Online visual inspection device and method

Abstract

The invention discloses an online visual inspection device and method. Comprising the following steps: scanning a coil mold by using a surface structured light scanning camera, and identifying an initial point location; winding is carried out according to a coil winding technology, first scanning data in the winding process are obtained, and after winding of a first part of the coil is completed, the mold is turned; re-identifying the initial point position by adopting a surface structured light scanning camera, and winding the rest coil according to a coil winding process to obtain second scanning data; and according to the initial point location, the first scanning data and the second scanning data, calculating the coil width, segment spacing and long and short axes of each segment and each layer of coil to obtain a detection result. The measurement result of each section and each layer of wound coil can be obtained through on-line visual detection of the high-voltage coil, the structure is simple, the cost is low, detection is accurate, and full-automatic work is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of coil manufacturing, and in particular to an online visual detection device and method. Background Art

[0002] At present, in the process of winding high-voltage coils of transformers, the traditional dimension measurement method mainly relies on manual measurement. Now after the high-voltage coil is wound by a machine, it is necessary for humans to cooperate with the machine to wrap white winding film on the wound coil. After winding the white winding film, the long and short axes, width and segment spacing of the coil are measured manually with a caliper. Because the coil size is too large (the conventional maximum size is 3600mm (length) * 300mm (width) * 670mm (height)) and there are many detection positions required, it is difficult to measure with a manual caliper. Therefore, a visual system is added to take photos of the above dimensions instead of manual detection.

[0003] In the prior art, the application number is CN202311264670Y, and the patent name is: An online visual inspection device and inspection method for the process dimensions of a transformer coil winding process, which provides a visual inspection device. The device is a transformer coil winding device that integrates a six-axis robot and a tracking three-dimensional scanning system. The main structure includes a gantry, a transformer coil winding mechanism, a support frame, a slider, a six-axis robot, and an optical tracker. The six-axis robot is suspended at the lower end of the slider on the support rod, and a three-dimensional scanning system is installed at the front end for real-time scanning and identification. The data is transmitted to the industrial computer display screen through the PLC to achieve real-time display and operation control. However, the mechanical structure required for the device is very complex and relatively expensive, and the suspended scanning device is easy to interfere with the staff in winding the coil. Therefore, it is not convenient during use. Summary of the invention

[0004] Therefore, the purpose of the present invention is to provide an online visual inspection device and method, which can obtain the edge of the coil by moving the camera to detect and output the width and major and minor axis measurement of each section and layer of the wound coil in real time.

[0005] In order to achieve the above object, the present invention provides an online visual inspection method for process dimensions during high voltage coil winding, comprising: Use the surface structured light scanning camera to scan the coil mold and identify the initial point position; Winding is performed according to the coil winding process, first scanning data in the winding process is obtained, and after the first part of the coil winding is completed, the mold is turned; The initial point position is re-identified using a surface structured light scanning camera, and the remaining coils are wound according to the coil winding process to obtain second scanning data; According to the initial point position, the first scanning data and the second scanning data, the coil width, segment spacing and major and minor axes of each segment and each layer of the coil are calculated to obtain the detection result.

[0006] Further preferably, before identifying the initial point position, the relative parallelism between the coil winding assembly and the surface structured light scanning camera is corrected, and the correction includes the following process: Collect multiple sets of 3D point cloud data when the mold rotates one circle; Perform cylindrical fitting on each set of 3D point cloud data to obtain multiple axes; The obtained multiple axes are optimized and the optimized axes are used as the point cloud axes; The angle between the axis of the point cloud and the axis of the surface structured light scanning camera is calculated and compensated to obtain the relative parallelism correction result between the coil winding component and the surface structured light scanning camera.

[0007] Further preferably, when cylindrical fitting is performed on each set of three-dimensional point cloud data, the fitting formula is calculated according to the following formula: in, represents the center of all axes obtained after cylinder fitting (i.e., the center of mass of the cylinder), N is the number of axes, pi is a point on each cylindrical axis (i.e., the center point of the fitted cylinder); To fit the axis direction of the cylinder, is the eigenvector corresponding to the minimum eigenvalue; is the average distance from all axes to the center of mass, dist i is the distance from the axis to the centroid of each set of 3D data.

[0008] Further preferably, after the calibration, the method further includes verifying the x-direction parallelism of the field of view of the surface structured light scanning camera according to the following process; Move the calibration plate horizontally to two positions within the field of view of the area structured light scanning camera; According to the position and posture of the calibration plate at two positions in the camera coordinate system, calculate the two positions and postures of the calibration plate ; Determine the angle Whether it meets the coil process requirements. If so, the x-direction parallelism of the surface structured light scanning camera meets the requirements. If not, readjust and verify.

[0009] Further preferably, after the calibration, the method further includes verifying the parallelism between the surface structured light scanning camera and the coil mold when the surface structured light scanning camera moves horizontally according to the following process; Place the calibration plate at the same position on the square axis and move the surface structured light scanning camera horizontally to two different positions; When the surface structured light scanning camera is at two positions, the point cloud data obtained by scanning the calibration plate is transferred to the same position using matrix transformation; The point cloud data of the calibration plate taken at the two positions after conversion are difference calculated to obtain the X-direction deviation and Z-direction deviation of the parallelism with the coil mold.

[0010] Further preferably, the coil winding process includes the requirements for the number of coil segments, the winding order of each coil segment, the number of layers of each coil segment, the width of each coil segment, and the interval between adjacent coil segments; wherein according to the requirements for the number of coil segments, the coil as a whole is divided into odd-numbered coil segments and even-numbered coil segments, and the scanning data during the winding process of the odd-numbered coil segments is recorded as the first scanning data; and the scanning data during the winding process of the even-numbered coil segments is recorded as the second scanning data.

[0011] Further preferably, the calculation of the coil width of each section and each layer of the coil according to the initial point position, the first scanning data and the second scanning data includes: Calculate the center position of the coil to be wound according to the initial point position and coil winding process; Move the surface structured light scanning camera to the center of each section and layer of the coil to be tested, and collect scanning data of the area to be tested within the field of view; The grayscale image and depth data of the winding coil area at the current position are extracted, the left and right boundaries are obtained by edge extraction, and the distance between the two boundaries is calculated as the coil width.

[0012] Further preferably, when calculating the segment spacing, the first scan data and the second scan data are spliced ​​according to the initial points identified twice before and after, and the odd-numbered coil boundaries in the first scan data and the even-numbered coil boundaries in the second scan data are extracted; Then the segment spacing d = d1-d2-d3; Among them, d1 is the distance between the center position of the target odd segment and the adjacent target even segment coil; d2 is the distance between the left boundary line of the target odd segment and the center position of the target odd segment coil; d3 is the distance between the right boundary line of the target even segment and the center position of the target even segment coil.

[0013] Further preferably, when calculating the major and minor axes, the mean value of the depth data z1 and the mean value of the mold depth data z2 when the coil is not wound are calculated based on the grayscale image and depth data of the coil winding area at the current position. Major and minor axes = (z1 - z2 + D) * 2; where D is the mold radius.

[0014] The present invention also provides an online visual inspection device for process dimensions during the winding process of a high-voltage coil, comprising: Surface structured light scanning camera, used to obtain scanning data during the coil winding process; A horizontal driving component, used to drive the surface structured light scanning camera to move in translation; A coil winding assembly is used to drive the mold to rotate for coil winding; The controller is used to control the horizontal drive assembly and the coil winding assembly, and calculate the detection results according to the online visual detection method of the process dimensions during the high-voltage coil winding process.

[0015] The online visual inspection device and method disclosed in this application have at least the following advantages over the prior art: Through the parallelism correction between the coil winding assembly and the surface structured light scanning camera, as well as two accuracy verifications when the calibration plate is fixed and the camera moves alternately, the camera field of view accuracy and the parallelism accuracy between the camera and the mold are verified, ensuring the accuracy of the subsequent calculation of the coil data.

[0016] The center position of each section and layer of the coil is calculated by moving the camera, and the edge of the coil is obtained by visual detection. The width of each section and layer of the coil, the distance between sections, the measurement of the major and minor axes are calculated and output in real time. It has a simple structure, low cost, and completely replaces manual operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic structural diagram of an online visual inspection device provided by the present invention; Figure 2 A schematic diagram of a process flow of an online visual inspection method provided by the present invention; Figure 3 It is a schematic diagram of the coil winding process drawing of the present invention; Figure 4 To calibrate the front axis and fit the mold point cloud; Figure 5 To calibrate the rear axis and fit the mold point cloud; Figure 6 Collect images for the verification process of the camera X-axis being parallel to the square axis; Figure 7 Two sets of point cloud data before and after the camera translation transformation; Figure 8 It is a schematic diagram of the mold after inversion of the present invention.

[0018] In the figure: 1. 3D surface structured light camera; 2. Horizontal moving guide device; 3. Optical detection electrical cabinet; 4. Bobbin positioning wedge; 5. High-voltage coil mold; 6. Square shaft. DETAILED DESCRIPTION

[0019] The present invention is further described in detail below through the accompanying drawings and specific embodiments.

[0020] like Figure 1As shown, an online visual inspection device for process dimensions in a high-voltage coil winding process provided by an embodiment of one aspect of the present invention comprises: a surface structured light scanning camera, a horizontal drive component, a coil winding component and a controller; wherein the surface structured light scanning camera adopts a 3D surface structured light camera 1; the horizontal drive component adopts a horizontal moving guide rail device 2, and the coil winding component comprises a bobbin positioning wedge 4, a square shaft 6 and a high-voltage coil mold 5; The 3D surface structured light camera 1 is installed on the horizontal moving guide rail device 2, and is driven by the horizontal moving guide rail device 2 to scan the entire high-voltage coil mold, identify the initial position of the high-voltage coil mold, and store the three-dimensional data of the high-voltage coil mold when winding the coil. Through the process dimensions issued by MES, the controller calculates the center position of each section and layer of coils, and provides shooting points for subsequent coil major and minor axis, width and segment spacing measurements. Among them, the width and major and minor axis measurements of each section and layer of the wound coil can be output in real time after mobile photography, and the segment spacing of each section and layer is measured by the segment spacing measurement method.

[0021] The bobbin positioning wedge is used to fix the center of the high-voltage coil. Due to the gap between the high-voltage coil mold 5 and the central square shaft 6, the coil as a whole will jitter and deviate in an uncertain position up and down, left and right during the coil winding process. In order to avoid the detection error caused by this jitter and deviation, the bobbin positioning wedge needs to be installed after the central square shaft is passed through to ensure that the center position of the high-voltage coil does not randomly jump and deviate during the winding process.

[0022] The present invention also provides an online visual detection method for process dimensions during high-voltage coil winding, comprising the following steps: S1. Scan the coil mold using a surface structured light scanning camera to identify the initial point position; It should be noted that if Figure 3 As shown, the initial point is the fixed edge position at one end of the mold. When the mold is flipped, the other end of the mold is at the edge position at this time, and it is necessary to re-identify this as the initial point.

[0023] Since the guide rail and the camera installation cannot ensure relative parallelism with the winding device, the angle between the camera and the winding device will affect the visual detection accuracy. Therefore, before identifying the initial point position, the relative parallelism of the coil winding assembly and the surface structured light scanning camera is also corrected. The correction includes the following process: Collect multiple sets of 3D point cloud data when the mold rotates one circle; Perform cylinder fitting on each set of 3D point cloud data to obtain multiple axes, which are the central axes of the fitted cylinders; The obtained multiple axes are optimized, and the optimized axes are used as point cloud axes; The angle between the axis of the point cloud and the axis of the surface structured light scanning camera is calculated and compensated to obtain the relative parallelism correction result between the coil winding component and the surface structured light scanning camera.

[0024] During the specific calibration, first, place the cylindrical mold on the square axis, collect the 3D point cloud of the mold after one rotation (calculated according to the camera's field of view, each rotation is 30°), perform cylindrical fitting on the 12 sets of collected 3D point clouds to obtain 12 sets of cylindrical axes, and perform fitting optimization on the 12 sets of cylindrical axes to obtain the final axes. The cylindrical axis fitting optimization is shown in formula (1).

[0025] Formula (1) in, represents the center of all axes obtained after cylinder fitting (i.e., the center of mass of the cylinder), N is the number of axes, pi is a point on each cylindrical axis (i.e., the center point of the fitted cylinder); To fit the axis direction of the cylinder, is the eigenvector corresponding to the minimum eigenvalue; is the average distance from all axes to the center of mass, dist i is the distance from the axis to the centroid of each set of 3D data.

[0026] When fitting, the xyz coordinates of all three-dimensional data points are first used to calculate the center point c of all axis starting points, and the eigenvector with the smallest eigenvalue is selected as the axis direction d of the fitting cylinder; combined with the average distance from the axis to the center of mass; that is, the final axis Cylinder is obtained by optimizing the axis fitting based on the three parameters c, d, and r.

[0027] Then, compensation is performed based on the angle between the point cloud axis and the camera coordinate axis. After compensation, the camera coordinate axis is parallel to the square axis, which is used to more accurately calculate the major and minor axes, width and segment spacing of the coil.

[0028] Correct the front and rear axes and fit the position of the mold point cloud in the camera coordinate system as follows Figure 4 shown.

[0029] After calibration, the accuracy verification of the visual inspection device considers two situations: 1) Within the field of view of the camera, move the calibration plate parallel to the edge of the square axis to two different positions to ensure the parallelism of the x-axis direction under the field of view of the camera; 2) Within the field of view of the camera, fix the calibration plate at a specific position, and the horizontal guide rail carries the camera to move, verify the parallelism of the horizontal moving stage and the square axis, and ensure the overall measurement accuracy. The specific operation schemes of the above two accuracy verifications are described below. Since the width of the coil mainly depends on the data in the X direction of the camera, only by ensuring the parallelism of the X axis and the square axis can the width and segment spacing data be accurate. The test accuracy of the long and short axes of the coil depends on the accuracy in the Z direction. Only by verifying the parallelism of the horizontal moving stage and the square axis (X direction), as well as the measurement accuracy in the three directions of XYZ, can the accuracy requirements for the subsequent measurement of the long and short axes of the coil be guaranteed.

[0030] like Figure 6 As shown, the x-direction parallelism of the field of view of the surface structured light scanning camera is verified according to the following process; Move the calibration plate horizontally to two positions within the field of view of the area structured light scanning camera; According to the position of the calibration plate in the camera coordinate system, calculate the angle between the x-axis of the calibration plate in the camera coordinate system before and after the movement ; Determine the angle Whether it meets the coil process requirements. If so, the x-direction parallelism of the surface structured light scanning camera meets the requirements. If not, readjust and verify.

[0031] That is, the calibration plate is attached to the edge of the square axis, and the calibration plate is moved two positions within the camera field of view. By calculating the position and posture of the calibration plate during the two movements in the camera coordinate system, the angle between the two positions and the position of the calibration plate before and after the movement is obtained using formula (2): If the angle between the two moving positions is The parallelism in the x-direction is good within the camera’s field of view and does not exceed 0.085°, which can provide accurate coil width and segment spacing detection data.

[0032] Formula (2) in, is the angle between the two moves, is the position and posture of the calibration plate at position 1, is the position of the calibration plate at position 2. According to the coil winding process requirements, the conversion of the two movements in the x-direction angle within 0.085° is qualified, so this method can be used to calculate the accuracy requirements of the first case.

[0033] like Figure 7As shown, for the second case, the accuracy requirement is as follows: verify the parallelism between the surface structured light scanning camera and the coil mold when it moves horizontally; Place the calibration plate at any fixed position on the square axis and move the surface structured light scanning camera horizontally to two different positions; When the surface structured light scanning camera is at two positions, the point cloud data obtained by scanning the calibration plate is transferred to a fixed position using matrix transformation; The point cloud data of the calibration plate taken at the two positions after the conversion are calculated by difference, and the X-direction deviation and Z-direction deviation of the parallelism of the structured light scanning camera with the coil mold when it moves horizontally are obtained. That is to say, after the calibration plate is set at a fixed position, when the camera is in the first position, the first point cloud data of the calibration plate is captured; when the camera is in the second position, the second point cloud data of the calibration plate captured by the camera at this time is converted into the coordinate system of the first point cloud data. At this time, the coordinate systems of the first point cloud data and the second point cloud data are consistent, and the difference calculation can be performed. The difference in the X direction of any corner point of the calibration plate in the point cloud data in the two point cloud data can be used as the X-direction deviation of the parallelism of the coil mold; similarly, the difference in the Z direction of any corner point in the two point cloud data is used as the Z-direction deviation of the parallelism of the coil mold.

[0034] The calibration plate is placed at the same position of the square axis, and the camera is moved to two different positions through the horizontal guide rail. The point cloud data obtained; the point cloud data of the calibration plate is converted to the same position only through the translation matrix, and the point cloud data of the two calibration plate identification points after the conversion are calculated for difference. The deviation of the camera shooting identification points before and after the guide rail moves, the maximum deviation in the X direction is within 1 mm, and the maximum deviation in the Z direction is within 1.5 mm. Therefore, the visual inspection system is qualified if the width and segment spacing detection accuracy is within 1 mm under ideal imaging, and the long and short axis accuracy is within 1.5 mm.

[0035] S2, winding according to the coil winding process, obtaining the first scanning data in the winding process, and turning the mold after completing the winding of the first part of the coil; S3, using a surface structured light scanning camera to re-identify the initial point position, winding the remaining coil according to the coil winding process, and obtaining second scanning data; The coil winding process includes the requirements for the number of coil segments, the winding order of each coil segment, the number of layers of each coil segment, the width of each coil segment, and the interval between adjacent coil segments; wherein, according to the requirements for the number of coil segments, the entire coil is divided into odd-numbered coil segments and even-numbered coil segments, and the scanning data during the winding process of the odd-numbered coil segments is recorded as the first scanning data; and the scanning data during the winding process of the even-numbered coil segments is recorded as the second scanning data.

[0036] S4. Calculate the coil width, segment spacing, and major and minor axes of each section and layer of coils according to the initial point position, the first scanning data, and the second scanning data to obtain the test results. The coil width refers to the size of each section and layer of coils in the axial direction during the coil winding process. The segment spacing is the spacing between adjacent sections of coils; the major and minor axes represent the diameter of the coil. According to the coil model requirements, when the mold is cylindrical, the major axis and the minor axis are equal to the diameter of the mold after the coil is wound; when the model requires the mold to be elliptical, the major axis and the minor axis are not equal. In this case, this method can be used to calculate the major axis and the minor axis separately.

[0037] Further preferably, the calculation of the coil width of each section and each layer of the coil according to the initial point position, the first scanning data and the second scanning data includes: Calculate the center position of the coil to be wound according to the initial point position and coil winding process; Move the surface structured light scanning camera to the center of each section and layer of the coil to be tested, and collect scanning data of the area to be tested within the field of view; Extract the grayscale image and depth data of the coil winding area at the current position, use edge extraction to obtain the left and right boundaries, and calculate the distance between the two boundaries as the coil width. Figure 8 In the measurement, the center position of each layer in Segment I = the initial position of the mold - (coil insulation height + coil width of each layer in Segment I / 2). After the camera moves to the position to be measured, the area to be measured is completely covered and selected based on the camera's horizontal x data image (the coil process width is expanded by a certain width). The area to be measured is accurately extracted using the grayscale image and the depth z data image of the area to be measured. The left and right boundaries are obtained using edge extraction, and the distance between the two boundaries is calculated as the coil width.

[0038] Further preferably, when calculating the segment spacing, the first scan data and the second scan data are spliced ​​according to the initial points identified twice before and after, and the odd-numbered coil boundaries in the first scan data and the even-numbered coil boundaries in the second scan data are extracted; Then the segment spacing d = d1-d2-d3; Among them, d1 is the distance between the center position of the target odd segment and the adjacent target even segment coil; d2 is the distance between the left boundary line of the target odd segment and the center position of the target odd segment coil; d3 is the distance between the right boundary line of the target even segment and the center position of the target even segment coil.

[0039] According to the high-voltage coil winding process, after each layer of the odd or even sections of the coil is wound, the winding mold is reversed and wound around the remaining sections. The schematic diagram of the mold after the reversal is as follows: Figure 8As shown. Taking the odd-numbered segments as an example, after winding the i, ii, and iii layers of segments Ⅰ and Ⅲ respectively, the entire mold is reversed to wind the i, ii, and iii layers of even-numbered segments Ⅱ and Ⅳ. Therefore, the distance between adjacent segments of each layer can only be measured after the mold is reversed. The segment spacing measurement process is to re-identify the initial position of the mold after reversal, and calculate the center photo position of the layer to be measured after reversal through the drawing. Retrieve the adjacent images of the current segment and the current layer stored before the mold is reversed. For example, to measure the ii layer of segment Ⅱ, the x, y, z, and grayscale images of the ii layer of segment Ⅰ and the ii layer of segment Ⅲ need to be called. The process of identifying the boundary line of the coil is the same as that of identifying the boundary line of the coil width measurement. Taking the distance between adjacent segments Ⅰ and Ⅱ as an example, the actual winding distance between segments Ⅰ and Ⅱ = the distance between the center photo positions of segments Ⅰ and Ⅱ – the left boundary line of segment Ⅰ relative to the photo position – the right boundary line of segment Ⅱ relative to the photo position.

[0040] Further preferably, when calculating the major and minor axes, the mean value of the depth data z1 and the mean value of the mold depth data z2 when the coil is not wound are calculated based on the grayscale image and depth data of the coil winding area at the current position; Major and minor axes = (z1 - z2 + D) * 2; where D is the mold radius. The surface structured light (3D) camera used in this article can obtain the depth of the object being measured (relative to the 2D camera). The depth data refers to the depth data of the coil after winding, that is, the depth of the position relative to the camera. The mold depth data and the wound coil depth data are both relative to the camera.

[0041] The present invention provides a linear visual inspection device for process dimensions during the winding process of a high-voltage coil, and provides a method for correcting the visual inspection device and a method for verifying the accuracy of the corrected inspection device. The center position of each section and layer of the coil required for winding is calculated through the winding process, and the edge of the coil is obtained by visual inspection. The width and major and minor axis measurements of each section and layer of the coil can be output in real time by moving and photographing. The segment spacing at this position is obtained by subtracting the center position of the coil and the edge distance after two movements.

[0042] Obviously, the above embodiments are only examples for clear explanation, and are not intended to limit the implementation methods. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. An online visual inspection method, characterized in that: include: Use the surface structured light scanning camera to scan the coil mold and identify the initial point position; Winding is performed according to the coil winding process, first scanning data in the winding process is obtained, and after the first part of the coil winding is completed, the mold is turned; The initial point position is re-identified using a surface structured light scanning camera, and the remaining coils are wound according to the coil winding process to obtain second scanning data; According to the initial point position, the first scanning data and the second scanning data, the coil width, segment spacing and major and minor axes of each segment and each layer of the coil are calculated to obtain the detection result.

2. The online visual inspection method according to claim 1, characterized in that: Before identifying the initial point position, the relative parallelism between the coil winding assembly and the surface structured light scanning camera is corrected, and the correction includes the following process: Collect multiple sets of 3D point cloud data when the mold rotates one circle; Perform cylindrical fitting on each set of 3D point cloud data to obtain multiple axes; The obtained multiple axes are optimized, and the optimized axes are used as point cloud axes; The angle between the axis of the point cloud and the axis of the surface structured light scanning camera is calculated and compensated to obtain the relative parallelism correction result between the coil winding component and the surface structured light scanning camera.

3. The online visual inspection method according to claim 2, characterized in that: When cylindrical fitting is performed on each set of 3D point cloud data, the fitting formula is calculated according to the following formula: in, Represents the center of all axes obtained after cylinder fitting, recorded as the centroid of the fitted cylinder, N is the number of axes, pi is the center point of the fitted cylinder; To fit the cylinder axis direction, is the eigenvector corresponding to the minimum eigenvalue; is the average distance from all axes to the center of mass; dist i is the distance from the axis to the centroid of each set of 3D data.

4. The online visual inspection method according to claim 2, characterized in that: After calibration, the x-direction parallelism of the field of view of the surface structured light scanning camera is verified according to the following process; Move the calibration plate horizontally to two positions within the field of view of the area structured light scanning camera; According to the position of the calibration plate at two positions in the camera coordinate system, calculate the angle between the two positions of the calibration plate ; Determine the angle Whether it meets the coil process requirements. If so, the x-direction parallelism of the surface structured light scanning camera meets the requirements. If not, readjust and verify.

5. The online visual inspection method according to claim 2, characterized in that: After calibration, the parallelism between the surface structured light scanning camera and the coil mold when moving horizontally is also verified according to the following process; Place the calibration plate at any fixed position on the square axis and move the surface structured light scanning camera horizontally to two different positions; When the surface structured light scanning camera is at two positions, the point cloud data obtained by scanning the calibration plate is transferred to the fixed position by using matrix transformation; The point cloud data of the calibration plate taken at the two positions after conversion are difference calculated to obtain the X-direction deviation and Z-direction deviation of the parallelism with the coil mold.

6. The online visual inspection method according to claim 1, characterized in that: The coil winding process includes the requirements for the number of coil segments, the winding order of each coil segment, the number of layers of each coil segment, the width of each coil segment, and the interval between adjacent coil segments; wherein according to the requirements for the number of coil segments, the coil as a whole is divided into odd-numbered coil segments and even-numbered coil segments, and the scanning data during the winding process of the odd-numbered coil segments is recorded as the first scanning data; and the scanning data during the winding process of the even-numbered coil segments is recorded as the second scanning data.

7. The online visual inspection method according to claim 6, characterized in that: The calculation of the coil width of each section and each layer of the coil according to the initial point position, the first scanning data and the second scanning data includes: Calculate the center position of the coil to be wound according to the initial point position and coil winding process; Move the surface structured light scanning camera to the center of each section and layer of the coil to be tested, and collect scanning data of the area to be tested within the field of view; The grayscale image and depth data of the winding coil area at the current position are extracted, the left and right boundaries are obtained by edge extraction, and the distance between the two boundaries is calculated as the coil width.

8. The online visual inspection method according to claim 6, characterized in that: When calculating the segment spacing, the first scan data and the second scan data are spliced ​​according to the initial points recognized twice before and after, and the odd-numbered coil boundaries in the first scan data and the even-numbered coil boundaries in the second scan data are extracted; Then the segment spacing d = d1-d2-d3; Among them, d1 is the distance between the center position of the target odd segment and the adjacent target even segment coil; d2 is the distance between the left boundary line of the target odd segment and the center position of the target odd segment coil; d3 is the distance between the right boundary line of the target even segment and the center position of the target even segment coil.

9. The online visual inspection method according to claim 6, characterized in that: When calculating the major and minor axes, the depth data mean z1 and the mold depth data mean z2 when the coil is not wound are calculated based on the grayscale image and depth data of the coil winding area at the current position; Major and minor axes = (z1 - z2 + D) * 2; where D is the mold radius.

10. An online visual inspection device, characterized in that: include: Surface structured light scanning camera, used to obtain scanning data during the coil winding process; A horizontal driving component, used to drive the surface structured light scanning camera to move in translation; A coil winding assembly is used to drive the mold to rotate for coil winding; A controller is used to control the horizontal drive assembly and the coil winding assembly, and calculate the detection result according to the online visual detection method described in any one of claims 1 to 8.

Images