images;
  • the pixel points in the partition are used as initial feature points, and the flow vector of the initial feature point is calculated based on the minimum difference square and SSD matching;
  • the offset distance of the initial feature point is calculated according to the flow vector corresponding to the initial feature point
  • Use k-means clustering algorithm to cluster multiple offset distances corresponding to multiple initial feature points to obtain multiple clusters; determine each of the multiple clusters Whether the average value of the offset distance is within the preset range; if so, determine that the partition corresponding to the initial feature point in the cluster is a motion partition; retain the motion in the multi-frame to-be-processed image of the target video Partition to form multiple frames of the target video.
  • some areas include moving pixels, and some areas do not. Removal of areas that do not include moving pixels helps to obtain a more streamlined image for more efficient Perform the subsequent decomposition of the airspace pyramid.
  • partition the image to be processed When partitioning, you can perform rectangular partitioning. For example, divide R*R pixels into one partition, where R can be any integer greater than 1, and then obtain the initial feature points in each partition.
  • the feature points can be corner points, edge points, bright spots in dark areas, dark points in bright areas, etc., and then based on the minimum difference square and SSD matching, the flow vector of the initial feature points is calculated. The smaller the value of SSD, the greater the similarity between the feature points.
  • the motion trajectory of the initial feature point can be determined, and then the flow vector of the initial feature point can be obtained.
  • calculate the offset distance of the initial feature point according to the flow vector for example, Find the modulus, get It is the offset distance of the initial feature point from point A to point B.
  • the K-means clustering algorithm is used to cluster the multiple offset distances to obtain multiple clusters, and then calculate the average value of each cluster respectively. And determine whether the average value of each cluster is in the preset range.
  • the preset range is used to characterize the reciprocating motion of the vibrating object. If the average value of the cluster is in the preset range, it means that the area corresponding to the initial feature point is reciprocating. Determine the partition corresponding to the initial feature point as a motion partition, retain the motion partition, remove the non-motion partition, and obtain the final multi-frame image of the target video.
  • the method before performing time-domain band-pass filtering on the multiple sub-images in the pyramid structure to obtain the transformed signal corresponding to the target frequency band, the method further includes: determining that the vibrating object is a circular motion object; and obtaining the rotational speed of the vibrating object , And determine the target frequency band according to the speed.
  • the rotation frequency of the object can be calculated according to the rotation speed and other parameters.
  • the rotation speed value is equal to the rotation frequency value.
  • the rotation frequency of the vibrating object during normal operation its vibration frequency can be further determined, and then the standard frequency of the vibration image after pyramid decomposition can be determined, and then the target frequency band can be determined.
  • the method before performing time-domain band-pass filtering on the multiple sub-images in the pyramid structure to obtain the transformed signal corresponding to the target frequency band, the method further includes: obtaining the resonance frequency of the vibrating object; and determining the target frequency band according to the resonance frequency.
  • the resonance frequency will be different according to the shape, size and material of the object.
  • the target frequency band is determined according to the resonance frequency, and then the transformed signal corresponding to the target frequency band is amplified to extract the vibration information, which is beneficial to discover the cause of the vibration of the vibrating object.
  • the phase correlation algorithm uses the following formula to calculate the cross cross power spectrum.
  • Fa is the Fourier transform of a frame image
  • the lower side of the division formula is the modulus of the correlation product of the two Fourier transformed signals.
  • R crosses the cross power spectrum of the calculation result of this step.
  • the cross cross power spectrum After the cross cross power spectrum is obtained, it contains frequency domain noise, so it can be filtered to improve the signal-to-noise ratio, so as to improve the accuracy of the subsequent extracted vibration information.
  • the method further includes: obtaining multiple states corresponding to the cross cross power spectrum obtained by performing phase correlation calculation on the frame sequence corresponding to the detected video Change signal, the state change signal is a time domain signal; analyze multiple state change signals to obtain aperiodic signals in multiple state change signals; remove aperiodic signals from multiple state change signals to obtain frequency domain noise after filtering The cross cross power spectrum.
  • the cross cross power spectrum is a frequency domain signal, which includes one or more correlation peaks.
  • 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 target video.
  • the phase correlation calculation is performed on the frame sequence corresponding to the target video to obtain the cross cross power spectrum. It can be understood as extracting the state in the video picture from the target video Change information.
  • the state change information includes vibration information and other noise information. For example, changes in illumination can also cause state changes in the video screen, and the vibration information can reflect the operating conditions of the object to be vibrated.
  • the vibration of the device to be tested is periodic when it is running, and the state change caused by the vibration is also periodic.
  • the state change caused by noise is often not periodic, and when the operating condition of the device to be tested is analyzed based on 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, so this part of the non-periodic signal cannot be used to analyze the device to be tested.
  • the operating status of the device 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 detection video can be More useful information.
  • the analyzing multiple state change signals to obtain aperiodic signals among the multiple state change signals includes: extracting a predetermined length of a target state change signal segment from each state change signal, and obtaining the target The target frequency of the state change signal segment; the corresponding sliding window is set according to the target frequency corresponding to each state change signal, and each state change signal is sent to the corresponding sliding window; the state change signal that cannot pass the corresponding sliding window is taken as the destination The non-periodic signal.
  • the target state change signal segment of a preset length can be extracted first, the target frequency of the target change signal segment can be obtained, and then the frequency of other parts in the state change signal can be compared with the target frequency. By comparison, if the frequency of other parts of the state change signal is not consistent with the target frequency, the state change signal can be considered as a non-periodic signal.
  • the preset length can be set by the 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.
  • the window size of the sliding window can be set according to the target frequency.
  • 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.
  • 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.
  • the cross cross power spectrum reflects the vibration information of the vibrating object in the frequency domain, and it is necessary to perform the inverse Fourier transform (or inverse Fourier transform) to observe the vibration information of the vibrating object in the time domain.
  • the corresponding formula is:
  • FIG. 1D is a schematic diagram of a vibration information display provided by an embodiment of the application.
  • the vibration detection sensing device is connected to the user interface through the interface unit, and the interface unit is multi-mode output on the user interface.
  • Vibration information is displayed.
  • the zoomed-in video is displayed in the left area, and the zoomed-in video is displayed in the right area.
  • the vibration parameters corresponding to the target detection point are displayed.
  • the target detection point is a circular area corresponding to 130, and the right is Its corresponding vibration parameters.
  • the difference between the current target video and the vibration information of the standard vibration mode can be found. By tracking the location and reason of these differences, you can find that the target video corresponds to the electric fan Vibration failure.
  • the amplification method amplifies the target video to obtain the amplified output video; obtains the frame sequence corresponding to the amplified output video, uses the phase correlation algorithm for the frame sequence to calculate the cross cross power spectrum between the frame sequences; performs the inverse Fourier transform on the cross cross power spectrum, Obtain the vibration information of the pixels in the target video; finally, the vibration fault of the electric fan is determined by the matching result of the standard vibration pattern and the vibration information.
  • This method can amplify the small motions in the video by adopting the Lagrangian motion amplification method, and then extract the vibration information in the video, which improves the accuracy of information extraction and thus the reliability of vibration analysis. Finally, the vibration fault is determined by comparing the standard vibration mode and the vibration information, which improves the accuracy and effectiveness of vibration detection.
  • FIG. 2 is a schematic flowchart of another method for detecting vibration failure of an electric fan according to an embodiment of the application. As shown in FIG. 2, the method includes the following steps:
  • steps 201 to 206 For specific descriptions of steps 201 to 206 above, reference may be made to the corresponding descriptions of the method for detecting vibration faults of an electric fan described in steps 101 to 107, which will not be repeated here.
  • the electric fan vibration fault detection method disclosed in the embodiment of the present application obtains the target video corresponding to the vibrating object; uses the Euler motion amplification method to amplify the target video to obtain an amplified output video of the vibrating object with a motion amplification effect; Obtain the frame sequence corresponding to the amplified output video, use the phase correlation algorithm for the frame sequence to calculate the cross cross power spectrum between the frame sequences; perform the inverse Fourier transform on the cross cross power spectrum to obtain the vibration information of the pixel in the target video.
  • This method can amplify the small motions in the video by adopting the Euler motion amplification method, and then extract the vibration information in the video, which improves the accuracy of information extraction and further improves the reliability of vibration analysis.
  • FIG. 3 is a schematic flow chart of a video enlargement processing method provided by an embodiment of the application. As shown in FIG. 3, the method includes the following steps:
  • the frequency band is successfully matched with the standard frequency band, determine that the frequency band is a target frequency band, and acquire a sub-image corresponding to the frequency domain as a transformed signal corresponding to the target frequency band;
  • the electric fan vibration fault detection method disclosed in the embodiment of the application uses the Euler motion amplification method to amplify the target video to obtain the amplified output video; including spatial pyramid decomposition of the image frame in the target video, and the pyramid
  • the sub-image in the type structure is band-pass filtered, and then the transformed signal corresponding to the target frequency band is obtained and amplified, and finally the amplified output video is obtained.
  • This process further determines the specific process of using Euler motion amplification to amplify the target video. This improves the effectiveness of the video magnification process, and obtains a more accurate magnified output video.
  • FIG. 4 is a schematic flowchart of another method for detecting vibration failure of an electric fan according to an embodiment of the application. As shown in FIG. 4, the method includes the following steps:
  • the Euler motion amplification method uses the Euler motion amplification method to amplify the target video to obtain an amplified output video with a motion amplification effect of the vibrating object.
  • the motion amplification effect refers to the movement of the vibrating object in the area where the reciprocating motion occurs in the target video.
  • Power spectrum Inverse Fourier transform is performed on the cross cross power spectrum to obtain the vibration information of the pixels in the target video. In this process, by filtering the cross cross power spectrum, it is helpful to obtain more accurate vibration information. The whole process improves the accuracy of information extraction, thereby improving the reliability of vibration analysis.
  • FIG. 5 is a schematic structural diagram of an electric fan vibration failure detection device provided by an embodiment of the application.
  • an electric fan vibration failure detection device 500 includes:
  • the receiving unit 501 is configured to receive an instruction from a user to start a device detection function, and present a vibration detection portal of the target electric fan according to the instruction, the vibration detection portal provides a vibration detection position option, and the vibration detection position includes a base and a fan;
  • the selection unit 502 is configured to receive the vibration detection position option selected by the user, and determine a standard vibration mode according to the vibration detection position option;
  • the obtaining unit 503 is configured to locate the electric fan as a vibrating object, and obtain a target video corresponding to the electric fan;
  • the amplification unit 504 uses the Euler motion amplification method to amplify the target video to obtain an amplified output video with a motion amplification effect of the vibrating object.
  • the motion amplification effect refers to the movement of the vibrating object's reciprocating motion area in the target video Is magnified;
  • the calculation unit 505 is configured to obtain a frame sequence corresponding to the amplified output video, and use a phase correlation algorithm for the frame sequence to calculate the cross cross power spectrum between the frame sequences;
  • the output unit 506 is configured to perform inverse Fourier transform on the cross cross power spectrum to obtain the vibration information of the pixels in the target video;
  • the determining unit 507 is configured to match the vibration information with the vibration information corresponding to the standard vibration mode, and determine the vibration fault of the vibrating object according to the matching result.
  • the specific working process of the receiving unit 501, the selecting unit 502, the acquiring unit 503, the amplifying unit 504, the calculating unit 505, the output unit 506, and the determining unit 507 can be referred to the electric fan described in the above steps 101-107.
  • the corresponding description of the vibration fault detection method will not be repeated here.
  • the electric fan vibration fault detection device obtains the electric fan vibration detection entrance by receiving user instructions, and then provides the user with a standard vibration mode according to the vibration detection position option selected by the user; and then obtains the corresponding vibration object
  • the target video of the target video is amplified by the Euler motion amplification method to obtain the amplified output video; the frame sequence corresponding to the amplified output video is obtained, and the phase correlation algorithm is used for the frame sequence to calculate the cross power spectrum between the frame sequences;
  • the cross power spectrum performs inverse Fourier transform to obtain the vibration information of the pixels in the target video; finally, the vibration fault of the electric fan is determined by the matching result of the standard vibration pattern and the vibration information.
  • This method can amplify the small motions in the video by adopting the Lagrangian motion amplification method, and then extract the vibration information in the video, which improves the accuracy of information extraction and thus the reliability of vibration analysis. Finally, the vibration fault is determined by comparing the standard vibration mode and the vibration information, which improves the accuracy and effectiveness of vibration detection.
  • the acquiring unit 503 is specifically configured to:
  • gear position information of the electric fan where the gear position information includes the number of gear positions and the gear position mode;
  • the obtained multiple gear videos are used as target videos corresponding to the electric fan, and the multiple is the number of gears.
  • the amplifying unit 504 is specifically configured to:
  • Pyramid reconstruction is performed by combining the amplified signal and the pyramid structure to obtain the amplified output video corresponding to the gear video;
  • the amplified output videos corresponding to the multiple gear videos constitute an amplified output video of the vibrating object.
  • the amplifying unit 504 is also specifically configured to:
  • the sub-image corresponding to the frequency domain is acquired as a transformed signal corresponding to the target frequency band.
  • the electric fan vibration fault detection device further includes a partition unit 508, which is specifically used for:
  • the motion partitions in the multi-frame to-be-processed image of the target video are retained to form the multi-frame image of the target video.
  • the electric fan vibration fault detection device further includes a conversion unit 509, which is specifically configured to:
  • the amplifying unit 504 is specifically used for:
  • the Y-phase signal adopts Euler motion amplification method to enlarge the target video.
  • the amplifying unit 504 is also specifically configured to:
  • the Euler motion amplification algorithm is used to enlarge the target video.
  • the electric fan vibration fault detection device further includes a filtering unit 510, which is specifically configured to:
  • the filtering unit 510 is further specifically configured to:
  • the state change signal that cannot pass the corresponding sliding window is used as the non-periodic signal.
  • the amplifying unit 504 is also specifically configured to:
  • the amplifying unit 504 is also specifically configured to:
  • it is used to store a computer program for electronic data exchange, wherein the computer program causes a computer to execute instructions of any of the above-mentioned method steps.
  • the disclosed method can be implemented in other ways.
  • the method embodiments described above are only illustrative.
  • the division of units is only a logical function division. In actual implementation, there may be other divisions.
  • multiple units or components can be combined or integrated into Another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, methods 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.
  • the functional units in the various embodiments of the present application 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.
  • 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.
  • 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 make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk, or optical disk and other media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: a flash disk , Read-only memory (English: Read-Only Memory, abbreviation: ROM), random access device (English: Random Access Memory, abbreviation: RAM), magnetic disk or optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé de détection de défaut de vibration de ventilateur électrique consistant : à obtenir, par un objet vibrant constituant un ventilateur électrique, des vidéos cibles correspondant à l'objet vibrant (103) ; à amplifier les vidéos cibles à l'aide d'un procédé d'amplification de mouvement eulérien afin d'obtenir des vidéos de sortie amplifiées de l'objet vibrant présentant un effet d'amplification de mouvement, l'effet d'amplification de mouvement indiquant que le mouvement dans la zone où l'objet vibrant effectue un mouvement de va-et-vient est amplifié dans les vidéos cibles (104) ; à obtenir des séquences de trames correspondant aux vidéos de sortie amplifiées, et pour les séquences de trames, à calculer l'interspectre entre les séquences de trames à l'aide d'un algorithme de corrélation de phase (105) ; à réaliser une transformée de Fourier inverse sur l'interspectre afin d'obtenir les informations de vibration de pixels dans les vidéos cibles (106) ; et à mettre en correspondance les informations de vibration avec les informations de vibration correspondant à un mode de vibration standard, et à déterminer le défaut de vibration de l'objet vibrant en fonction du résultat de mise en correspondance (107). Le présent procédé peut améliorer la précision d'extraction d'informations, ce qui permet d'améliorer la fiabilité d'analyse de vibration. L'invention concerne également un appareil de détection de défaut de vibration de ventilateur électrique.
PCT/CN2020/105853 2019-04-26 2020-07-30 Procédé et appareil de détection de défaut de vibration de ventilateur électrique WO2021052025A1 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201910346028 2019-04-26
CN201910883646.1A CN110595749B (zh) 2019-04-26 2019-09-18 电风扇振动故障检测方法及装置
CN201910883646.1 2019-09-18

Publications (1)

Publication Number Publication Date
WO2021052025A1 true WO2021052025A1 (fr) 2021-03-25

Family

ID=68860952

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/105853 WO2021052025A1 (fr) 2019-04-26 2020-07-30 Procédé et appareil de détection de défaut de vibration de ventilateur électrique

Country Status (2)

Country Link
CN (1) CN110595749B (fr)
WO (1) WO2021052025A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113096194A (zh) * 2021-05-08 2021-07-09 北京字节跳动网络技术有限公司 确定时序的方法、装置、终端及非暂时性存储介质
CN114972349A (zh) * 2022-08-01 2022-08-30 山东西曼克技术有限公司 基于图像处理的托辊运行状态检测方法及系统
CN114993452A (zh) * 2022-07-14 2022-09-02 湖南大学 基于宽带相位运动放大的结构微小振动测量方法与系统
CN116593145A (zh) * 2023-05-16 2023-08-15 利维智能（深圳）有限公司 故障检测方法、装置、计算机设备和存储介质
CN117969070A (zh) * 2024-03-27 2024-05-03 矿冶科技集团有限公司 一种大型选矿旋转设备的低频机械振动频率表征方法
CN118309616A (zh) * 2024-06-06 2024-07-09 华电(福建)风电有限公司 海上风电设备的运维方法和系统

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110617965B (zh) * 2019-04-26 2021-10-15 深圳市豪视智能科技有限公司 齿轮组异常的检测方法及相关产品
CN110595749B (zh) * 2019-04-26 2021-08-20 深圳市豪视智能科技有限公司 电风扇振动故障检测方法及装置
CN112528854B (zh) * 2020-12-12 2023-07-25 南方电网调峰调频发电有限公司 振动对象监测方法、装置、计算机设备和存储介质
CN112254801B (zh) * 2020-12-21 2021-04-02 浙江中自庆安新能源技术有限公司 一种微小振动视觉测量方法及系统
CN112816053A (zh) * 2020-12-30 2021-05-18 武汉第二船舶设计研究所(中国船舶重工集团公司第七一九研究所) 一种船舶设备的非接触式振动信息检测方法及系统
CN113447111B (zh) * 2021-06-16 2022-09-27 合肥工业大学 基于形态分量分析的视觉振动放大方法、检测方法及系统
CN113464380B (zh) * 2021-08-09 2022-09-27 观为监测技术无锡股份有限公司 一种塔筒安全性能确定方法、装置、设备及存储介质
CN113682342A (zh) * 2021-08-25 2021-11-23 深圳市永安环保实业有限公司 轨道的异常检测方法及相关产品
CN114782902A (zh) * 2022-06-22 2022-07-22 中国科学技术大学先进技术研究院 石化气体泄露检测方法、系统、设备及存储介质
CN115430814A (zh) * 2022-09-27 2022-12-06 联峰钢铁（张家港）有限公司 一种连铸机状态判断及预警的方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016113587A1 (fr) * 2015-01-13 2016-07-21 Morpho Procédé et système de détection d'usurpation de vidéo sur la base de l'évaluation de vivacité
CN106127688A (zh) * 2016-06-30 2016-11-16 北京大学 一种超分辨率图像重建方法及其系统
WO2018042424A1 (fr) * 2016-08-29 2018-03-08 Elbit Systems Land And C4I Ltd. Détection optique de vibrations
JP2019013927A (ja) * 2017-07-04 2019-01-31 Ｊｆｅスチール株式会社 鋳型振動監視方法及びブレークアウト監視方法
CN109520690A (zh) * 2018-10-30 2019-03-26 西安交通大学 一种基于视频的旋转机械转子模态振型全局测量装置及方法
CN110595749A (zh) * 2019-04-26 2019-12-20 深圳市豪视智能科技有限公司 电风扇振动故障检测方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140254678A1 (en) * 2013-03-11 2014-09-11 Aleksandar Beric Motion estimation using hierarchical phase plane correlation and block matching
US9418279B2 (en) * 2013-11-19 2016-08-16 Qualcomm Incorporated Detection of an object's varying features with a non-stationary device
CN103727979A (zh) * 2013-12-19 2014-04-16 安徽泰特斯电力技术有限公司 一种风机振动在线监测终端
US9599532B2 (en) * 2015-02-27 2017-03-21 The United States Of America As Represented By The Secretary Of The Navy Characterization and evaluation of optical elements under vibrational loading
CN105651377B (zh) * 2016-01-11 2018-12-07 衢州学院 一种基于视频数据挖掘的非接触式物体振动频率测量方法
CN106657713B (zh) * 2016-12-30 2019-03-22 华中科技大学 一种视频运动放大方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016113587A1 (fr) * 2015-01-13 2016-07-21 Morpho Procédé et système de détection d'usurpation de vidéo sur la base de l'évaluation de vivacité
CN106127688A (zh) * 2016-06-30 2016-11-16 北京大学 一种超分辨率图像重建方法及其系统
WO2018042424A1 (fr) * 2016-08-29 2018-03-08 Elbit Systems Land And C4I Ltd. Détection optique de vibrations
JP2019013927A (ja) * 2017-07-04 2019-01-31 Ｊｆｅスチール株式会社 鋳型振動監視方法及びブレークアウト監視方法
CN109520690A (zh) * 2018-10-30 2019-03-26 西安交通大学 一种基于视频的旋转机械转子模态振型全局测量装置及方法
CN110595749A (zh) * 2019-04-26 2019-12-20 深圳市豪视智能科技有限公司 电风扇振动故障检测方法及装置

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113096194A (zh) * 2021-05-08 2021-07-09 北京字节跳动网络技术有限公司 确定时序的方法、装置、终端及非暂时性存储介质
CN113096194B (zh) * 2021-05-08 2024-03-26 北京字节跳动网络技术有限公司 确定时序的方法、装置、终端及非暂时性存储介质
CN114993452A (zh) * 2022-07-14 2022-09-02 湖南大学 基于宽带相位运动放大的结构微小振动测量方法与系统
CN114993452B (zh) * 2022-07-14 2023-03-24 湖南大学 基于宽带相位运动放大的结构微小振动测量方法与系统
CN114972349A (zh) * 2022-08-01 2022-08-30 山东西曼克技术有限公司 基于图像处理的托辊运行状态检测方法及系统
CN114972349B (zh) * 2022-08-01 2022-10-25 山东西曼克技术有限公司 基于图像处理的托辊运行状态检测方法及系统
CN116593145A (zh) * 2023-05-16 2023-08-15 利维智能（深圳）有限公司 故障检测方法、装置、计算机设备和存储介质
CN116593145B (zh) * 2023-05-16 2024-01-09 利维智能（深圳）有限公司 故障检测方法、装置、计算机设备和存储介质
CN117969070A (zh) * 2024-03-27 2024-05-03 矿冶科技集团有限公司 一种大型选矿旋转设备的低频机械振动频率表征方法
CN118309616A (zh) * 2024-06-06 2024-07-09 华电(福建)风电有限公司 海上风电设备的运维方法和系统

Also Published As

Publication number Publication date
CN110595749B (zh) 2021-08-20
CN110595749A (zh) 2019-12-20

Similar Documents

Publication Publication Date Title
WO2021052025A1 (fr) Procédé et appareil de détection de défaut de vibration de ventilateur électrique
CN109919869B (zh) 一种图像增强方法、装置及存储介质
WO2021036670A1 (fr) Procédé et appareil de détection intelligente de vibration à transmission multimode
US8269722B2 (en) Gesture recognition system and method thereof
WO2021036663A1 (fr) Procédé de détection d'anomalie de vis fixe pour dispositif et produits associés
KR101479387B1 (ko) 얼굴 검출을 위한 방법 및 장치
CN105205815B (zh) 基于云台可控制摄像机的实时视频跟踪方法
JP6437514B2 (ja) 特徴の空間局所化を利用することによる物体検出時間の減少
KR101457313B1 (ko) 템플릿 스위칭 및 특징 적응을 이용한 오브젝트 추적을 제공하는 방법, 장치 및 컴퓨터 프로그램 제품
CN110674700B (zh) 基于数字孪生模型的电子设备的智能健康预测方法及装置
WO2021052024A1 (fr) Procédé et appareil de détection de défaut de vibration de machine à laver
JP2017520050A5 (fr)
CN111260037B (zh) 图像数据的卷积运算方法、装置、电子设备及存储介质
JP2019062527A (ja) エッジ演算を用いる多カメラシステムでのリアルタイムの対象再識別
KR20150027291A (ko) 광류 추적 방법 및 장치
Indhumadhi et al. Enhanced image fusion algorithm using laplacian pyramid and spatial frequency based wavelet algorithm
JP2018170003A (ja) ビデオ中のイベントの検出装置、方法及び画像処理装置
JP2021523347A (ja) 飛行時間カメラの低減された出力動作
WO2021036662A1 (fr) Procédé et dispositif de traitement de signal, et produit associé
WO2021036634A1 (fr) Procédé de détection de défaut et produit associé
WO2021036661A1 (fr) Procédé et appareil de filtrage, et produit associé
CN112183431A (zh) 实时行人数量统计方法、装置、相机和服务器
WO2021036669A1 (fr) Procédé de détection de vibrations intelligente et produits associés
CN116129016B (zh) 一种姿态运动的数字同步方法、装置、设备及存储介质
Nie et al. LFC-SSD: Multiscale aircraft detection based on local feature correlation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20865276

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20865276

Country of ref document: EP

Kind code of ref document: A1