Propulsion motor rotor winding method and system

Abstract

The invention relates to the technical field of motor manufacturing, in particular to a propulsion motor rotor winding method and system. The method comprises the following steps: acquiring a frequency spectrum image of a winding grayscale image, and selecting and screening high-frequency information by a central circle to obtain a high-frequency image; determining a motion stability factor according to the position of the winding probe, and determining an image stability factor through edge detection and image recognition; screening to obtain a stable frame image; performing gradient analysis on the stable frame image and the high-frequency image, determining a first histogram and a second histogram, and determining similar parameters of the first histogram and the second histogram according to the gradient distribution structure difference of the first histogram and the second histogram; and screening according to the similar parameters to obtain an optimal radius, converting the high-frequency image under the optimal radius into a spatial domain to obtain a deblurred image, carrying out winding detection on the deblurred image, and determining a winding grayscale image with abnormal winding. According to the invention, the accuracy of rotor winding detection in the propulsion motor manufacturing process can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of motor manufacturing, and in particular to a propulsion motor rotor winding method and system. Background Art

[0002] The rotor of a motor generally includes a rotor core and a rotor winding. Currently, most manufacturers on the market use high-speed stamping machines to process and produce the rotor core, and then use special production equipment to wind copper wire around the rotor core to form a rotor winding. The quality of the rotor is closely related to the processing quality of the rotor core and the winding quality of the rotor winding. Uneven rotor winding is an important factor affecting the quality of the rotor winding.

[0003] In the related art, image information is obtained and then checked based on the image information to see if any rotor winding anomalies occur during the motor manufacturing process (such as uneven winding, incorrect wiring, etc.). In this way, the shutter speed of the camera will cause motion blur when the rotor rotates. This motion blur effect will blur the rotor area, causing the subtle features of the rotor surface and the motion details during the winding process to be lost, affecting the winding detection during the motor manufacturing process and causing poor accuracy in the motor rotor winding detection. Summary of the invention

[0004] In order to solve the technical problem in the related art that the accuracy of propulsion motor rotor winding detection is poor due to motion blur caused by rotor rotation, the present invention provides a propulsion motor rotor winding method and system, and the technical solution adopted is as follows: The present invention proposes a propulsion motor rotor winding method, the method comprising: At different sampling times, a winding grayscale image of the motor side winding probe during the rotor winding process is obtained, the winding grayscale image is converted into a spectrum image in the frequency domain, different radii are used to select the center circle, and high-frequency information of the center circle area is filtered from the spectrum image to obtain high-frequency images at different radii; According to the position of the winding probe in the winding grayscale image, a motion stability factor is determined, edge detection and image recognition are performed on the winding grayscale image to determine the image connected domain belonging to the rotor, and an image stability factor is determined according to the size of the image connected domain and the number of edge pixels; the motion stability factor and the image stability factor are combined to screen out stable frame images from different frames of winding grayscale images; For a high-frequency image of any radius, a gradient analysis is performed on the stable frame image and the high-frequency image of the same winding grayscale image, and the gradient distribution histogram of the stable frame image is determined as the first histogram, and the gradient distribution histogram of the high-frequency image is determined as the second histogram. According to the difference in the gradient distribution structures between the first histogram and the second histogram, the similarity parameters of the first histogram and the second histogram are determined; An optimal radius is obtained by screening according to the similarity parameters, a high-frequency image under the optimal radius is converted into a spatial domain to obtain a deblurred image, winding detection is performed on the deblurred image, and a winding grayscale image with winding abnormalities is determined.

[0005] Furthermore, the method of selecting the central circle using different radii, filtering high-frequency information of the central circle area from the spectrum image, and obtaining high-frequency images at different radii includes: The spectrum image is cut using a straight line passing through the center of the image and parallel to both sides, and the four corners of the spectrum image after cutting are assembled to a central point to obtain an image to be selected with low-frequency information in the center; Taking the center point of the image to be selected as the center of the circle, different radii are used to determine the center circle of the image to be selected, and the center circle part is deleted to obtain high-frequency images under different radii.

[0006] Furthermore, determining the motion stability factor according to the position of the wire winding probe in the wire winding grayscale image includes: Determine the position of the wire winding probe in all frame wire winding grayscale images, obtain the motion trajectory of the wire winding probe, and obtain two endpoints of the motion trajectory; The Euclidean distances between the position of the winding probe and the two end points in any frame of the winding grayscale image are obtained, and the maximum value of the Euclidean distances is used as the motion stability factor of the corresponding frame of the winding grayscale image.

[0007] Furthermore, the performing edge detection and image recognition on the winding grayscale image to determine the image connected domain belonging to the rotor includes: Performing canny edge detection on the winding grayscale image to obtain edge pixels, wherein the edge pixels constitute an initial connected domain; Image recognition is performed on the initial connected domain, and the initial connected domain belonging to the rotor is identified as the image connected domain.

[0008] Furthermore, determining the image stabilization factor according to the size of the image connected domain and the number of edge pixels includes: The ratio of the number of pixels in the connected domain to the number of edge pixels obtained by edge detection is calculated as an image stabilization factor.

[0009] Furthermore, the combining of the motion stabilization factor and the image stabilization factor to obtain a stable frame image from different frame winding grayscale images includes: Calculating the product of the motion stability factor and the image stability factor, and normalizing the maximum and minimum values ​​to obtain a stability index; The winding grayscale image whose stability index is greater than a preset stability threshold is used as a stable frame image.

[0010] Further, the determining of similarity parameters of the first histogram and the second histogram according to the difference in the gradient distribution structures of the first histogram and the second histogram includes: Dividing the gradient strengths in the first histogram and the second histogram into the same intervals to obtain corresponding gradient intervals in the first histogram and the second histogram; Calculate the square value of the difference between the frequencies in the same gradient interval in the first histogram and the second histogram to obtain a first index; Calculate the sum of the frequencies in the same gradient interval in the first histogram and the second histogram as a second indicator; Calculate the ratio of the first index to the second index, and perform maximum and minimum normalization processing on the inverse of the ratio as the interval similarity coefficient of the corresponding gradient interval; The mean of the interval similarity coefficients of all gradient intervals is taken as the similarity parameter of the first histogram and the second histogram.

[0011] Further, the optimal radius is obtained by screening according to the similarity parameters, including: The radius at the maximum value of similar parameters corresponding to all high-frequency images is taken as the optimal radius.

[0012] Further, performing winding detection on the deblurred image to determine a winding grayscale image with abnormal winding includes: The deblurred image is input into a pre-trained winding detection model, and a winding abnormality inspection result of the winding grayscale image is output.

[0013] On the other hand, the present invention also provides a propulsion motor rotor winding system, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of a propulsion motor rotor winding method as described in any one of the above items.

[0014] The present invention has the following beneficial effects: The present invention selects the center circle through the spectrum image, removes the low-frequency information affected by motion blur, retains the high-frequency information, and obtains high-frequency images of different radii; then, the stable frame image is determined according to the position of the winding probe, the number of edge pixels of the rotor, and the size of the area; the stable frame image and the high-frequency image are subjected to gradient analysis, the similarity parameters of the gradient feature are determined through the gradient distribution histogram, the optimal radius is obtained according to the similarity parameter screening, the high-frequency image under the optimal radius is converted into the spatial domain to obtain a deblurred image, the deblurred image is subjected to winding detection, and the winding grayscale image with winding abnormality is determined. The present invention can effectively analyze the winding process of the rotating rotor, and through the analysis of the characteristics of the image acquisition device itself and the analysis of the dynamic blur characteristics generated by the rotation of the rotor, the stable frame image can be accurately selected, and the deblurring process is performed using an adaptive and appropriate scale to obtain a clearer and more reliable deblurred image, and the winding detection is performed through the deblurred image, which avoids the interference caused by dynamic blur and improves the accuracy of rotor winding detection in the manufacturing process of the propulsion motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a propulsion motor rotor winding method provided by one embodiment of the present invention; Figure 2 A schematic diagram of a motor rotor winding provided by an embodiment of the present invention; Figure 3 A schematic diagram of a high-frequency image acquisition process provided by an embodiment of the present invention; Figure 4 A structural diagram of a propulsion motor rotor winding system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a propulsion motor rotor winding method and system according to the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] It should be noted that in order to ensure that the calculation results are meaningful, when performing fractional operations in the embodiments of the present invention, when the denominator is 0, it is necessary to add a parameter adjustment factor greater than 0 to the denominator to prevent the denominator from being 0. The value of the parameter adjustment factor is set by the implementer according to actual conditions, and this application does not impose any special restrictions.

[0020] The specific scheme of the propulsion motor rotor winding method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a propulsion motor rotor winding method provided by an embodiment of the present invention, the method comprising: S101: Obtain winding grayscale images of the motor side winding probe during the rotor winding process at different sampling times, convert the winding grayscale images into spectrum images in the frequency domain, use different radii to select the center circle, filter high-frequency information of the center circle area from the spectrum image, and obtain high-frequency images at different radii.

[0022] The scenario corresponding to the embodiment of the present invention is the motor rotor winding scenario, see Figure 2 , Figure 2 A schematic diagram of motor rotor winding provided by an embodiment of the present invention; during the winding process, the rotor rotates, and the winding probe moves up and down in a cycle to achieve the winding of copper wire on the motor.

[0023] In an embodiment of the present invention, a high-resolution industrial camera can be mounted on the side of the rotor to continuously photograph the winding process of the motor rotor at different sampling times to obtain an original image, and then the original image is gray-scaled to obtain a winding gray-scale image.

[0024] In the embodiment of the present invention, the original image may be collected every 0.1 second, and the grayscale processing may use mean grayscale, which is not limited.

[0025] It should be noted that in two adjacent frames of winding grayscale images, the changes occur in the rotor and the winding probe, and the rotor rotates at a high speed. At this time, if the shutter speed of the industrial camera is slow, the rotor rotation will cause motion blur. This motion blur effect will blur the rotor area, lose the subtle features of the rotor surface and the motion details of the winding process, and affect the winding detection of the winding process. Therefore, deblurring can be performed.

[0026] In the image captured by the camera, the edge information of the rotor and the coil belongs to the detail information, which is the high-frequency component in the winding grayscale image; the motion blur belongs to the interference information, which is manifested as a low-frequency component and needs to be removed. The Fourier transform can convert the image to the frequency domain. The frequency domain image is usually presented as a complex image, and its amplitude represents the intensity of the frequency. According to the frequency domain characteristics, the present invention designs a filter by selecting appropriate parameters (radius) to remove the interference of the low-frequency component and achieve the purpose of removing motion blur.

[0027] Furthermore, in some embodiments of the present invention, different radii are used to select the center circle, and high-frequency information in the center circle area is filtered from the spectrum image to obtain high-frequency images at different radii, including: using a straight line passing through the center of the image and parallel to both sides to cut the spectrum image, and splicing the four corners of the spectrum image after cutting to a center point to obtain an image to be selected with low-frequency information in the center; using the center point of the image to be selected as the center of the circle, using different radii to determine the center circle of the image to be selected, and deleting the center circle part to obtain high-frequency images at different radii.

[0028] See also Figure 3 , Figure 3 This is a schematic diagram of the high-frequency image acquisition process provided by an embodiment of the present invention; the image is Fourier transformed to obtain a spectrum image, and in the spectrum avatar, the central area represents the high-frequency part, and the four corner areas represent the low-frequency part. Therefore, the four corner areas are transposed so that the low-frequency information remains in the center of the image to be selected, and then the low-frequency information can be directly selected using the center circle frame, and deleted to obtain a high-frequency image. That is, the high-frequency image is an image in which the low-frequency information is removed and the high-frequency information is retained.

[0029] Among them, the edge information of the rotor and coil in the winding grayscale image belongs to high-frequency information due to the drastic changes in brightness or grayscale; the structural information interfered by motion blur changes slowly and belongs to low-frequency information.

[0030] Specifically, a coordinate system is established with the frequency domain center of the image to be selected as the coordinate origin, and a parametric equation is established according to the shape characteristics of the image to be selected: Among them, r represents the radius, that is, the selection parameter for removing low-frequency components, x represents the horizontal coordinate in the coordinate system of the image to be selected; y represents the vertical coordinate in the coordinate system of the image to be selected, and t represents the angle.

[0031] According to the parametric equation, determine the cutoff frequency of the high-pass filter: in is the cutoff frequency of the high-pass filter; r represents the radius, and the selected image is treated with different pixel lengths such as r=10, 20, 30, 40 and 50 to remove low-frequency information.

[0032] Thus, high-frequency images under different radii are obtained. Since low-frequency information can be effectively removed and high-frequency information can be retained only when the radius is selected appropriately, it is necessary to conduct a specific analysis for each high-frequency image.

[0033] S102: Determine the motion stability factor according to the position of the winding probe in the winding grayscale image, perform edge detection and image recognition on the winding grayscale image to determine the image connected domain belonging to the rotor, and determine the image stability factor according to the size of the image connected domain and the number of edge pixels; combine the motion stability factor and the image stability factor to screen out stable frame images from different frames of winding grayscale images.

[0034] Among them, the motion stability factor represents the coefficient index of the motion law corresponding to the position of the winding probe. The larger the value of the motion stability factor, the more stable the motion of the winding probe at the corresponding sampling time. Since the winding probe is a cyclical motion, when the winding probe moves to the bottom and top of the winding column, the interference of the winding probe in the captured image is small, and the motion blur interference in the image can be ignored. At this time, the overall motion characteristics of the image are more stable. According to the motion law of the winding probe, the motion stability factor and image stability factor of the winding probe are calculated to screen out stable frame images.

[0035] Furthermore, in some embodiments of the present invention, a motion stability factor is determined based on the position of the winding probe in the winding grayscale image, including: determining the position of the winding probe in all frame winding grayscale images, obtaining the motion trajectory of the winding probe, and obtaining two endpoints of the motion trajectory; obtaining the Euclidean distance between the position of the winding probe in any frame winding grayscale image and the two endpoints, and taking the maximum value of the Euclidean distance as the motion stability factor of the corresponding frame winding grayscale image.

[0036] Taking the up and down movement of the winding probe as an example, mark the movement position of the winding probe in the winding grayscale image, obtain the corresponding sampling time, form the position-time coordinate, and calculate the movement stability factor of the winding probe: in, represents the motion stability factor of the winding probe photographing the rotor at the i-th sampling moment, represents the position of the winding probe photographed at the i-th sampling moment, Indicates the highest point (first endpoint) of the wire-wound probe position; Indicates the lowest point (second endpoint) of the wire-wound probe position. Represents the maximum value function.

[0037] Understandably, express and The maximum value in is also the maximum value of the Euclidean distance from the two end points. The larger the motion stability factor is, the farther the winding probe is from one of the end points, which means it is closer to the other end point. Therefore, its motion state is more in line with the stable state.

[0038] Furthermore, in some embodiments of the present invention, edge detection and image recognition are performed on the winding grayscale image to determine the image connected domain belonging to the rotor, including: performing canny edge detection on the winding grayscale image to obtain edge pixel points, and the edge pixel points constitute an initial connected domain; performing image recognition on the initial connected domain to identify the initial connected domain belonging to the rotor as the image connected domain.

[0039] Among them, canny edge detection is an edge detection algorithm well known to relevant technical personnel in the field. Edge pixels are obtained through canny edge detection, and the area surrounded by the edge pixels is used as the initial connected domain. It should be noted that since the initial connected domain represents the connected domain information of an entire image, further screening is required, and image recognition technology can be used to determine the initial connected domain belonging to the rotor as the image connected domain, wherein the image recognition technology can be specifically, for example, image recognition based on a big data model, or, for example, image annotation based on an artificial intelligence algorithm, so as to annotate the initial connected domain belonging to the rotor as the image connected domain, and there is no limitation on this.

[0040] It can be understood that in a clear image, the more accurate the edge information of the rotor is, the larger the area of ​​the connected domain of the rotor is. In the motion blur state, the blurred state of the high-speed rotation of the rotor will produce low-frequency information, which increases the number of edge pixels and reduces the connected domain belonging to the rotor area. Based on this feature, another factor that characterizes motion stability can be determined, namely the image stability factor.

[0041] Furthermore, in some embodiments of the present invention, an image stabilization factor is determined based on the size of a connected domain of the image and the number of edge pixels, including: calculating the ratio of the number of pixels in the connected domain to the number of edge pixels obtained by edge detection as the image stabilization factor.

[0042] That is to say, by directly calculating the ratio of the number of pixels in the connected domain to the number of edge pixels obtained by edge detection, the image stabilization factor is obtained. The image stabilization factor is positively correlated with the number of pixels in the connected domain, and negatively correlated with the number of edge pixels obtained by edge detection. The larger the ratio of the number of pixels in the connected domain to the number of edge pixels obtained by edge detection, the more stable the motion state in the winding grayscale image is, and the smaller the motion blur interference is.

[0043] It should be noted that a positive correlation indicates that there is a same-direction change relationship between the independent variable and the dependent variable, that is, the larger the independent variable is, the larger the dependent variable is; a negative correlation indicates that there is an opposite-direction change relationship between the independent variable and the dependent variable, that is, the smaller the independent variable is, the larger the dependent variable is; the specific manifestations of the positive correlation and the negative correlation are determined by actual applications and are not particularly limited in this application.

[0044] Furthermore, in some embodiments of the present invention, the motion stability factor and the image stability factor are combined to screen out stable frame images from different frame winding grayscale images, including: calculating the product of the motion stability factor and the image stability factor, and normalizing the maximum and minimum values ​​to obtain a stability index; and taking the winding grayscale image whose stability index is greater than a preset stability threshold as a stable frame image.

[0045] Combined with the above analysis, the larger the motion stability factor, the farther the winding probe is from one of the endpoints, which means it is closer to the other endpoint, so its motion state is more consistent with the stable state; and the larger the value of the image stability factor, the more stable the motion state in the winding grayscale image, and the smaller the motion blur interference. Therefore, the product of the motion stability factor and the image stability factor can be directly calculated, and the maximum and minimum values ​​can be normalized to obtain the stability index.

[0046] Among them, the preset stability threshold is the threshold value of the stability index. In the embodiment of the present invention, the preset stability threshold can be specifically 0.75, for example. That is to say, the winding grayscale image with a stability index greater than 0.75 is used as a stable frame image.

[0047] S103: For a high-frequency image of any radius, gradient analysis is performed on the stable frame image and the high-frequency image of the same winding grayscale image, and the gradient distribution histogram of the stable frame image is determined to be the first histogram, and the gradient distribution histogram of the high-frequency image is determined to be the second histogram. Based on the difference in the gradient distribution structures between the first histogram and the second histogram, similarity parameters of the first histogram and the second histogram are determined.

[0048] The stable frame image represents the winding grayscale image that is less affected by motion obtained by dynamic blur analysis. That is, when the winding grayscale image has a stable frame image, it can be preliminarily indicated that it has stable characteristics. Therefore, by combining the gradient analysis of the frequency domain and the spatial domain, similar situations can be determined. The higher the similarity, the more corresponding the high-frequency information is to the spatial domain gradient, that is, the stronger the stability is.

[0049] The Sobel operator is used to obtain the gradient amplitude of each pixel in the stable frame image and the high-frequency image, and a normalized gradient distribution histogram is generated. The horizontal axis represents the gradient intensity and the vertical axis represents the frequency.

[0050] When the high-frequency image in the rotor winding process is deblurred (i.e., the low-frequency interference information is removed), it should be similar to the edge information, image texture, and local features of the stable frame image, and there will be several peaks with similar heights and positions in the gradient distribution histogram of the image. By calculating the performance similarity between the gradient distribution histograms of the stable frame image and the high-frequency image, the structural difference between the two gradient distribution histograms is obtained, and then the deblurring effect of the high-frequency image is judged.

[0051] Further, in some embodiments of the present invention, similarity parameters of the first histogram and the second histogram are determined based on the difference in gradient distribution structures between the first histogram and the second histogram, including: dividing the gradient intensity in the first histogram and the second histogram into the same interval to obtain corresponding gradient intervals in the first histogram and the second histogram; calculating the square value of the difference in frequency in the same gradient interval in the first histogram and the second histogram to obtain a first indicator; calculating the sum of the frequency in the same gradient interval in the first histogram and the second histogram as the second indicator; calculating the ratio of the first indicator to the second indicator, and normalizing the inverse of the ratio to the maximum and minimum values ​​as the interval similarity coefficient of the corresponding gradient interval; and taking the average of the interval similarity coefficients of all gradient intervals as the similarity parameter of the first histogram and the second histogram.

[0052] The gradient strengths in the two gradient distribution histograms are divided into the same number of intervals. For example, the gradient strengths of 1-3 are taken as one interval, the gradient strengths of 4-6 are taken as one interval, and so on, thereby respectively determining the corresponding gradient intervals in the first histogram and the second histogram.

[0053] The first histogram and the second histogram are similar in performance, mainly in the same gradient interval, the more similar, the smaller the structural difference. Therefore, the square value of the difference between the frequency in the same gradient interval in the first histogram and the second histogram is calculated to obtain the first index, and the sum of the frequency in the same gradient interval in the first histogram and the second histogram is calculated as the second index.

[0054] The larger the ratio of the first index to the second index, the greater the difference in frequency distribution within the same gradient interval, which means that the similarity between the first histogram and the second histogram in the corresponding gradient interval is lower. Therefore, the reciprocal of the ratio is normalized to the maximum and minimum values ​​to obtain the interval similarity coefficient of the gradient interval.

[0055] In the embodiment of the present invention, since a plurality of gradient intervals are obtained by division, all gradient intervals are integrated, and the mean values ​​of similarity coefficients of all intervals are calculated, thereby obtaining similarity parameters of the first histogram and the second histogram.

[0056] It should be noted that each radius corresponds to a high-frequency image, and the high-frequency image of each radius also corresponds to a similarity parameter.

[0057] S104: obtaining an optimal radius based on similar parameters, converting the high-frequency image under the optimal radius into a spatial domain to obtain a deblurred image, performing winding detection on the deblurred image, and determining a winding grayscale image with winding anomalies.

[0058] Furthermore, in some embodiments of the present invention, obtaining the optimal radius according to the screening of similar parameters includes: taking the radius at the maximum value of the similar parameters corresponding to all high-frequency images as the optimal radius.

[0059] Since the larger the value of the similarity parameter is, the less affected the corresponding high-frequency image is by motion blur, that is, the deblurring effect of the corresponding high-frequency image is stronger, the radius corresponding to the high-frequency image with the maximum value of the similarity parameter is taken as the optimal radius.

[0060] The high-frequency image under the optimal radius is converted into the spatial domain to obtain a deblurred image. The specific conversion method is inverse Fourier transform, which is a technology well known to those skilled in the art and will not be described in detail.

[0061] It should be noted that the high-frequency image corresponding to the optimal radius can be combined for deblurring, so as to further screen out a clearer and more reliable deblurred image. That is, under the optimal radius, the motion blur effect can be effectively screened out to obtain a clearer and more reliable deblurred image.

[0062] Furthermore, in some embodiments of the present invention, winding detection is performed on the deblurred image to determine the winding grayscale image with winding abnormalities, including: inputting the deblurred image into a pre-trained winding detection model, and outputting the winding abnormality inspection result of the winding grayscale image.

[0063] This scheme aims to determine a clearer and more reliable deblurred image. Therefore, winding detection can be performed on the deblurred image, specifically winding anomalies such as winding misalignment anomalies and uneven winding of coils. The winding detection model can be trained through multiple pre-annotated images to obtain a more reliable pre-trained winding detection model, and the deblurred image can be input into the pre-trained winding detection model to output the winding abnormality inspection result of the winding grayscale image.

[0064] Of course, in other embodiments of the present invention, winding detection may also be implemented by image analysis, and there is no limitation to this.

[0065] The present invention selects the center circle through the spectrum image, removes the low-frequency information affected by motion blur, retains the high-frequency information, and obtains high-frequency images of different radii; then, the stable frame image is determined according to the position of the winding probe, the number of edge pixels of the rotor, and the size of the area; the stable frame image and the high-frequency image are subjected to gradient analysis, the similarity parameters of the gradient feature are determined through the gradient distribution histogram, the optimal radius is obtained according to the similarity parameter screening, the high-frequency image under the optimal radius is converted into the spatial domain to obtain a deblurred image, the deblurred image is subjected to winding detection, and the winding grayscale image with winding abnormality is determined. The present invention can effectively analyze the winding process of the rotating rotor, and through the analysis of the characteristics of the image acquisition device itself and the analysis of the dynamic blur characteristics generated by the rotation of the rotor, the stable frame image can be accurately selected, and the deblurring process is performed using an adaptive and appropriate scale to obtain a clearer and more reliable deblurred image, and the winding detection is performed through the deblurred image, which avoids the interference caused by dynamic blur and improves the accuracy of the winding detection of the propulsion motor rotor.

[0066] The present invention also provides a propulsion motor rotor winding system, see Figure 4 , Figure 4 A structural diagram of a propulsion motor rotor winding system provided for an embodiment of the present invention, wherein the system 600 includes a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and executable on the processor 602, and when the processor 602 executes the computer program 603, the steps of a propulsion motor rotor winding method as described above are implemented.

[0067] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A propulsion motor rotor winding method, characterized in that: The method comprises: At different sampling times, a winding grayscale image of the motor side winding probe during the rotor winding process is obtained, the winding grayscale image is converted into a spectrum image in the frequency domain, different radii are used to select the center circle, and high-frequency information of the center circle area is filtered from the spectrum image to obtain high-frequency images at different radii; According to the position of the winding probe in the winding grayscale image, a motion stability factor is determined, edge detection and image recognition are performed on the winding grayscale image to determine the image connected domain belonging to the rotor, and an image stability factor is determined according to the size of the image connected domain and the number of edge pixels; the motion stability factor and the image stability factor are combined to screen out stable frame images from different frames of winding grayscale images; For a high-frequency image of any radius, a gradient analysis is performed on the stable frame image and the high-frequency image of the same winding grayscale image, and the gradient distribution histogram of the stable frame image is determined as the first histogram, and the gradient distribution histogram of the high-frequency image is determined as the second histogram. According to the difference in the gradient distribution structures between the first histogram and the second histogram, the similarity parameters of the first histogram and the second histogram are determined; An optimal radius is obtained by screening according to the similarity parameters, a high-frequency image under the optimal radius is converted into a spatial domain to obtain a deblurred image, winding detection is performed on the deblurred image, and a winding grayscale image with winding abnormalities is determined.

2. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The method of selecting the central circle using different radii, filtering high-frequency information of the central circle area from the spectrum image, and obtaining high-frequency images under different radii includes: The spectrum image is cut using a straight line passing through the center of the image and parallel to both sides, and the four corners of the spectrum image after cutting are assembled to a central point to obtain an image to be selected with low-frequency information in the center; Taking the center point of the image to be selected as the center of the circle, different radii are used to determine the center circle of the image to be selected, and the center circle part is deleted to obtain high-frequency images under different radii.

3. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The step of determining the motion stability factor according to the position of the wire winding probe in the wire winding grayscale image comprises: Determine the position of the wire winding probe in all frame wire winding grayscale images, obtain the motion trajectory of the wire winding probe, and obtain two endpoints of the motion trajectory; The Euclidean distances between the position of the winding probe and the two end points in any frame of the winding grayscale image are obtained, and the maximum value of the Euclidean distances is used as the motion stability factor of the corresponding frame of the winding grayscale image.

4. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The performing edge detection and image recognition on the winding grayscale image to determine the image connected domain belonging to the rotor includes: Performing canny edge detection on the winding grayscale image to obtain edge pixel points, wherein the edge pixel points constitute an initial connected domain; Image recognition is performed on the initial connected domain, and the initial connected domain belonging to the rotor is identified as the image connected domain.

5. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The determining of the image stabilization factor according to the size of the image connected domain and the number of edge pixels comprises: The ratio of the number of pixels in the connected domain to the number of edge pixels obtained by edge detection is calculated as an image stabilization factor.

6. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The method combines the motion stabilization factor and the image stabilization factor to screen out the stable frame images from the winding grayscale images of different frames, including: Calculating the product of the motion stability factor and the image stability factor, and normalizing the maximum and minimum values ​​to obtain a stability index; The winding grayscale image whose stability index is greater than a preset stability threshold is used as a stable frame image.

7. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: Determining similar parameters of the first histogram and the second histogram according to the difference in the gradient distribution structures of the first histogram and the second histogram includes: Dividing the gradient strengths in the first histogram and the second histogram into the same intervals to obtain corresponding gradient intervals in the first histogram and the second histogram; Calculate the square value of the difference between the frequencies in the same gradient interval in the first histogram and the second histogram to obtain a first index; Calculate the sum of the frequencies in the same gradient interval in the first histogram and the second histogram as a second indicator; Calculate the ratio of the first index to the second index, and perform maximum and minimum normalization processing on the inverse of the ratio as the interval similarity coefficient of the corresponding gradient interval; The mean of the interval similarity coefficients of all gradient intervals is taken as the similarity parameter of the first histogram and the second histogram.

8. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: The optimal radius is obtained by screening according to the similar parameters, including: The radius at the maximum value of similar parameters corresponding to all high-frequency images is taken as the optimal radius.

9. A propulsion motor rotor winding method as claimed in claim 1, characterized in that: Performing winding detection on the deblurred image to determine a winding grayscale image with abnormal winding includes: The deblurred image is input into a pre-trained winding detection model, and a winding abnormality inspection result of the winding grayscale image is output.

10. A propulsion motor rotor winding system, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a propulsion motor rotor winding method as described in any one of claims 1 to 9 are implemented.

Images