Laser processing method, system, equipment and medium based on machine vision

Abstract

The present application relates to a laser processing method, system, equipment and medium based on machine vision, and relates to the field of laser processing technology, which includes: identifying all planes of the processed object, mapping the preset cutting path to each plane; obtaining the focus moving path of the laser cutting head according to the preset cutting path; obtaining the light spot moving path actually cutting the processed object; correcting the preset cutting path according to the light spot moving path and the focus moving path; feeding back the corrected preset cutting path to the laser cutting control system, and dynamically adjusting the position of the laser cutting head. The present application can correct the deviation of the cutting path caused by the instability of the laser beam during the cutting of the processed object, so as to improve the accuracy of laser cutting.

Description

Technical Field

[0001] The present application relates to the field of laser processing technology, and in particular to a laser processing method, system, equipment and medium based on machine vision. Background Art

[0002] In modern manufacturing, laser processing technology plays a vital role. Laser processing technology is not only widely used in material cutting, engraving, marking and structural processing, but also with the continuous advancement of industrial automation and intelligent manufacturing, it puts forward higher standards for processing accuracy and speed.

[0003] At present, the machine vision system integrated in the laser cutting equipment can automatically identify the position and features of the workpiece, realize the rapid positioning of the workpiece and the automatic planning of the processing path. Through the correction and compensation of machine vision, the accuracy of the galvanometer laser processing system can be greatly improved, which improves the accuracy and automation level of laser processing to a certain extent and reduces the dependence on manual operation.

[0004] However, the existing technology has insufficient recognition accuracy for cutting trajectories of multi-sided processing objects, especially when problems such as laser beam output power fluctuations, mode instability or beam divergence may cause unstable cutting trajectory accuracy, and the real-time correction capability of the cutting trajectory is limited. Summary of the invention

[0005] The first purpose of the present application is to provide a laser processing method based on machine vision, which can correct the deviation of the cutting path caused by the instability of the laser beam during the cutting process of the processed object, so as to improve the accuracy of laser cutting.

[0006] This application provides a laser processing method based on machine vision, which adopts the following technical solutions:

[0007] A laser processing method based on machine vision, comprising:

[0008] Identify all planes of the object to be processed and map the preset cutting path to each plane;

[0009] According to the preset cutting path, obtaining the focus moving path of the laser cutting head;

[0010] Get the actual moving path of the light spot when cutting the object;

[0011] Correcting the preset cutting path according to the light spot moving path and the focus moving path;

[0012] The corrected preset cutting path is fed back to the laser cutting control system to dynamically adjust the position of the laser cutting head.

[0013] By adopting the above technical solution, since the spot of the laser beam emitted by the laser cutting head directly contacts the cutting surface of the processed object, the direct positioning of the spot can more accurately reflect the actual cutting path, and the spot movement path and the focus movement path are fitted and corrected, which effectively compensates for the cutting path deviation caused by the instability of the laser beam or the uneven surface of the workpiece, thereby improving the accuracy of laser cutting.

[0014] In a preferred example, the present application can be further configured as follows: the step of obtaining the actual moving path of the light spot in cutting the processed object includes:

[0015] Get the actual position of the center of the light spot cutting the object to be processed;

[0016] Connect the centers of several light spots on each plane of the processed object to obtain the moving path of the light spot on each plane.

[0017] By adopting the above technical solution, the light spot moving path formed by connecting the centers of the light spot circles can be accurately compared with the focus moving path, thereby further improving the accuracy of laser cutting.

[0018] In a preferred example, the present application can be further configured as follows: the step of obtaining the position of the center of the light spot actually cut on the processed object includes:

[0019] Performing image processing on the image captured by the camera to determine whether the light spot is circular or elliptical;

[0020] If the light spot is circular or elliptical, calculate and obtain the position of the center of the light spot;

[0021] If the light spot is not circular or elliptical, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

[0022] By adopting the above technical solution, the light spot movement path of processing objects of different shapes can be obtained, and the laser cutting path can be accurately corrected.

[0023] In a preferred example, the present application may be further configured as follows: if the light spot is not circular or elliptical, the step of obtaining the center point of the light spot as the center of the light spot, and obtaining the position of the center point of the light spot includes:

[0024] Determine the number of plane positions where the light spots appear on the actual processed object, and if the light spots appear on one plane, generate a warning message of abnormal cutting;

[0025] If the light spot appears in multiple planes, the plane position of the light spot in the actual processed object is obtained, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

[0026] By adopting the above technical solution, if a non-circular or elliptical light spot appears on a plane, it is considered to be a light spot caused by the instability of the laser beam, and an early warning message of abnormal cutting can be issued in time to remind. If non-circular or elliptical light spots appear on multiple planes, it is considered that the laser beam has moved to the intersection of multiple planes of the processed object. The center point of the light spot can be analogized as the center of the light spot circle, thereby reducing the loss of the light spot movement path.

[0027] In a preferred example, the present application can be further configured as follows: if the light spot appears in multiple planes, the steps of obtaining the plane position of the light spot in the actual processed object, obtaining the center point of the light spot as the center of the light spot, and obtaining the position of the center point of the light spot include:

[0028] The contour of the light spot is analyzed by a centroid algorithm to obtain the center point of the light spot.

[0029] By adopting the above technical solution, the center point of the light spot calculated by the centroid algorithm is used to restore the planar position of the center of the light spot circle, and the center point of the light spot is connected with the centers of other light spots to reduce the loss of the light spot movement path.

[0030] In a preferred example, the present application may be further configured as follows: before the step of correcting the preset cutting path according to the light spot moving path and the focus moving path, the step further includes:

[0031] According to the spatial position of the plane where the center of the light spot is located, the focus moving path of the plane where the light spot is located is retrieved.

[0032] By adopting the above technical solution, the laser cutting path is corrected for each plane to improve the accuracy of the laser cutting path correction.

[0033] In a preferred example, the present application can be further configured as follows: the step of correcting the preset cutting path according to the light spot moving path and the focus moving path includes:

[0034] Fitting the focus moving path of the plane where the light spot is located with the light spot moving path, and calculating the error between the light spot moving path and the focus moving path;

[0035] The preset cutting path is corrected according to the errors of the light spot moving paths and the focus moving paths by using a machine learning algorithm.

[0036] By adopting the above technical solution, the machine learning algorithm is used to learn the error of the laser cutting path of each plane, so as to realize real-time automatic correction of the laser cutting path.

[0037] In the second aspect, the present application provides a laser processing system based on machine vision, which adopts the following technical solution:

[0038] A laser processing system based on machine vision, comprising:

[0039] Preset path matching module: used to identify all planes of the processed object and map the preset cutting path to each plane;

[0040] Preset path simulation module: used to obtain the focus movement path of the laser cutting head according to the preset cutting path;

[0041] Actual path acquisition module: used to obtain the actual moving path of the light spot when cutting the processed object;

[0042] Preset path correction module: used to correct the preset cutting path according to the light spot moving path and the focus moving path;

[0043] Actual path correction module: used to feed back the corrected preset cutting path to the laser cutting control system to dynamically adjust the position of the laser cutting head.

[0044] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0045] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned laser processing method based on machine vision are implemented.

[0046] In a fourth aspect, the present application provides a computer storage medium, the following technical solution:

[0047] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned laser processing method based on machine vision are implemented.

[0048] In summary, this application has the following beneficial technical effects:

[0049] Since the spot of the laser beam directly contacts the plane of the processed object for cutting, the movement trajectory of the spot can reflect the actual cutting trajectory. The present application can effectively correct the cutting path deviation caused by unstable laser beam or uneven workpiece surface by fitting and correcting the spot movement path and the focus movement path, thereby improving the accuracy of laser cutting. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flow chart of a laser processing method structure based on machine vision in one embodiment of the present application.

[0051] Figure 2 It is a sub-step flow chart of step S3 in one embodiment of the present application.

[0052] Figure 3 It is a sub-step flow chart of step S30 in one embodiment of the present application.

[0053] Figure 4 It is a sub-step flow chart of step S302 in one embodiment of the present application.

[0054] Figure 5 It is a sub-step flow chart of step S3021 in one embodiment of the present application.

[0055] Figure 6 This is a flowchart of steps added before step S4 in one embodiment of the present application.

[0056] Figure 7 It is a sub-step flow chart of step S4 in one embodiment of the present application.

[0057] Figure 8 It is a structural schematic diagram of a laser processing system based on machine vision in one embodiment of the present application.

[0058] Fig. 9 It is a principle block diagram of an electronic device in one embodiment of the present application.

[0059] Figure numerals: 1. preset path matching module; 2. preset path simulation module; 3. actual path acquisition module; 4. preset path correction module; 5. actual path correction module. DETAILED DESCRIPTION

[0060] The following is combined with Figure 1-9 This application is described in further detail.

[0061] refer to Figure 1 , a laser processing method based on machine vision, specifically comprising:

[0062] A laser processing method based on machine vision, comprising:

[0063] S1. Identify all planes of the object to be processed and map the preset cutting path to each plane.

[0064] Specifically, the complete processed object can be photographed through a CDD camera or other shooting device, and then the captured image can be pre-processed by graying, filtering and other operations to improve the image quality. The edge detection algorithm can be used to identify the edge features in the image, and the image segmentation technology can be applied to segment the image into different areas. The feature points and edge information can be used to detect the planar area on the surface of the processed object through geometric analysis.

[0065] The preset cutting path is a moving path pre-planned by the technician based on the three-dimensional modeling of the processing object, generated by CAD, converted into G code through CAM, and transmitted to the laser cutting device through RS232, providing a data basis for the subsequent correction of the light spot moving path in units of planes. In another embodiment, the G code can be transmitted to the laser cutting device via Ethernet.

[0066] S2. According to the preset cutting path, the focus moving path of the laser cutting head is obtained.

[0067] Specifically, the laser cutting equipment controls the laser head to move along the preset cutting path according to the received G code instructions. According to the actual laser cutting requirements, the focal length of the laser beam may need to be changed when cutting on the preset cutting path, and the size of the laser beam may be inconsistent. In order to provide a more accurate preset cutting path, the focus movement path is mapped with a unified laser beam focus as the unit.

[0068] S3, obtaining the actual moving path of the light spot when cutting the processed object.

[0069] Specifically, the laser cutting process can be filmed by a shooting device such as a CDD camera, and each frame of the filmed video is processed to obtain a light spot. Several light spots are connected according to the time series of all images to form a light spot movement path.

[0070] S4. Correct the preset cutting path according to the light spot moving path and the focus moving path.

[0071] Specifically, the light spot moving path and the focus moving path are mapped in a two-dimensional coordinate system, and the line formed by the two paths is corrected.

[0072] S5. Feedback the corrected preset cutting path to the laser cutting control system to dynamically adjust the position of the laser cutting head.

[0073] In this embodiment, the precise cutting path of the laser beam is simulated by the focus moving path, and the laser beam spot directly acts on the cutting surface of the processing object, so the position of the positioning spot can more realistically reflect the actual cutting trajectory of the laser beam. The CDD camera monitors the position of the spot in real time and feeds back the spot moving path to the laser control system. The laser control system adjusts the cutting parameters according to the feedback, and then executes the adjusted cutting path through the laser cutting head to form a closed-loop system. By fitting and correcting the spot moving path and the focus moving path, the cutting path deviation caused by the laser beam fluctuation can be effectively compensated, thereby improving the accuracy of laser cutting.

[0074] refer to Figure 2Further, in one embodiment, step S3 is refined into the following sub-steps:

[0075] S30, obtaining the position of the center of the light spot actually cutting the processed object.

[0076] Specifically, the spot shape is usually a circle or ellipse with a Gaussian distribution, which means that the energy density is highest at the center of the spot and gradually decreases toward the edge. This shape is conducive to rapid heating and melting of the material, thereby achieving efficient cutting.

[0077] In the process of acquiring the light spot, we first receive the image data in the video captured by the CDD camera, pre-process the image data through Gaussian filtering, and then segment the part with the highest grayscale value, that is, separate the light spot from the background in the image. Then, we use the centroid algorithm for the segmented light spot to finally obtain the center of the light spot.

[0078] In addition, in actual operation, some special measures are usually required, such as using neutral density filters to reduce the brightness of the laser to ensure that the shape of the light spot can be captured while protecting the safety of the camera and technicians.

[0079] S31, connecting the centers of several light spots on each plane of the processed object to obtain the moving path of the light spot on each plane.

[0080] In this embodiment, the actual laser cutting path is accurately determined to be a light spot moving path connected by the center of the light spot circle, and the light spot moving path is compared with the focus moving path in a point-to-point manner, thereby further improving the accuracy of laser cutting.

[0081] In addition, reference Figure 3 Further, in one embodiment, step S30 is refined into the following sub-steps:

[0082] S300: performing image processing on the image captured by the camera to determine whether the light spot is circular or elliptical.

[0083] Specifically, in the actual laser cutting process, the cutting shape of the laser beam is usually circular or elliptical. Therefore, under normal circumstances, when the laser beam is not affected by the environment or the laser cutting head is not damaged, the spot formed by the laser beam on the processed object is circular or elliptical.

[0084] S301: If the light spot is circular or elliptical, calculate and obtain the position of the center of the light spot.

[0085] S302: If the light spot is not circular or elliptical, obtain the center point of the light spot as the center of the light spot circle, and obtain the position of the center point of the light spot.

[0086] Specifically, when the light spot is not circular or elliptical, the center point of the light spot is analogous to the center of the light spot circle, and discontinuity in the moving path of the light spot is avoided as much as possible.

[0087] In this embodiment, the laser beam may be deformed due to the influence of the environment or a malfunction of the laser cutting head, or the laser beam may be irradiated at the junction of different planes of a multi-sided processing object. Therefore, in order to ensure the cutting accuracy, it is necessary to find the center point of the deformed light spot as the center of the light spot.

[0088] In addition, reference Figure 4 Further, in one embodiment, step S302 is refined into the following sub-steps:

[0089] S3020, determining the number of plane positions where the light spots appear on the actual processed object, and if the light spots appear on one plane, generating a warning message of cutting abnormality.

[0090] Specifically, when the light spot appears on a plane, there will be basically no deformation on the surface of the processed object due to flatness issues. What should be considered is the change of the light spot caused by the laser cutting equipment or environmental factors. Timely generation of warning information on cutting abnormalities can remind technicians to check the laser cutting equipment or environment and eliminate the cause of the abnormality.

[0091] S3021. If the light spot appears in multiple planes, the plane position of the light spot in the actual processed object is obtained, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

[0092] Specifically, when the light spot appears on multiple planes, that is, when the light spot appears on more than one plane of the processed object, it is considered that the current light spot falls at the intersection of the planes of the processed object. At this time, the light spot is not circular or elliptical, but an irregular shape projected by the light spot on multiple planes.

[0093] In this embodiment, when a non-circular or non-elliptical light spot is detected to appear on one plane, it is generally considered that the laser cutting is abnormal; when a non-circular or non-elliptical light spot is detected to appear on multiple planes, it can be considered that the laser beam has moved to the junction of different planes of the processing object, thereby reducing the cutting error caused by the loss of the light spot movement path and improving the accuracy of laser cutting.

[0094] In addition, reference Figure 5 Further, in one embodiment, step S3021 is refined into the following sub-steps:

[0095] S30210. Analyze the contour of the light spot by using a centroid algorithm to obtain the center point of the light spot.

[0096] In this embodiment, the irregular light spot is first grayed, a Gaussian filter is applied for noise reduction, an edge detection algorithm is used to identify and extract the outline of the light spot, the largest outline is selected from the extracted outlines of the light spot, that is, the outline formed by the light spot, the center point of the light spot is obtained by using the centroid algorithm, the center point of the light spot is connected with the light spot on the same plane, and the moving path of the light spot is obtained, thereby reducing the loss of the moving path of the light spot.

[0097] In addition, reference Figure 6 Further, in one embodiment, before step S4, step S40 is added:

[0098] S40, according to the spatial position of the plane where the center of the light spot is located, retrieve the focus moving path of the plane where the light spot is located.

[0099] In this embodiment, the laser cutting head can be calibrated at different incident angles to improve the accuracy of the laser cutting path correction.

[0100] In addition, reference Figure 7 Further, in one embodiment, step S4 is refined into the following sub-steps:

[0101] S41, fitting the focus moving path of the plane where the light spot is located with the light spot moving path, and calculating the error between the light spot moving path and the focus moving path.

[0102] S42. Using a machine learning algorithm, the preset cutting path is corrected according to the errors of a number of light spot moving paths and focus moving paths.

[0103] In this embodiment, in the two-dimensional coordinate system, the error between the two lines composed of two paths can be calculated by the least squares method, and the error of each incident angle of the laser cutting head can be learned by the machine learning algorithm, so that the laser cutting path can be made closer to the preset cutting path, thereby realizing real-time correction of the laser cutting path.

[0104] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0105] The embodiment of the present application also provides a machine vision-based laser processing system, which corresponds one-to-one to the machine vision-based laser processing method in the embodiment.

[0106] refer to Figure 8, a laser processing system based on machine vision includes: a preset path matching module 1, a preset path simulation module 2, an actual path acquisition module 3, a preset path correction module 4, and an actual path correction module 5. The functional modules are described in detail as follows:

[0107] Preset path matching module 1: used to identify all planes of the processed object and map the preset cutting path to each plane;

[0108] Preset path simulation module 2: used to obtain the focus moving path of the laser cutting head according to the preset cutting path;

[0109] Actual path acquisition module 3: used to obtain the actual moving path of the light spot when cutting the processed object;

[0110] Preset path correction module 4: used to correct the preset cutting path according to the light spot moving path and the focus moving path;

[0111] Actual path correction module 5: used to feed back the corrected preset cutting path to the laser cutting control system and dynamically adjust the position of the laser cutting head.

[0112] Among them, the preset path matching module 1 identifies each plane of the processing object and accurately maps the preset cutting path to each plane; the preset path simulation module 2 calculates the focus moving path of the laser cutting head according to the preset cutting path, providing a basis for the simulation of the cutting path; in the actual cutting process, the actual path acquisition module 3 monitors and records the moving path of the light spot on the processing object in real time, that is, the light spot moving path, to capture the actual cutting situation; the preset path correction module 4 accurately corrects the preset cutting path by comparing the light spot moving path with the focus moving path to compensate for the cutting path offset caused by the instability of the laser beam; the actual path correction module 5 feeds back the corrected preset cutting path to the laser cutting control system to dynamically adjust the position of the laser cutting head and correct the cutting path in real time. Through the combination of various modules, laser cutting can maintain high precision and stability, effectively improving the accuracy of laser cutting technology, especially in the case of unstable laser beam, the precise control of the cutting path is achieved through dynamic adjustment.

[0113] For the specific definition of the laser processing system based on machine vision, please refer to the definition of the laser processing method based on machine vision in the context, which will not be repeated here. Each module in the above-mentioned laser processing system based on machine vision can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. In one embodiment, an electronic device is provided, which is a user terminal. Reference Fig. 9 , the electronic device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store a detection data table. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a laser processing method based on machine vision is implemented.

[0114] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0115] S1. Identify all planes of the object to be processed and map the preset cutting path to each plane.

[0116] S2. According to the preset cutting path, the focus moving path of the laser cutting head is obtained.

[0117] S3, obtaining the actual moving path of the light spot when cutting the processed object.

[0118] S4. Correct the preset cutting path according to the light spot moving path and the focus moving path.

[0119] S5. Feedback the corrected preset cutting path to the laser cutting control system to dynamically adjust the position of the laser cutting head.

[0120] In one embodiment, the detailed sub-steps of step S3 include:

[0121] S30, obtaining the position of the center of the light spot actually cutting the processed object.

[0122] S31, connecting the centers of several light spots on each plane of the processed object to obtain the moving path of the light spot on each plane.

[0123] In one embodiment, the detailed sub-steps of step S30 include:

[0124] S300, performing image processing on the image captured by the camera to determine whether the light spot is circular or elliptical;

[0125] S301: If the light spot is circular or elliptical, calculate and obtain the position of the center of the light spot.

[0126] S302: If the light spot is not circular or elliptical, obtain the center point of the light spot as the center of the light spot circle, and obtain the position of the center point of the light spot.

[0127] In one embodiment, the detailed sub-steps of step S302 include:

[0128] S3020, determining the number of plane positions where the light spots appear on the actual processed object, and if the light spots appear on one plane, generating a warning message of cutting abnormality.

[0129] S3021. If the light spot appears in multiple planes, the plane position of the light spot in the actual processed object is obtained, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

[0130] In one embodiment, the detailed sub-steps of step S3021 include:

[0131] S30210. Analyze the contour of the light spot by using a centroid algorithm to obtain the center point of the light spot.

[0132] In one embodiment, the steps added before step S4 include:

[0133] S40, according to the spatial position of the plane where the center of the light spot is located, retrieve the focus moving path of the plane where the light spot is located.

[0134] In one embodiment, the detailed sub-steps of step S4 include:

[0135] S41, fitting the focus moving path of the plane where the light spot is located with the light spot moving path, and calculating the error between the light spot moving path and the focus moving path;

[0136] S42. Using a machine learning algorithm, the preset cutting path is corrected according to the errors of a number of light spot moving paths and focus moving paths.

[0137] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0138] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A laser processing method based on machine vision, characterized in that: include: Identify all planes of the object to be processed and map the preset cutting path to each plane; According to the preset cutting path, the focus moving path of the laser cutting head is obtained, wherein the laser cutting device controls the laser cutting head to move along the preset cutting path according to the received G code instruction of the preset cutting path. According to the actual laser cutting requirements, the focal length of the laser beam may need to be changed when cutting on the preset cutting path, and the size of the laser beam may be non-uniform. In order to provide a more accurate preset cutting path, the focus moving path is mapped with a unified laser beam focus as a unit; Get the actual moving path of the light spot when cutting the object; According to the light spot moving path and the focus moving path, the preset cutting path is corrected, wherein the light spot moving path and the focus moving path are mapped in a two-dimensional coordinate system, and a line formed by the two paths is corrected; The corrected preset cutting path is fed back to the laser cutting control system to dynamically adjust the position of the laser cutting head.

2. The method according to claim 1, characterized in that: The step of obtaining the actual moving path of the light spot cutting the processed object comprises: Get the actual position of the center of the light spot cutting the object to be processed; Connect the centers of several light spots on each plane of the processed object to obtain the moving path of the light spot on each plane.

3. The method according to claim 2, characterized in that The step of obtaining the position of the center of the light spot actually cut on the processed object comprises: Performing image processing on the image captured by the camera to determine whether the light spot is circular or elliptical; If the light spot is circular or elliptical, calculate and obtain the position of the center of the light spot; If the light spot is not circular or elliptical, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

4. The method according to claim 3, characterized in that If the light spot is not circular or elliptical, the step of obtaining the center point of the light spot as the center of the light spot circle and obtaining the position of the center point of the light spot comprises: Determine the number of plane positions where the light spots appear on the actual processed object, and if the light spots appear on one plane, generate a warning message of abnormal cutting; If the light spot appears in multiple planes, the plane position of the light spot in the actual processed object is obtained, the center point of the light spot is obtained as the center of the light spot circle, and the position of the center point of the light spot is obtained.

5. The method according to claim 4, characterized in that If the light spot appears in multiple planes, the step of obtaining the plane position of the light spot on the actual processed object, obtaining the center point of the light spot as the center of the light spot, and obtaining the position of the center point of the light spot comprises: The contour of the light spot is analyzed by a centroid algorithm to obtain the center point of the light spot.

6. The method according to claim 2, characterized in that Before the step of correcting the preset cutting path according to the light spot moving path and the focus moving path, the method further includes: According to the spatial position of the plane where the center of the light spot is located, the focus moving path of the plane where the light spot is located is retrieved.

7. The method according to claim 6, characterized in that The step of correcting the preset cutting path according to the light spot moving path and the focus moving path comprises: Fitting the focus moving path of the plane where the light spot is located with the light spot moving path, and calculating the error between the light spot moving path and the focus moving path; The preset cutting path is corrected according to the errors of the light spot moving paths and the focus moving paths by using a machine learning algorithm.

8. A laser processing system based on machine vision, characterized in that: include: Preset path matching module (1): used to identify all planes of the processed object and map the preset cutting path to each plane; A preset path simulation module (2): used to obtain a focus moving path of a laser cutting head according to the preset cutting path, wherein the laser cutting device controls the laser cutting head to move along the preset cutting path according to the received G code instruction of the preset cutting path. According to actual laser cutting requirements, when cutting on the preset cutting path, it may be necessary to change the focal length of the laser beam, and the size of the laser beam may be inconsistent. In order to provide a more accurate preset cutting path, the focus moving path is mapped with a uniform laser beam focus as a unit; Actual path acquisition module (3): used to acquire the actual moving path of the light spot when cutting the processed object; A preset path correction module (4): used for correcting the preset cutting path according to the light spot moving path and the focus moving path; Actual path correction module (5): used to feed back the corrected preset cutting path to the laser cutting control system to dynamically adjust the position of the laser cutting head.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes any one of the machine vision-based laser processing methods according to claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer program is stored which can be loaded by a processor and executes the laser processing method based on machine vision according to any one of claims 1 to 7.

Images