An abnormal processing data identification method, device, equipment and medium

Abstract

This application discloses a method, apparatus, equipment, and medium for identifying abnormal machining data, belonging to the field of CNC machine tool machining and inspection technology, aiming to solve the technical problem that existing technologies cannot accurately identify abnormal working conditions that occur during the machining of aerospace parts. The method includes: acquiring periodic vibration data of the cutting teeth during the machining process of the aerospace part; wherein, the periodic vibration data of the cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the machining process of the aerospace part; obtaining a polar coordinate image based on the periodic vibration data of the cutting teeth; obtaining the principal direction and the cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image; performing adaptive region segmentation and extraction processing on the polar coordinate image based on the principal direction and the cross-orthogonal unit direction to obtain a vibration discrete point image; and identifying abnormal machining data based on the vibration discrete point image.

Description

Technical Field

[0001] This application relates to the field of CNC machine tool processing and testing technology, and in particular to a method, apparatus, equipment and medium for identifying abnormal processing data. Background Technology

[0002] Aircraft structural component manufacturing is characterized by small batches and multiple categories. The components are also characterized by complex features, a variety of cutting tools required during processing, variable processing trajectories, and significant influence from complex time-varying conditions. If vibration data signals obtained from sensors are directly used for time-frequency domain feature analysis for monitoring, the accuracy is often low, with many false alarms and missed alarms. This cannot meet the monitoring requirements for abnormal conditions such as tooth breakage and wear during the processing of aircraft structural components.

[0003] Therefore, there is an urgent need for a method to identify abnormal processing data that occurs during the manufacturing process of aerospace parts. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, equipment, and medium for identifying abnormal processing data, aiming to solve the technical problem that existing technologies cannot accurately identify abnormal working conditions that occur during the processing of aerospace parts.

[0005] To address the aforementioned technical problems, this application proposes a method for identifying abnormal processing data, comprising the following steps:

[0006] Acquire periodic vibration data of cutting teeth during the machining process of aerospace parts; wherein, the periodic vibration data of cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the machining process of aerospace parts;

[0007] Based on the periodic vibration data of the cutting teeth, a polar coordinate image is obtained;

[0008] Based on the polar coordinate image, obtain the principal direction and the cross-orthogonal unit direction of the polar coordinate image;

[0009] Based on the principal direction of the polar coordinate image and the cross-orthogonal unit direction, the polar coordinate image is subjected to region adaptive segmentation and extraction processing to obtain a vibration discrete point image.

[0010] Based on the vibration discrete point image, abnormal processing data is identified.

[0011] As some optional embodiments of this application, obtaining a polar coordinate image based on the periodic vibration data of the cutter teeth includes:

[0012] Based on the periodic vibration data of the cutting teeth, a polar coordinate image was obtained by plotting using Python.

[0013] As some optional embodiments of this application, obtaining the principal direction and cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image includes:

[0014] Multiple polar coordinate images generated from vibration signal data at different times are normalized to obtain multiple polar coordinate images of the same size, namely dst_image images;

[0015] Outlier noise points in the multiple polar coordinate images of the same size are removed to obtain multiple pro_image images;

[0016] The pro_image image is processed into grayscale to obtain the pro_image1 image;

[0017] Based on the pro_image1 image, the principal direction and cross-orthogonal unit direction of the polar coordinate image are obtained.

[0018] As some optional embodiments of this application, the outlier noise removal process in the multiple polar coordinate images of the same size satisfies the following relationship:

[0019]

[0020] Where point(x,y) and other_point(x,y) represent any point in the image; min Length represents the length value represented by the point in the image that has the closest Euclidean distance to point(x,y); dst_image represents the image to be processed; if represents the conditional statement; gray point(x,y) This represents the grayscale value at point(x, y) of the single-channel image after grayscale processing of the image dst_image; discard indicates that points that meet the if condition are discarded, i.e., the grayscale value is reduced to zero.

[0021] As some optional embodiments of this application, obtaining the principal direction and cross-orthogonal unit direction of the polar coordinate image based on the pro_image1 image includes:

[0022] Based on the pro_image1 image, obtain the longest target circle radius value of the pro_image1 image;

[0023] Based on the pro_image1 image, the target region is obtained, and after removing the effective feature pixels within the target region, the main direction of the polar coordinate image is obtained.

[0024] Based on the principal direction of the polar coordinate image, the cross-orthogonal unit direction of the polar coordinate image is obtained.

[0025] As some optional embodiments of this application, obtaining the longest target circle radius value of the pro_image1 image based on the pro_image1 image includes:

[0026] The image center of the pro_image1 image is taken as the starting reference point; wherein, the coordinates of the starting reference point are denoted as (cols). pro_image , rows pro_image );

[0027] Based on the aforementioned starting reference point, a length numerical statistics array is obtained; wherein, the array length of the length numerical statistics array is equal to cols. pro_image Furthermore, the initial value of all subscript arrays in the array is represented by number1, and all elements in the array are integers; the length numerical statistics array satisfies the following relationship: int array[cols pro_image ] = {number1};

[0028] Using the smallest positive integer in the length numerical statistics array as the starting point, the pixels on the circumference of the pro_image1 image are counted. The positive integer corresponding to the pixel in the pro_image1 image with a gray value equal to number1 is recorded as number2. Based on number2, the rotation center is obtained. The gray value in the pro_image1 image corresponding to the rotation center position is determined. If the gray value is different from the gray value of the background, the value corresponding to the subscript of number2 is incremented by 1.

[0029] Based on the rotation center, the pro_image1 image is rotated to obtain the pro_image2 image; based on the pro_image2 image, the grayscale value of the pro_image2 image at the rotation center is obtained; the grayscale value in the pro_image2 image corresponding to the rotation center position is determined, and if the grayscale value is different from the grayscale value of the background, the value corresponding to the subscript number2 is incremented by 1; wherein, the rotation angle during the rotation processing is any angle between 0° and 360°, and after each rotation processing, the value corresponding to the subscript number2 is obtained;

[0030] The maximum value corresponding to the multiple number2 subscripts is obtained by comparison, and the maximum value is used as the longest target circle radius value of the pro_image1 image.

[0031] As some optional embodiments of this application, the step of obtaining the target region based on the pro_image1 image, removing the effective feature pixels within the target region, and then obtaining the main direction of the polar coordinate image includes:

[0032] Based on the pro_image1 image, an image_new image is obtained; wherein the size and number of channels of the image_new image are the same as those of the pro_image1 image;

[0033] Using the geometric center of the image_new image as the center, draw a circle in the image_new image based on the longest target circle radius value to obtain the target region; remove the effective feature pixels in the area covered by the target region to obtain the pro_image3 image;

[0034] Using the geometric center of the pro_image3 image as a reference initial point, along N times The number of pixels on the ray with different gray values ​​from the background is counted in each angle direction to obtain the number of target pixels; wherein, the starting point of the rows ray is the geometric center of the pro_image3 image, and the length is pro_image3.rows; where .rows represents the number of rows in the pro_image3 image, and the number of rows in the image is fixed and unique; the N times This refers to dividing 360° into N equal parts. times Equally spaced angles N angles ;

[0035] The number of target pixels is used as the length value of the corresponding ray to obtain multiple rays of different lengths; the length values ​​of the multiple rays of different lengths are compared to obtain the target ray with the largest length value, and the direction of the target ray is used as the main direction of the polar coordinate image.

[0036] As some optional embodiments of this application, obtaining the cross-orthogonal unit direction of the polar coordinate image based on the principal direction of the polar coordinate image includes:

[0037] Acquire the number of cutting teeth and vibration signal data of adjacent cutting teeth during the machining process of aerospace parts;

[0038] Based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the main direction of the polar coordinate image, the angle value of the adjacent cutting teeth is obtained; the angle value includes a first angle value and a second angle value.

[0039] Based on the angle values ​​of the adjacent blades, the cross-orthogonal unit direction of the polar coordinate image is obtained.

[0040] As some optional embodiments of this application, the angle value of the adjacent cutting teeth is obtained based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the principal direction of the polar coordinate image; the angle value includes a first angle value and a second angle value, including:

[0041] If the number of cutting teeth in the machining process of the aerospace part is 2, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 180°, that is, the first angle value and the second angle value of the adjacent cutting teeth are both α+180°.

[0042] If the number of cutting teeth in the machining process of the aerospace part is 3, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 120°, that is, the first angle value and the second angle value of the adjacent cutting teeth are α+120° and α-120° respectively.

[0043] If the number of cutting teeth in the machining process of the aerospace part is 4, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 90°, that is, the first angle value and the second angle value of the adjacent cutting teeth are α+90° and α-90° respectively.

[0044] If the number of cutting teeth in the machining process of the aerospace part is N n Then the angle α between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is 360° / N. n That is, the first angle value and the second angle value of the adjacent cutting teeth are α+360° / N respectively. n and α-360° / N n .

[0045] As some optional embodiments of this application, the step of performing region adaptive segmentation and extraction processing on the polar coordinate image based on the principal direction of the polar coordinate image and the cross-shaped orthogonal unit direction to obtain a vibration discrete point image includes:

[0046] Based on the image_new, obtain a single-channel grayscale image of the same scale. gray ;

[0047] Based on the principal direction of the polar coordinate image and the orthogonal unit direction of the cross, segmentation rays are obtained; based on the segmentation rays, the image is... gray The image is segmented to obtain the image. gray Image segmentation;

[0048] Based on the cutting tool tooth data used in the machining of aerospace parts, the image grayAfter segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract discrete vibration point images.

[0049] As some optional embodiments of this application, the image is based on segmentation rays. gray The image is segmented to obtain the image. gray Image segmentation, including:

[0050] Based on the segmentation ray, the endpoints of the segmentation ray are set on the image. gray The boundary position of the image, the starting point of the segmentation ray is set on the image. gray The location of the center of the circle in the image.

[0051] As some optional embodiments of this application, the image is based on the cutting tool tooth data used in the machining process of aerospace parts. gray After segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract discrete vibration point images, including:

[0052] Based on the cutting tool tooth data N used in the machining of aerospace parts n The image gray The segmented image is rotated 360° clockwise by (2*N) n After grayscale difference, different strategies are applied to the image. gray The segmented image is processed to extract discrete vibration point images.

[0053] As some optional implementations of this application, the different strategies based on grayscale differences for image gray The segmented image is processed to extract discrete vibration point images, including:

[0054] Keep the image gray The segmented image is in .PNG lossless compressed format, and the grayscale values ​​of each channel of the pixels that make up each ray are kept consistent. gray ∈[0,255], background grayscale is B gray ∈[0,255] and B gray ≠N gray ;

[0055] Obtain the image gray Segment the grayscale value of each pixel in the image, if its grayscale value is N gray Then, taking this pixel as the initial point, the gray values ​​in its 4-neighborhood are also N. grayReassign grayscale values ​​to the pixels using random(R=N) new G=N new B=N new The initial grayscale values ​​are assigned in the same way.

[0056] After processing the images in sequence gray Segment all pixels in an image such that the gray value of each pixel is not equal to N. gray Get the first image gray Image segmentation;

[0057] Get the first image gray The segmented image contains grayscale B gray ∈[0,255] and B gray ≠N gray The number of grayscale categories is used to obtain the coordinate data (i.e., the image) of the corresponding region based on the grayscale value of each category. gray The unique pixel coordinates specified by the row and column are used to generate N based on the coordinates. n Aspect image;

[0058] The N n The amplitude images are integrated to obtain a discrete point image of vibration.

[0059] As some optional embodiments of this application, the N n The amplitude images are integrated to obtain a discrete point image of vibration, including:

[0060] The N n The sub-images are integrated according to their original positional relationships to obtain the final image;

[0061] The resulting image is subjected to quantitative analysis to obtain a discrete vibration point image.

[0062] To address the aforementioned technical problems, embodiments of this application also provide: a device for identifying abnormal processing data, comprising:

[0063] The first acquisition module is used to acquire the periodic vibration data of the cutting teeth during the processing of the aircraft parts; wherein, the periodic vibration data of the cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the processing of the aircraft parts;

[0064] The second acquisition module is used to obtain a polar coordinate image based on the periodic vibration data of the cutting teeth;

[0065] The third acquisition module is used to obtain the principal direction and cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image;

[0066] The fourth acquisition module is used to perform region adaptive segmentation and extraction processing on the polar coordinate image based on the main direction of the polar coordinate image and the cross orthogonal unit direction to obtain a vibration discrete point image.

[0067] The identification module is used to identify abnormal processing data based on the vibration discrete point image.

[0068] To address the aforementioned technical problems, this application also proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0069] To address the aforementioned technical problems, this application also proposes a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the method described above.

[0070] Existing technologies for monitoring processing data, whether using threshold-based judgment methods or learning-based approaches, all involve transforming high-frequency vibration signals. Parameters such as mean, variance, and entropy are central to the work, and monitoring is achieved based on designed judgment criteria. However, vibration signal data is characterized by high frequency and significant variations in values ​​across local time domains. Therefore, existing technologies cannot adaptively analyze this variable data.

[0071] The applicant's research found that images generated based on vibration signals consist of several discrete numbers, each data point having a certain correspondence with a cutting tooth. However, intuitive observation of these discrete points cannot accurately determine the correspondence between these data points and the cutting teeth on the tool. Therefore, images generated based on raw data are not conducive to displaying the data in a concrete manner, nor are they conducive to qualitative analysis of the wear of the cutting teeth or the presence of abnormalities such as broken or missing teeth. To facilitate the online detection and identification of abnormal signals in tool processing, and for further detailed analysis of tool tooth vibration signals, this application proposes a method for identifying abnormal processing data, comprising the following steps: acquiring periodic vibration data of tool teeth during the processing of aerospace parts; wherein, the periodic vibration data of tool teeth refers to the vibration signal data generated by the tool teeth at different times during the processing of the aerospace parts; obtaining a polar coordinate image based on the periodic vibration data of tool teeth; obtaining the principal direction and the cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image; performing adaptive region segmentation and extraction processing on the polar coordinate image based on the principal direction and the cross-orthogonal unit direction to obtain a vibration discrete point image; and identifying the abnormal processing data based on the vibration discrete point image. Taking an N-tooth cutting tool as the research object, the machining image corresponding to the N-tooth cutting tool is obtained based on the polar coordinate vibration signal data generation method. Then, based on the obtained image, the data features are extracted and quantified according to the design method to facilitate quantitative analysis of features and graphical display. Furthermore, the unique mapping and correspondence between the discrete points of the vibration signal and the cutting tool is realized. The identified feature areas can be further used to analyze the tool wear, thereby facilitating the intuitive and rapid judgment of whether the tool has abnormal working conditions such as broken teeth or broken tools. Attached Figure Description

[0072] Figure 1 This is a flowchart illustrating the method for identifying abnormal processing data according to an embodiment of this application;

[0073] Figure 2 This is a schematic diagram of a polar coordinate image related to an embodiment of this application;

[0074] Figure 3 This is a schematic diagram of the pro_image3 image involved in an embodiment of this application;

[0075] Figure 4 This is a schematic diagram of the main direction of the polar coordinate image involved in the embodiments of this application;

[0076] Figure 5 This is a schematic diagram of the cross-shaped orthogonal unit direction of the polar coordinate image involved in the embodiments of this application;

[0077] Figure 6 The image is related to the embodiments of this application. graySchematic diagram of image segmentation;

[0078] Figure 7 N is the embodiment of this application. n A schematic diagram of the image;

[0079] Figure 8 This is a schematic diagram of a discrete vibration point image related to an embodiment of this application. Detailed Implementation

[0080] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0081] Aircraft structural component manufacturing is characterized by small batches and multiple categories. The components are also characterized by complex features, a variety of cutting tools required during processing, variable processing trajectories, and significant influence from complex time-varying working conditions. If vibration data signals obtained from sensors are directly used for time-frequency domain feature analysis for monitoring, the accuracy is often low, with many false alarms and missed alarms. This cannot meet the monitoring requirements for abnormalities such as tooth breakage and wear during the processing of aircraft structural components.

[0082] The inventors' analysis revealed that existing vibration signal methods, whether based on threshold settings or learning, all involve transforming high-frequency vibration signals. Parameters such as mean, variance, and entropy are central to the process, and monitoring is achieved based on designed judgment criteria. However, vibration signal data is characterized by high frequency and significant variations in values ​​across local time domains. Therefore, existing methods cannot adaptively analyze this variable data.

[0083] Furthermore, images generated based on vibration signals are composed of several discrete numbers, each data point having a certain correspondence with a cutting tooth. However, intuitive observation of these discrete points cannot accurately determine the correspondence between these data points and the cutting teeth on the tool. Therefore, images generated based on raw data are not conducive to displaying the data in a concrete manner, nor are they conducive to qualitative analysis of the wear of the cutting teeth or the existence of abnormalities such as broken or missing teeth. To address the online detection and identification of abnormal signals in tool processing, and to further refine the analysis of cutting tooth vibration signals, this application proposes a method for identifying abnormal processing data, including the following steps: acquiring periodic vibration data of cutting teeth during the processing of aerospace parts; wherein, the periodic vibration data of cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the processing of aerospace parts; obtaining a polar coordinate image based on the periodic vibration data of cutting teeth; obtaining the principal direction and the cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image; performing adaptive region segmentation and extraction processing on the polar coordinate image based on the principal direction and the cross-orthogonal unit direction to obtain a vibration discrete point image; and identifying the abnormal processing data based on the vibration discrete point image. Taking an N-tooth cutting tool as the research object, the machining image corresponding to the N-tooth cutting tool is obtained based on the polar coordinate vibration signal data generation method. Then, based on the obtained image, the data features are extracted and quantified according to the design method to facilitate the quantitative analysis of features and the graphical display.

[0084] This application embodiment also provides an electronic device with a hardware operating environment, which may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0085] Those skilled in the art will understand that the above content does not constitute a limitation on the electronic device, and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, the memory 1005, as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and electronic programs. In a specific embodiment, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the electronic device of this application can be disposed in the electronic device, and the electronic device calls the abnormal processing data identification device stored in the memory 1005 through the processor 1001, and executes the abnormal processing data identification method provided in the embodiments of this application.

[0086] Based on this, such as Figure 1 As shown in the figure, this application proposes a method for identifying abnormal processing data, including the following steps:

[0087] Step S10: Obtain periodic vibration data of the cutting teeth during the machining process of the aircraft part; wherein, the periodic vibration data of the cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the machining process of the aircraft part.

[0088] Step S20: Obtain a polar coordinate image based on the periodic vibration data of the cutting teeth.

[0089] In practical applications, obtaining a polar coordinate image based on the periodic vibration data of the cutting teeth includes: plotting the image using Python language based on the periodic vibration data of the cutting teeth to obtain a polar coordinate image. The polar coordinate image is as follows: Figure 2 As shown.

[0090] It should be noted that the vibration data refers to the expression of characteristic signals during tool machining. Therefore, images generated based on periodic vibration signals can also be called characteristic data. Since the rotational speed and number of teeth of the tool are constants during machining, vibration signal data points at the same time interval S (S represents any size time interval) have a unique correspondence with the corresponding cutting tooth (that is, no matter how the time interval changes, the relative distribution of points corresponding to each cutting tooth in the plotted vibration data image will not change). In other words, vibration data with the same time interval represents the vibration amount corresponding to the same cutting tooth.

[0091] Step S30: Based on the polar coordinate image, obtain the principal direction and cross-orthogonal unit direction of the polar coordinate image.

[0092] In practical applications, obtaining the principal direction and the cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image includes:

[0093] Step S31: Normalize the multiple polar coordinate images generated from vibration signal data at different times to obtain multiple polar coordinate images of the same size, namely dst_image images.

[0094] Specifically, the above steps may include: normalizing the scale of the generated multiple polar coordinate images so that the images generated by the vibration signals at different times have the same length and width values, and setting the width of the uniform scale to numb. cols The length is numb rows The processed images are uniformly represented using dst_image.

[0095] Step S32: Remove outlier noise from the multiple polar coordinate images of the same size to obtain multiple pro_image images.

[0096] Specifically, the above steps may include: The acquired dst_image image contains some isolated outliers, which significantly affect the subsequent identification and display of leaf lobes; therefore, these outliers need to be removed. The outlier removal process for the multiple polar coordinate images of the same size satisfies the following relationship:

[0097]

[0098] Where point(x,y) and other_point(x,y) represent any point in the image; min Length represents the length value represented by the point in the image that has the closest Euclidean distance to point(x,y); dst_image represents the image being processed; if represents the conditional statement; gray point(x,y) This represents the grayscale value at point(x, y) of the single-channel image after grayscale processing of the image dst_image; discard indicates that points that meet the if condition are discarded, i.e., the grayscale value is reduced to zero.

[0099] After removing isolated outliers from the image based on the above relationship, the resulting image is named pro_image.

[0100] Step S33: Perform grayscale processing on the pro_image image to obtain the pro_image1 image.

[0101] Specifically, the above steps may include: processing the grayscale value of each channel of each pixel in the pro_image image to the same value, extracting the grayscale value of each channel of each pixel, comparing the grayscale values, and recording the maximum value (max).grayscale The values ​​in the remaining channels are transformed based on the maximum value, and the resulting multi-channel grayscale image, namely the pro_image1 image, is obtained after processing.

[0102] Step S34: Based on the pro_image1 image, obtain the principal direction and cross-orthogonal unit direction of the polar coordinate image.

[0103] In practical applications, obtaining the principal direction and cross-orthogonal unit direction of the polar coordinate image based on the pro_image1 image includes:

[0104] Step S341: Based on the pro_image1 image, obtain the longest target circle radius value of the pro_image1 image.

[0105] Specifically, the above steps may include: taking the image center of the pro_image1 image as the starting reference point; wherein, the coordinates of the starting reference point are denoted as (cols pro_image , rows pro_image );

[0106] Based on the aforementioned starting reference point, a length numerical statistics array is obtained; wherein, the array length of the length numerical statistics array is equal to cols. pro_image Furthermore, the initial value of all subscript arrays in the array is represented by number1, and all elements in the array are integers; the length numerical statistics array satisfies the following relationship: int array[cols pro_image ] = {number1};

[0107] Using the smallest positive integer in the length numerical statistics array as the starting point, the pixels on the circumference of the pro_image1 image are counted, and the positive integer corresponding to the pixel satisfying the gray value (the pixel in the pro_image1 image whose gray value is equal to number1) is recorded as number2; based on number2, the rotation center is obtained; the gray value in the pro_image1 image corresponding to the rotation center position is determined, and if the gray value is different from the background gray value, the value corresponding to the subscript of number2 is incremented by 1; wherein, the position coordinates of the rotation center can be represented as point(rows) pro_image ,cols pro_image +number2);

[0108] Based on the rotation center, the pro_image1 image is rotated to obtain the pro_image2 image; based on the pro_image2 image, the grayscale value of the pro_image2 image at the rotation center is obtained; the grayscale value in the pro_image2 image corresponding to the rotation center position is determined, and if the grayscale value is different from the grayscale value of the background, the value corresponding to the subscript number2 is incremented by 1; wherein, the rotation angle during the rotation processing is any angle between 0° and 360°, and after each rotation processing, the value corresponding to the subscript number2 is obtained;

[0109] The maximum value corresponding to each of the multiple number2 indices is obtained by comparison, and this maximum value is used as the radius of the longest target circle in the pro_image1 image. When comparing the values ​​at the multiple number2 indices, the value corresponding to each index in the value array can be read first, and then compared pairwise. The index corresponding to the maximum value max array[label] is taken as the radius value label of the circle. The array indices ∈ [0, cols...]. pro_image ], and the unit is px (px is the unit corresponding to a pixel, and 1 pixel can represent 1px).

[0110] Step S342: Based on the pro_image1 image, obtain the target region, remove the effective feature pixels in the target region, and then obtain the main direction of the polar coordinate image;

[0111] Specifically, the above steps may include: obtaining an image_new image based on the pro_image1 image; wherein the size and number of channels of the image_new image are the same as those of the pro_image1 image;

[0112] Using the geometric center of the image_new image as the center, a circle is drawn in the image_new image based on the longest target circle radius value to obtain the target region; the effective feature pixels in the area covered by the target region are removed to obtain the pro_image3 image; wherein, a schematic diagram of the pro_image3 image is shown below. Figure 3 As shown;

[0113] Using the geometric center of the pro_image3 image as a reference initial point, along N timesThe number of pixels on the ray with different gray values ​​from the background is counted in each angle direction to obtain the number of target pixels; wherein, the starting point of the rows ray is the geometric center of the pro_image3 image, and the length is pro_image3.rows, where .rows represents the number of rows in the pro_image3 image, and the number of rows in the image is fixed and unique; the N times This refers to dividing 360° into N equal parts. times Equally spaced angles N angles ;

[0114] The number of target pixels is used as the length value of the corresponding ray to obtain multiple rays of different lengths; the length values ​​of the multiple rays of different lengths are compared to obtain the target ray with the largest length value, and the direction of the target ray is used as the main direction of the polar coordinate image; wherein, a schematic diagram of the main direction of the polar coordinate image is shown below. Figure 4 As shown.

[0115] Step S343: Based on the main direction of the polar coordinate image, obtain the cross-orthogonal unit direction of the polar coordinate image.

[0116] Specifically, the above steps may include: acquiring the number of cutting teeth and vibration signal data of adjacent cutting teeth during the machining process of the aerospace parts;

[0117] Based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the main direction of the polar coordinate image, the angle value of the adjacent cutting teeth is obtained; the angle value includes a first angle value and a second angle value.

[0118] Based on the angle values ​​of the adjacent blades, the cross-orthogonal unit direction of the polar coordinate image is obtained.

[0119] More specifically, the angle value of the adjacent cutting teeth is obtained based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the principal direction of the polar coordinate image; the angle value includes a first angle value and a second angle value, including:

[0120] If the number of cutting teeth in the machining process of the aerospace part is 2, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 180°, that is, the first angle value and the second angle value of the adjacent cutting teeth are both α+180°.

[0121] If the number of cutting teeth in the machining process of the aerospace part is 3, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 120°, that is, the first angle value and the second angle value of the adjacent cutting teeth are α+120° and α-120° respectively.

[0122] If the number of cutting teeth in the machining process of the aerospace part is 4, then the angle α between the vibration signal data of the adjacent cutting teeth and the main direction of the polar coordinate image is 90°, that is, the first angle value and the second angle value of the adjacent cutting teeth are α+90° and α-90° respectively.

[0123] If the number of cutting teeth in the machining process of the aerospace part is N n Then the angle α between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is 360° / N. n That is, the first angle value and the second angle value of the adjacent cutting teeth are α+360° / N respectively. n and α-360° / N n .

[0124] The schematic diagram of the cross-shaped unit direction of the polar coordinate image is shown below. Figure 5 As shown.

[0125] Step S40: Based on the main direction of the polar coordinate image and the cross-shaped orthogonal unit direction, perform region adaptive segmentation and extraction processing on the polar coordinate image to obtain a vibration discrete point image.

[0126] In practical applications, the process of performing adaptive region segmentation and extraction on the polar coordinate image based on the principal direction and the orthogonal unit direction to obtain a vibration discrete point image includes:

[0127] Step S41: Based on the image_new image, obtain a single-channel grayscale image of the same scale. gray .

[0128] Step S42: Based on the principal direction of the polar coordinate image and the cross-shaped unit direction, obtain the segmentation ray; based on the segmentation ray, divide the image... gray The image is segmented to obtain the image. gray Segment the image.

[0129] Specifically, the image is based on segmentation rays. gray The image is segmented to obtain the image. gray Segmenting an image, including: setting the endpoints of the segmentation rays on the image based on segmentation rays. gray The boundary position of the image, the starting point of the segmentation ray is set on the image. gray The center position of the image; that is, the segmentation ray will... gray The image is divided into N n share.

[0130] Step S43: Based on the cutting tool tooth data used in the machining process of aerospace parts, the image is... gray After segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract discrete vibration point images.

[0131] Specifically, the image is based on the cutting tool tooth data used in the machining of aerospace parts. gray After segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract vibration discrete point images, including: data N based on the cutting tool teeth used in the machining of aerospace parts. n The image gray The segmented image is rotated 360° clockwise by (2*N) n After grayscale difference, different strategies are applied to the image. gray The image is segmented and processed to obtain a discrete vibration point image. It should be noted that the image size remains unchanged during rotation, and the endpoints of the rays remain at the image boundaries, ensuring that the regions segmented by each ray maintain a distinct relationship, i.e., there is no spatial pixel adjacency. The image... gray Image segmentation diagram as shown Figure 6 As shown.

[0132] It should be noted that the different strategies based on grayscale differences applied to the image... gray The segmented image is processed to extract discrete vibration point images, including:

[0133] Keep the image gray The segmented image is in .PNG lossless compressed format, and the grayscale values ​​of each channel of the pixels that make up each ray are kept consistent. gray ∈[0,255], background grayscale is B gray ∈[0,255] and B gray ≠N gray ;

[0134] Obtain the image gray Segment the grayscale value of each pixel in the image, if its grayscale value is N gray Then, taking this pixel as the initial point, the gray values ​​in its 4-neighborhood are also N. gray Reassign grayscale values ​​to the pixels using random(R=N) new G=N new B=N new The initial grayscale values ​​are assigned in the same way.

[0135] After processing the images in sequence gray Segment all pixels in an image such that the gray value of each pixel is not equal to N. gray Get the first image gray Image segmentation;

[0136] Get the first image gray The segmented image contains grayscale B gray ∈[0,255] and B gray ≠N gray The number of grayscale categories is used to obtain the coordinate data (i.e., the image) of the corresponding region based on the grayscale value of each category. gray The unique pixel coordinates specified by the row and column are used to generate N based on the coordinates. n A sub-image; wherein, the N n The sub-images can be denoted as: image1, image2, ..., image num_all The N n A schematic diagram of the image is shown below. Figure 7 As shown.

[0137] The N n The amplitude images are integrated to obtain a discrete point image of vibration.

[0138] Specifically, the N n The amplitude images are integrated to obtain a discrete point image of vibration, including:

[0139] The N n The sub-images are integrated according to their original positional relationships to obtain a result image; the result image is then subjected to quantitative analysis to obtain a vibration discrete point image; the vibration discrete point image is as follows: Figure 8 As shown.

[0140] More specifically, the grayscale point furthest from the geometric center of the image is calculated and identified. Based on this point, the outermost points are connected sequentially to form a closed region that meets certain characteristics: the angle between each line segment of the closed region is greater than or equal to 90°, and the area of ​​the closed region formed by the line segments is maximized. (This step refers to the process of acquiring the discrete vibration point image.)

[0141] By N n The feature images are stitched together according to their original positional relationships in the image (representing image pro_image3) to obtain the vibration discrete point image, i.e., result. image Image; the result imageThe image represents the final recognition result. Based on this result, further quantitative analysis of the feature data can be performed, and the data for different cutting teeth can be displayed intuitively, facilitating real-time online identification of anomalies. A cyclical processing method can be used to process the images generated from each vibration data point in real-time online.

[0142] Step S50: Identify abnormal processing data based on the vibration discrete point image.

[0143] It should be noted that the identification method described in this application can be implemented using a program based on a 64-bit Windows 7 system with an Intel(R) Xeon(R) W-2223 3.60GHz processor, 32GB of RAM, a frequency of 3200MHz, and a hard disk capacity of 256GB. The software development platform is based on Visual Studio 2019, the programming language is C++, the corresponding discrete point image of the raw tool signal data is drawn using Python, and the corresponding image processing library is OpenCV 4.5.2, based on the Release x64 platform.

[0144] As can be seen, the embodiments of this application represent discrete single vibration data at different time points in a centralized graphical manner, which improves the ability to identify abnormal vibration signals during processing. Based on this result, the feature data is further quantitatively analyzed, and the data of different cutting teeth are displayed intuitively, which is conducive to real-time online judgment of abnormal situations by humans, reduces the difficulty of identifying abnormal data, improves the accuracy of abnormal identification, and ensures the processing quality of aerospace structural parts. The identified feature areas can be further used to analyze tool wear, which is conducive to intuitive and quick judgment of whether the tool has broken teeth, broken tools, etc. At the same time, it provides a guiding reference method for the identification of vibration signals of different cutting teeth.

[0145] To address the aforementioned technical problems, this application also proposes: a device for identifying abnormal processing data, comprising:

[0146] The first acquisition module is used to acquire the periodic vibration data of the cutting teeth during the processing of the aircraft parts; wherein, the periodic vibration data of the cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the processing of the aircraft parts;

[0147] The second acquisition module is used to obtain a polar coordinate image based on the periodic vibration data of the cutting teeth;

[0148] The third acquisition module is used to obtain the principal direction and cross-orthogonal unit direction of the polar coordinate image based on the polar coordinate image;

[0149] The fourth acquisition module is used to perform region adaptive segmentation and extraction processing on the polar coordinate image based on the main direction of the polar coordinate image and the cross orthogonal unit direction to obtain a vibration discrete point image.

[0150] The identification module is used to identify abnormal processing data based on the vibration discrete point image.

[0151] It should be noted that each module in the abnormal processing data identification device in this embodiment corresponds one-to-one with each step in the abnormal processing data identification method in the aforementioned embodiment. Therefore, the specific implementation method and the technical effects achieved in this embodiment can be referred to the implementation method of the aforementioned abnormal processing data identification method, and will not be repeated here.

[0152] Furthermore, in one embodiment, this application also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the steps of the methods described in the foregoing embodiments.

[0153] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0154] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0155] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0156] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0157] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0158] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0159] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0160] The above-disclosed embodiments are merely partial examples of this application and should not be construed as limiting the scope of this application. Those skilled in the art will understand that implementing all or part of the above embodiments and making equivalent changes in accordance with the claims of this application are still within the scope of the invention.

Claims

1. A method for identifying abnormal processing data, characterized in that, Includes the following steps: Acquire periodic vibration data of cutting teeth during the machining process of aerospace parts; wherein, the periodic vibration data of cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the machining process of aerospace parts; Based on the periodic vibration data of the cutting teeth, a polar coordinate image is obtained; Multiple polar coordinate images generated from vibration signal data at different times are normalized to obtain multiple polar coordinate images of the same size, namely dst_image images; outlier noise points in the multiple polar coordinate images of the same size are removed to obtain multiple pro_image images; the pro_image images are processed into grayscale to obtain pro_image1 images; based on the pro_image1 images, the longest target circle radius value of the pro_image1 images is obtained; based on the pro_image1 images, the target region is obtained, and the effective feature pixels in the target region are removed to obtain the main direction of the polar coordinate image; wherein, the target region is obtained based on the following steps: in the image_new image with the same grayscale image size and number of channels, the longest target circle radius is obtained, and a circle is drawn with this value as the radius, and this circle is the target region; the main direction of the polar coordinate image is obtained based on the following steps: taking the geometric center of the image after removing the effective feature pixels in the "target region" as the starting point, and taking the angle Nangles as the step, in 360 degrees... Draw a ray within the range of degrees, count the number of pixels on the ray that have different gray values ​​from the background, and take the ray direction with the most pixels as the main direction of the polar coordinate image; based on the main direction of the polar coordinate image, obtain the cross-shaped orthogonal unit direction of the polar coordinate image; Based on the principal direction of the polar coordinate image and the cross-orthogonal unit direction, the polar coordinate image is subjected to region adaptive segmentation and extraction processing to obtain a vibration discrete point image. Abnormal processing data is identified based on the vibration discrete point image.

2. The method for identifying abnormal processing data according to claim 1, characterized in that, The process of obtaining a polar coordinate image based on the periodic vibration data of the cutting teeth includes: Based on the periodic vibration data of the cutting teeth, a polar coordinate image was obtained by plotting using Python.

3. The method for identifying abnormal processing data according to claim 1, characterized in that, The outlier noise removal process performed on the multiple polar coordinate images of the same size satisfies the following relationship: in, point ( x , y )and other _ point ( x , y () represents any point in the image; min Length Indicates the same in the image point ( x , y The length value represented by the point with the closest Euclidean distance; dst_image represents the image to be processed; if indicates the condition for judgment; This represents the grayscale value at point (x, y) of the single-channel image after grayscale processing of the image dst_image; discard indicates that points that meet the if condition are discarded, i.e., the grayscale value is reduced to zero.

4. The method for identifying abnormal processing data according to claim 1, characterized in that, The step of obtaining the longest target circle radius value of the pro_image1 image based on the pro_image1 image includes: The image center of the pro_image1 image is taken as the starting reference point; wherein, the coordinates of the starting reference point are denoted as (cols). pro_image , rows pro_image ); Based on the aforementioned starting reference point, a length numerical statistics array is obtained; wherein, the array length of the length numerical statistics array is equal to cols. pro_image Furthermore, the initial value of all subscript arrays in the array is represented by number1, and all elements in the array are integers; the length numerical statistics array satisfies the following relationship: int array[cols pro_image = {number1}; denote the positive integer corresponding to the pixel in the pro_image1 image whose gray value is equal to number1 as number2; obtain the rotation center based on number2; determine the gray value in the pro_image1 image corresponding to the rotation center position, if the gray value is different from the gray value of the background, then increment the value corresponding to the subscript of number2 by 1; Based on the rotation center, the pro_image1 image is rotated to obtain the pro_image2 image; based on the pro_image2 image, the grayscale value of the pro_image2 image at the rotation center is obtained; the grayscale value in the pro_image2 image corresponding to the rotation center position is determined, and if the grayscale value is different from the grayscale value of the background, the value corresponding to the subscript number2 is incremented by 1; wherein, the rotation angle during the rotation processing is any angle between 0° and 360°, and after each rotation processing, the value corresponding to the subscript number2 is obtained; The maximum value corresponding to the multiple number2 subscripts is obtained by comparison, and the maximum value is used as the longest target circle radius value of the pro_image1 image.

5. The method for identifying abnormal processing data according to claim 1, characterized in that, The process of obtaining the target region based on the pro_image1 image, removing the effective feature pixels within the target region, and then obtaining the main direction of the polar coordinate image includes: Based on the pro_image1 image, an image_new image is obtained; wherein the size and number of channels of the image_new image are the same as those of the pro_image1 image; Using the geometric center of the image_new image as the center, draw a circle in the image_new image based on the longest target circle radius value to obtain the target region; remove the effective feature pixels in the area covered by the target region to obtain the pro_image3 image; Using the geometric center of the pro_image3 image as a reference initial point, along... N times The number of pixels on the ray with different grayscale values ​​from the background is counted in each of the three angle directions to obtain the number of target pixels; wherein, the starting point of the ray is the geometric center of the pro_image3 image, and the length is pro_image3.rows; N times This refers to dividing 360° into equal parts. N times An evenly spaced angle N angles ; The number of target pixels is used as the length value of the corresponding ray to obtain multiple rays of different lengths; the length values ​​of the multiple rays of different lengths are compared to obtain the target ray with the largest length value, and the direction of the target ray is used as the main direction of the polar coordinate image.

6. The method for identifying abnormal processing data according to claim 1, characterized in that, The step of obtaining the cross-shaped orthogonal unit direction of the polar coordinate image based on the principal direction of the polar coordinate image includes: Acquire the number of cutting teeth and vibration signal data of adjacent cutting teeth during the machining process of aerospace parts; Based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the main direction of the polar coordinate image, the angle value of the adjacent cutting teeth is obtained; the angle value includes a first angle value and a second angle value. Based on the angle values ​​of the adjacent blades, the cross-orthogonal unit direction of the polar coordinate image is obtained.

7. The method for identifying abnormal processing data according to claim 6, characterized in that, The angle value of the adjacent cutting teeth is obtained based on the number of cutting teeth, the vibration signal data of the adjacent cutting teeth, and the main direction of the polar coordinate image. The angle value includes a first angle value and a second angle value, including: If the number of cutting teeth in the machining process of the aerospace part is 2, then the angle between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is... α It is 180°, that is, the first angle value and the second angle value of the adjacent cutting teeth are both 180°. α + 180 ° ; If the number of cutting teeth in the machining process of the aerospace part is 3, then the angle between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is... α 120 ° That is, the first angle value and the second angle value of the adjacent cutting teeth are respectively α+ 120 ° and α- 120 ° ; If the number of cutting teeth in the machining process of the aerospace part is 4, then the angle between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is... α For 90 ° That is, the first angle value and the second angle value of the adjacent cutting teeth are respectively α+ 90 ° and α- 90 ° ; If the number of cutting teeth in the machining process of the aerospace part is N n The angle between the vibration signal data of the adjacent cutting teeth and the principal direction of the polar coordinate image is... α For 360 ° / N n That is, the first angle value and the second angle value of the adjacent cutting teeth are respectively α+ 360 ° / N n and α- 360 ° / N n .

8. The method for identifying abnormal processing data according to claim 1, characterized in that, The process of performing adaptive region segmentation and extraction on the polar coordinate image based on the principal direction and the orthogonal unit direction to obtain a vibration discrete point image includes: Based on the image_new, obtain a single-channel grayscale image of the same scale. gray ; Based on the principal direction of the polar coordinate image and the orthogonal unit direction of the cross, segmentation rays are obtained; based on the segmentation rays, the image is... gray The image is segmented to obtain the image. gray Image segmentation; Based on the cutting tool tooth data used in the machining of aerospace parts, the image gray After segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract discrete vibration point images.

9. The method for identifying abnormal processing data according to claim 8, characterized in that, The image is based on segmentation rays. gray The image is segmented to obtain the image. gray Image segmentation, including: Based on the segmentation ray, the endpoints of the segmentation ray are set on the image. gray The boundary position of the image, the starting point of the segmentation ray is set on the image. gray The location of the center of the circle in the image.

10. The method for identifying abnormal processing data according to claim 9, characterized in that, The image is based on the cutting tool tooth data used in the machining of aerospace parts. gray After segmenting and rotating the image, different strategies are applied to the image based on grayscale differences. gray The segmented image is processed to extract discrete vibration point images, including: Based on the cutting tool tooth data used in the machining of aerospace parts N n The image gray Segment the image and rotate it 360 degrees clockwise. ° / (2* N n After grayscale difference, different strategies are applied to the image. gray The segmented image is processed to extract discrete vibration point images.

11. The method for identifying abnormal processing data according to claim 10, characterized in that, The image based on different strategies of grayscale difference gray The segmented image is processed to extract discrete vibration point images, including: Keep the image gray The segmented image is in .PNG lossless compressed format, and the grayscale values ​​of each channel of the pixels that make up each ray are consistent. N gray ∈[0,255], background grayscale is B gray ∈[0,255] and B gray ≠ N gray ; Obtain the image gray Segment the grayscale value of each pixel in the image. If its grayscale value is... N gray ， Then, taking this pixel as the initial point, the gray values ​​within its 4-neighborhood are also... N gray Reassign grayscale values ​​to random (R=) pixels. N new G= N new B= N new The initial grayscale values ​​are assigned in the same way. After processing the images in sequence gray Segment all pixels in the image such that the gray value of each pixel is not equal to 0. N gray Get the first image gray Image segmentation; Get the first image gray Grayscale removal included in image segmentation B gray ∈[0,255] and B gray ≠ N gray The number of grayscale categories is determined, and the coordinate data of the corresponding region is obtained based on the grayscale value of each category. Then, a [database / database] is generated based on the coordinates. N n Aspect image; The N n The amplitude images are integrated to obtain a discrete point image of vibration.

12. The method for identifying abnormal processing data according to claim 11, characterized in that, The N n The amplitude images are integrated to obtain a discrete point image of vibration, including: The N n The sub-images are integrated according to their original positional relationships to obtain the final image; The resulting image is subjected to quantitative analysis to obtain a discrete vibration point image.

13. A device for identifying abnormal processing data, characterized in that, include: The first acquisition module is used to acquire the periodic vibration data of the cutting teeth during the processing of the aircraft parts; wherein, the periodic vibration data of the cutting teeth refers to the vibration signal data generated by the cutting teeth at different times during the processing of the aircraft parts; The second acquisition module is used to obtain a polar coordinate image based on the periodic vibration data of the cutting teeth; The third acquisition module is used to normalize multiple polar coordinate images generated from vibration signal data at different times to obtain multiple polar coordinate images of the same size, namely dst_image images; remove outlier noise points in the multiple polar coordinate images of the same size to obtain multiple pro_image images; perform grayscale processing on the pro_image images to obtain pro_image1 images; obtain the longest target circle radius value of the pro_image1 images based on the pro_image1 images; obtain the target region based on the pro_image1 images, and remove the effective feature pixels in the target region to obtain the main direction of the polar coordinate image; wherein, the target region is obtained based on the following steps: in the image_new image with the same grayscale image size and number of channels, obtain the longest target circle radius, draw a circle with this value as the radius, and this circle is the target region; the main direction of the polar coordinate image is obtained based on the following steps: taking the geometric center of the image after removing the effective feature pixels in the "target region" as the starting point, and taking the angle Nangles as the step, in 360 degrees... Draw a ray within the range of degrees, count the number of pixels on the ray that have different gray values ​​from the background, and take the ray direction with the most pixels as the main direction of the polar coordinate image; based on the main direction of the polar coordinate image, obtain the cross-shaped orthogonal unit direction of the polar coordinate image; The fourth acquisition module is used to perform region adaptive segmentation and extraction processing on the polar coordinate image based on the main direction of the polar coordinate image and the cross orthogonal unit direction to obtain a vibration discrete point image. The identification module is used to identify abnormal processing data based on the vibration discrete point image.

14. An electronic device, characterized in that, The electronic device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method as described in any one of claims 1-12.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-12.

Images