Precise laser welding control method, device and system for VCM motor

Abstract

The invention relates to the technical field of laser welding, in particular to a precise laser welding control method, device and system for a VCM motor. The method comprises the following steps: acquiring edge pixel points in an image of a VCM motor elastic sheet to be welded; obtaining an isolation score of each edge pixel point according to the number distribution condition of the edge pixel points in different preset directions of each edge pixel point; screening outer frame pixel points by using the isolation score; making rays in a plurality of directions by taking the center of the motor elastic sheet as a starting point of the rays, and obtaining inner frame pixel points according to position distribution of edge pixel points on the rays; and according to the position differences between the welding points in the continuous multi-frame welding images and the outer frame pixel points and the inner frame pixel points, the welding path coincidence degree is obtained, and pulse parameters are adjusted according to the welding path coincidence degree. According to the invention, the pulse parameters of laser welding can be adaptively controlled, and the welding quality of the motor elastic sheet is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of laser welding, and specifically relates to a precise laser welding control method, device and system for a VCM motor. Background Art

[0002] Laser welding technology belongs to fusion welding, which uses a laser beam as the energy source to impact on the weld joint of the workpiece to achieve the purpose of welding. It consists of an optical oscillator and a medium placed between the mirrors at both ends of the oscillator cavity. The main objects of laser welding include the shrapnel of the VCM motor behind the mobile phone lens. Laser welding of such shrapnel mainly includes the following processes: (1) obtaining materials; (2) taking pictures; (3) flatness detection; (4) welding point positioning based on the image; (5) laser welding. The main technical implementation process is to control the parameters of laser welding, so as to achieve more accurate positioning welding. In the process of precision laser welding of mobile phone lenses, it involves multiple links from material acquisition to laser welding control. The technical key point is the precise control of welding parameters, including laser power, pulse frequency, spot size, focal position, etc. Through image processing, sensor feedback, and an automated control system, high-precision positioning and real-time parameter adjustment can be achieved, which can ensure the accuracy and consistency of welding, and ultimately ensure the quality stability of the welding of the VCM motor shrapnel.

[0003] In the process of welding the VCM motor shrapnel, due to the different welding requirements for the inner and outer frames of the shrapnel, in the long outer frame area, if high-frequency pulses or too long pulse widths are used, excessive heat accumulation will occur, resulting in over-melting, deformation of the material, or a large heat-affected zone, affecting the structural stability of the shrapnel; when welding the fine inner frame area, if low-frequency pulses and long pulse widths are continued to be used, the welding points may be too large to meet the fine requirements, and there may even be problems such as over-melting or insufficient welding at complex structures. Summary of the Invention

[0004] In order to solve the problem that the inappropriate setting of welding parameters in the existing method leads to poor welding effects in the process of welding the VCM motor shrapnel, the purpose of the present invention is to provide a precise laser welding control method, device and system for a VCM motor, and the specific technical solutions adopted are as follows: In the first aspect, the present invention provides a precise laser welding control method for a VCM motor, and the method includes the following steps: Obtain the edge pixel points in the image of the VCM motor shrapnel to be welded; According to the quantity distribution of edge pixel points in different preset directions of each edge pixel point, obtain the isolation score of each edge pixel point; use the isolation score to screen out the outer frame pixel points; take the center of the motor elastic piece as the starting point of the ray to make rays in several directions, and obtain the inner frame pixel points according to the position distribution of the edge pixel points on the rays, where the center of the motor elastic piece is determined based on the outer frame pixel points; According to the position difference between the welding points and the envelope pixel points in consecutive frames of welding images, obtain the welding path coincidence degree. The consecutive frames of welding images are images of the motor elastic piece collected during the process of welding the to-be-welded VCM motor elastic piece using the precision laser welding technology, and the envelope pixel points include outer frame pixel points and inner frame pixel points; Adjust the pulse parameters according to the welding path coincidence degree.

[0005] Preferably, the obtaining the isolation score of each edge pixel point according to the quantity distribution of edge pixel points in different preset directions of each edge pixel point includes: According to the quantity of edge pixel points in each preset direction of the candidate pixel point, obtain the quantity isolation value of the candidate pixel point. The quantity of edge pixel points in each preset direction of the candidate pixel point has a negative correlation with the quantity isolation value; According to the quantity of preset directions where the quantity of edge pixel points in all preset directions of the candidate pixel point is 0 and the quantity isolation value, obtain the isolation score of the candidate pixel point; The candidate pixel point is any edge pixel point, and the preset directions include above, below, left, and right.

[0006] Preferably, the obtaining the isolation score of the candidate pixel point according to the quantity of preset directions where the quantity of edge pixel points in all preset directions of the candidate pixel point is 0 and the quantity isolation value includes: Calculate the first sum value of the quantity of preset directions where the quantity of edge pixel points in all preset directions of the candidate pixel point is 0 and the constant 1; Determine the normalized result of the product between the quantity isolation value of the candidate pixel point and the first sum value as the isolation score of the candidate pixel point.

[0007] Preferably, the using the isolation score to screen out the outer frame pixel points includes: Arrange the isolation scores of all edge pixel points in descending order to construct an isolation score sequence; Calculate the numerical difference between every two adjacent elements in the isolation score sequence; determine the edge pixel points corresponding to all elements before the latter element among the two elements corresponding to the largest numerical difference as the outer frame pixel points.

[0008] Preferably, obtaining the center of the motor elastic piece includes: performing a convex hull detection on all outer frame pixel points to obtain a corresponding convex hull region, and taking the center point of the convex hull region as the center of the motor elastic piece.

[0009] Preferably, obtaining the inner frame pixel points according to the position distribution of the upper edge pixel points on the ray includes: Taking the pixel point adjacent to the starting point of the ray on the ray as the starting point, and obtaining the first edge pixel point along each ray as the inner frame pixel point.

[0010] Preferably, obtaining the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in consecutive multi-frame welding images includes: Taking the outer frame pixel point and the inner frame pixel point closest to the welding point as the first reference point and the second reference point respectively; Obtaining the outer welding path coincidence degree according to the coordinate difference between the welding points and the corresponding first reference points in all welding images; obtaining the inner welding path coincidence degree according to the coordinate difference between the welding points and the corresponding second reference points in all welding images; where the welding point is the pixel point with the highest infrared value in the welding image; The welding path coincidence degree includes the outer welding path coincidence degree and the inner welding path coincidence degree.

[0011] Preferably, adjusting the pulse parameters according to the welding path coincidence degree includes: If the outer welding path coincidence degree is greater than a preset first threshold, continue welding with a short-wave pulse and a pulsed laser with a low frequency; if the outer welding path coincidence degree is less than or equal to the preset first threshold and the inner welding path coincidence degree is greater than the preset first threshold, continue welding with a short-wave pulse width and a pulsed laser with a high frequency; otherwise, continue welding using the welding pulse parameters of the inner frame line.

[0012] In a second aspect, the present invention provides a precision laser welding control device for a VCM motor, including a memory and a processor, and the processor executes the computer program stored in the memory to implement a precision laser welding control method for a VCM motor.

[0013] In a third aspect, the present invention further provides a precision laser welding control system for a VCM motor, and the system includes: An image acquisition module, configured to acquire edge pixel points in multiple frames of monitoring images of a VCM motor elastic piece to be welded; A screening module, configured to obtain the isolation score of each edge pixel point according to the number distribution of edge pixel points in different preset directions of each edge pixel point; screen the outer frame pixel points by using the isolation score; draw rays in several directions with the center of the motor spring piece as the starting point of the ray, and obtain the inner frame pixel points according to the position distribution of the edge pixel points on the ray, where the center of the motor spring piece is determined based on the outer frame pixel points; A calculation module, configured to obtain the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in a plurality of consecutive welding images, where the plurality of consecutive welding images are images of the motor spring piece collected during the process of welding the to-be-welded VCM motor spring piece by using the precision laser welding technology, and the envelope pixel points include outer frame pixel points and inner frame pixel points; A control module, configured to adjust the pulse parameters according to the welding path coincidence degree.

[0014] The present invention has at least the following beneficial effects: The present invention first obtains the edge pixel points in the image of the to-be-welded VCM motor spring piece, then combines the structural features of the inner and outer frame lines of the to-be-welded VCM motor spring piece to identify the outer frame pixel points and the inner frame pixel points from all the edge pixel points, collects a plurality of welding images during the welding process of the to-be-welded VCM motor spring piece, and evaluates the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in the collected plurality of welding images, that is, judges the specific welding position, and assigns corresponding welding pulse parameters according to the judgment result. The method provided by the present invention adaptively controls the pulse parameters of the laser welding, eliminates the problem of reduced welding accuracy and quality caused by the thermal effect of welding, and improves the welding quality of the motor spring piece. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of a precision laser welding control method for a VCM motor provided by an embodiment of the present invention; Figure 2 It is a result diagram of edge detection provided by an embodiment of the present invention; Figure 3 It is a structural block diagram of a precision laser welding control system for a VCM motor provided by an embodiment of the present invention. Detailed Implementation Manner

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following provides a detailed description of the precision laser welding control method, device, and system for a VCM motor according to the present invention in combination with the accompanying drawings and preferred embodiments as follows.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] The following specifically describes the specific solutions of the precision laser welding control method, device, and system for a VCM motor provided by the present invention in combination with the accompanying drawings.

[0020] Embodiment of the precision laser welding control method for a VCM motor: The specific scenario targeted by this embodiment is: during the laser welding of the VCM motor shrapnel, in order to ensure the welding quality, an image of the VCM motor shrapnel is acquired, edge detection using the Canny operator is performed on it, the structural characteristics of the shrapnel are analyzed, and the envelope results of the inner and outer frames of the motor are obtained; the welding results are analyzed in combination with the welding sequence in different frames, and the pulse parameters in the subsequent welding process are adjusted based on the current welding results.

[0021] This embodiment proposes a precision laser welding control method for a VCM motor, as Figure 1 shown, the precision laser welding control method for a VCM motor in this embodiment includes the following steps: Step S1, obtain the edge pixel points in the image of the VCM motor shrapnel to be welded.

[0022] First, fix the VCM motor shrapnel to be welded on the welding platform through a fixture or vacuum adsorption to ensure that the material does not move during the welding process; the positioning accuracy is ±0.01 mm, and the fixing force is appropriate to prevent deformation. Install an industrial camera, align it with the VCM motor shrapnel to be welded, and ensure that the lighting system (such as a ring light or a laser-assisted light source) evenly covers the surface of the VCM motor shrapnel to be welded to reduce reflection and shadow. Set the resolution to 2000x2000 pixels or above, the frame rate to 30fps, and the exposure time to 100µs~1ms (adjusted according to the ambient light), capture the RGB image of the VCM motor shrapnel to be welded, and transmit it to a computer or a PLC system for processing. Perform grayscale processing on the captured RGB image of the VCM motor shrapnel to be welded, and record the grayscale processed image as the image of the VCM motor shrapnel to be welded. Image grayscale processing is a prior art and will not be elaborated here too much.

[0023] The Canny algorithm is a standard algorithm widely used in edge detection. Its goal is to find an optimal edge detection solution or locate the positions with the strongest changes in gray intensity in an image. Optimal edge detection is mainly evaluated by three criteria: low error rate, high localization, and minimum response. When using the Canny algorithm to perform edge detection on the image of the VCM motor chip to be welded, since the distinction between the target and the background in the original image is relatively low, it is necessary to control the high and low thresholds during the edge detection stage. The low threshold is 0.12 and the high threshold is 0.16 to extract the edge pixel points in the image of the VCM motor chip to be welded. The Canny algorithm is a prior art and will not be elaborated here. In specific applications, the implementer can set the threshold according to the specific situation.

[0024] So far, all the edge pixel points in the image of the VCM motor chip to be welded have been obtained in this embodiment.

[0025] Step S2: Obtain the isolation score of each edge pixel point according to the number distribution of edge pixel points in different preset directions of each edge pixel point; use the isolation score to screen the outer frame pixel points; draw rays in several directions with the center of the motor chip as the starting point of the ray, and obtain the inner frame pixel points according to the position distribution of the edge pixel points on the ray. The center of the motor chip is determined based on the outer frame pixel points.

[0026] The structure of the VCM motor chip is relatively regular and neat, mainly divided into the outer frame line to be welded, the inner frame line, and the included filling line. The outer frame line presents a quasi-rectangular shape and appears as a relatively regular geometric body in the image; the inner frame line presents an elliptical or circular shape and is generally simple and regular. Due to the special structure of the VCM motor chip, the welding parameters and requirements of the inner and outer frame lines are different during the welding process. Using the welding parameters of the same laser pulse will cause situations such as fusing and insufficient welding. To solve this problem, it is achieved through the self-adaptation of the pulse parameters. The main logic of the self-adaptation is to detect the inner and outer frame lines by analyzing the image in real time, and combine the structural characteristics of the chip frame line for recognition to obtain the envelope result of the inner and outer frames, that is, to recognize the specific structure of the chip. Further, in order to accurately assign the corresponding welding pulse parameters, it is necessary to predict and analyze the pulse parameters in combination with the welding path and welding sequence, and then realize the configuration of accurate and timely pulse frequency and other parameters.

[0027] In this embodiment, edge detection is performed on the image of the VCM motor chip to be welded in step S1, and a plurality of edge pixel points are obtained, such as Figure 2 As shown, the part with a gray value of 1 in the figure is the edge pixel point of the VCM motor chip to be welded, and the part with a gray value of 0 is the background part and the non-edge part on the VCM motor chip to be welded.

[0028] In order to assign precise welding pulse parameters, it is necessary to identify the specific position distribution of edge pixel points, that is, whether the edge pixel points are on the outer frame edge line or the inner frame edge line of the motor spring piece, and then adjust the corresponding pulse parameters according to different requirements.

[0029] When the edge pixel points are on the outer frame line, due to the absence of other pixel points as auxiliary recognition around them and only a certain background exists, their isolation is relatively high, and they can better represent the outermost part of the motor spring piece to be welded. For the outer frame line part, since it is usually relatively long and the requirement for precision is relatively low, extremely high welding details are not required, but a fast welding speed and sufficient welding strength are required; when welding the outer frame, pulse lasers with shorter pulses and lower frequencies can be used. This method reduces heat accumulation, ensures that the outer frame welding area will not generate a large heat affected zone or material deformation due to excessive heat input, and improves welding efficiency at the same time. Based on the above characteristics, next, analyze the regional isolation of edge pixel points and identify the inner and outer frame lines in combination with the structural characteristics of the frame.

[0030] In this embodiment, an edge pixel point is taken as an example for illustration, and the method provided in this embodiment can be used to process other edge pixel points.

[0031] Specifically, any edge pixel point is denoted as a candidate pixel point, and the quantity isolation value of the candidate pixel point is obtained according to the number of edge pixel points in each preset direction of the candidate pixel point. The number of edge pixel points in each preset direction of the candidate pixel point has a negative correlation with the quantity isolation value.

[0032] In this embodiment, there are a total of four preset directions, namely the upper direction, the lower direction, the left direction, and the right direction.

[0033] Among them, the negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by the actual application.

[0034] In this embodiment, the specific calculation formula of the quantity isolation value is given. The quantity isolation value of the u-th edge pixel point can be expressed as: Among them, represents the quantity isolation value of the u-th edge pixel point, represents the number of preset directions, represents the number of edge pixel points in the i-th preset direction of the u-th edge pixel point, represents the preset first adjustment parameter.

[0035] In this embodiment, a preset first adjustment is introduced into the calculation formula of the quantity isolation value to prevent the denominator from being 0. In this embodiment, the value of the preset first adjustment parameter is 0.01. In specific applications, the implementer can set it according to specific circumstances. When there are fewer edge pixels in each preset direction of the u-th edge pixel, the number of frame orders of the u-th edge pixel in all preset directions is lower. At this time, its corresponding isolation is higher, and it is more likely to be part of the outer frame of the motor shrapnel, that is, the quantity isolation value of the u-th edge pixel is larger.

[0036] Furthermore, when the edge pixel is a pixel of the outer frame part, due to space limitations, there must be a preset direction in which the number of edge pixels is 0. Therefore, this feature is added to the isolation judgment to obtain the isolation score. For a candidate pixel: calculate the first sum value of the number of preset directions in which the number of edge pixels in all preset directions of the candidate pixel is 0 and the constant 1; determine the normalized result of the product between the quantity isolation value of the candidate pixel and the first sum value as the isolation score of the candidate pixel.

[0037] In this embodiment, a specific calculation formula for the isolation score is given. The isolation score of the u-th edge pixel can be expressed as: Where, represents the isolation score of the u-th edge pixel, represents the quantity isolation value of the u-th edge pixel, represents the number of preset directions in which the number of edge pixels in all preset directions of the u-th edge pixel is 0, and norm( ) represents the linear normalization function, represents the first sum value.

[0038] When there are more preset directions in which the number of edge pixels in all preset directions of the u-th edge pixel is 0 and the quantity isolation value of the u-th edge pixel is larger, it is closer to the distribution law of the outer frame pixels, that is, the isolation score of the u-th edge pixel is larger.

[0039] By using the above method, the isolation score of each edge pixel can be obtained. Arrange the isolation scores of all edge pixels in descending order to obtain an isolation score sequence; calculate the numerical difference between every two adjacent elements in the isolation score sequence; determine the edge pixels corresponding to all elements before the latter element among the two elements corresponding to the largest numerical difference as the outer frame pixels, that is, multiple outer frame pixels are screened out from all edge pixels.

[0040] In this embodiment, multiple outer frame pixels are screened in the above steps. Then, convex hull detection is performed on all outer frame pixels to obtain the corresponding convex hull area, and the center point of the convex hull area is used as the center of the motor spring. Convex hull detection is a prior art and will not be described in detail here.

[0041] Then, multiple rays are drawn with the center of the motor shrapnel as the starting point. The starting points of these rays are the same, that is, the center of the motor shrapnel. In this embodiment, the angle between each two adjacent rays is set to 3°, that is, multiple rays in different directions are obtained.

[0042] For any ray: Take the pixel point adjacent to the starting point of the ray as the starting point, and obtain the first edge pixel along the ray as the inner border pixel point. Use the above method to process each ray to obtain multiple inner border pixels.

[0043] Step S3, obtaining the welding path overlap based on the position difference between the welding point and the envelope pixel point in the continuous multi-frame welding image, wherein the continuous multi-frame welding image is an image of the motor shrapnel collected during the process of welding the VCM motor shrapnel to be welded using precision laser welding technology, and the envelope pixel point includes the outer frame pixel point and the inner frame pixel point.

[0044] To evaluate the current welding results and achieve adaptive adjustment of welding parameters, it is necessary to analyze welding images from different frames. Therefore, it is necessary to analyze welding results at different times to obtain the final predicted configuration. Therefore, this embodiment captures multiple frames of welding images of the VCM motor shrapnel to be welded within the current time period. The current time period is the set of all historical moments whose time interval with the current moment is less than or equal to a preset duration. It should be noted that the current time period is the time period during which the VCM motor shrapnel to be welded is welded using precision laser welding technology. In this embodiment, the preset duration is 2 minutes. In specific applications, the implementer can set the preset duration and welding image acquisition frequency based on specific circumstances. Thus, multiple consecutive frames of welding images of the VCM motor shrapnel welding process have been captured. It should be noted that all welding images captured in this embodiment are of the same size as the image of the VCM motor shrapnel to be welded captured in step S1. That is, the field of view and position of the image acquisition device remain fixed during the capture of all images.

[0045] For any frame of welding image, obtain the infrared value of each pixel point in the frame of welding image, take the pixel point with the maximum infrared value as the welding point, and respectively take the outer frame pixel point closest to the welding point as the first reference point and the inner frame pixel point closest to the welding point as the second reference point. It should be noted that: if there is more than one pixel point with the maximum infrared value in a frame of welding image, then take the pixel point in the welding image that is the same as the center position of the motor chip in the image of the VCM motor chip to be welded as the mapping point of the center of the motor chip, and take the pixel point with the maximum infrared value that is closest to the mapping point of the center of the motor chip as the welding point. By using this method, the welding point in each frame of welding image and the corresponding first reference point and second reference point in each frame of welding image can be obtained.

[0046] According to the coordinate differences between the welding points and the corresponding first reference points in all welding images, obtain the coincidence degree of the outer welding path; according to the coordinate differences between the welding points and the corresponding second reference points in all welding images, obtain the coincidence degree of the inner welding path; where the welding point is the pixel point with the highest infrared value in the welding image; the coincidence degree of the welding path includes the coincidence degree of the outer welding path and the coincidence degree of the inner welding path.

[0047] In this embodiment, specific calculation formulas for the coincidence degree of the outer welding path and the coincidence degree of the inner welding path are given. The coincidence degree of the outer welding path and the coincidence degree of the inner welding path can be respectively expressed as: Among them, represents the coincidence degree of the outer welding path, represents the coincidence degree of the inner welding path, U represents the number of welding images, represents the difference in the abscissa between the welding point and the corresponding first reference point in the u-th frame of welding image, represents the difference in the ordinate between the welding point and the corresponding first reference point in the u-th frame of welding image, represents the difference in the abscissa between the welding point and the corresponding second reference point in the u-th frame of welding image, represents the difference in the ordinate between the welding point and the corresponding second reference point in the u-th frame of welding image, represents the absolute value symbol.

[0048] It should be noted that: in this embodiment, both the difference in the abscissa and the difference in the ordinate are characterized by the absolute value of the difference between the corresponding coordinates.

[0049] Adding a constant 1 to the denominator in the calculation formulas of the coincidence degree of the outer welding path and the coincidence degree of the inner welding path is to prevent the denominator from being 0. Used to characterize the coordinate difference between the welding points in the u-th frame of the welding image and the corresponding first reference point. The larger this value is, the greater the coordinate difference between the two points and the farther the distance between the two points. Used to characterize the coordinate difference between the welding points in the u-th frame of the welding image and the corresponding second reference point. The larger this value is, the greater the coordinate difference between the two points and the farther the distance between the two points.

[0050] So far, by using the above method, the welding path coincidence degree has been obtained, where the welding path coincidence degree includes the outer welding path coincidence degree and the inner welding path coincidence degree.

[0051] Step S4, adjust the pulse parameters according to the welding path coincidence degree.

[0052] In this embodiment, the outer welding path coincidence degree and the inner welding path coincidence degree are obtained in the above steps. Next, the pulse parameters will be adjusted based on the outer welding path coincidence degree and the inner welding path coincidence degree.

[0053] Specifically, if the outer welding path coincidence degree is greater than a preset first threshold, continue welding with short-wave pulses and pulsed laser at a low frequency (the lowest gear); this method reduces heat accumulation, ensures that the outer frame welding area will not generate a large heat-affected zone or material deformation due to excessive heat input, and improves welding efficiency at the same time. If the outer welding path coincidence degree is less than or equal to the preset first threshold and the inner welding path coincidence degree is greater than the preset first threshold, continue welding with short-wave pulse width and high-frequency pulsed laser (the highest gear), making the welding more precise, the welding points smaller, and the heat-affected zone more concentrated and controllable; otherwise, continue welding using the welding pulse parameters of the inner frame line. In this embodiment, the preset first threshold is 0.95. In specific applications, the implementer can set it according to specific circumstances.

[0054] So far, by using the method provided in this embodiment, the adaptive adjustment of the pulse parameters during the laser welding process has been completed.

[0055] This embodiment first obtains the edge pixel points in the image of the VCM motor shrapnel to be welded, then combines the structural characteristics of the inner and outer frame lines of the VCM motor shrapnel to be welded, identifies the outer frame pixel points and the inner frame pixel points from all the edge pixel points, collects multiple frames of welding images during the welding process of the VCM motor shrapnel to be welded, and evaluates the welding path coincidence degree based on the position difference between the welding points and the envelope pixel points in the collected multiple frames of welding images, that is, judges the specific welding position, and assigns corresponding welding pulse parameters according to the judgment result. The method provided in this embodiment adapts the pulse parameters of the laser welding, eliminates the problem of reduced welding accuracy and quality caused by the thermal effect of welding, and improves the welding quality of the motor shrapnel.

[0056] Embodiment of a precision laser welding control device for a VCM motor: A precision laser welding control device for a VCM motor in this embodiment includes a memory and a processor. The processor executes the computer program stored in the memory to implement the precision laser welding control method for the VCM motor described above.

[0057] Embodiment of a precision laser welding control system for a VCM motor: As Figure 3 shown, the figure shows a structural block diagram of a precision laser welding control system for a VCM motor. The system includes an image acquisition module, a screening module, a calculation module, and a control module; Among them, the image acquisition module is used to obtain the edge pixel points in multiple frames of monitoring images of the VCM motor shrapnel to be welded; The screening module is used to obtain the isolation score of each edge pixel point according to the number distribution of edge pixel points in different preset directions of each edge pixel point; use the isolation score to screen the outer frame pixel points; make rays in several directions with the center of the shrapnel as the starting point of the ray, and obtain the inner frame pixel points according to the position distribution of the edge pixel points on the ray, and the center of the shrapnel is determined based on the outer frame pixel points; The calculation module is used to obtain the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in consecutive multiple frames of welding images. The consecutive multiple frames of welding images are images of the shrapnel collected during the process of welding the VCM motor shrapnel to be welded using precision laser welding technology, and the envelope pixel points include outer frame pixel points and inner frame pixel points; The control module is used to adjust the pulse parameters according to the welding path coincidence degree.

[0058] It should be understood that Figure 3The block diagram of the structure of a precision laser welding control system for a VCM motor and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented through hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer-executable instructions and / or included in processor control code. For example, such code is provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the above hardware circuits and software (e.g., firmware).

[0059] For more details about each of the above modules, reference can be made to other parts of this specification, and no further elaboration will be provided here.

[0060] In other embodiments, a medium is also provided, and the medium stores at least one program that can be run by a computer. When the at least one program is run by the computer, the computer is caused to execute the steps in the precision laser welding control method for a VCM motor in the above embodiments. The medium can be a computer-readable storage medium.

[0061] Among them, the provided device, system, and medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and no further elaboration will be provided here.

[0062] It should be noted that: The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A precise laser welding control method for a VCM motor, characterized in that, The method includes the following steps: Obtain edge pixel points in the image of the VCM motor shrapnel to be welded; According to the number distribution of edge pixel points in different preset directions of each edge pixel point, obtain the isolation score of each edge pixel point; use the isolation score to screen out outer frame pixel points; draw rays in several directions with the center of the motor shrapnel as the starting point of the ray, and obtain inner frame pixel points according to the position distribution of edge pixel points on the ray, and the center of the motor shrapnel is determined based on the outer frame pixel points; Obtain the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in consecutive multi-frame welding images, where the consecutive multi-frame welding images are images of the motor shrapnel collected during the process of welding the VCM motor shrapnel to be welded using precision laser welding technology, and the envelope pixel points include outer frame pixel points and inner frame pixel points; Adjust the pulse parameters according to the welding path coincidence degree.

2. The precision laser welding control method for a VCM motor according to claim 1, wherein The obtaining of the isolation score of each edge pixel point according to the number distribution of edge pixel points in different preset directions of each edge pixel point includes: Obtain the number isolation value of the candidate pixel point according to the number of edge pixel points in each preset direction of the candidate pixel point, and the number of edge pixel points in each preset direction of the candidate pixel point has a negative correlation with the number isolation value; Obtain the isolation score of the candidate pixel point according to the number of preset directions with the number of edge pixel points being 0 in all preset directions of the candidate pixel point and the number isolation value; The candidate pixel point is any edge pixel point, and the preset directions include above, below, left, and right.

3. The precision laser welding control method for a VCM motor according to claim 2, characterized in that The obtaining of the isolation score of the candidate pixel point according to the number of preset directions with the number of edge pixel points being 0 in all preset directions of the candidate pixel point and the number isolation value includes: Calculate the first sum value of the number of preset directions with the number of edge pixel points being 0 in all preset directions of the candidate pixel point and the constant 1; Determine the normalized result of the product between the number isolation value of the candidate pixel point and the first sum value as the isolation score of the candidate pixel point.

4. The precision laser welding control method for a VCM motor according to claim 1, wherein The screening of the outer frame pixel points using the isolation score includes: Arrange the isolation scores of all edge pixel points in descending order to construct an isolation score sequence; Calculate the numerical difference between every two adjacent elements in the isolation score sequence; determine the edge pixel points corresponding to all elements before the latter element among the two elements corresponding to the largest numerical difference as the outer frame pixel points.

5. The precision laser welding control method for a VCM motor according to claim 1, wherein The obtaining of the center of the motor shrapnel includes: performing a convex hull detection on all outer frame pixel points to obtain the corresponding convex hull area, and taking the center point of the convex hull area as the center of the motor shrapnel.

6. The precision laser welding control method for a VCM motor according to claim 1, characterized in that The obtaining of the inner frame pixel points according to the position distribution of edge pixel points on the ray includes: Taking the pixel point adjacent to the starting point of the ray on the ray as the starting point, and obtaining the first edge pixel point along each ray as the inner frame pixel point.

7. The precision laser welding control method for a VCM motor according to claim 1, characterized in that The obtaining of the welding path coincidence degree according to the position difference between the welding points and the envelope pixel points in consecutive multi-frame welding images includes: The outermost frame pixel point and the innermost frame pixel point closest to the welding point are respectively used as the first reference point and the second reference point; According to the coordinate differences between the welding points and the corresponding first reference points in all welding images, the coincidence degree of the outer welding path is obtained; according to the coordinate differences between the welding points and the corresponding second reference points in all welding images, the coincidence degree of the inner welding path is obtained; wherein the welding point is the pixel point with the highest infrared value in the welding image; The welding path coincidence degree includes the coincidence degree of the outer welding path and the coincidence degree of the inner welding path.

8. The precision laser welding control method for a VCM motor according to claim 7, wherein, The adjusting the pulse parameters according to the welding path coincidence degree includes: If the coincidence degree of the outer welding path is greater than a preset first threshold, continue welding with a short-wave pulse and a pulsed laser with a low frequency; if the coincidence degree of the outer welding path is less than or equal to the preset first threshold and the coincidence degree of the inner welding path is greater than the preset first threshold, continue welding with a short-wave pulse width and a pulsed laser with a high frequency; otherwise, continue welding using the welding pulse parameters of the inner frame line.

9. A precision laser welding control device for a VCM motor, comprising a memory and a processor, characterized in that, The processor executes the computer program stored in the memory to implement the precision laser welding control method for a VCM motor according to any one of claims 1-8.

10. A precision laser welding control system for a VCM motor, characterized in that, The system includes: An image acquisition module for acquiring edge pixel points in multiple frames of monitoring images of the VCM motor shrapnel to be welded; A screening module for obtaining the isolation score of each edge pixel point according to the number distribution of edge pixel points in different preset directions of each edge pixel point; screening the outermost frame pixel points using the isolation score; making rays in several directions with the center of the motor shrapnel as the starting point of the ray, and obtaining the innermost frame pixel points according to the position distribution of the edge pixel points on the ray, wherein the center of the motor shrapnel is determined based on the outermost frame pixel points; A calculation module for obtaining the welding path coincidence degree according to the position differences between the welding points and the envelope pixel points in multiple consecutive frames of welding images, wherein the multiple consecutive frames of welding images are images of the motor shrapnel acquired during the process of welding the VCM motor shrapnel to be welded using the precision laser welding technology, and the envelope pixel points include the outermost frame pixel points and the innermost frame pixel points; A control module for adjusting the pulse parameters according to the welding path coincidence degree.

Images