Multi-workpiece batch laser engraving method based on workpiece material self-adaptive matching machining parameters and related equipment

Abstract

The invention provides a multi-workpiece batch laser engraving method and related equipment based on workpiece material self-adaptive matching machining parameters, and the method comprises the following steps: controlling a top view camera module to shoot to obtain a workpiece image; extracting the contour of each workpiece from the workpiece image; determining pose data of each workpiece according to the contour of each workpiece; the material type of each workpiece is determined according to the image area corresponding to the contour of each workpiece, and a laser engraving parameter set is set for each workpiece according to the material type of each workpiece; generating a laser engraving path for each workpiece according to the design pattern and the pose data of each workpiece; generating a laser engraving program according to the pose data of each workpiece, the laser engraving parameter set and the laser engraving path; and controlling the laser engraving machine to execute a laser engraving program so as to perform laser engraving on each workpiece. When multiple materials exist in the workpieces machined in batches, the machining parameters are matched in a self-adaptive mode according to the workpiece materials, and the conditions of over-burning, under-etching or deformation and the like are avoided.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of laser engraving, and particularly relates to a multi-workpiece batch laser engraving method based on adaptive matching of processing parameters of workpiece materials and related equipment. BACKGROUND

[0002] In the existing consumer-grade laser engraving machine, fixed parameters such as uniform power and uniform speed are usually used in batch processing, which can cause overburning (such as blackening of leather), under-engraving or deformation (such as shallow engraving or melting deformation of plastic) of the workpieces when the workpieces have multiple materials (such as mixed arrangement of leather cup pads and plastic cup pads), because the requirements of different materials for laser power and speed are quite different. In order to avoid these situations, the user can only work in batches or manually adjust the parameters one by one, which can cause low workpiece processing efficiency, and manual parameter adjustment is more dependent on experience and prone to errors. SUMMARY

[0003] The application provides a multi-workpiece batch laser engraving method based on adaptive matching of processing parameters of workpiece materials and related equipment. The application can adaptively match the processing parameters according to the workpiece materials when the workpieces have multiple materials in batch processing, thereby avoiding overburning, under-engraving or deformation and the like.

[0004] In a first aspect, the application provides a multi-workpiece batch laser engraving method based on adaptive matching of processing parameters of workpiece materials. The method comprises: controlling a top-view camera module to capture an image of the workpieces; the field of view of the top-view camera module covers the entire workbench of the laser engraving machine, and the workbench is pre-placed with multiple workpieces; extracting the contour of each workpiece from the image of the workpieces; determining the pose data of each workpiece according to the contour of each workpiece; determining the material type of each workpiece according to the image area corresponding to the contour of each workpiece, and setting a laser engraving parameter set for each workpiece according to the material type of each workpiece; wherein different material types correspond to different laser engraving parameter sets; generating a laser engraving path for each workpiece according to the design pattern submitted by the user and the pose data of each workpiece; generating a laser engraving program according to the pose data of each workpiece, the laser engraving parameter set and the laser engraving path; and controlling the laser engraving machine to execute the laser engraving program to perform laser engraving on each workpiece.

[0005] In some embodiments, determining the material type of each workpiece according to the image area corresponding to the contour of each workpiece comprises: extracting a color histogram and a local binary pattern texture feature from the image area corresponding to the contour of each workpiece; inputting the color histogram and the local binary pattern texture feature related to each workpiece into a lightweight convolutional neural network after concatenation; and determining the material type of each workpiece according to the output result of the lightweight convolutional neural network.

[0006] In some embodiments, the laser engraving parameter set for each workpiece is set according to the material type of each workpiece, including: reading the corresponding laser engraving parameters from the pre-set material parameter database indexed by the material type of each workpiece to generate the corresponding laser engraving parameter set for each workpiece; the material parameter database includes recommended power, speed, engraving times and safety threshold of multiple materials at different thicknesses.

[0007] In some embodiments, the pose data includes center coordinates and rotation angles; the contour of each workpiece is extracted from the workpiece image, and the pose data of each workpiece is determined according to the contour of each workpiece, including: taking the contour image of any workpiece as a shape reference, and performing shape matching on the contour images of other workpieces to obtain a coarse position; based on the coarse position, the corner points of each workpiece are extracted, and the corner points of each workpiece are converted from the image coordinate system to the machine tool coordinate system through perspective transformation to obtain the center coordinates and rotation angles of the contour of each workpiece.

[0008] In some embodiments, the laser engraving parameter set for each workpiece is set according to the material type of each workpiece, including: obtaining the thickness information of each workpiece through an additional depth camera or a binocular camera; taking the thickness information and the material type of each workpiece as a joint index, reading the corresponding laser engraving parameters from the pre-set material parameter database to generate the corresponding laser engraving parameter set for each workpiece.

[0009] In some embodiments, the laser engraving machine includes multiple laser modules; the laser engraving program is generated according to the pose data, the laser engraving parameter set and the laser engraving path of each workpiece, and the laser engraving machine is controlled to execute the laser engraving program to perform laser engraving on each workpiece, including: dividing the machining table surface into multiple material areas according to the material types of all workpieces, and respectively assigning each laser module to a corresponding material area; generating a sub-laser engraving program corresponding to each material area, and controlling each laser module to execute the corresponding sub-laser engraving program in parallel to simultaneously perform laser engraving on workpieces in different material areas.

[0010] In some embodiments, when the laser engraving machine executes the laser engraving program, each workpiece is processed in turn, and before the laser head moves to the next workpiece, the parameters of the laser head are reset according to the laser engraving parameter set of the next workpiece.

[0011] In a second aspect, the present application provides a multi-workpiece batch laser engraving device based on adaptive matching of workpiece material processing parameters, the device comprising: A shooting control module is configured to control the top-view camera module to shoot and obtain workpiece images; the field of view of the top-view camera module covers the entire machining table surface of the laser engraving machine, and the machining table surface has pre-placed multiple workpieces; A workpiece contour extraction module is configured to extract the contour of each workpiece from the workpiece image. a workpiece pose determination module configured to determine pose data of each workpiece according to the contour of each workpiece; a machining parameter adaptive setting module configured to determine a material type of each workpiece according to an image region corresponding to the contour of each workpiece, and set a laser engraving parameter set for each workpiece according to the material type of each workpiece; wherein different material types correspond to different laser engraving parameter sets; an engraving path generation module configured to generate a laser engraving path for each workpiece according to a design pattern submitted by a user and the pose data of each workpiece; an engraving program generation module configured to generate a laser engraving program according to the pose data of each workpiece, the laser engraving parameter set, and the laser engraving path; an engraving control module configured to control a laser engraving machine to execute the laser engraving program to perform laser engraving on each workpiece.

[0012] In a third aspect, the present application provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor to implement the multi-workpiece batch laser engraving method based on adaptive matching of workpiece material and machining parameters according to any of the embodiments of the first aspect.

[0013] In a fourth aspect, the present application provides a computer device including one or more processors, a memory, and one or more computer programs, the processor and the memory being connected through a bus, the one or more computer programs being stored in the memory and configured to be executed by the one or more processors, the processor executing the computer program to implement the multi-workpiece batch laser engraving method based on adaptive matching of workpiece material and machining parameters according to any of the embodiments of the first aspect.

[0014] The present application can realize batch processing of workpieces, and has higher processing efficiency. When the workpieces processed in batches have multiple materials, the processing parameters are adaptively matched according to the materials of the workpieces, thereby avoiding overburning, under-engraving, or deformation, etc. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 is a flowchart of the multi-workpiece batch laser engraving method based on adaptive matching of workpiece material and machining parameters according to an embodiment of the present application.

[0016] Figure 2 is a functional module block diagram of the multi-workpiece batch laser engraving device based on adaptive matching of workpiece material and machining parameters according to an embodiment of the present application.

[0017] Figure 3 is a specific structural block diagram of the computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purposes, technical solutions and beneficial effects of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0019] In order to illustrate the technical solutions described in the present application, the following will be described by specific embodiments.

[0020] In a first aspect, the present application provides a multi-workpiece batch laser engraving method based on adaptive matching of workpiece material to processing parameters. The method can realize batch processing of workpieces, and has higher processing efficiency. When the batch-processed workpieces have multiple materials, the processing parameters are adaptively matched according to the workpiece materials, thereby avoiding overburning, under-engraving, or deformation, etc.

[0021] The steps included in the method can be seen from Figure 1 The following describes each step included in the method.

[0022] S101, control the top-view camera module to take a picture to obtain a workpiece image.

[0023] The method can be applied to a laser engraving device. The laser engraving device can be an XYZ frame type laser engraving machine, which can be simply referred to as a laser engraving machine. The top-view camera module is one or more cameras integrated on the top of the laser engraving machine. The optical axis of the top-view camera module is vertically downward, and the field of view can completely cover the entire processing table of the laser engraving machine.

[0024] When a batch of workpieces need to be processed, the user can arbitrarily place the batch of workpieces on the processing table. The shapes of these workpieces are the same, such as circular, square, etc., and the present application does not particularly limit the shape of the workpiece. The materials of these workpieces can be one or more (such as leather cup pads and plastic cup pads). After the user triggers the processing instruction (such as pressing the start button), the laser engraving machine can automatically execute the processing flow.

[0025] The laser engraving machine controls the top-view camera module to take a picture, and a workpiece image is obtained. The workpiece image can be a single frame of RGB image output by the top-view camera module, which is used for subsequent contour extraction, pose calculation and material identification. Since the field of view of the top-view camera module covers the entire processing table, each workpiece will be included in the workpiece image.

[0026] S102, extract the contour of each workpiece from the workpiece image.

[0027] The contour of each workpiece can be extracted from the workpiece image by an image segmentation algorithm. For example, the workpiece image is first binarized to obtain a binary image, and then the findContours of OpenCV is used to find the workpiece contour from the binary image, and finally the contour of each workpiece can be obtained.

[0028] The contour of the workpiece is specifically a closed edge sequence of the workpiece in the workpiece image, which is used to represent the outer boundary of the workpiece and calculate geometric features. For example, the contour of a circular coaster is a closed circle composed of about 500 pixel points, the contour area is 78000 pixel², and the circumference can be 1080 pixels. pixel represents a pixel point.

[0029] S103, determining the pose data of each workpiece according to the contour of each workpiece.

[0030] The pose data of the workpiece is the minimum data set used to describe the position and rotation amount of the workpiece in the machine tool coordinate system, which can be generally represented as (x, y, θ), where x and y represent the machine tool coordinates of the contour center (referred to as the center coordinates), and θ represents the rotation angle, i.e. the angle between the long axis of the workpiece and the X axis of the machine tool. For example, the pose data of a certain leather coaster is (214.5 mm (millimeters), 156.3 mm, 3.2°), and the subsequent pattern mapping will be aligned with the point as the local origin and counterclockwise rotation of 3.2°.

[0031] When calculating the pose data of the workpiece, the contour of the workpiece is first preprocessed, which includes removing burrs on the contour (such as using Gaussian filter smoothing to process the contour of the workpiece), and when the contour is a concave polygon, the contour is processed as a convex polygon.

[0032] After the contour is preprocessed, the geometric moment method can be used to calculate the contour center, which includes the following specific operations: a. Calculate the pixel area, vertical axis first moment and horizontal axis first moment of the contour; The calculation of the pixel area of the contour is to regard each pixel inside (or on the edge of) the contour as a small mass of 1 gram, and add up the total mass of all pixels to obtain the pixel area.

[0033] The calculation of the vertical axis first moment is to multiply the horizontal coordinate x of each pixel inside the contour by the gram corresponding to the pixel, i.e. "1 gram", and then sum all the pixels to obtain the vertical axis first moment. The vertical axis first moment is used to measure the distribution of pixels in the left and right directions.

[0034] The calculation of the horizontal axis first moment is to multiply the vertical coordinate y of each pixel inside the contour by the gram corresponding to the pixel, i.e. "1 gram", and then sum all the pixels to obtain the horizontal axis first moment. The horizontal axis first moment is used to measure the distribution of pixels in the up and down directions.

[0035] b. Divide the first moment of the vertical axis by the pixel area to obtain the horizontal coordinate of the profile center (which can be represented as u), and divide the first moment of the horizontal axis by the pixel area to obtain the vertical coordinate of the profile center (which can be represented as v), and finally obtain the pixel coordinates (u, v) of the profile center.

[0036] Then, the machine tool coordinates are calculated according to the profile center. For example, the top-view camera module and the machine tool are calibrated in advance by a checkerboard, and the perspective transformation matrix of the camera and the machine tool is obtained, which can be represented as H (3x3); the pixel coordinates are converted into machine tool coordinates using the perspective transformation matrix, which can be represented as (x, y).

[0037] Finally, the rotation angle is calculated using the minimum enclosing rectangle method. The specific operation can be: a. The minAreaRect function of OpenCV is used to process the profile point set to obtain the rectangular long-side angle, which can be represented as θ_raw (the value range is -90°-0°) b. The rectangular long-side angle is angle-normalized to obtain the rotation angle; for example, if the rectangular long-side is closer to the X-axis, the rectangular long-side angle is taken as the rotation angle, and if the rectangular long-side is closer to the Y-axis, the sum of the rectangular long-side angle and 90° is taken as the rotation angle, so as to limit the rotation angle within the range of [-45°, 45°].

[0038] S104, determine the material type of each workpiece according to the image area corresponding to the profile of each workpiece, and set a set of laser engraving parameters for each workpiece according to the material type of each workpiece.

[0039] The material type of the workpiece is the material category label set for the workpiece according to the visual feature or RFID tag, for example, 0=leather, 1=ABS, 2=acrylic, 3=birch, 4=EVA.

[0040] In some embodiments, determining the material type of each workpiece according to the image area corresponding to the profile of each workpiece includes: extracting color histograms and local binary pattern texture features from the image area corresponding to the profile of each workpiece; cascading the color histograms and local binary pattern texture features related to each workpiece and inputting them into a lightweight convolutional neural network, and the output result of the lightweight convolutional neural network determines the material type of each workpiece.

[0041] In some embodiments, the operation of determining the material type of the workpiece according to the image region corresponding to the contour of the workpiece can include: taking the image region corresponding to the contour as a region of interest, extracting color features and texture features of the region of interest, and inputting the color features and the texture features into a first classifier to obtain a first material probability; inputting the region of interest into a lightweight convolutional neural network to obtain a second material probability; and fusing the first material probability and the second material probability according to a preset weight, and taking a category corresponding to a maximum probability in a fusion result as the material type of the workpiece.

[0042] The color features can be obtained by an HSV space histogram, and the texture features can be obtained by a local binary pattern. The first classifier can be a linear support vector machine, and the lightweight convolutional neural network can be a MobileNet series network. Further, after fusing the first material probability and the second material probability according to the preset weight, if a maximum probability of the fusion result is lower than a first threshold, the material type is determined by a human.

[0043] In some embodiments, the operation of setting a laser engraving parameter set for each workpiece according to the material type of each workpiece can further include: obtaining thickness information of each workpiece by an additional depth camera or a binocular camera; and taking the thickness information and the material type of each workpiece as a joint index to read corresponding laser engraving parameters from a preset material parameter database to generate a laser engraving parameter set corresponding to each workpiece. By introducing the thickness information of the workpiece, the laser engraving parameters can be refined, and the problems of overburning and under-engraving can be further avoided.

[0044] After determining the material type of the workpiece, a laser engraving parameter set can be set for each workpiece according to the material type of each workpiece. The specific operation can include: taking the material type of each workpiece as an index to read corresponding laser engraving parameters from a preset material parameter database to generate a laser engraving parameter set corresponding to each workpiece; and the material parameter database includes recommended power, speed, engraving times, and safety thresholds of multiple materials at different thicknesses.

[0045] The laser engraving machine can include a pre-constructed material parameter database, which includes a laser engraving parameter set corresponding to each material. Based on this, after determining the material type of the workpiece, the material parameter database can be queried by taking the material type of the workpiece as an index to obtain a dedicated laser engraving parameter set for each workpiece. Generally, different material types correspond to different laser engraving parameter sets.

[0046] S105, generating a laser engraving path for each workpiece according to the design pattern submitted by the user and the pose data of each workpiece.

[0047] According to the design pattern submitted by the user and the pose data of each workpiece, the laser engraving path of each workpiece is generated, which can include: taking the center coordinate in the pose data as a local origin and the rotation angle as a transformation angle to construct an affine transformation matrix of the global coordinate system to the local coordinate system; mapping the path points of the design pattern to the local coordinate system using the affine transformation matrix to obtain a preliminary laser engraving path; performing boundary clipping and / or idle stroke optimization on the preliminary laser engraving path to form a final laser engraving path.

[0048] Wherein, the boundary clipping can be to take the contour of the workpiece as a clipping window, and delete the path line segment falling outside the window; the idle stroke optimization can include rearranging the mapped path line segment in the order of nearest neighbor, and introducing a micro line segment of tool entry or tool exit at the beginning and / or end of the segment.

[0049] S106, generating a laser engraving program according to the pose data of each workpiece, the laser engraving parameter set and the laser engraving path.

[0050] When generating a laser engraving program according to the pose data of each workpiece, the laser engraving parameter set and the laser engraving path, the center coordinates of all workpieces can be taken as nodes to perform shortest path sorting, thereby obtaining a processing order, then outputting G-code by workpiece according to the processing order, wherein positioning and focusing instructions are written in the idle stroke segment first, then extended parameter switching instructions are written to realize immediate changes of laser power, speed, Z-axis offset and / or PWM waveform, then the laser engraving path of the workpiece is written, until all workpieces are processed, forming a single continuous laser engraving program.

[0051] S107, controlling the laser engraving machine to execute the laser engraving program to perform laser engraving on each workpiece.

[0052] When the laser engraving machine executes the laser engraving program, each workpiece is processed in turn, and before the laser head moves to the next workpiece, the parameters of the laser head are reset according to the laser engraving parameter set of the next workpiece. Specifically, the G-code of the laser engraving program can be parsed and executed line by line in real time, and the immediate switching of laser power, speed, Z-axis height and / or PWM waveform is completed in the idle stroke phase, so that the laser head completes parameter change before moving to the next workpiece, realizing continuous and uninterrupted engraving of multiple material workpieces. Wherein, the immediate switching can be realized by extended M100 instruction, and the switching time is shorter, not more than 20 ms (milliseconds).

[0053] In some embodiments, the laser engraving machine comprises a plurality of laser modules; on this basis, the laser engraving program is generated according to the pose data of each workpiece, the laser engraving parameter set and the laser engraving path, and the laser engraving machine is controlled to execute the laser engraving program to perform the operation of laser engraving on each workpiece, comprising: dividing the machining table into a plurality of material areas according to the material types of all workpieces, and respectively assigning each laser module to a corresponding material area; generating a sub-laser engraving program corresponding to each material area, and controlling each laser module to execute the corresponding sub-laser engraving program in parallel to simultaneously laser engrave the workpieces in different material areas.

[0054] By letting different laser modules be responsible for different material areas, the batch processing efficiency can be further improved. Among them, a safety seam can be left when dividing the material area to prevent the laser heads from colliding with each other; and / or each laser module is instructed to execute by the same line number beat through a hardware synchronization word, and the positions are compared in real time, and when the position difference is less than a safety threshold, the machine is immediately stopped to ensure safety during parallel processing.

[0055] In some embodiments, when the pose data comprises a center coordinate and a rotation angle, the operation of extracting the contour of each workpiece from the workpiece image and determining the pose data of each workpiece according to the contour of each workpiece can further comprise: taking the contour image of any workpiece as a shape reference, and performing shape matching on the contour images of other workpieces to obtain a coarse position; extracting the corner points of each workpiece based on the coarse position, and converting the corner points of each workpiece from the image coordinate system to the machine tool coordinate system through perspective transformation to obtain the center coordinate and the rotation angle of the contour of each workpiece.

[0056] Based on shape matching and perspective transformation, high-precision real-time positioning of multiple workpieces can be achieved, with an accuracy of ±0.2 mm.

[0057] The following illustrates the batch processing flow of the present application through the example of batch engraving of mixed cup pads: (1) The workbench places 4 pieces of leather cup pads and 6 pieces of ABS plastic cup pads, and the positions are random. After the device takes a photo, it detects a total of 10 circular workpieces.

[0058] (2) The visual algorithm judges 4 of them as leather based on color and surface texture, and the rest as ABS.

[0059] (3) Leather parameters (power 35%, speed 800 mm / s) and ABS parameters (power 55%, speed 600 mm / s, and air blowing is enabled) are extracted from the material parameter database respectively.

[0060] (4) The single LOGO pattern submitted by the user is copied onto the 10 circular contours to generate a laser engraving program.

[0061] (5) The laser engraving machine will automatically execute the program, specifically processing according to the shortest path. When encountering a leather area, it will automatically switch to leather parameters, with a switching time of less than 50ms.

[0062] (6) All coaster engravings can be completed in one operation, and the leather coasters are not overheated, and the patterns on the ABS coasters are consistent in depth.

[0063] Secondly, this application provides a multi-workpiece batch laser engraving device based on adaptive matching of processing parameters for workpiece materials, such as... Figure 2 As shown, the device includes a shooting control module 101, a workpiece contour extraction module 102, a workpiece pose determination module 103, a machining parameter adaptive setting module 104, a carving path generation module 105, a carving program generation module 106, and a carving control module 107.

[0064] The shooting control module 101 is used to control the top-view camera module to shoot and obtain workpiece images; the field of view of the top-view camera module covers the entire processing table of the laser engraving machine, and multiple workpieces are pre-placed on the processing table. The workpiece contour extraction module 102 is used to extract the contour of each workpiece from the workpiece image. The workpiece pose determination module 103 is used to determine the pose data of each workpiece based on the contour of each workpiece. The adaptive setting module 104 for processing parameters is used to determine the material type of each workpiece based on the image area corresponding to the contour of each workpiece, and to set a laser engraving parameter set for each workpiece based on the material type of each workpiece; wherein, different material types correspond to different laser engraving parameter sets; The engraving path generation module 105 is used to generate a laser engraving path for each workpiece based on the design pattern submitted by the user and the pose data of each workpiece. The engraving program generation module 106 is used to generate a laser engraving program based on the pose data of each workpiece, the laser engraving parameter set, and the laser engraving path. The engraving control module 107 is used to control the laser engraving machine to execute the laser engraving program to laser engrave each workpiece.

[0065] In one embodiment, the material type of each workpiece is determined based on the image region corresponding to the contour of each workpiece. Specifically, this includes: extracting color histograms and local binary pattern texture features from the image region corresponding to the contour of each workpiece; concatenating the color histograms and local binary pattern texture features related to each workpiece and inputting them into a lightweight convolutional neural network; and determining the material type of each workpiece based on the output of the lightweight convolutional neural network.

[0066] In one embodiment, a laser engraving parameter set is set for each workpiece according to its material type. Specifically, this includes: using the material type of each workpiece as an index, reading the corresponding laser engraving parameters from a preset material parameter database, and generating a laser engraving parameter set for each workpiece. The material parameter database includes recommended power, speed, number of engravings, and safety thresholds for various materials at different thicknesses.

[0067] In one embodiment, the pose data includes center coordinates and rotation angle; extracting the contour of each workpiece from the workpiece image, and determining the pose data of each workpiece based on the contour of each workpiece, specifically includes: using the contour image of any workpiece as a shape reference, performing shape matching on the contour images of other workpieces to obtain a coarse position; extracting the corner points of each workpiece based on the coarse position, and transforming the corner points of each workpiece from the image coordinate system to the machine tool coordinate system through perspective transformation to obtain the center coordinates and rotation angle of the contour of each workpiece.

[0068] In one embodiment, a laser engraving parameter set is set for each workpiece according to its material type. Specifically, this includes: acquiring the thickness information of each workpiece through an additional depth camera or binocular camera; using the thickness information and material type of each workpiece as a joint index, reading the corresponding laser engraving parameters from a preset material parameter database, and generating a laser engraving parameter set for each workpiece.

[0069] In one embodiment, the laser engraving machine includes multiple laser modules; a laser engraving program is generated based on the pose data of each workpiece, the laser engraving parameter set, and the laser engraving path; the laser engraving machine is controlled to execute the laser engraving program to laser engrave each workpiece; specifically, the processing table is divided into multiple material regions according to the material type of all workpieces, and a corresponding material region is assigned to each laser module; a sub-laser engraving program corresponding to each material region is generated, and each laser module is controlled to execute the corresponding sub-laser engraving program in parallel to simultaneously laser engrave workpieces in different material regions.

[0070] In one embodiment, when the laser engraving machine executes the laser engraving program, it processes each workpiece sequentially, and before the laser head moves to the next workpiece, it resets the parameters of the laser head according to the laser engraving parameter set of the next workpiece.

[0071] The multi-workpiece batch laser engraving device based on adaptive matching of processing parameters for workpiece materials provided in this application belongs to the same inventive concept as the multi-workpiece batch laser engraving method based on adaptive matching of processing parameters for workpiece materials provided in the first aspect of this application. The specific implementation process is detailed in the full text of the specification, especially the various embodiments provided in the first aspect, which will not be repeated here.

[0072] In a third aspect, the present application provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the multi-workpiece batch laser engraving method based on adaptive matching of processing parameters according to the material of a workpiece according to any one of the embodiments of the first aspect.

[0073] In a fourth aspect, the present application provides a computer device, Figure 3 The specific structure block diagram of the computer device is shown in the figure. The computer device comprises one or more processors 101, a memory 102, and one or more computer programs. The processor 101 and the memory 102 are connected through a bus. The one or more computer programs are stored in the memory 102 and configured to be executed by the one or more processors 101. The processor 101 executes the computer program to implement the multi-workpiece batch laser engraving method based on adaptive matching of processing parameters according to the material of a workpiece according to any one of the embodiments of the first aspect. The computer device can be a desktop computer, a mobile terminal, and at least one of a mobile terminal including a mobile phone, a tablet computer, a personal digital assistant, or a wearable device.

[0074] It should be understood that the steps in each of the embodiments of the present application are not necessarily executed in the order indicated by the step numbers. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment can comprise multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times. The execution sequence of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least a part of other steps or sub-steps or stages of other steps.

[0075] 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. The program can be stored in a non-volatile computer readable storage medium, and when the program is executed, the processes of the above-mentioned embodiment methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), 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), etc.

[0076] The technical features of the above embodiments can be combined in any way. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0077] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for batch laser engraving of multiple workpieces based on adaptive matching of processing parameters according to workpiece material, characterized in that, The method includes: The top-view camera module is controlled to capture images of the workpiece; the field of view of the top-view camera module covers the entire processing table of the laser engraving machine, and multiple workpieces are pre-placed on the processing table. Extract the outline of each workpiece from the workpiece image; The pose data of each workpiece is determined based on the contour of each workpiece; The material type of each workpiece is determined based on the image region corresponding to the contour of each workpiece, and a laser engraving parameter set is set for each workpiece based on the material type of each workpiece; wherein, different material types correspond to different laser engraving parameter sets; A laser engraving path is generated for each workpiece based on the design pattern submitted by the user and the pose data of each workpiece. A laser engraving program is generated based on the pose data, laser engraving parameter set, and laser engraving path of each workpiece. The laser engraving machine is controlled to execute the laser engraving program to laser engrave each of the workpieces.

2. The method according to claim 1, characterized in that, Determining the material type of each workpiece based on the image region corresponding to the contour of each workpiece includes: Extract color histograms and local binary pattern texture features from the image region corresponding to the contour of each workpiece; The color histogram and local binary pattern texture features associated with each workpiece are concatenated and input into a lightweight convolutional neural network, and the output of the lightweight convolutional neural network determines the material type of each workpiece.

3. The method according to claim 1, characterized in that, A laser engraving parameter set is set for each workpiece according to its material type, including: Using the material type of each workpiece as an index, the corresponding laser engraving parameters are read from a preset material parameter database to generate a laser engraving parameter set for each workpiece; the material parameter database includes recommended power, speed, number of engravings and safety thresholds for various materials at different thicknesses.

4. The method according to claim 1, characterized in that, The pose data includes center coordinates and rotation angles; extracting the contour of each workpiece from the workpiece image, and determining the pose data of each workpiece based on its contour, includes: Using the contour image of any of the workpieces as a shape reference, shape matching is performed on the contour images of the other workpieces to obtain the coarse position. Based on the coarse position, the corner points of each workpiece are extracted, and the corner points of each workpiece are transformed from the image coordinate system to the machine tool coordinate system through perspective transformation to obtain the center coordinates and rotation angle of the contour of each workpiece.

5. The method according to claim 1, characterized in that, A laser engraving parameter set is set for each workpiece according to its material type, including: Thickness information for each workpiece is obtained using an additional depth camera or binocular camera; Using the thickness information and material type of each workpiece as a joint index, the corresponding laser engraving parameters are read from a preset material parameter database to generate a laser engraving parameter set for each workpiece.

6. The method according to claim 1, characterized in that, The laser engraving machine includes multiple laser modules; it generates a laser engraving program based on the pose data, laser engraving parameter set, and laser engraving path of each workpiece, and controls the laser engraving machine to execute the laser engraving program to perform laser engraving on each workpiece, including: The processing table is divided into multiple material regions according to the material type of all the workpieces, and a corresponding material region is assigned to each of the laser modules; A sub-laser engraving program corresponding to each of the material regions is generated, and each of the laser modules is controlled to execute the corresponding sub-laser engraving program in parallel, so as to simultaneously perform laser engraving on workpieces in different material regions.

7. The method according to claim 1, characterized in that, When the laser engraving machine executes the laser engraving program, it processes each workpiece in sequence, and before the laser head moves to the next workpiece, it resets the parameters of the laser head according to the laser engraving parameter set of the next workpiece.

8. A multi-workpiece batch laser engraving device based on adaptive matching of processing parameters for workpiece materials, characterized in that, The device includes: The shooting control module is used to control the top-view camera module to shoot and obtain workpiece images; the field of view of the top-view camera module covers the entire processing table of the laser engraving machine, and multiple workpieces are pre-placed on the processing table; A workpiece contour extraction module is used to extract the contour of each workpiece from the workpiece image; The workpiece pose determination module is used to determine the pose data of each workpiece based on the contour of each workpiece. The adaptive setting module for processing parameters is used to determine the material type of each workpiece based on the image region corresponding to the contour of each workpiece, and to set a laser engraving parameter set for each workpiece based on the material type of each workpiece; wherein, different material types correspond to different laser engraving parameter sets; The engraving path generation module is used to generate a laser engraving path for each workpiece based on the design pattern submitted by the user and the pose data of each workpiece. The engraving program generation module is used to generate a laser engraving program based on the pose data, laser engraving parameter set, and laser engraving path of each workpiece. The engraving control module is used to control the laser engraving machine to execute the laser engraving program to laser engrave each of the workpieces.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

10. A computer device comprising one or more processors, a memory, and one or more computer programs, wherein the processors and the memory are connected via a bus, and the one or more computer programs are stored in the memory and configured to be executed by the one or more processors, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 7.

Images