An Adaptive Laser Cutting Method and System Based on Feature Parameters of Sheet Metal Parts

Abstract

The present invention relates to the field of adaptive control laser cutting technology, and specifically to an adaptive laser cutting method and system based on the characteristic parameters of sheet metal parts. First, by establishing a spatial coordinate system and obtaining a top view image of the cutting platform, the contour deviation is calculated and the corrected starting position is generated, thereby optimizing the cutting path. The laser cutting head moves to the corrected starting position according to this path and performs the cutting task. In addition, the method also includes dividing the image of the sheet metal part to be processed into multiple sub-images and establishing a cross-linked list of sub-images to describe the connection relationship of each sub-image. The feature vectors of the sub-images are extracted through a feature learning model, and the control parameters are adjusted using cutting simulation information to compensate for errors. For each sub-image, based on the cutting results and connection relationships, the control parameters are adaptively adjusted to ensure the accuracy of subsequent cutting steps. Finally, by updating the cutting marks and merging the sub-images, a complete cutting task is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive control laser cutting, and specifically provides an adaptive laser cutting method and system based on the characteristic parameters of sheet metal parts. Background Art

[0002] As an important manufacturing workpiece, sheet metal parts are widely used in various industries, especially in the fields of automobiles, aviation, household appliances, and construction, playing an important role. Sheet metal parts generally refer to parts made of thin sheet metals (such as steel, aluminum, stainless steel, and copper) through a series of production processes (such as stamping, bending, cutting, welding, stretching, etc.).

[0003] In the production process of sheet metal parts, cutting is a very crucial step, which is used to cut large metal sheets into the required shapes and sizes according to design requirements. The cutting process not only affects the accuracy and appearance of the product, but also is closely related to aspects such as production efficiency and material utilization rate. In modern sheet metal processing, laser cutting, as an advanced cutting technology, has gradually become the mainstream cutting method.

[0004] The laser cutting method is a high-precision non-contact material cutting process, which mainly focuses a high-intensity laser beam on the surface of the sheet metal part, causing the local area to rapidly heat up and melt or evaporate, thereby achieving cutting. During the laser cutting process, multiple laser parameters need to be strictly controlled to ensure the cutting accuracy and quality.

[0005] Currently, existing laser cutting methods mainly rely on set fixed parameters and are difficult to adapt to sheet metal parts with different thicknesses, materials, and surface states. Based on the above, how to efficiently and accurately cut various different specifications of sheet metal parts remains a difficult problem in production.

[0006] Therefore, the present invention proposes an adaptive laser cutting method and system based on the characteristic parameters of sheet metal parts. Summary of the Invention

[0007] The purpose of the present invention is to provide an adaptive laser cutting method and system based on the characteristic parameters of sheet metal parts. This method and system are used to adaptively adjust preset control parameters during the laser cutting process of sheet metal parts, specifically including: First, use the laser cutting head to accurately position and correct the starting position, and generate the movement path of the laser cutting head according to the contour and finished product characteristics of the sheet metal part. By processing the images of the cutting platform and the sheet metal part to be processed, further optimize the contour deviation and calculate and correct the starting position, and at the same time extract the contour deviation vector. Then, by dividing the sheet metal part image and establishing a cross-linked list, sequentially obtain the characteristics of each sub-image and perform cutting simulation, calculate the error between the simulated cutting information and the expected cutting information, and thereby dynamically adjust the control parameters.

[0008] In addition, this method provides real-time feedback on the cutting situation of each sub-image to be processed, automatically adjusts the control parameters in subsequent processing steps to ensure the accuracy and efficiency of the cutting process. Especially when there is a connection relationship between multiple sub-images, the system can expand based on the information of the cut sub-images, merge the current sub-image to be processed and the cut sub-images, and further perform standardization processing and impact analysis. Finally, the system optimizes the adjustment process of the control parameters by combining the sub-image features with the cut impact vector, making the entire cutting process more in line with the predetermined processing requirements.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] An adaptive laser cutting method based on the characteristic parameters of sheet metal parts, comprising:

[0011] Using the control panel to move the laser cutting head to the corrected starting position; wherein, moving the laser cutting head to the corrected starting position includes:

[0012] Taking the current position of the laser cutting head as the origin, establishing a spatial coordinate system;

[0013] Furthermore, obtaining the current top view image of the cutting platform;

[0014] Furthermore, denoising and enhancing the contrast of the current top view image to obtain the first top view image;

[0015] Furthermore, extracting the cutting platform contour and the contour of the sheet metal part to be processed in the first top view image to obtain the cutting platform contour image and the contour image of the sheet metal part to be processed;

[0016] Furthermore, calculating the contour deviation between the cutting platform contour image and the contour image of the sheet metal part to be processed, and constructing a contour deviation vector;

[0017] Furthermore, obtaining the expected cutting information of the sheet metal part to be processed and performing feature extraction to obtain an expected feature vector;

[0018] Furthermore, generating the movement path of the laser cutting head and the corrected starting position according to the contour deviation vector and the expected feature vector;

[0019] Wherein, the generation process of the movement path and the corrected starting position includes:

[0020] Calculating the corrected starting position on the contour image of the sheet metal part to be processed according to the contour deviation vector, and the calculation formula is: ; wherein, is the corrected starting position; is the preset starting position; It is a function for correcting the starting position calculation; It is to obtain the centroid coordinate point from the contour image of the sheet metal part to be processed; It is the expected feature vector; It is the set of boundary points of the contour image of the sheet metal part to be processed; It is the correction parameter for the corrected starting position;

[0021] Furthermore, obtain the candidate movable path set from the origin to the corrected starting position;

[0022] Furthermore, select the candidate movable path set according to the contour deviation vector to obtain the movable path.

[0023] Furthermore, the laser cutting head moves to the corrected starting position according to the movable path.

[0024] Furthermore, obtain the image of the sheet metal part to be processed;

[0025] Furthermore, divide the image of the sheet metal part to be processed according to the cutting content to obtain N sub-images;

[0026] Furthermore, establish a sub-image cross-linked list for the sub-images according to the image of the sheet metal part to be processed; wherein, the sub-image cross-linked list includes: processing mark, sub-image serial number and sub-image connection relationship;

[0027] Furthermore, obtain the starting sub-image to be processed;

[0028] Furthermore, preprocess the starting sub-image to be processed to obtain a standard first sub-image;

[0029] Furthermore, input the standard first sub-image into the sheet metal part feature learning model to obtain a sub-image feature vector;

[0030] Furthermore, obtain the pixel coordinates corresponding to the sub-image feature vector;

[0031] Furthermore, establish a sub-graph feature-location set according to the pixel coordinates and the sub-image feature vector;

[0032] Furthermore, perform cutting simulation on the sub-graph feature-location set using a preset control parameter to obtain simulation cutting information;

[0033] Furthermore, calculate the error between the simulation cutting information and the expected cutting information to obtain a cutting error vector;

[0034] Furthermore, calculate the compensation control parameter using a control parameter compensation function; wherein, the control parameter compensation function is expressed as: ; wherein, is the control parameter compensation function; is the pixel coordinate compensation control parameter at; is the pixel coordinate cutting error vector at; is the cutting simulation function; is the pixel coordinate preset control parameter at; is the pixel coordinate sub-image feature vector at; is the pixel coordinate position information of.

[0035] Further, control the laser cutting head to cut according to the compensation control parameter, and update the cutting mark of the starting sub-image to be processed to 1;

[0036] Further, adaptively adjust the preset control parameter in the subsequent processing step according to the processing result of the starting sub-image to be processed, and use the laser cutting head to cut;

[0037] Among them, the process of adaptively adjusting the preset control parameter in the subsequent processing step includes:

[0038] Further, obtain the corresponding next sub-image to be processed according to the sub-image serial number, denoted as the current sub-image to be processed;

[0039] Further, obtain the sub-image that has the sub-image connection relationship with the current sub-image to be processed and the cutting mark is 1, denoted as the cut sub-image; among them, the sub-image connection relationship includes: upper connection, lower connection, left connection and right connection;

[0040] Further, merge the current sub-image to be processed and the cut sub-image to obtain the current extended sub-image to be processed;

[0041] Further, perform the preprocessing on the current extended sub-image to be processed to obtain the standard current extended sub-image to be processed;

[0042] Further, perform an impact analysis on the cut sub-image in the standard current extended sub-image to be processed to obtain a cut impact vector;

[0043] Further, input the current sub-image to be processed in the standard current extended sub-image to be processed into the sheet metal part feature learning model to obtain the current sub-image feature vector;

[0044] Further, adjust the current preset control parameter according to the cut impact vector and the current sub-image feature vector;

[0045] When all the cutting marks in the cross-linked list of sub-images are 1, the cutting task is completed.

[0046] An adaptive laser cutting system based on the characteristic parameters of sheet metal parts, comprising:

[0047] An intelligent control unit for controlling the laser cutting head through a control panel;

[0048] A monitoring unit for monitoring the sheet metal part during the cutting process;

[0049] An acquisition unit for acquiring images during the monitoring process of the monitoring unit; A preprocessing unit for preprocessing the acquired images;

[0050] A starting movement calculation unit for calculating the movement path of the laser cutting head and correcting the starting position; wherein, the starting movement calculation unit includes:

[0051] Taking the current position of the laser cutting head as the origin, a spatial coordinate system is established;

[0052] Furthermore, obtain the current top view image of the cutting platform;

[0053] Furthermore, denoise and enhance the contrast of the current top view image to obtain a first top view image;

[0054] Furthermore, extract the cutting platform contour and the contour of the sheet metal part to be processed in the first top view image to obtain a cutting platform contour image and a contour image of the sheet metal part to be processed;

[0055] Furthermore, calculate the contour deviation between the cutting platform contour image and the contour image of the sheet metal part to be processed, and construct a contour deviation vector;

[0056] Furthermore, obtain the expected cutting information of the sheet metal part to be processed and perform feature extraction to obtain an expected feature vector;

[0057] Furthermore, generate the movement path of the laser cutting head and the corrected starting position according to the contour deviation vector and the expected feature vector;

[0058] Wherein, the corrected starting position on the contour image of the sheet metal part to be processed is calculated according to the contour deviation vector, and the calculation formula is: ; wherein, is the corrected starting position; is the preset starting position; is the corrected starting position calculation function; is the centroid coordinate point obtained through the contour image of the sheet metal part to be processed; is the expected feature vector; is the set of boundary points of the contour image of the sheet metal part to be processed; is the correction parameter for the corrected starting position;

[0059] Further, obtain a candidate movable path set from the origin to the corrected starting position;

[0060] Further, select the candidate movable path set according to the contour deviation vector to obtain the movable path.

[0061] The control parameter optimization unit is used to optimize the control parameters for sheet metal cutting; wherein, the control parameter optimization unit includes:

[0062] Obtain the image of the sheet metal part to be processed;

[0063] Further, divide the image of the sheet metal part to be processed according to the cutting content to obtain N sub-images;

[0064] Further, establish a sub-image cross-linked list for the sub-images according to the image of the sheet metal part to be processed; wherein, the sub-image cross-linked list includes: processing marks, sub-image numbers, and sub-image connection relationships;

[0065] Further, obtain the starting sub-image to be processed;

[0066] Further, preprocess the starting sub-image to be processed to obtain a standard first sub-image;

[0067] Further, input the standard first sub-image into the sheet metal part feature learning model to obtain a sub-image feature vector;

[0068] Further, obtain the pixel coordinates corresponding to the sub-image feature vector;

[0069] Further, establish a sub-graph feature - position set according to the pixel coordinates and the sub-image feature vector;

[0070] Further, use the preset control parameters to perform cutting simulation on the sub-graph feature - position set to obtain simulation cutting information;

[0071] Further, calculate the error between the simulation cutting information and the expected cutting information to obtain a cutting error vector;

[0072] Further, calculate the compensation control parameter using the control parameter compensation function; wherein, the control parameter compensation function is expressed as: ; wherein, is the control parameter compensation function; are the pixel coordinates The compensation control parameter at is the pixel coordinate The cutting error vector at is the cutting simulation function is the pixel coordinate The preset control parameter at is the pixel coordinate The sub-image feature vector at is the pixel coordinate The position information of

[0073] Further, control the laser cutting head to cut according to the compensation control parameter, and update the cutting mark of the starting sub-image to be processed to 1;

[0074] Further, adaptively adjust the preset control parameter in the subsequent processing step according to the processing result of the starting sub-image to be processed, and obtain the corresponding next sub-image to be processed according to the sub-image serial number, denoted as the current sub-image to be processed;

[0075] Further, obtain the sub-image that has the sub-image connection relationship with the current sub-image to be processed and the cutting mark is 1, denoted as the cut sub-image; wherein, the sub-image connection relationship includes: upper connection, lower connection, left connection and right connection;

[0076] Further, merge the current sub-image to be processed and the cut sub-image to obtain the current extended sub-image to be processed;

[0077] Further, perform the preprocessing on the current extended sub-image to be processed to obtain the standard current extended sub-image to be processed;

[0078] Further, perform an impact analysis on the cut sub-image in the standard current extended sub-image to be processed to obtain the cut impact vector;

[0079] Further, input the current sub-image to be processed in the standard current extended sub-image to be processed into the sheet metal part feature learning model to obtain the current sub-image feature vector;

[0080] Further, adjust the current preset control parameter according to the cut impact vector and the current sub-image feature vector;

[0081] A display unit for displaying the cutting state of the sheet metal part and the control parameter.

[0082] Compared with the prior art, the beneficial effects of the present invention are:

[0083] 1. The present invention proposes a method for calculating the correction starting position of sheet metal parts; this method can effectively optimize the moving path of the laser cutting head, reduce errors during cutting, and improve cutting accuracy. By establishing a spatial coordinate system, obtaining and processing the top view of the cutting platform, extracting the contours of the cutting platform and the sheet metal parts to be processed, and calculating the contour deviation vector, the moving path and correction starting position of the cutting head are generated in combination with the expected feature vector. The method of the present invention can not only accurately determine the starting position of laser cutting, but also dynamically adjust the path during cutting to adapt to the shape of the sheet metal parts and the requirements of the finished product, thereby improving cutting efficiency and accuracy.

[0084] 2. The present invention proposes a method for adaptively adjusting control parameters; this method can accurately calculate and compensate for machining errors through the step-by-step processing of the sheet metal part image and cutting simulation, thereby dynamically optimizing the control parameters during the laser cutting process. By dividing and extracting features from the image of the sheet metal part to be processed, combined with the cross-linked list management of sub-images, the control parameters can be monitored and adjusted in real time during cutting to ensure that the cutting accuracy of each sub-image reaches the expected value. This method can effectively reduce machining errors, thereby significantly improving the cutting quality and machining efficiency of sheet metal parts.

[0085] 3. The present invention proposes a method for optimizing control parameters for subsequent processing steps; by tracking the cutting progress of sub-images and based on the connection relationship and cutting mark status of sub-images, the currently to-be-processed sub-image and the already-cut sub-images are obtained in real time. Combining influence analysis and the sheet metal part feature learning model, the method can accurately calculate the feature vector of the current sub-image and adjust the preset control parameters according to the already-cut influence vector to ensure the cutting quality and efficiency of subsequent processing steps. Description of the Drawings

[0086] Figure 1 It is a schematic diagram of the scenario for sheet metal part cutting provided by an embodiment of the present invention;

[0087] Figure 2 It is a flowchart of an adaptive laser cutting method based on sheet metal part feature parameters provided by an embodiment of the present invention;

[0088] Figure 3 It is a structural diagram of an adaptive laser cutting system based on sheet metal part feature parameters provided by an embodiment of the present invention;

[0089] Figure 4 It is a schematic diagram of the division of the image of the sheet metal part to be processed provided by an embodiment of the present invention;

[0090] Figure 5 It is a schematic diagram of the merging of sub-images provided by an embodiment of the present invention.

[0091] In the figure: 1, control panel; 2, cutting platform; 3, laser cutting head; 4, monitoring device; 5, sheet metal part to be processed. Detailed implementation mode

[0092] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present invention.

[0093] As an important manufacturing workpiece, sheet metal parts are widely used in various industries, especially in the fields of automobiles, aviation, household appliances, and construction, and play an important role. Sheet metal parts generally refer to parts made of thin sheet metal (such as steel, aluminum, stainless steel, and copper) through a series of production processes (such as stamping, bending, cutting, welding, and stretching).

[0094] Among the many production processes of sheet metal parts, cutting is one of the most common and important processes. This process is mainly used to cut metal sheets into the shapes and sizes required by the design. Common cutting methods include laser cutting, plasma cutting, flame cutting, and water jet cutting, etc.; among them, the laser cutting method is a high-precision non-contact material cutting process, which mainly focuses a high-intensity laser beam on the surface of the sheet metal part, so that the local area quickly heats up and melts or evaporates, thereby realizing the cutting process. During the laser cutting process, it is indeed necessary to strictly control multiple laser parameters to ensure the cutting accuracy and quality.

[0095] In the existing laser cutting methods, they mainly rely on set fixed parameters and are difficult to adapt to sheet metal parts with different scales, thicknesses, materials, and surface states; especially in mass production, how to efficiently and accurately cut various different specifications of sheet metal parts is still a difficult problem in production. For this reason, the present invention proposes an adaptive laser cutting method and system based on the characteristic parameters of sheet metal parts. It will be described in detail from the following two embodiments.

[0096] Embodiment 1:

[0097] In the embodiment of the present application, through the combination of the method and system of the present invention, the adjustment of the adaptive control parameters is realized during the laser cutting process of the sheet metal part to be processed; among them, the sheet metal part 5 to be processed is cut by a laser cutting device; in the example of the present application, the laser cutting device includes: a control panel 1, a cutting platform 2, a laser cutting head 3, and a monitoring device 4, and the specific structure is shown in Figure 1 . In Figure 1In it, the sheet metal part 5 is placed on the cutting platform 2, and the laser cutting head 3 is controlled by the control panel 1 to cut the sheet metal part 5. The monitoring device 4 is installed above the cutting platform 2 for real-time monitoring of the cutting process.

[0098] For Figure 1 the implementation process of Figure 2 and Figure 3 is realized through the content of Figure 2 The method flow of the present invention includes: S10. Place the sheet metal part to be processed on the cutting platform; S20. Use the control panel to move the laser cutting head to the correction starting position; S30. Obtain the image of the sheet metal part to be processed; S40. Divide the image of the sheet metal part to be processed according to the cutting content to obtain N sub-images; S50. Establish a cross-linked list of sub-images; S60. Obtain the starting sub-image to be processed; S70. Calculate the starting compensation control parameters according to the starting sub-image to be processed; S80. Adaptively adjust the preset control parameters in the subsequent processing steps according to the processing result of the starting sub-image to be processed, and perform cutting. Figure 3 The system structure diagram of the present invention includes: an intelligent control unit, a monitoring unit, a collection unit, a preprocessing unit, a starting movement calculation unit, a control parameter optimization unit, and a display unit.

[0099] The cutting process of the sheet metal part 5 to be processed is described according to the above content, which specifically includes the following content;

[0100] Place the sheet metal part 5 to be processed on the cutting platform 2 according to the above S10 step;

[0101] Furthermore, obtain the correction starting position and the movement path obtained by the starting movement calculation unit of the system, and use the intelligent control unit of the system to control the laser cutting head 3 to move to the correction starting position, corresponding to the above S10 step; wherein, the control panel 1 integrates all the functions realized by the intelligent control unit of the system;

[0102] Among them, the specific movement process of the laser cutting head 3 includes:

[0103] Taking the current position of the laser cutting head 3 as the origin, establish a spatial coordinate system;

[0104] Furthermore, use the collection unit of the system to obtain the current top view image of the cutting platform 2 taken by the monitoring device 4;

[0105] Furthermore, denoise and enhance the contrast of the current top view image to obtain the first top view image;

[0106] Furthermore, extract the contour images of the cutting platform 2 and the sheet metal part 5 to be processed in the first top view image to obtain the cutting platform contour image and the sheet metal part contour image to be processed;

[0107] Further, calculate the contour deviation between the contour image of the cutting platform and the contour image of the sheet metal part to be processed, and construct a contour deviation vector; wherein, the contour deviation vector includes: scale deviation, relative position deviation, and angular deviation;

[0108] Among them, the calculation formula for the scale deviation is: ; if the sizes are the same, the scale deviation is 0;

[0109] The calculation formula for the relative position deviation is: ; wherein, and are the centroids of the sheet metal part to be processed and the cutting platform respectively; if the centroids of the two coincide, the position deviation is 0;

[0110] The calculation formula for the angular deviation is: ; wherein, and are the main direction vectors of the contours of the cutting platform and the sheet metal part to be processed respectively;

[0111] Further, obtain the expected cutting information of the sheet metal part 5 to be processed; wherein, the expected cutting information includes: cutting shape, cutting path, and cutting shape size;

[0112] Further, characterize the expected cutting information to obtain an expected feature vector;

[0113] Further, calculate the corrected starting position of the sheet metal part 5 to be processed; wherein, the calculation formula for the corrected starting position is:

[0114] ;

[0115] Wherein, is the corrected starting position; is the preset starting position; is the corrected starting position calculation function; is the centroid coordinate point obtained from the contour image of the sheet metal part to be processed; is the expected feature vector; is the set of boundary points of the contour image of the sheet metal part to be processed; is the correction parameter of the corrected starting position;

[0116] For the corrected starting position calculation function it can be defined as:

[0117] ;

[0118] Wherein, is the number of the set of boundary points; is the boundary point Distance from the centroid coordinate point; is a boundary point , ; is an expected feature , ; is an expected feature weight of; is the number of expected features;

[0119] Taking Figure 1 the sheet metal part 5 to be processed in as an example; among them, , that is, there are 3 points in the boundary point set; calculating the distances from each point in the boundary point set to the centroid coordinate point are: , and ; among them, the geometric influence part is: ;

[0120] Calculating the influence part of the expected cutting information; among them, the expected feature vector is: ; the expected feature weights are: , and ; therefore, ;

[0121] Setting the correction parameter to 0.05; given the preset starting position is (101.5, 125); according to the above calculation results, the corrected starting position is: ;

[0122] Furthermore, obtaining the candidate movable path set from the origin to the corrected starting point; among them, the candidate movable path set includes multiple moving paths, and the corresponding paths can be generated using the space algorithm;

[0123] Furthermore, selecting from the candidate movable path set according to the contour deviation vector to obtain the moving path; among them, the steps for generating the moving path include:

[0124] Step 1. Evaluating the adaptability of each candidate path according to the calculated contour deviation vector;

[0125] Step 2. Selecting the path with the smallest contour deviation and most in line with the expected requirements as the final moving path according to the adaptability score of each candidate path;

[0126] Step 3. Smoothing the selected best path to reduce unnecessary sharp turns, complex bends, etc. in the path, and improving the stability and execution efficiency of the path;

[0127] Step 4: The path after optimization and smoothing is used as the final movement path and is prepared for the laser cutting head 3 to execute.

[0128] In the embodiment of the present application, by correcting the starting position of the sheet metal part to be processed and obtaining the movement path of the laser cutting head to the starting position, the cutting accuracy is improved and the error is reduced. Specifically, by analyzing the contour deviation vector of the sheet metal part to be processed, the starting position can be corrected to ensure that the laser cutting head cuts at the correct starting position, thereby minimizing the cutting error caused by the deviation of the starting point.

[0129] Further, the control panel 1 controls the laser cutting head 3 to move to the corrected starting position according to the movement path.

[0130] In the embodiment of the present application, through precise image processing and path optimization technology, the laser cutting head can accurately move to the corrected starting position. First, a spatial coordinate system is established based on the current position of the laser cutting head, and a real-time top view image of the cutting platform is obtained. After denoising and enhancing the contrast, the contour images of the cutting platform and the sheet metal part are extracted, the contour deviation is calculated, and a deviation vector is constructed. Through the characterization of the expected cutting information and the combination of the deviation vector, the corrected path of the laser cutting head is generated, and finally, the cutting head is accurately guided to move to the corrected starting position. This process effectively solves the cutting deviation caused by position error or deformation, ensuring the high precision and high stability of the laser cutting process.

[0131] Further, according to the content of step S30, the image acquisition unit is used to acquire the image of the sheet metal part 5 to be processed;

[0132] Further, the control parameter optimization unit is used to optimize the control parameters of the laser cutting head 3 during the cutting process of the sheet metal part 5 to be processed; the specific process includes:

[0133] According to the cutting content, the image of the sheet metal part 5 to be processed is divided into multiple sub-images, corresponding to the content of step S40; among them, the image of the sheet metal part 5 to be processed is divided into 9 sub-images in total; refer to Table 1;

[0134] Further, according to the content of step S50, a sub-image cross-linked list is established for the sub-images; the sub-image cross-linked list includes: processing mark, sub-image serial number, and sub-image connection relationship; among them, the processing mark includes: 0 and 1; "0" indicates uncut; "1" indicates cut; the sub-image serial number corresponds to the cutting step; the sub-image connection relationship includes: upper connection, lower connection, left connection, and right connection between sub-images; refer to the content of Table 1, and the initial information in the sub-image cross-linked list is given in Table 1; "NULL" in Table 1 indicates empty;

[0135] Table 1 Initial information in the sub-image cross-linked list

[0136]

[0137] Further, according to the content of step S60, obtain the starting sub-image to be processed; wherein, the starting sub-image to be processed is the sub-image with sub-image serial number 1.

[0138] Further, use the preprocessing unit to preprocess the starting sub-image to be processed to obtain a standard first sub-image; wherein, the preprocessing of the preprocessing unit includes: image denoising, image enhancement, and geometric correction.

[0139] Further, input the standard first sub-image into the sheet metal part feature learning model to obtain a sub-image feature vector; wherein, the sheet metal part feature learning model includes:

[0140] A cutting state recognition layer for recognizing the cutting state of the input image.

[0141] A sub-item feature learning layer for performing sub-item feature learning on the input image according to the cutting recognition result, including: a cut feature learning module and an uncut feature learning module; wherein, the cut feature learning module uses a convolutional neural network to learn the local features of the cutting area, such as the smoothness, precision, burrs, burns, and coherence of the cutting edge, etc.

[0142] The uncut feature learning module uses a deep learning model to obtain information such as geometric shapes, boundary features, dimensions, and textures in the uncut image.

[0143] According to the recognition result of the cutting state recognition layer, it can be known that there is a cut part in the standard first sub-image; therefore, only the uncut feature learning module is used for feature learning.

[0144] Further, input the features learned by the uncut feature learning module into the attention enhancement layer to focus on relevant defective features; output the focused features by the output layer to obtain a sub-image feature vector.

[0145] Further, obtain the pixel coordinates of the sub-image feature vector in the sub-image.

[0146] Further, establish a sub-graph feature - position set according to the pixel coordinates and the sub-image feature vector.

[0147] Further, use the preset control parameters to perform cutting simulation on the sub-graph feature - position set to obtain simulation cutting information.

[0148] Further, calculate the error between the simulation cutting information and the expected cutting information to obtain a cutting error vector; wherein, the cutting error vector includes: dimensional error, path error, geometric error, and surface damage degree error; refer to Table 2, in Table 2,Figure 4 Error information between the simulated cutting and the desired cutting at different pixel points of the neutron image 1;

[0149] Table 2 Error information between the simulated cutting and the desired cutting

[0150]

[0151] Furthermore, a compensation control parameter is calculated using a control parameter compensation function; wherein, the control parameter compensation function is expressed as: ; wherein, is the control parameter compensation function; is the pixel coordinate The compensation control parameter at; is the pixel coordinate The cutting error vector at; is the cutting simulation function; is the pixel coordinate The preset control parameter at; is the pixel coordinate The sub-image feature vector at; is the pixel coordinate The position information of;

[0152] In the embodiment of the present application, a compensation control parameter is calculated using a control parameter compensation function, so as to precisely adjust and compensate key cutting parameters such as the cutting angle, speed, power, temperature, and position of the laser cutting head. Referring to Table 3 and Table 4, the changes in the control parameters before and after compensation for the pixel coordinate serial numbers L1 and L2 are given in Table 3 and Table 4 respectively;

[0153] Table 3 Changes in the control parameters before and after compensation for the pixel coordinate serial number L1

[0154]

[0155] Table 4 Changes in the control parameters before and after compensation for the pixel coordinate serial number L2

[0156]

[0157] In the embodiment of the present application, a control parameter compensation function is used to adjust the preset control parameter. This function dynamically adjusts the preset control parameter by precisely calculating the error of each pixel coordinate and using cutting simulation and feature vectors to improve the cutting accuracy and quality.

[0158] Furthermore, the control panel 1 controls the laser cutting head 3 to perform cutting according to the compensation control parameter, and updates the cutting mark of the starting sub-image to be processed to 1;

[0159] Further, adaptively adjust the preset control parameters of the uncut sub-images according to the cut sub-images, corresponding to step S80; the specific process includes:

[0160] Further, obtain the corresponding next sub-image to be processed according to the sub-image serial number, denoted as the current sub-image to be processed; according to Figure 4 the content, it can be known that the sub-image corresponding to the sub-image serial number 2 is the current sub-image to be processed;

[0161] Further, refer to Figure 5 , combine the current sub-image to be processed 2 and the cut sub-image 1 to obtain the current extended sub-image to be processed;

[0162] Further, preprocess the current extended sub-image to be processed by the preprocessing unit to obtain the standard current extended sub-image to be processed;

[0163] Further, perform influence analysis on the cut sub-images in the standard current extended sub-image to be processed to obtain the cut influence vector;

[0164] Among them, the process of obtaining the cut influence vector includes:

[0165] Identify the cut sub-images as cut by the cut state recognition layer;

[0166] Further, input the cut sub-images into the cut feature learning module to obtain the cut feature vectors;

[0167] Further, output the cut feature vectors through the output layer;

[0168] Further, according to the sub-image connection relationship between the current sub-image to be processed and the cut images in the sub-image cross-linked list, combined with the cut feature vectors, obtain the cut influence vector; it is known that the sub-image connection relationship between sub-image serial number 2 and sub-image serial number 1 is "left connection"; among them, the calculation method of the cut influence vector is: ; among them, is the cut influence vector; is to build an analysis model through big data training of the front and back steps in the multiple sheet metal cutting processes; is the cut feature vector; is the influence weight analysis function of different connected cut areas on the current area to be cut; is the current sub-image to be processed; is the cut sub-image;

[0169] Further, input the current sub-image to be processed in the standard current extended sub-image to be processed into the sheet metal part feature learning model to obtain the current sub-image feature vector;

[0170] Further, adjust the current preset control parameters with the cut influence vector and the current sub-image feature vector; among them, the adjustment formula for the preset control parameters of the existing cut area on the current area to be cut is:

[0171] ;

[0172] Among them, is the compensation control parameter of the current sub-image to be processed with respect to the pixel point ; is the weight value after non-linear transformation of the th influencing factor in the cut influence vector; is the preset control parameter of the current sub-image to be processed with respect to the pixel point ; is the sub-image feature vector of the current sub-image to be processed with respect to the pixel point ; is the position information of the current sub-image to be processed with respect to the pixel point ; is the number of influencing factors in the cut influence vector.

[0173] Referring to Table 5, according to the above calculation process, the change situation of the control parameters of sub-image 2 before and after adjustment at the pixel point can be obtained;

[0174] Table 5 Change situation of control parameters before and after compensation at the pixel point ;

[0175]

[0176] In the embodiment of the present application, through the influence analysis of the cut sub-image and the adaptive adjustment mechanism based on the feature learning model, the preset control parameters can be adjusted more accurately during the cutting process of the sheet metal part. This method can effectively optimize the cutting quality, improve the processing efficiency, and reduce errors.

[0177] Further, according to the adjusted control parameters, control the laser cutting head 3 to cut the Figure 5 sub-image 2 corresponding to the sheet metal part 5 to be processed in

[0178] ; and record the cutting state of sub-image 2 in the cross-linked list of sub-images as 1;

[0179] Further, during the cutting process of the sheet metal part 5 to be processed, the display unit displays the cutting status and control parameters in real time.

[0180] In the embodiment of the present application, the management and control method based on the sub-image cross-linked list can effectively improve the accuracy and efficiency of the laser cutting process. Specifically, by dividing the image of the sheet metal part to be processed and combining the sheet metal part feature learning model, the cutting parameters can be adjusted and optimized in real time, thereby reducing errors and improving the final cutting quality. During the cutting process, the laser cutting head performs simulated cutting according to the preset control parameters and the sub-image feature - position set, and dynamically adjusts the control parameters by comparing the error between the simulated result and the expected result. This process further eliminates the influence caused by processing errors through the calculation of compensation control parameters, thereby ensuring that the cutting accuracy of each sub-image meets the requirements. With the feedback of each processing result, the control parameters will be gradually adaptively adjusted to adapt to the processing characteristics of different sub-images. In addition, as the entire cutting task progresses, when the cutting marks of all sub-images in the sub-image cross-linked list are updated to 1, it means that all predetermined cutting tasks have been completed and the cutting operation ends smoothly. At this time, through the complete adaptive control process, the execution efficiency and cutting accuracy of the entire cutting task have been significantly improved.

[0181] Embodiment 2:

[0182] In Embodiment 1, through Figure 1 , Figure 2 and Figure 3 the content realizes the process control of the adaptive laser cutting of the sheet metal part; in order to further demonstrate the applicability of the method of the present invention to the cutting of different sheet metal parts, the following is further illustrated through the embodiments of the present application, and the specific process is as follows:

[0183] Use the control panel to move the laser cutting head to the corrected starting position of the sheet metal part to be processed;

[0184] Further, obtain the image of the sheet metal part to be processed;

[0185] Further, divide the image of the sheet metal part to be processed according to the cutting content to obtain N sub-images;

[0186] Further, establish a sub-image cross-linked list for the sub-images according to the image of the sheet metal part to be processed;

[0187] Further, obtain the starting sub-image to be processed;

[0188] Further, preprocess the starting sub-image to be processed to obtain a standard first sub-image;

[0189] Further, input the standard first sub-image into the sheet metal part feature learning model to obtain a sub-image feature vector;

[0190] Further, obtain the pixel coordinates corresponding to the sub-image feature vector;

[0191] Further, establish a sub-graph feature - position set according to the pixel coordinates and the sub-image feature vector;

[0192] Further, perform cutting simulation on the sub-graph feature - position set using a preset control parameter to obtain simulation cutting information;

[0193] Further, calculate the error between the simulation cutting information and the expected cutting information to obtain a cutting error vector;

[0194] Further, calculate the compensation control parameter using a control parameter compensation function; wherein, the control parameter compensation function is expressed as: ; wherein, is the control parameter compensation function; is the pixel coordinate The compensation control parameter at; is the pixel coordinate The cutting error vector at; is the cutting simulation function; is the pixel coordinate The preset control parameter at; is the pixel coordinate The sub-image feature vector at; is the pixel coordinate The position information of;

[0195] Further, the control panel controls the laser cutting head to perform cutting according to the compensation control parameter and updates the cutting mark of the starting sub-image to be processed to 1;

[0196] Further, adaptively adjust the preset control parameter in the subsequent processing step according to the processing result of the starting sub-image to be processed, and perform cutting using the laser cutting head;

[0197] Among them, the process of adaptively adjusting the preset control parameter in the subsequent processing step includes:

[0198] Further, obtain the corresponding next sub-image to be processed according to the sub-image serial number, denoted as the current sub-image to be processed;

[0199] Further, obtain the sub-image that has the sub-image connection relationship with the current sub-image to be processed and whose cutting mark is 1, denoted as the cut sub-image;

[0200] Further, merge the current sub-image to be processed and the cut sub-image to obtain the current extended sub-image to be processed;

[0201] Further, perform the preprocessing on the currently extended sub-image to be processed to obtain a standard currently extended sub-image to be processed;

[0202] Further, perform an influence analysis on the cut sub-images in the standard currently extended sub-image to be processed to obtain a cut influence vector;

[0203] Further, input the currently sub-image to be processed in the standard currently extended sub-image to be processed into a sheet metal part feature learning model to obtain a current sub-image feature vector;

[0204] Further, adjust the current preset control parameters according to the cut influence vector and the current sub-image feature vector;

[0205] When the cutting marks in the sub-image cross linked list are all 1, the cutting task of the sheet metal part to be processed is completed.

[0206] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive laser cutting method based on characteristic parameters of sheet metal parts, characterized in that: include: Use the control panel to move the laser cutting head to the correction starting position; Acquire the image of the sheet metal part to be processed; Dividing the image of the sheet metal part to be processed according to the cutting content to obtain N sub-images; Establishing a sub-image cross-link list for the sub-image according to the sheet metal part image to be processed; wherein the sub-image cross-link list includes: processing marks, sub-image serial numbers and sub-image connection relationships; Obtaining a starting sub-image to be processed; Preprocessing the initial sub-image to be processed to obtain a standard first sub-image; Inputting the standard first sub-image into a sheet metal feature learning model to obtain a sub-image feature vector; Obtaining pixel coordinates corresponding to the sub-image feature vector; Establishing a sub-image feature-position set according to the pixel coordinates and the sub-image feature vector; Using preset control parameters to simulate cutting of the sub-graph feature-position set to obtain simulated cutting information; Calculating the error between the simulated cutting information and the expected cutting information to obtain a cutting error vector; Compensating the control parameter using a control parameter compensation function; Control the laser cutting head to perform cutting according to the compensation control parameter, and update the cutting mark of the starting sub-image to be processed to 1; The preset control parameters in the subsequent processing steps are adaptively adjusted according to the processing result of the initial sub-image to be processed, and cutting is performed; when the cutting marks in the cross linked list of the sub-image are all 1, the cutting task is completed.

2. The adaptive laser cutting method based on sheet metal feature parameters according to claim 1, characterized in that: Moving the laser cutting head to the corrected starting position includes: establishing a spatial coordinate system with the current position of the laser cutting head as the origin; Get the current top view image of the cutting platform; De-noising and contrast enhancing the current overhead image to obtain a first overhead image; Extracting the contour of the cutting platform and the contour of the sheet metal part to be processed in the first top view image to obtain a contour image of the cutting platform and a contour image of the sheet metal part to be processed; Calculating the contour deviation between the cutting platform contour image and the to-be-processed sheet metal part contour image, and constructing a contour deviation vector; Acquiring the expected cutting information of the sheet metal part to be processed, and characterizing it to obtain an expected feature vector; The moving path of the laser cutting head and the corrected starting position are generated according to the contour deviation vector and the expected feature vector; the laser cutting head moves to the corrected starting position according to the moving path.

3. The adaptive laser cutting method based on sheet metal feature parameters according to claim 2, characterized in that: The generation process of the moving path and the corrected starting position includes: The correction starting position on the contour image of the sheet metal part to be processed is calculated according to the contour deviation vector, and the calculation formula is: in, is the correction starting position; is the preset starting position; Calculate the function for correcting the starting position; To obtain the centroid coordinate point through the contour image of the sheet metal part to be processed; is the expected feature vector; is a set of boundary points of the contour image of the sheet metal part to be processed; is the correction parameter of the correction starting position; Acquire a set of candidate movable paths from the origin to the corrected starting position; The candidate movable path set is selected according to the contour deviation vector to obtain the moving path.

4. The adaptive laser cutting method based on sheet metal feature parameters according to claim 1, characterized in that: The control parameter compensation function is expressed as: in, is the control parameter compensation function; is the pixel coordinate Compensation control parameters at ; is the pixel coordinate The cutting error vector at ; Simulates the function for cutting; is the pixel coordinate Preset control parameters at is the pixel coordinate The sub-image feature vector at ; is the pixel coordinate location information.

5. The adaptive laser cutting method based on sheet metal feature parameters according to claim 1, characterized in that: The process of adaptively adjusting the preset control parameters in the subsequent processing steps includes: According to the sub-image sequence number, the next sub-image to be processed is obtained, which is recorded as the current sub-image to be processed; Obtain a sub-image that has the sub-image connection relationship with the current sub-image to be processed and the cutting mark is 1, and record it as a cut sub-image; wherein the sub-image connection relationship includes: upper connection, lower connection, left connection and right connection; Merging the current sub-image to be processed and the cut sub-image to obtain a current extended sub-image to be processed; Performing the preprocessing on the current extended sub-image to be processed to obtain a standard current extended sub-image to be processed; Performing an influence analysis on the cut sub-image in the standard current extended sub-image to be processed to obtain a cut influence vector; Inputting the current sub-image to be processed in the standard current extended sub-image to be processed into the sheet metal feature learning model to obtain a feature vector of the current sub-image; The current preset control parameter is adjusted according to the cut influence vector and the current sub-image feature vector.

6. An adaptive laser cutting system based on sheet metal feature parameters, the system being used to execute an adaptive laser cutting method based on sheet metal feature parameters as claimed in any one of claims 1 to 5, characterized in that: include: Intelligent control unit, which controls the laser cutting head through the control panel; A monitoring unit, used to monitor the sheet metal cutting process; A collection unit, used for collecting images during the monitoring process of the monitoring unit; A preprocessing unit, used for preprocessing the collected images; A starting movement calculation unit, used to calculate the moving path of the laser cutting head and correct the starting position; Control parameter optimization unit, used to optimize the control parameters of sheet metal cutting; The display unit is used to display the cutting status and control parameters of the sheet metal parts.

Images