Laser cutting path planning system for 3D cutting

Abstract

The present application provides a laser cutting path planning system for stereoscopic cutting, which relates to the field of laser cutting technology. The system includes: a positioning scanning module for completing the mapping construction of the blank from reality to virtuality; an alignment analysis module for establishing a removal fitting area of the blank; a cutting analysis module for establishing cutting constraints; a calculation module for generating compensation cutting constraints; a path generation module for generating a graphic cutting path set and establishing a connection path set; and an optimization module for performing combined optimization. This application can solve the technical problem of insufficient cutting efficiency in the prior art due to the lack of partition analysis of the cutting area. By establishing a removal fitting area of the blank and performing internal and external partitioning, the cutting path generation and path connection of the independent graphic area are performed according to the cutting constraints, and the combined optimization of the cutting path is realized, thereby achieving the technical effect of improving the planning accuracy of the cutting path and improving the cutting efficiency.

Description

Technical Field

[0001] The present application relates to the field of laser cutting technology, and in particular to a laser cutting path planning system for three-dimensional cutting. Background Art

[0002] Laser cutting technology offers numerous advantages, such as high speed, high precision, and a minimal heat-affected zone, which have led to its widespread application in various material processing fields. However, with the increasing variety of materials and the increasing complexity of cutting requirements, traditional cutting path planning technologies have become unable to meet production needs.

[0003] Existing laser cutting path planning technologies mostly directly plan a complete set of cutting paths based on the shape and size of the product to be processed. However, during the laser cutting process, it is often necessary to cut multiple position areas, and different areas may affect each other.

[0004] The existing technology has a technical problem of insufficient cutting efficiency due to the lack of partition analysis of the cutting area. Summary of the Invention

[0005] The purpose of this application is to provide a laser cutting path planning system for three-dimensional cutting, so as to solve the technical problem in the prior art of insufficient cutting efficiency due to the lack of partition analysis of the cutting area.

[0006] In view of the above problems, the present application provides a laser cutting path planning system for stereo cutting, the system comprising: a positioning scanning module, for establishing point cloud data of the blank through three-dimensional scanning after positioning the blank, and completing the mapping construction of the blank from reality to virtuality based on the point cloud data; an alignment analysis module, for establishing a three-dimensional model of the product to be cut, and performing alignment analysis between the three-dimensional model and the mapping construction result according to the blank positioning, and establishing a removal fitting area of the blank; a cutting analysis module, for partitioning the removal fitting area into inner and outer partitions, and establishing cutting constraints based on the inner and outer partition results, wherein the cutting constraints include cutting order constraints and cutting accuracy constraints; a calculation module, for calculating the complexity of the graphics of the three-dimensional model, Generate a graphic complexity calculation result, perform a resection complexity calculation on the removed fitting area, generate a resection complexity calculation result, perform cutting constraint compensation based on the graphic complexity calculation result and the resection complexity calculation result, and generate a compensated cutting constraint; a path generation module is used to fit the cutting scheme of the independent graphic area based on the compensated cutting constraint, generate a graphic cutting path set, and use the cutting path set to establish N cutting starting points and end points in the graphic, use the N cutting starting points and end points in the graphic to fit the connection paths between graphics, and establish a connection path set; an optimization module is used to perform combined optimization based on the connection path set and the graphic cutting path set, and control the laser cutting head to perform laser cutting according to the combined optimization result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The positioning scanning module is used to locate the blank, establish the point cloud data of the blank through three-dimensional scanning, and complete the mapping construction of the blank from reality to virtuality based on the point cloud data; the alignment analysis module is used to establish a three-dimensional model of the product to be cut, and according to the positioning of the blank, perform alignment analysis between the three-dimensional model and the mapping construction result, and establish the removal fitting area of the blank; the cutting analysis module is used to partition the removal fitting area into inner and outer partitions, and establish cutting constraints based on the inner and outer partition results, wherein the cutting constraints include cutting order constraints and cutting accuracy constraints; the calculation module is used to calculate the complexity of the graphics of the three-dimensional model, generate the graphics complexity calculation result, and perform the removal fitting analysis on the three-dimensional model. The cutting complexity calculation of the area is performed to generate the cutting complexity calculation result, and the cutting constraint compensation is performed based on the graphic complexity calculation result and the cutting complexity calculation result to generate the compensation cutting constraint; the path generation module is used to fit the cutting scheme of the independent graphic area based on the compensation cutting constraint, generate a graphic cutting path set, and use the cutting path set to establish N cutting starting points and end points in the graphic, and use the N cutting starting points and end points in the graphic to fit the connection paths between graphics to establish a connection path set; the optimization module is used to perform combined optimization based on the connection path set and the graphic cutting path set, and control the laser cutting head to perform laser cutting according to the combined optimization result. By establishing the removal fitting area of the blank and partitioning it into internal and external areas, the cutting path generation and path connection of the independent graphic area are performed according to the cutting constraint, and the combined optimization of the cutting path is realized, so as to achieve the technical effect of improving the planning accuracy of the cutting path and improving the cutting efficiency.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0011] Figure 1 This is a schematic diagram of the structure of the laser cutting path planning system for three-dimensional cutting in this application;

[0012] Figure 2 This is a flow chart of the method steps executed by the laser cutting path planning system for three-dimensional cutting in this application.

[0013] Explanation of the accompanying drawings: positioning scanning module 11, alignment analysis module 12, cutting analysis module 13, calculation module 14, path generation module 15, optimization module 16. DETAILED DESCRIPTION

[0014] This application provides a laser cutting path planning system for three-dimensional cutting, solving the technical problem of insufficient cutting efficiency in the prior art due to the lack of zoning analysis of the cutting area. By establishing a removal fitting area for the blank and performing internal and external partitioning, cutting paths for independent graphic areas are generated and connected according to cutting constraints, achieving combined optimization of the cutting path, achieving the technical effect of improving the planning accuracy of the cutting path and improving cutting efficiency.

[0015] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0016] Please see the attached Figure 1 , this application provides a laser cutting path planning system for three-dimensional cutting, which is used to perform Figure 2 The adaptive adjustment method for photovoltaic components shown in the figure includes:

[0017] The positioning and scanning module 11 is used to locate the blank, establish point cloud data of the blank through three-dimensional scanning, and complete the mapping construction of the blank from reality to virtuality based on the point cloud data;

[0018] Specifically, a blank refers to the raw material or semi-finished product to be laser cut, including but not limited to metal blocks, plastic pellets, wood, etc. Precisely placing the blank in a predetermined position typically requires the use of existing fixtures or other positioning devices to ensure that the blank remains stable and unchanged during the scanning process. Once positioned, the blank is scanned using an existing 3D scanner. A 3D scanner emits lasers or other types of rays and measures the time and angle of reflection from the blank to obtain the blank's 3D coordinate information. This 3D coordinate information constitutes the point cloud data, which consists of a series of discrete 3D points.

[0019] Based on the point cloud data, existing three-dimensional modeling software can be used to complete the mapping construction of the blank from reality to virtuality. For example, the point cloud data is imported into the modeling software, and then a virtual model of the blank is generated through the existing surface reconstruction method as the mapping construction result.

[0020] An alignment analysis module 12 is used to establish a three-dimensional model of the product to be cut, and based on the positioning of the blank, perform alignment analysis between the three-dimensional model and the mapping construction result to establish a removal fitting area of the blank;

[0021] The product to be cut is the desired final product formed by laser cutting the blank, such as a component. The specific product needs to be determined based on the actual situation. Using existing 3D modeling tools, a 3D model of the product to be cut is created based on the shape, size and other data of the product to be cut.

[0022] Import the mapping results previously obtained through 3D scanning and point cloud data processing into the same modeling environment, ensuring that the mapping results and the 3D model of the product to be cut are in the same coordinate system. Align the 3D model of the product to be cut with the mapping results of the blank, that is, align the mapping results with the same locations in the 3D model of the product to be cut to ensure consistency in size and position. After the alignment is completed, by comparing the 3D model of the product to be cut and the mapping results of the blank, the unnecessary parts of the mapping results are obtained, that is, the areas outside the 3D model are used as the removal fitting areas of the blank to support the subsequent cutting operation.

[0023] A cutting analysis module 13 is used to partition the removed fitting area into inner and outer partitions, and establish cutting constraints based on the inner and outer partition results, wherein the cutting constraints include cutting order constraints and cutting accuracy constraints;

[0024] Specifically, the inner partition refers to the removal of the area within the fitting area that is inside the final shape of the product to be cut, and the inner contour of the product to be cut is formed by removing the excess stock in the inner partition; the outer partition refers to the removal of the part of the fitting area that is outside the final shape of the product to be cut, and the outer contour of the product to be cut is formed by removing the stock in the outer partition. Specifically, professional and technical personnel in this field can establish the coordinate position of the product to be cut based on the three-dimensional model of the product to be cut, and set the coordinate range of the inner partition and the outer partition with the coordinate position of the product to be cut as a reference, so as to perform inner and outer partitioning on the removed fitting area. Different colors, lines or layers can be used to distinguish the inner and outer partitions so that they can be clearly identified in subsequent operations, thereby obtaining the inner and outer partition results. Furthermore, a reasonable cutting order is determined based on the characteristics of the inner and outer partitions. Usually, the larger waste material in the inner partition is cut first to remove the excess stock inside and fix the stock position, and then the outer contour of the outer partition is cut. The cutting order constraint is the cutting order of the inner partition first and then the outer partition.

[0025] It should be noted that the internal and external partitions do not only refer to the internal and external partitions, but can also be the upper and lower parts. For example, the upper material is cut first, and then the lower material is cut to avoid the material that falls off from the upper cutting affecting the products that have been cut below. In other words, as long as there are cutting sequence requirements for different positions, the partitions are performed according to the cutting sequence, and the partition results and the corresponding cutting sequence are obtained as cutting sequence constraints. The accuracy requirements for different areas in the internal and external partition results may be different. For example, the cutting accuracy requirements for the larger blanks in the internal partition are not high, and the cutting accuracy required for the external contour cutting in the external partition is higher. The specific setting is made by those skilled in the art in combination with the actual situation to obtain the cutting accuracy constraint. The cutting constraint is composed of the cutting sequence constraint and the cutting accuracy constraint.

[0026] A calculation module 14 is configured to perform a graphics complexity calculation on the three-dimensional model to generate a graphics complexity calculation result, perform a resection complexity calculation on the removed fitting area to generate a resection complexity calculation result, perform cutting constraint compensation based on the graphics complexity calculation result and the resection complexity calculation result to generate a compensated cutting constraint;

[0027] Specifically, the three-dimensional model is analyzed to identify the geometric features of the three-dimensional model, such as the number of corners, the number of holes, the number of faces, the change in surface curvature, and other features. The complexity is calculated based on the geometric features. For example, the more corners, the more holes, the more faces, and the greater the change in surface curvature, the higher the complexity. Specifically, professional and technical personnel in this field can configure geometric feature samples and corresponding complexity samples, and then use the geometric feature samples and complexity samples as training data to train a complexity recognition model based on an existing machine learning model. That is, the geometric feature samples are input into the complexity recognition model, and the output is supervised and adjusted using the complexity samples, so that the complexity recognition model is trained to convergence. The training of the machine learning model is a common technical means used by those skilled in the art and will not be expanded here. The geometric features of the three-dimensional model are input into the complexity recognition model for analysis, and a graphic complexity calculation result that can quantify the complexity of the three-dimensional model is output.

[0028] Similarly, the same method as the graphic complexity calculation result is used to perform geometric feature recognition on the removed fitting area and then perform excision complexity analysis to obtain the excision complexity calculation result that reflects the difficulty of cutting the excision fitting area. The method for obtaining the excision complexity calculation result is the same as the method for obtaining the graphic complexity calculation result. For the sake of brevity of the specification, it will not be repeated here.

[0029] Cutting constraint compensation is further performed based on the graphic complexity calculation results and the resection complexity calculation results, that is, the cutting accuracy constraints of partitions of different orders in the cutting constraints are compensated after weighted calculation based on the graphic complexity calculation results and the resection complexity calculation results, and compensated cutting constraints are generated to improve cutting accuracy and ensure the cutting effect of complex products.

[0030] a path generation module 15 for fitting a cutting scheme for an independent graphic region based on the compensation cutting constraint, generating a graphic cutting path set, establishing N cutting start points and end points within the graphic using the cutting path set, fitting connection paths between graphics using the N cutting start points and end points within the graphic, and establishing a connection path set;

[0031] Specifically, an independent graphic region is any inner or outer partition in the inner and outer partition results. Compensatory cutting constraints are applied to the cutting scheme fitting of the independent graphic region. The compensatory cutting constraints include cutting order constraints and cutting accuracy constraints. The cutting accuracy of the independent graphic region is obtained based on the compensatory cutting constraints. Cutting parameters that meet the cutting accuracy constraints are set for the independent graphic region, and then a cutting scheme fitting is performed on the independent region. This means fitting different cutting paths within the independent graphic region, that is, different cutting start and end points, to obtain a graphic cutting path set.

[0032] The graphic cutting path set includes different cutting paths corresponding to independent graphic regions, each cutting path having a cutting start point and an end point, thereby obtaining N cutting start points and end points in the graphic cutting path set, where N is an integer greater than or equal to 1. According to the cutting order constraint in the compensation cutting constraint, the N cutting start points and end points of different independent graphic regions are connected. For example, for consecutive adjacent regions executed sequentially, any end point of the previously executed region is connected with any cutting start point of the adjacent region, thereby connecting the N cutting start points and end points to obtain multiple different connection paths, which constitute the cutting path set.

[0033] The optimization module 16 is configured to perform combined optimization based on the connection path set and the graphic cutting path set, and control the laser cutting head to perform laser cutting according to the combined optimization result.

[0034] Specifically, the connection path set only includes paths connecting different areas, that is, it only includes connection paths that can connect the cutting start and end points of two independent graphic areas. The graphic cutting path set includes the cutting paths within each independent graphic area. Through the connection paths in the connection path set, the graphic cutting paths of different independent graphic areas in the graphic cutting path set can be connected to obtain multiple paths for cutting the blank. By analyzing the cutting time of multiple paths for cutting the blank, the optimal path is selected as the combined optimization result. According to the combined optimization result, the laser cutting head is controlled to perform laser cutting to achieve the optimization of the laser cutting path, thereby improving the accuracy of path planning and improving cutting efficiency.

[0035] Furthermore, the optimization module 16 is further configured to:

[0036] Establish a basic penalty factor for the empty path, and set the empty path evaluation fitness function based on the basic penalty factor; establish a repeated additional penalty factor for the empty path and the cut path, wherein the repeated additional penalty factor has a weighted coefficient of the repeated interval; update the empty path evaluation fitness function based on the repeated additional penalty factor and the weighted coefficient; perform fitness evaluation of the combined optimization process according to the updated empty path evaluation fitness function, and generate an optimization result.

[0037] Specifically, the process of performing combinatorial optimization based on the connection path set and the graph cut path set is as follows:

[0038] Idle travel refers to the movement of the laser cutting head in a non-cutting state, which directly affects the laser cutting efficiency. According to factors such as the length, time or proportion of the idle travel in the entire cutting path, a basic penalty factor is set to quantify the impact of the idle travel on the overall processing time. The basic penalty factor can be the degree of influence of an idle travel of a certain distance on the overall processing time, and the specific setting needs to be combined with the actual situation. Based on the basic penalty factor value, the fitness function for idle travel evaluation is constructed using the basic penalty factor. It can be a simple linear function, such as the product of the basic penalty factor and the idle travel distance. For idle travel that repeats the cut path, a repeated additional penalty factor is established. The factor contains a weighting coefficient for the repetition interval to reflect the additional negative impact of the repeated path on efficiency. The weighting coefficient can be adjusted according to the length of the repetition interval or the number of repetitions to increase the penalty for repeated paths.

[0039] The repeated additional penalty factor is integrated into the idle path evaluation fitness function to obtain an updated fitness function. For example, the original idle path evaluation fitness function is the product of the basic penalty factor and the idle path distance. On this basis, the product of the weighted coefficient and the repeated path length is added. The repeated path length is the repeated path length of the idle path and the cut path, thereby updating the idle path evaluation fitness function. The idle path evaluation fitness function is used to perform path combination optimization, wherein the idle path evaluation fitness function is used to evaluate the fitness of each combination result obtained based on the connection path set and the graphic cutting path set, and obtain the combination result corresponding to the minimum idle path evaluation fitness as the optimization result, thereby reducing the idle time in the laser cutting process and improving cutting efficiency.

[0040] Furthermore, the optimization module 16 is further configured to:

[0041] A time evaluation fitness function is established, and the total time of the combined optimization process is analyzed based on the time evaluation fitness function to generate the time fitness; a quality evaluation fitness function is established, and the cutting quality of the combined optimization process is evaluated by the quality evaluation fitness function to generate the quality fitness; a balance conversion is performed on the time fitness and the quality fitness, and an optimization result is generated based on the balance conversion result and the idle fitness evaluation result.

[0042] Specifically, a time-evaluation fitness function is established to evaluate and compare the total time of different cutting path combinations. By connecting the connection paths in the connection path set, the graphic cutting paths of different independent graphic areas in the graphic cutting path set can be connected to obtain different cutting path combinations. The time-evaluation fitness function is the sum of the cutting times of the connection paths and graphic cutting paths contained in the cutting path combination. The time-evaluation fitness function is used to calculate the total time of different cutting path combinations during the combinatorial optimization process to generate the time fitness.

[0043] A quality evaluation fitness function is established to evaluate the impact of the cutting path on product quality, such as cutting accuracy, edge roughness, size of the heat-affected zone, etc. In other words, the quality evaluation fitness function is a relationship between cutting quality and cutting path. It can be constructed by professional and technical personnel in this field based on practical experience, and the quality evaluation fitness function is used to evaluate the cutting quality of different cutting path combinations to generate quality fitness.

[0044] Since there may be a conflict between time fitness and quality fitness, for example, reducing time may sacrifice quality, and vice versa, a balanced conversion is required. For example, the weights of time fitness and quality fitness can be determined. Usually, the weight of quality fitness is greater than the weight of time fitness because cutting quality is more important. The specific weight can be set by those skilled in the art. In this way, a weighted calculation is performed on time fitness and quality fitness to generate a balanced fitness that comprehensively considers the two. Then, combined with the idle fitness evaluation results, the result with the minimum idle fitness and the minimum balanced fitness is obtained as the optimization result, which ensures the cutting quality while reducing the cutting time, thereby improving the efficiency of laser cutting.

[0045] Furthermore, the optimization module 16 is further configured to:

[0046] The method further comprises configuring additional constraints for starting and stopping; accumulating the number of starts and stops in the combined optimization process, and performing weighted calculation on the accumulated results of the number of starts and stops based on the additional constraints; and compensating the optimization result according to the weighted calculation result to update the optimization result.

[0047] Specifically, during the laser cutting process, the number of starts and stops not only affects cutting efficiency, but can also negatively impact cutting quality and equipment life. Therefore, during the combined optimization process, the number of starts and stops is accumulated and weighted based on additional constraints to compensate and optimize the optimization results. The specific steps are as follows:

[0048] Define additional constraints for starts and stops. For example, set the degree of impact of a certain number of starts and stops on cutting quality as an additional constraint. The specific setting can be determined by those skilled in the art based on actual conditions. During the combined optimization process, the number of starts and stops of the laser cutting head is recorded. Each time the laser cutting head switches from a mobile state to a cutting state, or from a cutting state to a mobile state, is counted as a start and stop, resulting in a cumulative number of starts and stops. The cumulative number of starts and stops is weighted according to the additional constraints. That is, based on the additional constraints and the degree of impact of a certain number of starts and stops on cutting quality, the comprehensive impact of the starts and stops included in the cumulative number of starts and stops on cutting quality is calculated to obtain a weighted calculation result. The optimization result is compensated based on the weighted calculation result. That is, for paths with a weighted calculation result greater than a preset threshold, the number of starts and stops is reduced by adjusting the cutting order, merging similar cutting areas, and other methods to achieve compensation for the optimization result. These adjustments must meet other constraints, such as cutting quality and idle stroke, to effectively reduce the number of starts and stops, thereby improving cutting efficiency.

[0049] Furthermore, the positioning scanning module 11 is also used for:

[0050] After positioning the blank, call the 3D scanner; obtain the key position evaluation of the product to be cut and establish the position key value; perform attention scanning with the 3D scanner using the position key value to establish the attention scanning result; and establish point cloud data of the blank based on the attention scanning result.

[0051] Specifically, after the blank is positioned, the process of creating the blank's point cloud data through 3D scanning is as follows:

[0052] After the blank is accurately placed in the predetermined position, the existing 3D scanner is called. The key position of the product to be cut refers to the key position that needs to be focused on and accurately cut, such as the part that needs to be precisely controlled in size, the part with complex structure or the part that needs to maintain a certain precision, etc., which can be specifically marked and determined by those skilled in the art. According to the coordinates, size, shape and other information of the key position, the position key value is established. According to the position key value, a specific scanning area is set in the 3D scanner to make the scanning process more focused and efficient. The 3D scanner is started and the set scanning area is scanned with high precision to obtain detailed 3D data of the blank as the scanning result. The scanning result obtained by the scanning is converted into point cloud data, which is a common technical means used by those skilled in the art. Point cloud data is a digital representation of the surface shape of the blank and contains a large number of 3D coordinate points. Using the 3D coordinate points as the point cloud data of the blank provides a basis for subsequent cutting path planning and optimization.

[0053] Furthermore, the calculation module 14 is further configured to:

[0054] Calling the processing accuracy of the graph, generating a first complexity calculation result with the processing accuracy; obtaining the topological structure of the graph, generating a second complexity calculation result based on the topological structure; generating a graph complexity calculation result through the first complexity calculation result and the second complexity calculation result.

[0055] The process of performing graphic complexity calculation on the three-dimensional model and generating a graphic complexity calculation result further includes:

[0056] The processing accuracy of graphics refers to the degree of detail used when processing and analyzing graphic data, including parameters such as the resolution and sampling rate of the three-dimensional model. Resolution refers to the degree of detail in the three-dimensional model, that is, the pixel density or the number of vertices on the model surface. The sampling rate refers to the frequency with which the surface of an object is sampled during three-dimensional scanning or reconstruction. Based on the processing accuracy, the complexity of the graphic data can be calculated. For example, if the processing accuracy is very high, the graphic data will contain more detailed information, which may lead to higher complexity. Conversely, if the processing accuracy is low, the complexity may be relatively low. Specifically, the mapping relationship between processing accuracy and complexity can be set by professional and technical personnel in this field based on actual experience. For example, a processing accuracy within a certain range corresponds to a certain complexity, thereby obtaining a first complexity calculation result based on the processing accuracy mapping of the graphics.

[0057] The topological structure describes the connection relationship and spatial layout between the various elements in the graph. Specifically, the connection relationship of the edges, vertices, and faces of the three-dimensional model can be analyzed as the topological structure of the graph. The complexity of the topological structure can be evaluated in a variety of ways, such as calculating the number of branches and the number of rings of the graph. These indicators can reflect the complexity of the graph at the structural level. For example, different topological structure samples and complexity samples marked by those skilled in the art are obtained, and then based on the topological structure samples and the structural complexity samples, a structural complexity recognition model is constructed based on the existing machine learning model training. The training of the machine learning model is a common technical means used by those skilled in the art and will not be expanded here. The topological structure of the graph is analyzed by the structural complexity recognition model to obtain a second complexity calculation result.

[0058] Appropriate weights are assigned to the first complexity calculation result and the second complexity calculation result, which are specifically set by technical personnel in this field, so as to perform weighted calculation on the first complexity calculation result and the second complexity calculation result to generate the final graphic complexity calculation result to provide support for cutting constraint compensation.

[0059] Similarly, the same method can be used to perform excision complexity calculation on the removed fitting area, that is, the processing accuracy and topological structure analysis of the removed fitting area is also performed to generate the excision complexity calculation result, which will not be described in detail here.

[0060] Furthermore, the system further includes a group processing module, which is configured to:

[0061] Perform data collection for all blanks, and perform blank consistency evaluation based on the data collection results and mapping construction results; configure fine-tuning parameters based on the consistency evaluation results and combined optimization results; and perform corresponding laser cutting management for all blanks using the fine-tuning parameters.

[0062] Specifically, a 3D scanner or other measuring tool is used to collect point cloud data of all blanks corresponding to the product to be cut to obtain data collection results. Based on the data collection results, virtual models of all blanks are generated by existing 3D modeling software, and the virtual models of all blanks are compared with the mapping construction results for consistency. The differences between the virtual models of all blanks and the mapping construction results are compared, including the shape, size, and degree of deviation. The degree of deviation is subtracted from 1 as the consistency evaluation result. Fine-tuning parameters are configured based on the consistency evaluation results and the combined optimization results. That is, according to the consistency evaluation results, the cutting path in the combined optimization results is fine-tuned. Specifically, according to the difference between the virtual model and the mapping construction results, the cutting path of the part with differences can be fine-tuned according to its shape to obtain a path that conforms to its shape. The adjustment results are used as fine-tuning parameters. The configured fine-tuning parameters are used to manage laser cutting of each blank, so that the laser cutting process can adapt to the individual differences of the blanks and improve the efficiency of laser cutting.

[0063] Furthermore, the system further includes an early warning module, which is used to:

[0064] If the consistency evaluation result fails to meet the preset threshold, a blank abnormality is reported; and the corresponding blank is reset and optimized based on the blank abnormality.

[0065] Specifically, a preset threshold value for consistency evaluation is set by professional and technical personnel in this field. The preset threshold value refers to the critical value at which the difference between the blanks is too large and high-quality cutting cannot be achieved by fine-tuning the cutting path. The consistency evaluation result is compared with the preset threshold value. If the consistency evaluation result exceeds the preset threshold value, the blank abnormality is automatically reported. The reporting method can be an audible and visual alarm, a display screen prompt, or a notification sent to relevant personnel. The corresponding blank is reset and optimized according to the blank abnormality, that is, according to the laser cutting path planning system for three-dimensional cutting provided by this application, the blank with the blank abnormality is analyzed for cutting path, instead of fine-tuning the optimization results of other blanks that have been obtained, so as to improve the accuracy of the cutting path.

[0066] In summary, the laser cutting path planning system for three-dimensional cutting provided by this application has the following technical effects:

[0067] The positioning scanning module is used to locate the blank, establish the point cloud data of the blank through three-dimensional scanning, and complete the mapping construction of the blank from reality to virtuality based on the point cloud data; the alignment analysis module is used to establish a three-dimensional model of the product to be cut, and according to the positioning of the blank, perform alignment analysis between the three-dimensional model and the mapping construction result, and establish the removal fitting area of the blank; the cutting analysis module is used to partition the removal fitting area into inner and outer partitions, and establish cutting constraints based on the inner and outer partition results, wherein the cutting constraints include cutting order constraints and cutting accuracy constraints; the calculation module is used to calculate the complexity of the graphics of the three-dimensional model, generate the graphics complexity calculation result, and perform the removal fitting analysis on the three-dimensional model. The cutting complexity calculation of the area is performed to generate the cutting complexity calculation result, and the cutting constraint compensation is performed based on the graphic complexity calculation result and the cutting complexity calculation result to generate the compensation cutting constraint; the path generation module is used to fit the cutting scheme of the independent graphic area based on the compensation cutting constraint, generate a graphic cutting path set, and use the cutting path set to establish N cutting starting points and end points in the graphic, and use the N cutting starting points and end points in the graphic to fit the connection paths between graphics to establish a connection path set; the optimization module is used to perform combined optimization based on the connection path set and the graphic cutting path set, and control the laser cutting head to perform laser cutting according to the combined optimization result. By establishing the removal fitting area of the blank and partitioning it into internal and external areas, the cutting path generation and path connection of the independent graphic area are performed according to the cutting constraint, and the combined optimization of the cutting path is realized, so as to achieve the technical effect of improving the planning accuracy of the cutting path and improving the cutting efficiency.

[0068] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0069] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. Laser cutting path planning system for three-dimensional cutting, characterized in that: The system comprises: The positioning and scanning module is used to locate the blank, establish point cloud data of the blank through three-dimensional scanning, and complete the mapping construction of the blank from reality to virtual based on the point cloud data; The alignment analysis module is used to build a 3D model of the product to be cut, and based on the positioning of the blank, perform alignment analysis between the 3D model and the mapping construction result to establish the removal fitting area of the blank; A cutting analysis module, configured to partition the removed fitting area into inner and outer partitions, and establish cutting constraints based on the inner and outer partition results, wherein the cutting constraints include cutting order constraints and cutting accuracy constraints; A calculation module is used to perform graphic complexity calculation on the three-dimensional model to generate a graphic complexity calculation result, perform excision complexity calculation on the removed fitting area to generate an excision complexity calculation result, perform cutting constraint compensation based on the graphic complexity calculation result and the excision complexity calculation result to generate a compensated cutting constraint, and the complexity calculation includes: analyzing the three-dimensional model, identifying the geometric features of the three-dimensional model, the geometric features including the number of corners, the number of holes, the number of faces, and the surface curvature change features, calculating the complexity based on the geometric features, using the geometric feature samples and the corresponding complexity samples as training data, and training the complexity recognition model based on the machine learning model: inputting the geometric feature samples into the complexity recognition model, and using the complexity samples as training data. The method performs output supervision adjustment, trains the complexity recognition model to convergence, inputs the geometric features of the three-dimensional model into the complexity recognition model for analysis, outputs a graphic complexity calculation result that can quantify the complexity of the three-dimensional model, and uses the same method of the graphic complexity calculation result to perform excision complexity analysis on the geometric features of the removed fitting area to obtain an excision complexity calculation result that reflects the difficulty of cutting the excision fitting area; performing cutting constraint compensation based on the graphic complexity calculation result and the excision complexity calculation result includes: performing weighted calculation on the graphic complexity calculation result and the excision complexity calculation result, compensating for the cutting accuracy constraints of partitions of different orders in the cutting constraint, and generating a compensated cutting constraint; a path generation module, configured to fit a cutting scheme for an independent graphic region based on the compensation cutting constraint, generate a graphic cutting path set, establish N cutting start points and end points within the graphic using the cutting path set, fit connection paths between graphics using the N cutting start points and end points within the graphic, and establish a connection path set; The optimization module is used to perform combined optimization based on the connection path set and the graphic cutting path set, and control the laser cutting head to perform laser cutting according to the combined optimization result.

2. The system according to claim 1, wherein The optimization module is also used for: Establish a basic penalty factor for the idle process, and use the basic penalty factor to set the fitness function for the idle process evaluation; Establishing a repetition additional penalty factor for the empty path and the cut path, wherein the repetition additional penalty factor has a weighting coefficient of the repetition interval; Updating the idle process evaluation fitness function based on the repeated additional penalty factor and the weighted coefficient; The fitness evaluation of the combined optimization process is performed according to the updated idle process evaluation fitness function to generate the optimization result.

3. The system according to claim 2, wherein: The optimization module is also used for: Establishing a time evaluation fitness function, performing a total time analysis of the combined optimization process based on the time evaluation fitness function, and generating a time fitness; Establishing a quality evaluation fitness function, and performing cutting quality evaluation in a combination optimization process by using the quality evaluation fitness function to generate quality fitness; A balance conversion is performed on the time fitness and the quality fitness, and an optimization result is generated based on the balance conversion result and the idle fitness evaluation result.

4. The system according to claim 3, wherein: The optimization module is also used for: Configure additional constraints for start and stop; accumulating the number of starts and stops of the combined optimization process, and performing weighted calculation on the accumulated results of the number of starts and stops based on the additional constraints; The optimization result is compensated according to the weighted calculation result to update the optimization result.

5. The system according to claim 1, wherein: The positioning scanning module is also used for: After positioning the blank, call the 3D scanner; Obtain key position evaluation of the product to be cut and establish key values of the position; Performing an attention scan of a three-dimensional scanner using the position key value to establish an attention scan result; The point cloud data of the blank is established based on the scanning results.

6. The system according to claim 1, wherein: The calculation module is also used for: calling the processing precision of the graph, and generating a first complexity calculation result with the processing precision; Obtaining a topological structure of the graph, and generating a second complexity calculation result based on the topological structure; A graphic complexity calculation result is generated by using the first complexity calculation result and the second complexity calculation result.

7. The system according to claim 1, wherein: The system further includes a group processing module, wherein the group processing module is configured to: Perform data collection for all blanks and conduct blank consistency evaluation based on the data collection results and mapping construction results; Configure fine-tuning parameters based on consistency evaluation results and combined optimization results; The corresponding laser cutting management of all blanks is performed through the fine-tuning parameters.

8. The system according to claim 7, wherein: The system further includes an early warning module, which is configured to: If the consistency evaluation result fails to meet the preset threshold, a blank abnormality is reported; The corresponding blank is reset and optimized according to the blank abnormality.

Images