Closed-loop control method, device and system for cutting hole site quality and storage medium

Abstract

The invention provides a closed-loop control method and device for cutting hole site quality, a storage medium and a system, and the method comprises the following steps: carrying out the image collection of a completely-cut qualified workpiece, selecting a feature region containing a hole site contour, and generating a hole site feature region image; performing standardized preprocessing on the hole site feature region image to generate a binary template image; after laser cutting, acquiring an image of the workpiece to be detected, and automatically extracting a detection area image corresponding to the feature area; performing standardization preprocessing on the detection area image to generate a binary detection image; calculating a matching value of the binarized detection image and the binarized template image, and comparing the matching value with a second preset threshold value; and judging that the hole site quality is qualified or triggering a laser cutting parameter adjusting instruction or generating a defect alarm signal. According to the closed-loop control method for the laser cutting hole site quality, the cutting quality of the hole site can be recognized, the cutting parameters can be automatically adjusted, and the cutting quality is ensured.

Description

Technical Field

[0001] The present application belongs to the field of laser processing technology, and more specifically, to a closed-loop control method, device, storage medium and system for cutting hole quality. Background Art

[0002] With the development of laser cutting technology and the expansion of its application areas, the requirements for cutting quality are becoming increasingly stringent. In the traditional laser cutting process, the cutting quality of the hole position often depends on the operator's experience and regular manual inspection. This method is not only inefficient, but also difficult to ensure consistency and accuracy. Summary of the invention

[0003] The embodiment of the present application provides a closed-loop control method for the quality of laser cutting holes, which can identify the cutting quality of holes and automatically adjust cutting parameters to ensure cutting quality.

[0004] The technical solution adopted in the embodiment of the present application is: to provide a closed-loop control method for the quality of laser cutting holes, including the following steps:

[0005] (1) Template construction phase:

[0006] Capture images of completely cut and qualified workpieces, and generate hole feature area images by interactively selecting feature areas containing hole contours;

[0007] Performing standardized preprocessing on the hole feature region image to generate a binary template image, wherein the standardized preprocessing includes denoising, grayscale, contrast enhancement, and binary processing based on a first preset threshold;

[0008] (2) Online detection and feedback stage:

[0009] After laser cutting, an image of the workpiece to be inspected is collected, and an image of the inspection area corresponding to the characteristic area is automatically extracted;

[0010] Performing the standardization preprocessing on the detection area image to generate a binary detection image;

[0011] Calculating a matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and comparing the matching value with a second preset threshold;

[0012] If the matching value does not exceed the second preset threshold, the hole position quality is determined to be qualified;

[0013] If the matching value exceeds the second preset threshold, a laser cutting parameter adjustment instruction is triggered or a defect alarm signal is generated.

[0014] Further, the interactive selection includes:

[0015] In the captured image of the qualified workpiece, an area including the hole feature and excluding the workpiece contour is manually framed to obtain the hole feature area image.

[0016] Furthermore, the first preset threshold is manually set according to a processing environment of the target device, or is generated through an iterative optimization algorithm.

[0017] Furthermore, the method for generating the first preset threshold includes:

[0018] The operator directly inputs the binarization threshold through the interactive interface; or

[0019] Multiple groups of images of matched workpieces are collected in the target environment, and the optimal threshold is determined through iterative search with the maximization of the hole edge gradient as the optimization goal.

[0020] Furthermore, the method for extracting the detection area image includes:

[0021] Reading the area selection coordinates of the hole feature area image;

[0022] In the image of the workpiece to be inspected, regions at the same position are automatically extracted based on the region selection coordinates to obtain an inspection region image.

[0023] Furthermore, the triggering laser cutting parameter adjustment instruction is implemented as follows:

[0024] The system pre-stores multiple sets of standard cutting parameters, each set of standard cutting parameters corresponds to a matching value interval;

[0025] When the matching value exceeds a second preset threshold, automatically switching to the corresponding standard cutting parameter group according to the matching value interval in which the matching value is located, and performing cutting parameter adjustment;

[0026] The standard cutting parameters include adjustment amounts of power and / or action time, and the adjustment amounts corresponding to different intervals are in a gradient increasing relationship.

[0027] Furthermore, the gradient increasing relationship satisfies:

[0028] The greater the deviation of the matching value interval to which the matching value belongs from the second preset threshold is, the higher the power increase ratio and / or action time extension ratio in the corresponding standard cutting parameters is.

[0029] The embodiment of the present application also provides a closed-loop control device for laser cutting hole quality, comprising:

[0030] An image acquisition module is used to acquire images of qualified workpieces during the template construction phase, and to acquire images of workpieces to be inspected during the online inspection and feedback phase;

[0031] An interactive area selection module is used to manually select a feature area containing a hole contour during the template construction phase, generate a hole feature area image, and record coordinates;

[0032] A preprocessing module performs denoising, grayscale, contrast enhancement and binarization based on a first preset threshold on the image to generate a binary template image;

[0033] An automatic area extraction module extracts a corresponding detection area image according to the coordinates;

[0034] A matching and comparison module calculates a matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and compares the matching value with a second preset threshold;

[0035] The feedback execution module generates a hole quality qualified signal, a laser cutting parameter adjustment instruction or a defect alarm signal according to the comparison result.

[0036] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of any of the methods described above.

[0037] An embodiment of the present application also provides a laser cutting control system, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of any of the methods described above.

[0038] The closed-loop control method for the quality of laser cutting holes provided in the embodiment of the present application has the beneficial effect that: the closed-loop control method for the quality of laser cutting holes in the embodiment of the present application collects images of completely cut qualified workpieces, extracts hole feature areas, and performs standardized preprocessing to form a binary template image. The detection area image obtained after the image of the workpiece to be inspected is processed in the same way after cutting is matched and compared with the binary template image, so that it can automatically determine whether the workpiece is qualified, output the judgment effect, and trigger the laser cutting parameter adjustment instruction when it is unqualified, so as to automatically adjust the cutting parameters to ensure the quality of the next cutting, or issue an alarm to remind the operator to perform relevant processing. That is, this method can automatically determine the cutting quality of the hole and automatically adjust the cutting parameters to ensure the cutting quality and improve the cutting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0040] Figure 1 A flow chart of a closed-loop control method for laser cutting hole quality provided in an embodiment of the present application;

[0041] Figure 2 A flowchart of a standardized preprocessing module provided in an embodiment of the present application;

[0042] Figure 3 A module connection diagram of a closed-loop control device for laser cutting hole quality provided in an embodiment of the present application.

[0043] Among them, the reference numerals in the figure are:

[0044] 10. Image acquisition module; 20. Interactive area selection module; 30. Preprocessing module; 40. Automatic area extraction module; 50. Matching and comparison module; 60. Feedback execution module; 70. Laser cutting equipment. DETAILED DESCRIPTION

[0045] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0047] It should be understood that the orientation or position relationship indicated by terms such as "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0048] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0049] See also Figure 1, the closed-loop control method for the quality of laser cutting holes provided in the embodiment of the present application is now described. The closed-loop control method for the quality of laser cutting holes provided in the embodiment of the present application comprises the following steps:

[0050] (1) Template construction phase:

[0051] S10: Capture images of the workpiece that has been completely cut and qualified, and generate a hole feature area image by interactively selecting a feature area containing a hole profile.

[0052] In this step, the image of the qualified workpiece is collected. When collecting, the completely cut qualified workpiece (no hole residue, smooth edge) is placed in the processing station of the laser cutting machine, and the light source system is started.

[0053] Adjust the light source angle to 30° to 75°, such as 40°, 45°, 50°, 55°, or 60°, to eliminate reflections on the metal surface (a polarizing plate may be further used to eliminate reflections) and ensure that there is no shadow in the hole area.

[0054] An industrial camera is used to shoot the workpiece at a suitable focal length to obtain the original image of the workpiece.

[0055] The interactive selection includes: manually selecting an area including the hole feature and excluding the workpiece contour in the acquired image of the qualified workpiece to obtain the hole feature area image.

[0056] For example, open the original image of the workpiece in the human-machine interface of the device, and use image processing tools (such as image cropping tools) to manually or automatically select the area containing the hole (excluding the outer contour of the workpiece), such as a 5mm diameter round hole, excluding the outer contour of the workpiece (selection range: 5mm diameter + 2mm surrounding buffer area). The purpose is to accurately extract the hole feature area, avoid background interference, and greatly reduce the effective area, greatly reducing the amount of data processing. For example, the effective area is reduced to 30%-70% of the original image, and the data processing volume is reduced by 70%. It should be noted that when selecting the frame, it is necessary to avoid interference areas such as scratches and oil stains.

[0057] In addition, the automatic screenshot assist function can be activated. When the offset between the manually selected boundary and the hole edge exceeds the pixel tolerance (for example, 5 pixels), a visual warning is triggered, such as a pop-up warning or a red flashing warning.

[0058] At the same time, the system records the coordinates of the selected area, for example (x1, y1, x2, y2).

[0059] S20: performing standardization preprocessing on the hole feature region image to generate a binary template image, wherein the standardization preprocessing includes denoising, grayscale, contrast enhancement, and binary processing based on a first preset threshold.

[0060] The purpose of this step is to pre-process the image and express the same image features to improve the robustness of the matching algorithm.

[0061] Reference Figure 2 , standardization preprocessing specifically includes:

[0062] S201: Denoising: Gaussian filtering or median filtering is used to reduce random noise in the image, such as sensor noise.

[0063] S202: Grayscale. The grayscale operation converts the color image into a grayscale image, which simplifies the image data volume while retaining enough information for feature extraction. Specifically, the weighted average method (R: 0.299, G: 0.587, B: 0.114) can be used to generate an 8-bit grayscale image.

[0064] S203: Contrast enhancement. By adjusting the brightness and contrast of the image, the hole edge is made clearer. Specifically, histogram equalization can be used to stretch the grayscale distribution to 0-255. It should be noted that histogram equalization needs to limit the stretching range of contrast to avoid excessive enhancement and the introduction of noise.

[0065] S204: Binarization based on the first preset threshold. Adjust the preprocessed image to a suitable threshold, perform a binarization operation on the image, and convert the grayscale image into a black and white image. The first preset threshold can be a grayscale value of 130 or 110. It can be understood that different materials need to use different threshold ranges according to the situation, such as 120 to 140 for stainless steel and 100 to 120 for aluminum alloy.

[0066] After completion, the preprocessed binary template image, the selection coordinates, and the first preset threshold of binary are packaged into a template file. In addition, the file name is stored in the local database with the equipment number + workpiece model, so as to establish a traceable template library and support fast switching of multiple models of workpieces.

[0067] In some embodiments, the first preset threshold is manually set according to the processing environment of the target device. That is, the first preset threshold is manually set. For example, according to the lighting environment on the cutting station, the operator directly inputs the binarization threshold through the operation interface, which is convenient for rapid deployment, but relies on experience accumulation and is suitable for standardized production lines and dedicated production lines with stable equipment parameters.

[0068] In some embodiments, the first preset threshold is generated by an iterative optimization algorithm.

[0069] Specifically, multiple groups of qualified workpiece images are collected under the target environment, and the optimal threshold is determined by iterative search with the maximization of the hole edge gradient as the optimization goal. For example, the system automatically collects 10 qualified images, with the maximization of the hole edge gradient as the goal, traverses the threshold range of 80-160 (each adjustment step is 10), selects the threshold with the largest gradient mean (for example, 136), and saves the threshold as the first preset threshold.

[0070] (2) Online detection and feedback stage:

[0071] S30: After laser cutting, an image of the workpiece to be inspected is collected, and an inspection area image corresponding to the feature area is automatically extracted.

[0072] That is, after the cutting is completed, the workpiece position is kept unchanged, and the industrial camera is triggered to capture the real-time image. Then the image of the detection area is extracted.

[0073] Wherein, the method for automatically extracting the detection area image includes:

[0074] S301: Reading the area selection coordinates of the hole feature area image.

[0075] S302: In the image of the workpiece to be inspected, automatically extracting regions at the same position based on the region selection coordinates to obtain an inspection region image.

[0076] For example, the coordinates (x1, y1, x2, y2) stored in the template construction stage are read, and in the image of the workpiece to be inspected, the area at the same position is automatically extracted based on the area selection coordinates to obtain the inspection area image.

[0077] The purpose of step S30 is to ensure that the detection area and the template area are aligned in space, so as to ensure the accuracy of the subsequent matching algorithm.

[0078] It should be noted that operators should calibrate the coordinate mapping relationship regularly.

[0079] Preferably, if the workpiece position deviation causes the interception area to be out of bounds, an alarm can be triggered, and the operator can detect and clear the alarm.

[0080] S40: performing the standardization preprocessing on the detection area image to generate a binary detection image.

[0081] That is, in this step, the detection area image is subjected to the same standardized preprocessing process as the template (denoising → grayscale → contrast enhancement → binarization) to obtain a binary detection image.

[0082] The same image operation is used to ensure that other interference factors of the binary detection image and the binary template image are eliminated, and the two are as similar as possible except for the hole position.

[0083] S50: Calculating a matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and comparing the matching value with a second preset threshold.

[0084] Among them, the square difference matching algorithm is:

[0085]

[0086] In this formula, T(x′, y′) represents the pixel value of the template image at the position (x', y').

[0087] I(x+x′,y+y′) represents the pixel value at the position (x+x',y+y') of the image to be detected. R(x,y) represents the matching value at the position (x,y) in the image to be detected.

[0088] The meaning of the formula is to slide the template image in the image to be detected, and for each possible position (x, y), calculate the sum of the squares of the pixel differences between the template and the corresponding area of ​​the image to be detected. The smaller the sum, the higher the matching degree of the position. Specifically, the matching value ranges from 0 to 1, with 0 being a complete match. By comparing the matching value with the second preset threshold, it is determined whether the two holes are consistent, and then whether the hole just cut is qualified.

[0089] S60: If the matching value does not exceed the second preset threshold, the hole position quality is determined to be qualified.

[0090] Among them, the second preset threshold is a preset value, which is set by the operator according to the lighting environment of the equipment and the size of the hole. The second preset threshold can be 0.3, 0.5, or 0.8, which is selected according to actual conditions.

[0091] Taking the second preset threshold of 0.85 as an example, if the matching value does not exceed the second preset threshold, that is, if R(x,y) ≤0.85, it is judged to be qualified and the hole has been completely perforated. The hole wall should be perpendicular to the material surface, the hole wall surface should be smooth, without obvious defects such as burrs, pits or protrusions, there should be no collapse or deformation at the entrance and exit of the hole, and there should be no residual slag, spatter or other impurities in the hole.

[0092] S70: If the matching value exceeds the second preset threshold, trigger a laser cutting parameter adjustment instruction or generate a defect alarm signal.

[0093] Taking the second preset threshold of 0.85 as an example, if the matching value R(x,y)>0.85, the adjustment of cutting parameters or alarm is triggered. By adjusting the cutting parameters to appropriate values, it is ensured that the matching of the holes after subsequent cutting is less than the second preset threshold, and the quality of the cut holes is ensured to be qualified.

[0094] Preferably, the system stores several sets of pre-set standard cutting parameters, each set of standard cutting parameters corresponds to a different matching value range. According to the actual size of the matching value, the matching value can be checked to see which range the matching value falls within, and the cutting parameters can be automatically adjusted to the standard cutting parameters corresponding to the range.

[0095] For example, when the matching value range is 0.85 to 0.90, it corresponds to the first set of standard cutting parameters, in which the power is A and the action time is T.

[0096] When the matching value range is 0.90 to 0.95, it corresponds to the second set of standard cutting parameters, in which the power is 1.1A and the action time is 1.2T.

[0097] When the matching value range is 0.90-0.95, the machine will be shut down, the sound and light alarm will be triggered, and the defective hole position will be marked on the interface.

[0098] Preferably, when the cutting is unqualified for the first time during cutting, the system automatically adjusts the cutting parameters. Only when the cutting parameters are still unqualified after adjustment, the alarm is triggered again.

[0099] The embodiment of the present application also provides a closed-loop control device for the quality of laser cutting holes, including an image acquisition module 10, an interactive area selection module 20, a preprocessing module 30, an automatic area extraction module 40, a matching and comparison module 50 and a feedback execution module 60.

[0100] The image acquisition module 10 is used to acquire images of qualified workpieces in the template construction stage, and to acquire images of workpieces to be inspected in the online inspection and feedback stage.

[0101] The image acquisition module 10 is mainly responsible for acquiring required images at different stages.

[0102] In the template construction stage, a qualified workpiece needs to be obtained as a reference standard. The image acquisition module 10 will acquire an image of the qualified workpiece, which will serve as the template basis for subsequent inspections and contains hole position information that meets quality requirements.

[0103] In the actual production process, each workpiece to be inspected needs to be inspected for quality, that is, the online inspection and feedback stage. At this time, the image acquisition module 10 will collect the image of the workpiece to be inspected for subsequent comparison with the qualified template.

[0104] The interactive region selection module 20 is used to manually select a feature region containing a hole contour during the template construction phase, generate a hole feature region image and record coordinates.

[0105] The operator manually selects the feature area containing the hole contour on the acquired qualified workpiece image through human-computer interaction. This is because there may be a lot of information irrelevant to the hole quality in the image, and manual selection can accurately locate the hole part that needs attention.

[0106] After the selection is completed, the module will generate a hole feature region image based on the selected region, and this image only contains the hole position related information we are interested in. At the same time, the coordinates of the feature region in the original image will be recorded, and these coordinates will play an important role in the subsequent automatic region extraction module 40.

[0107] The pre-processing module 30 performs denoising, gray-scaling, contrast enhancement and binarization based on a first preset threshold on the image to generate a binary template image.

[0108] That is, the preprocessing module 30 performs a series of preprocessing operations on the collected images to improve the quality and analyzability of the images.

[0109] Specific processing steps:

[0110] Denoising: Images may be affected by various noises during the acquisition process, such as sensor noise, ambient light noise, etc. Denoising can remove these noises, making the image clearer and reducing the impact of noise on subsequent analysis.

[0111] Grayscale: Color images contain rich color information, but color information is not necessary when analyzing hole characteristics. Grayscale processing converts color images into grayscale images, reducing the amount of data while highlighting the brightness information of the image for easy subsequent processing.

[0112] Contrast enhancement: In order to make the hole features in the image more obvious and facilitate subsequent analysis and identification, the image contrast needs to be enhanced. By adjusting the brightness and contrast of the image, the hole contours can be made clearer and easier to detect and analyze.

[0113] Binarization based on the first preset threshold: Binarization is to convert the grayscale image into an image with only two colors (usually black and white). According to the preset first preset threshold, the part of the image with a pixel value greater than the threshold is set to white, and the part less than the threshold is set to black. In this way, the hole feature can be separated from the background and a binary template image can be generated, which is convenient for subsequent matching and comparison operations.

[0114] The automatic region extraction module 40 extracts the corresponding detection region image according to the coordinates.

[0115] That is, according to the previously recorded feature area coordinates, the corresponding detection area image is extracted from the image of the workpiece to be detected.

[0116] Since the interactive area selection module 20 has recorded the coordinates of the hole feature area in the qualified workpiece image during the template construction stage, the automatic area extraction module 40 will accurately extract the area at the same position in the workpiece image to be inspected based on these coordinates during the online inspection and feedback stage, and generate an inspection area image. This ensures that the subsequent matching and comparison is performed in the same hole area, thereby improving the accuracy of the inspection.

[0117] The matching and comparison module 50 calculates the matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and compares the matching value with a second preset threshold.

[0118] The matching and comparison module 50 uses a square difference matching algorithm to calculate the matching value between the binary detection image and the binary template image. The square difference matching algorithm measures the similarity between the two images by calculating the sum of the squares of the differences between the corresponding pixels of the two images. The smaller the matching value, the more similar the two images are.

[0119] The calculated matching value is compared with a preset second threshold value, which is set according to actual production requirements and experience, and is used to determine whether the hole quality of the workpiece to be inspected is qualified.

[0120] The feedback execution module 60 generates a hole quality qualified signal, a laser cutting parameter adjustment instruction or a defect alarm signal according to the comparison result. That is, according to the comparison result of the matching comparison module 50, a corresponding signal is generated to realize closed-loop control of the laser cutting hole quality.

[0121] If the matching value is less than or equal to the second preset threshold, it means that the hole position of the workpiece to be inspected matches the hole position of the qualified template to a high degree, and the hole position quality is qualified. At this time, the feedback execution module 60 will generate a hole position quality qualified signal, indicating that the workpiece can pass the quality inspection.

[0122] If the matching value is greater than the second preset threshold value, but has not reached the level of a serious defect, it indicates that the hole position of the laser cutting may have a certain deviation, and the laser cutting parameters need to be adjusted. The feedback execution module 60 generates a laser cutting parameter adjustment instruction and sends it to the laser cutting device 70 to adjust the cutting parameters to improve the hole position quality of subsequent workpieces.

[0123] If the matching value is much greater than the second preset threshold, it means that the hole position of the workpiece to be inspected has serious defects and may not meet the quality requirements. At this time, the feedback execution module 60 will generate a defect alarm signal to remind the operator to handle it in time to avoid mass production of unqualified products.

[0124] Furthermore, the interactive area selection module 20 includes a visualization interface and a coordinate storage unit.

[0125] The visualization interface displays the qualified workpiece image and provides a selection tool. The visualization interface can clearly display the qualified workpiece image previously acquired by the image acquisition module 10 during the template construction phase. This allows the operator to intuitively observe the hole position in the image, including the hole position, shape, size and other information.

[0126] In order to facilitate operators to accurately select the feature area containing the hole contour, the visual interface provides a special box selection tool. Operators can use this tool to manually draw a rectangular box on the image to select the area they think contains the key hole features. This interactive operation method makes full use of the operator's professional knowledge and experience to more accurately locate the hole area that needs to be analyzed.

[0127] In actual system implementation, the visualization interface is usually developed based on graphical user interface (GUI) technology. Libraries such as Python's Tkinter and PyQt, or GUI development toolkits corresponding to other programming languages ​​can be used. The interface will load and display the qualified workpiece image in a specific area, and provide corresponding mouse interaction functions, so that the operator can draw a box selection area by dragging the mouse.

[0128] The coordinate storage unit records the coordinates of the manually selected area. When the operator completes the selection of the feature area using the selection tool of the visual interface, the coordinate storage unit will immediately record the coordinates of the selected area in the qualified workpiece image, and the subsequent automatic area extraction module 40 will extract the corresponding detection area from the workpiece image to be detected based on these coordinates.

[0129] The coordinate storage unit will store the recorded coordinate information in a suitable data structure. At the same time, in order to ensure the persistence and reusability of the data, these coordinate information may be stored in a database or file so that it can be called at any time in the subsequent detection process.

[0130] Furthermore, the preprocessing module 30 includes: a threshold configuration unit, which supports a first preset threshold value that is manually input or generated by an iterative optimization algorithm.

[0131] The operator manually inputs a suitable first preset threshold value based on his own experience and observation of the image. This method is suitable for situations where the operator has a deep understanding of the image features and the image features are relatively stable and easy to judge. This manual input method is highly flexible and targeted. Operators can directly set a threshold value that they think is most suitable based on actual conditions, such as the color of the hole position, contrast, image noise level and other factors, and can quickly respond to some special situations or specific image requirements.

[0132] The iterative optimization algorithm is used to automatically calculate a suitable first preset threshold value, which can automatically find a threshold value that best separates the image foreground (hole position features) and background to a certain extent, with high objectivity and accuracy. The algorithm will calculate according to the actual grayscale distribution of the image, does not rely on the subjective judgment of the operator, and can find the relatively optimal threshold value in complex images. Moreover, for a large number of similar images, the algorithm can quickly and stably generate a suitable threshold value, which improves processing efficiency.

[0133] Furthermore, the threshold configuration unit includes a manual input interface or an iterative optimization processor.

[0134] The manual input interface is used to receive the binarization threshold set by the operator. In practical applications, the operator may have rich experience in processing specific types of workpiece images and can manually input a threshold they think is appropriate by observing the grayscale distribution and hole characteristics of the image with the naked eye.

[0135] The iterative optimization processor searches for a binary threshold based on multiple sets of grid workpiece images with the goal of maximizing the gradient of the hole edge.

[0136] The iterative optimization processor uses an iterative optimization algorithm to maximize the hole edge gradient and search for a suitable binarization threshold on multiple groups of grid workpiece images. Maximizing the hole edge gradient means that the hole edge can be more clearly highlighted in the binarized image, which is convenient for subsequent matching, comparison and quality inspection.

[0137] First, it is necessary to collect multiple groups of qualified workpiece images, which contain qualified hole position information under different angles and lighting conditions, to ensure that the searched threshold has good versatility.

[0138] The processor will traverse a series of possible thresholds and perform binarization on each group of grid workpiece images. For each binarized image, the gradient value of the hole edge is calculated. The gradient value reflects the rate of change of the pixel value in the image, and the gradient value at the edge is usually larger. The threshold is adjusted continuously until a threshold is found that maximizes the sum of the hole edge gradients, which is used as the final binarization threshold.

[0139] Furthermore, the automatic region extraction module 40 includes a coordinate mapping unit and an image capture unit.

[0140] The coordinate mapping unit reads the coordinates. The function of the coordinate mapping unit is to read the coordinate information of the characteristic area containing the hole profile previously recorded by the interactive area selection module 20, and the coordinate information clarifies the specific position of the hole characteristic area in the qualified workpiece image.

[0141] The image capture unit automatically extracts the area at the same position in the image to be detected based on the coordinates to obtain a detection area image.

[0142] The image capture unit automatically extracts the area at the same position in the image of the workpiece to be inspected based on the coordinate information read by the coordinate mapping unit, thereby obtaining an inspection area image. This step ensures that the subsequent matching and comparison is performed in the same hole area as in the template construction stage, improving the accuracy and reliability of the inspection.

[0143] First, the unit receives the image of the workpiece to be inspected and the coordinate information transmitted by the coordinate mapping unit. Then, the boundary of the area to be intercepted is determined based on the coordinate information, and the corresponding area is accurately intercepted in the image to be inspected. During the interception process, it is necessary to ensure that the size and position of the intercepted area are consistent with the feature area in the qualified workpiece image.

[0144] An embodiment of the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the method described in any of the above embodiments.

[0145] The computer-readable storage medium of the embodiment of the present application includes the closed-loop control method for the quality of the laser cutting hole position in any of the above-mentioned embodiments, and therefore has the beneficial effects brought by the closed-loop control method for the quality of the laser cutting hole position in any of the above-mentioned embodiments, which will not be repeated here.

[0146] An embodiment of the present application also provides a laser cutting control system, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method described in any of the above embodiments.

[0147] The laser cutting control system of the embodiment of the present application includes the closed-loop control method for the laser cutting hole position quality in any of the above embodiments, so it has the beneficial effects brought by the closed-loop control method for the laser cutting hole position quality in any of the above embodiments, which will not be repeated here.

[0148] It should be noted that the above-mentioned closed-loop control method, device, storage medium and system for cutting hole position quality belong to a general inventive concept, and the contents of the closed-loop control method, device, storage medium and system for cutting hole position quality can be mutually applicable. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0149] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A closed-loop control method for laser cutting hole quality, characterized in that: The following steps are involved: (1) Template construction phase: Capture images of completely cut and qualified workpieces, and generate hole feature area images by interactively selecting feature areas containing hole contours; Performing standardized preprocessing on the hole feature region image to generate a binary template image, wherein the standardized preprocessing includes denoising, grayscale, contrast enhancement, and binary processing based on a first preset threshold; (2) Online detection and feedback stage: After laser cutting, an image of the workpiece to be inspected is collected, and an image of the inspection area corresponding to the characteristic area is automatically extracted; Performing the standardization preprocessing on the detection area image to generate a binary detection image; Calculating a matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and comparing the matching value with a second preset threshold; If the matching value does not exceed the second preset threshold, the hole position quality is determined to be qualified; If the matching value exceeds the second preset threshold, a laser cutting parameter adjustment instruction is triggered or a defect alarm signal is generated.

2. The closed-loop control method for laser cutting hole quality according to claim 1, characterized in that: The interactive selection includes: In the captured image of the qualified workpiece, an area including the hole feature and excluding the workpiece contour is manually framed to obtain the hole feature area image.

3. The closed-loop control method for laser cutting hole quality according to claim 1, characterized in that: The first preset threshold is manually set according to the processing environment of the target device, or generated through an iterative optimization algorithm.

4. The closed-loop control method for laser cutting hole quality according to claim 3 is characterized in that: The method for generating the first preset threshold comprises: The operator directly inputs the binarization threshold through the interactive interface; or Multiple groups of images of matched workpieces are collected in the target environment, and the optimal threshold is determined through iterative search with the maximization of the hole edge gradient as the optimization goal.

5. The closed-loop control method for laser cutting hole quality according to claim 1, characterized in that: The method for extracting the detection area image comprises: Reading the area selection coordinates of the hole feature area image; In the image of the workpiece to be inspected, regions at the same position are automatically extracted based on the region selection coordinates to obtain an inspection region image.

6. The closed-loop control method for laser cutting hole quality according to claim 1, characterized in that: The triggering laser cutting parameter adjustment instruction is implemented as follows: The system pre-stores multiple sets of standard cutting parameters, each set of standard cutting parameters corresponds to a matching value interval; When the matching value exceeds a second preset threshold, automatically switching to the corresponding standard cutting parameter group according to the matching value interval in which the matching value is located, and performing cutting parameter adjustment; The standard cutting parameters include adjustment amounts of power and / or action time, and the adjustment amounts corresponding to different intervals are in a gradient increasing relationship.

7. The closed-loop control method for laser cutting hole quality according to claim 6, characterized in that: The gradient increasing relationship satisfies: The greater the deviation of the matching value interval to which the matching value belongs from the second preset threshold is, the higher the power increase ratio and / or action time extension ratio in the corresponding standard cutting parameters is.

8. A closed-loop control device for laser cutting hole quality, characterized in that: include: An image acquisition module is used to acquire images of qualified workpieces during the template construction phase, and to acquire images of workpieces to be inspected during the online inspection and feedback phase; An interactive area selection module is used to manually select a feature area containing a hole contour during the template construction phase, generate a hole feature area image, and record coordinates; A preprocessing module performs denoising, grayscale, contrast enhancement and binarization based on a first preset threshold on the image to generate a binary template image; An automatic area extraction module extracts a corresponding detection area image according to the coordinates; A matching and comparison module calculates a matching value between the binary detection image and the binary template image by using a square difference matching algorithm, and compares the matching value with a second preset threshold; The feedback execution module generates a hole quality qualified signal, a laser cutting parameter adjustment instruction or a defect alarm signal according to the comparison result.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A laser cutting control system, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Images