Intelligent laser and automatic focusing and image correction method thereof for laser processing

Abstract

The invention provides an intelligent laser which comprises an adjusting assembly, and the adjusting assembly comprises a machine shell, a stepping motor, a transmission gear, a conveying rack, a supporting plate, a heat dissipation frame, a laser machine body and two guide optical shafts. A camera is installed on the outer side wall of the machine shell. The laser head camera system is utilized, a large-view-angle top-view camera does not need to be additionally installed, therefore, the machine body size and the system complexity are reduced, a high-precision and distortion-free machining area panorama can be obtained through splicing and correction of multiple images, accurate positioning is achieved, and the machining precision is improved through image definition criteria and automatic focusing control. Rapid and accurate automatic focusing is achieved, the tedious process of manual focusing is omitted, the operation difficulty is reduced, rapid automatic focusing can be achieved according to different workpiece materials and surface height changes, and the machining quality and adaptability are improved.

Description

Technical Field

[0001] The present invention relates to an autofocusing and image correction method, specifically an intelligent laser and its autofocusing and image correction method for laser processing, belonging to the technical field of laser processing equipment. Background Art

[0002] Laser processing equipment is the carrier of laser processing technology. It mainly utilizes the characteristics of the interaction between the laser beam and the material to cut, weld, surface-treat, punch, and micro-machine materials (including metals and non-metals). It is a high-tech product integrating multiple high technologies and has become one of the key technical equipment for developing emerging industries and transforming traditional manufacturing industries.

[0003] Currently, in laser processing equipment (such as laser engraving machines), in order to achieve precise positioning and focusing operations on the processing area, the following means are usually adopted: 1. Wide-angle top-view camera scheme: A wide-angle camera is installed above the processing area to obtain a panoramic image of the working area; however, this scheme requires a large installation space and often has problems such as image distortion and insufficient accuracy. At the same time, in order to obtain a large field of view, the distance between the camera and the workbench increases, resulting in a decrease in resolution and accuracy, affecting subsequent focusing and positioning.

[0004] 2. Traditional focusing method: Focusing is mostly carried out manually or mechanically, such as through thickness measurement, trial engraving, and manual focusing. The operation is complex, and the accuracy and efficiency are not ideal. In addition, some automated focusing schemes still require separate sensors (such as laser rangefinders) or relatively complex system integration, increasing the system cost and complexity.

[0005] Based on the above problems, there is an urgent need to provide an intelligent laser device that can simultaneously meet high-precision imaging and autofocusing. By integrating a camera system and an autofocus mechanism inside the laser emitting head and using camera image processing algorithms, it is possible to achieve autofocusing and distortion-free stitching correction of the entire image without relying on an external wide-angle top-view camera or manual measurement, thereby improving the processing accuracy and operation convenience. For this reason, an intelligent laser and its autofocusing and image correction method for laser processing are proposed. Summary of the Invention

[0006] In view of this, the present invention provides an intelligent laser and its autofocusing and image correction method for laser processing to solve or alleviate the technical problems existing in the prior art and at least provide a beneficial option.

[0007] The technical solution of the embodiment of the present invention is realized as follows: An intelligent laser includes an adjustment component, and the adjustment component includes a machine shell, a stepping motor, a transmission gear, a transmission rack, a support plate, a heat dissipation frame, a laser body, and two guiding optical axes; A camera is installed on the outer side wall of the housing, a laser head is installed at the bottom of the laser machine body, the heat dissipation rack is slidably connected to the inner side wall of the housing, the tops of the two guiding optical axes are symmetrically and fixedly connected to the lower surface of the support plate, the transmission gear is fixedly connected to the output shaft of the stepping motor, and the outer side wall of the transmission gear is meshed with the outer side wall of the transmission rack. The transmission rack, the laser machine body and the guiding optical axes are all installed inside the housing.

[0008] Further preferably, the support plate is fixedly connected to the upper part of the inner side wall of the housing, a heat dissipation fan is installed on the upper surface of the support plate, and a heat dissipation groove adapted to the shape of the heat dissipation fan is provided on the upper surface of the housing.

[0009] Further preferably, mounting grooves and recesses are provided on the outer side wall of the heat dissipation rack, and two through holes are symmetrically provided inside the heat dissipation rack.

[0010] Further preferably, the laser machine body is installed on the inner side wall of the mounting groove, the transmission rack is installed on the inner side wall of the recess, and the guiding optical axis is slidably connected to the inner side wall of the through hole.

[0011] Further preferably, heat dissipation fins are symmetrically arranged on the outer side wall of the heat dissipation rack, and the stepping motor is installed on the inner side wall of the housing.

[0012] Further preferably, a carving material is arranged below the housing, and a lens group that can rotate or axially slide is arranged inside the laser head for automatically focusing by changing the focal point of the light path.

[0013] An automatic focusing and image correction method for laser processing includes an automatic stitching correction method and an automatic focusing method; The automatic stitching correction method includes the following steps: Laser head positioning and shooting: Using the moving ability of the laser head in the X-Y plane, move the camera to a plurality of preset positions, use the camera to shoot the surface to be processed, and obtain multiple images; Image feature recognition: In the multiple images taken, identify calibration marks or known features in the overlapping area, including built-in calibration patterns and calibration points on the processing table; Image stitching: Apply computer vision algorithms to accurately stitch multiple images, and through algorithm processing, generate a distortion-free and complete overall image field of view, that is, a panoramic image; Application of panoramic image: Use the stitched panoramic image to plan the laser processing path, perform processing positioning according to the panoramic image, and use the panoramic image as a real-time reference during processing.

[0014] Further preferably, in the image stitching step, first use the Scale-Invariant Feature Transform (SIFT) algorithm to extract the feature points and their descriptors in each image. Then, use the feature matching algorithm to find the corresponding relationships of these feature points in different images. Use the Random Sample Consensus (RANSAC) algorithm to screen out the inliers that conform to the geometric transformation model from the matched feature points, and calculate the transformation matrix between the images accordingly; Use the transformation matrix to transform one image into the coordinate system of another image to achieve image stitching. During the stitching process, multi-band fusion is used to process the overlapping area to eliminate the stitching trace and generate a distortion-free and complete panoramic image.

[0015] Further preferably, the autofocus method includes the following steps: Real-time image capture: Use a camera to obtain a local image of the surface to be processed in real time. Apply an image sharpness evaluation algorithm to score the sharpness of the captured image, and determine the current focus state according to the scoring result; Focus adjustment preparation: Configure the adjustment component or the rotating lens mechanism to prepare for focus adjustment; Optimized search algorithm selection: Use the hill climbing algorithm to find the focus position that makes the image sharpest; Focus adjustment and optimized search: Control the adjustment component or the rotating lens mechanism to continuously adjust the laser focus position. Use the hill climbing algorithm to continuously evaluate the image sharpness during the adjustment process and find the focus position that makes the image sharpest; Autofocus completed: When the optimal focus position is found, the autofocus process ends, and the laser focus is accurately aligned with the surface to be processed, preparing for the subsequent laser processing operation.

[0016] Further preferably, when performing the sharpness scoring, first analyze and process the image captured by the camera, quantify the clarity of the details or the distinctness of the light and dark contrast in the image, and give a sharpness score, which reflects the accuracy of the image focus.

[0017] Due to the above technical solutions, the embodiments of the present invention have the following advantages: By utilizing its own laser head imaging system, the present invention eliminates the need for additional installation of a large-angle top-view camera, thereby reducing the size of the machine body and the complexity of the system. Through the stitching and correction of multiple images, a panoramic view of the processing area with high precision and no distortion can be obtained to achieve accurate positioning. By using the image sharpness criterion and automatic focusing control, rapid and accurate automatic focusing can be realized, eliminating the cumbersome process of manual focusing, reducing the operation difficulty, and enabling rapid automatic focusing according to different workpiece materials and surface height changes, improving the processing quality and adaptability. Compared with the prior art, the present invention realizes high-precision imaging and automatic focusing of the processing object through the integration of a camera, an automatic focusing mechanism, an automatic stitching and correction method, and an automatic focusing method, simplifies the operation, improves the processing precision and production efficiency, and provides an innovative and practical solution for the laser processing industry.

[0018] The above summary is only for the purpose of the specification and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present invention will be readily apparent by reference to the drawings and the following detailed description. Brief Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 Structural diagram of an intelligent laser of the present invention; Figure 2 Schematic diagram of the connection between the cooling fan and the support plate of the present invention; Figure 3 Structural diagram of the adjustment component of the present invention; Figure 4 Structural diagram of the heat dissipation rack of the present invention; Figure 5 Working state diagram of an intelligent laser of the present invention; Figure 6 Flowchart of the steps of the automatic stitching and correction method of the present invention; Figure 7 Flowchart of the steps of the automatic focusing method of the present invention.

[0021] Reference Numerals: 101, adjustment assembly; 11, housing; 12, camera; 14, laser head; 15, stepper motor; 16, transmission gear; 17, transmission rack; 18, support plate; 19, cooling fan; 20, heat dissipation frame; 21, laser body; 22, guiding optical axis; 23, through hole; 24, mounting groove; 25, heat sink; 26, groove; 27, engraving material. Detailed Embodiment

[0022] In the following, only some exemplary embodiments are simply described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the drawings and the description are considered to be exemplary in nature rather than restrictive.

[0023] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0024] As Figures 1 - 5 shown, an embodiment of the present invention provides an intelligent laser, including an adjustment assembly 101, and the adjustment assembly 101 is used to realize the Z-direction adjustment of the laser head 14; The adjustment assembly 101 includes a housing 11, a stepper motor 15, a transmission gear 16, a transmission rack 17, a support plate 18, a heat dissipation frame 20, a laser body 21, and two guiding optical axes 22; A camera 12 is installed on the outer side wall of the housing 11. The camera 12 can adopt a zoom lens, and the applicable range can be further expanded by adjusting the lens focal length; A laser head 14 is installed at the bottom of the laser body 21. Through the cooperation of the laser head 14 and the laser body 21, laser engraving operations can be realized; The heat dissipation frame 20 is slidably connected to the inner side wall of the housing 11. The transmission rack 17, the laser body 21, and the guiding optical axes 22 are all installed inside the housing 11. The position of the transmission rack 17, the laser body 21, and the guiding optical axes 22 can be limited by the heat dissipation frame 20, thereby enhancing the structural stability; The support plate 18 is fixedly connected to the upper part of the inner side wall of the housing 11. A cooling fan 19 is installed on the upper surface of the support plate 18. A heat dissipation slot adapted to the shape of the cooling fan 19 is opened on the upper surface of the housing 11. Heat sinks 25 are symmetrically arranged on the outer side wall of the heat dissipation frame 20. Through the cooperation of the heat sinks 25 and the cooling fan 19, the heat dissipation effect of the laser can be enhanced, and the laser will not overheat during long-term operation; The tops of two guiding optical axes 22 are symmetrically and fixedly connected to the lower surface of the support plate 18. The transmission gear 16 is fixedly connected to the output shaft of the stepping motor 15. The outer sidewall of the transmission gear 16 is meshed and connected to the outer sidewall of the transmission rack 17. The stepping motor 15 is installed on the inner sidewall of the machine shell 11. By driving the transmission gear 16 to rotate through the stepping motor 15, the transmission gear 16 drives the transmission rack 17 through its teeth. Since the transmission rack 17 is connected to the heat dissipation frame 20, the transmission gear 16 can drive the heat dissipation frame 20 to move in the Z direction, thereby realizing the automatic focusing of laser processing.

[0025] In one embodiment, mounting grooves 24 and grooves 26 are formed in the outer sidewall of the heat dissipation frame 20. Two through holes 23 are symmetrically formed inside the heat dissipation frame 20. The laser machine body 21 is installed on the inner sidewall of the mounting groove 24. The transmission rack 17 is installed on the inner sidewall of the groove 26. The guiding optical axis 22 is slidably connected to the inner sidewall of the through hole 23. The positions of the laser machine body 21, the transmission rack 17, and the guiding optical axis 22 can be respectively defined through the mounting groove 24, the groove 26, and the through hole 23, while reducing the overall volume.

[0026] In one embodiment, a carving material 27 is arranged below the machine shell 11. Inside the laser head 14, there is a lens group that can rotate or axially slide, for realizing automatic focusing by changing the focal point of the optical path. Inside the laser head 14, there is a drive and control module: including a motor, a linear slide or a rotating mechanism for Z-axis adjustment, and a control board, and precise position movement and lens adjustment are realized through software commands.

[0027] During operation, the radiator can move along the X-Y direction and drive the camera 12 during the movement. The plane of the carving material 27 can be collected through the camera 12. Then, the stepping motor 15 drives the transmission gear 16 to rotate. The transmission gear 16 drives the transmission rack 17 through its teeth. Since the transmission rack 17 is connected to the heat dissipation frame 20, the transmission gear 16 can drive the heat dissipation frame 20 to move in the Z direction. The heat dissipation frame 20 drives the laser head 14, and thus the focusing of the laser head 14 can be realized.

[0028] As Figures 6 - 7 shown, the embodiment of the present invention provides an automatic focusing and image correction method for laser processing, including an automatic stitching and correction method and an automatic focusing method; The automatic stitching and correction method includes the following steps: Laser head positioning and shooting: Utilizing the moving ability of the laser head in the X-Y plane, moving the camera to a plurality of preset positions, and using the camera to shoot the surface to be processed to obtain multiple images; Image Feature Recognition: In multiple captured images, identify calibration marks or known features within the overlapping area, including built-in calibration patterns and calibration points on the processing table; Image Stitching: Apply computer vision algorithms to precisely stitch multiple images. Through algorithm processing, generate a distortion-free and complete overall image field, i.e., a panoramic image; Application of Panoramic Image: Utilize the stitched panoramic image for the planning of laser processing paths, perform processing positioning based on the panoramic image, and use the panoramic image as a real-time reference during processing.

[0029] In the image stitching step, first use the Scale-Invariant Feature Transform (SIFT) algorithm to extract feature points and their descriptors in each image. Then, through the feature matching algorithm, find the corresponding relationships of these feature points in different images. Use the Random Sample Consensus (RANSAC) algorithm to screen out inliers that conform to the geometric transformation model from the matched feature points, and calculate the transformation matrix between the images based on this; Use the transformation matrix to transform one image into the coordinate system of another image to achieve image stitching. During the stitching process, adopt multi-band fusion to process the overlapping area, eliminate stitching traces, and generate a distortion-free and complete panoramic image.

[0030] The automatic focusing method includes the following steps: Real-time Image Capture: Use a camera to obtain a local image of the surface to be processed in real time. Apply an image sharpness evaluation algorithm to score the sharpness of the captured image, and determine the current focusing state based on the scoring result; Focus Adjustment Preparation: Configure the adjustment component or the rotating lens mechanism to prepare for focus adjustment; Optimized Search Algorithm Selection: Through the hill-climbing algorithm, find the focus position that makes the image sharpest; Focus Adjustment and Optimized Search: By controlling the adjustment component or the rotating lens mechanism, continuously adjust the laser focus position. Use the hill-climbing algorithm to continuously evaluate the image sharpness during the adjustment process and find the focus position that makes the image sharpest; Automatic Focusing Completion: When the optimal focus position is found, the automatic focusing process ends, and the laser focus is precisely aligned with the surface to be processed, preparing for subsequent laser processing operations.

[0031] When performing the sharpness scoring, first analyze and process the image captured by the camera, quantify the clarity of details or the distinctness of light and dark contrast in the image, and give a sharpness score, which reflects the accuracy of image focusing; Through the above steps, the automatic focusing method can achieve fast and accurate automatic focusing without the need for manual measurement of the working distance and external sensors, bringing a more intelligent and automated solution to the field of laser processing.

[0032] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various changes or substitutions, and these should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claimed rights.

Claims

1. An intelligent laser, comprising an adjustment component (101), characterized in that: The adjustment component (101) comprises a housing (11), a stepping motor (15), a transmission gear (16), a transmission rack (17), a support plate (18), a heat sink (20), a laser body (21) and two guide optical axes (22); A camera (12) is installed on the outer wall of the housing (11), a laser head (14) is installed on the bottom of the laser body (21), the heat sink (20) is slidably connected to the inner wall of the housing (11), the top ends of the two guide optical axes (22) are symmetrically fixedly connected to the lower surface of the support plate (18), the transmission gear (16) is fixedly connected to the output shaft of the stepper motor (15), the outer wall of the transmission gear (16) is meshingly connected to the outer wall of the transmission rack (17), and the transmission rack (17), the laser body (21) and the guide optical axis (22) are all installed inside the housing (11).

2. The intelligent laser according to claim 1, characterized in that: The support plate (18) is fixedly connected to the upper portion of the inner wall of the casing (11); a heat dissipation fan (19) is installed on the upper surface of the support plate (18); and a heat dissipation groove matching the shape of the heat dissipation fan (19) is provided on the upper surface of the casing (11).

3. The intelligent laser according to claim 1, characterized in that: The outer wall of the heat dissipation frame (20) is provided with a mounting groove (24) and a groove (26), and the interior of the heat dissipation frame (20) is symmetrically provided with two through holes (23).

4. The intelligent laser according to claim 3, characterized in that: The laser body (21) is mounted on the inner side wall of the mounting groove (24), the transmission rack (17) is mounted on the inner side wall of the groove (26), and the guide optical axis (22) is slidably connected to the inner side wall of the through hole (23).

5. The intelligent laser according to claim 1, characterized in that: The outer side wall of the heat dissipation frame (20) is symmetrically provided with heat dissipation fins (25), and the stepping motor (15) is mounted on the inner side wall of the housing (11).

6. The intelligent laser according to claim 5, characterized in that: An engraving material (27) is arranged below the housing (11), and a lens group that can rotate or axially slide is arranged inside the laser head (14) for achieving automatic focusing by changing the focal point of the light path.

7. An automatic focusing and image correction method for laser processing, applied to an intelligent laser as claimed in any one of claims 1 to 6, characterized in that: Including automatic stitching correction method and automatic focusing method; The automatic stitching correction method comprises the following steps: Laser head positioning and shooting: Using the laser head's ability to move on the XY plane, move the camera to multiple preset positions, use the camera to shoot the surface to be processed, and obtain multiple images; Image feature recognition: Identify calibration marks or known features in overlapping areas of multiple captured images, including built-in calibration patterns and calibration points on the processing table; Image stitching: Apply computer vision algorithms to accurately stitch multiple images and generate a distortion-free, complete overall image field, i.e., a panoramic image, through algorithm processing; Panoramic image application: Use the stitched panoramic image to plan the laser processing path, perform processing positioning based on the panoramic image, and use the panoramic image as a real-time reference during processing.

8. The method for automatic focusing and image correction for laser processing according to claim 7, characterized in that: In the image stitching step, the scale-invariant feature transformation algorithm is first used to extract the feature points and their descriptors in each image. Then, the feature matching algorithm is used to find the corresponding relationship between these feature points in different images. The random sampling consensus algorithm is used to filter out the internal points that meet the geometric transformation model from the matched feature points, and the transformation matrix between the images is calculated based on this. The transformation matrix is ​​used to transform one image into the coordinate system of another image to achieve image stitching. During the stitching process, multi-band fusion is used to process the overlapping area to eliminate the stitching marks and generate a distortion-free and complete panoramic image.

9. The method for automatic focusing and image correction for laser processing according to claim 7, characterized in that: The automatic focusing method comprises the following steps: Real-time image capture: Use the camera to obtain a local image of the surface to be processed in real time, apply the image clarity evaluation algorithm to score the clarity of the captured image, and determine the current focus state based on the scoring results; Focus adjustment preparation: configure the adjustment components or rotate the lens mechanism to prepare for focus adjustment; Optimize search algorithm selection: Use the hill climbing algorithm to find the focal position that gives the highest image clarity; Focus adjustment and optimization search: By controlling the adjustment component or rotating the lens mechanism, the laser focus position is continuously adjusted. The image clarity is continuously evaluated during the adjustment process using the hill climbing algorithm to find the focus position that gives the highest image clarity. Autofocus complete: When the optimal focus position is found, the autofocus process ends, the laser focus is accurately aligned with the surface to be processed, and is ready for subsequent laser processing operations.

10. The method for automatic focusing and image correction for laser processing according to claim 9, characterized in that: When scoring clarity, the image captured by the camera is first analyzed and processed to quantify the clarity of details or the vividness of light and dark contrast in the image, and a clarity score is given. This score reflects the accuracy of image focus.

Images