Method and system for optimizing laser cutting path of laser

Abstract

The invention relates to the technical field of data processing, in particular to a method and a system for optimizing a laser cutting path of a laser. The method comprises the following steps: collecting a cutting point of a to-be-cut plate, obtaining a primary damage degree of a random removal operator in an ALNS algorithm when a new solution is generated in each iteration, and obtaining a target function value of the new solution generated in each iteration; according to the target function value and the primary damage degree of the new solution generated in each time of iteration, obtaining the damage degree of a random removal operator in the ALNS algorithm when the new solution is generated in each time of iteration, and according to the damage degree of the random removal operator in the ALNS algorithm when the new solution is generated in each time of iteration, obtaining the damage proportion of the random removal operator in the ALNS algorithm when the new solution is generated in each time of iteration, and according to the damage proportion of the randomly removed operator in the ALNS algorithm when the new solution is iteratively generated each time, the optimal path of the to-be-cut plate is obtained in combination with the SA algorithm and the ALNS algorithm, and the accuracy of the optimal path of the to-be-cut plate is improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for optimizing laser cutting paths. Background Technology

[0002] In the context of the current intelligent upgrading of manufacturing, laser cutting technology, as a core means of high-precision processing, is applied in fields such as automobiles, aerospace, and consumer electronics. However, traditional path planning methods often lack flexibility, which may lead to unnecessary backtracking or redundant paths, thus wasting time and energy and reducing cutting efficiency. This solution introduces the SA algorithm to optimize the laser cutting path. This algorithm, through a mechanism of probabilistically accepting inferior solutions and combined with an iterative search strategy based on temperature decay, can escape local optima and efficiently search for the globally optimal path in the solution space. The application of this algorithm aligns with the demands of Industry 4.0 for flexible manufacturing and energy conservation, directly shortening processing time and reducing enterprise production costs. However, the SA algorithm only makes small changes within the neighborhood of the current solution in each iteration to generate a new solution for each iteration, which cannot effectively explore the entire search space. Especially for complex cutting paths, the SA algorithm may get stuck in local optima, resulting in slower convergence speed in the later stages of the iteration and failure to accurately find the optimal solution. Therefore, the ALNS algorithm (Adaptive Large Neighborhood Search) is used in each iteration to generate a new solution for each iteration. The generation of high-quality solutions is accelerated by dynamically selecting destruction operators and repair operators. Since the destruction operator removes cut points in the current solution by a fixed destruction ratio, thereby breaking the local structure of the current solution, if the destruction ratio is set too large, it may cause excessive perturbation in the later stages of iteration, making it impossible for the algorithm to converge to the optimal solution effectively. If the destruction ratio is too small, the algorithm's search in the early stages of iteration will be too limited, making it impossible to effectively explore the solution space, causing the algorithm to easily get stuck in the local optimum region, thus missing the global optimum solution. Summary of the Invention

[0003] To address the technical problem that an accurate optimal solution cannot be obtained when the destruction ratio of the destruction operator is set too small or too large, this invention provides a method and system for optimizing the laser cutting path of a laser.

[0004] In a first aspect, the present invention provides a method for optimizing the laser cutting path of a laser, employing the following technical solution: A method for optimizing the laser cutting path of a laser includes the following steps: Collect the cutting points of the material to be cut; During the iterative acquisition of the optimal path for the plate to be cut by the SA algorithm, the initial degree of destruction of the random removal operator in the ALNS algorithm is obtained based on the number of cutting points of the plate to be cut and the temperature value of the SA algorithm when a new solution is generated in each iteration; the objective function value of the new solution is obtained in each iteration. Based on the objective function value of the new solution generated in each iteration and the primary degree of destruction, the degree of destruction of the random removal operator in the ALNS algorithm is obtained when a new solution is generated in each iteration. Based on the degree of destruction caused by the random removal of operators in the ALNS algorithm when generating a new solution in each iteration, the destruction ratio of the random removal of operators in the ALNS algorithm when generating a new solution in each iteration is obtained; based on the destruction ratio of the random removal of operators in the ALNS algorithm when generating a new solution in each iteration, the optimal path of the plate to be cut is obtained by combining the SA algorithm and the ALNS algorithm.

[0005] The innovation of this invention lies in introducing a random removal operator from the Adaptive Large Neighborhood Operation (ALNS) into the SA algorithm. Based on the number of cutting points of the material to be cut and the temperature value of the SA algorithm when generating a new solution in each iteration, the initial degree of destruction of the random removal operator in the ALNS algorithm is obtained when generating a new solution in each iteration. Then, considering the quality of the new solution generated in each iteration, the initial degree of destruction is adjusted to obtain the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration, and thus the destruction ratio of the random removal operator in the ALNS algorithm when generating a new solution in each iteration. By dynamically adjusting the destruction ratio of the random removal operator, the perturbation intensity can be flexibly controlled according to the quality and degree of destruction of the current solution at different iteration stages, thereby searching in a larger solution space and finding the optimal path faster and more accurately in complex laser cutting path problems.

[0006] Preferably, obtaining the initial degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration includes: ; In the formula, This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of cutting points on the material to be cut. This represents the temperature value of the SA algorithm when a new solution is generated in the i-th iteration; This represents the initial temperature value for the preset SA algorithm; norm() represents the normalization function.

[0007] Taking into account the number of cutting points on the plate to be cut and the temperature value of the SA algorithm, the initial degree of destruction of the random removal operator in the ALNS algorithm is obtained when a new solution is generated in each iteration.

[0008] Preferably, obtaining the objective function value for generating a new solution in each iteration includes: ; In the formula, This represents the objective function value used to generate a new solution in the i-th iteration. The path length during the entire cutting process represents the length of the laser when it generates a new solution based on the i-th iteration to cut a material identical to the material to be cut. exp() represents the temperature increment during the entire cutting process when the laser generates a new solution based on the i-th iteration and cuts a material identical to the material to be cut; exp() represents an exponential function with the natural constant as the base; norm() represents a normalization function.

[0009] It reflects the quality of the new solution generated in each iteration.

[0010] Preferably, obtaining the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration includes: ; In the formula, This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of previous iterations before the i-th iteration; This represents the objective function value used to generate a new solution in the m-th historical iteration prior to the i-th iteration. The objective function value represents the current solution of the historical iteration before the i-th iteration; The range represents the objective function values ​​generated from all previous iterations before the i-th iteration; || represents the absolute value sign; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base. This represents the preset adjustment coefficient.

[0011] Preferably, obtaining the number of historical iterations prior to the i-th iteration includes: The number of previous iterations before each iteration is set to M. The M iterations before each iteration are taken as the previous iterations before the i-th iteration.

[0012] This facilitates subsequent determination of the degree of disruption caused by the random removal of operators in the ALNS algorithm during each iteration when generating a new solution.

[0013] Preferably, obtaining the destruction ratio of the randomly removed operator in the ALNS algorithm when generating a new solution in each iteration includes: ; In the formula, This represents the proportion of disruption caused by the random removal of operators in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. This represents the proportion of disruption caused by randomly removing operators in the default ALNS algorithm.

[0014] The perturbation intensity can be flexibly controlled at different iteration stages based on the quality and degree of damage of the current solution.

[0015] Preferably, the acquisition of the temperature value of the SA algorithm when generating a new solution in the i-th iteration includes: A preset temperature cooling coefficient is used. When a new solution is generated in the first iteration, the temperature value of the SA algorithm is the initial temperature value. When a new solution is generated in the second iteration, the temperature value of the SA algorithm is the product of the temperature value of the SA algorithm when a new solution is generated in the first iteration and the temperature cooling coefficient. And so on. When a new solution is generated in the i-th iteration, the temperature value of the SA algorithm is the product of the temperature value of the SA algorithm when a new solution is generated in the (i-1)-th iteration and the temperature cooling coefficient.

[0016] Preferably, the step of collecting the cutting points of the material to be cut includes: The CAD drawing file of the board to be cut is imported into the API interface of the CAD software for loading, and the position coordinates of all cutting points in the board to be cut are extracted.

[0017] Preferably, obtaining the range of the objective function values ​​generated in all historical iterations prior to the i-th iteration includes: The difference between the maximum and minimum values ​​of the objective function values ​​generated by all previous iterations before the i-th iteration is taken as the range of the objective function values ​​generated by all previous iterations before the i-th iteration.

[0018] Secondly, the present invention provides a laser cutting path optimization system for lasers, which adopts the following technical solution: A laser cutting path optimization system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the aforementioned laser cutting path optimization method is implemented.

[0019] By adopting the above technical solution, a computer program is generated from the laser cutting path optimization method described above and stored in a memory so that it can be loaded and executed by a processor. This allows for the creation of a terminal device based on the memory and processor, making it convenient to use.

[0020] The present invention has the following technical effects: By introducing a random removal operator from the Adaptive Large Neighborhood Operation (ALNS) into the SA algorithm, the present invention obtains the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration based on the number of cutting points of the material to be cut, the temperature value of the SA algorithm when generating a new solution in each iteration, and the quality of the new solution generated in each iteration. Based on the degree of destruction, the invention adaptively obtains the proportion of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration. The perturbation intensity can be flexibly controlled according to the quality and degree of destruction of the current solution at different iteration stages, so as to find the optimal path faster and more accurately in complex laser cutting path problems. Attached Figure Description

[0021] Figure 1 This is a flowchart of a laser cutting path optimization method according to an embodiment of the present invention. Detailed Implementation

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0023] This invention discloses a method for optimizing the laser cutting path of a laser, referring to... Figure 1 This includes steps S1-S4: S1: Collect the cutting points of the material to be cut.

[0024] In this embodiment of the invention, the CAD drawing file of the board to be cut is input into the API interface of the CAD software for loading, and the position coordinates of all cutting points in the board to be cut are extracted; wherein, the cutting point usually refers to the point at the division or boundary in the board, and the position coordinates of the endpoints or intersections of all lines or polylines are obtained through the API.

[0025] S2: Obtain the initial degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration.

[0026] It should be noted that this invention outputs the optimal path for laser cutting of sheet metal based on the SA algorithm. The SA algorithm (Simulated Annealing) typically obtains the optimal solution after multiple iterations. In each iteration, there is a current solution, and a new solution is generated based on the current solution. Then, a better-quality solution is selected from the current solution and the new solution in each iteration as the current solution for the next iteration, and so on until the number of iterations is reached. The current solution of the last iteration is the optimal solution. However, when the SA algorithm obtains the optimal cutting path, each iteration only makes small changes within the neighborhood of the current solution (e.g., swapping two cutting points in the cutting path) to generate a new solution for each iteration. This operation may not be able to effectively explore the entire search space, especially for complex cutting paths. This limitation may cause the SA algorithm to get stuck in local optima, resulting in a slower convergence speed in the later stages of iteration and the inability to accurately find the optimal solution.

[0027] Therefore, the ALNS algorithm (Adaptive Large Neighborhood Search) is used in each iteration to generate a new solution for each iteration. The generation of high-quality solutions is accelerated by dynamically selecting the destruction operator (which destroys the structure of the current solution) and the repair operator (which reconstructs the solution based on the destroyed structure). However, a random removal operator in the destruction operator will remove the cutting points in the current solution at a fixed destruction ratio, thereby breaking the local structure of the current solution. Then, the repair operator will reconstruct the complete solution on the broken structure, that is, obtain the new solution for the next iteration.

[0028] While this operation aims to introduce more variations by disrupting the local structure and preventing the algorithm from getting stuck in local optima, the choice of the disruption ratio also affects the algorithm's convergence. If the disruption ratio is set too high, it may lead to excessive perturbation (i.e., significant modification of the current solution) in the later stages of iteration. This perturbation may disrupt a solution that is close to the optimal solution, making it impossible for the algorithm to converge effectively to the optimal solution. If the disruption ratio is too low, the algorithm's search in the early stages of iteration will be too limited, making it unable to effectively explore the solution space, causing the algorithm to easily get stuck in the local optimum region and thus miss the global optimum. Therefore, this invention analyzes the degree of disruption of the ALNS algorithm when randomly removing operators in each iteration to generate a new solution, and then adapts the disruption ratio of the ALNS algorithm when randomly removing operators in each iteration to generate a new solution based on the degree of disruption. This ensures that the quality of the optimal solution is guaranteed while maximizing the algorithm's computational efficiency.

[0029] It should be further explained that the more cutting points there are in the material to be cut, the larger the scale of the problem encountered when obtaining the cutting path. Therefore, the random removal operator in the ALNS algorithm needs to set a larger destruction ratio to randomly remove some cutting points when generating a new solution in each iteration. At this time, the initial destruction degree of the random removal operator in the ALNS algorithm is greater when generating a new solution in each iteration. In addition, in the SA algorithm, when the temperature value of the SA algorithm is close to the initial temperature, it means that the algorithm is in the early stage of the search. At this time, a larger perturbation is needed to explore the solution space over a larger area. Therefore, the initial destruction degree of the random removal operator in the ALNS algorithm is obtained according to the number of cutting points in the material to be cut and the temperature value of the SA algorithm when generating a new solution in each iteration.

[0030] In this embodiment of the invention, the initial temperature value of the SA algorithm is preset to 100℃, the temperature threshold is 1℃, and the temperature cooling coefficient is 0.98. The SA algorithm is used to iteratively obtain the optimal solution (optimal path) for the plate to be cut. Specifically, the initial destructive degree of the random removal operator in the ALNS algorithm is obtained when a new solution is generated in each iteration. ; In the formula, This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of cutting points on the material to be cut. This represents the temperature value of the SA algorithm when a new solution is generated in the i-th iteration; This represents the initial temperature value of the preset SA algorithm. Celsius; norm() represents the normalization function; It should be noted that the temperature value of the SA algorithm when generating a new solution in the first iteration is the initial temperature value; the temperature value of the SA algorithm when generating a new solution in the second iteration is the product of the temperature value of the SA algorithm when generating a new solution in the first iteration and the temperature cooling coefficient; and the temperature value of the SA algorithm when generating a new solution in the third iteration is the product of the temperature value of the SA algorithm when generating a new solution in the second iteration and the temperature cooling coefficient. The larger the value, the more cutting points there are in the board to be cut, which means that the problem scale is larger when obtaining the optimal cutting path of the board to be cut. Therefore, when generating a new solution in each iteration, the random removal operator in the ALNS algorithm needs to set a larger destruction ratio to randomly remove some cutting points. At this time, the initial destruction degree of the random removal operator in the ALNS algorithm is greater when generating a new solution in the i-th iteration. Because the temperature value of the SA algorithm decreases continuously with the increase of the number of iterations, the iteration stops when the temperature threshold is reached. The larger the value, the closer the temperature value of the SA algorithm is to the initial temperature value when the i-th iteration generates a new solution. This indicates that the i-th iteration is in the early stage of several iterations of the i-th iteration algorithm, and the greater the proportion of destruction required. Therefore, the greater the degree of primary destruction of the random removal operator in the ALNS algorithm when the i-th iteration generates a new solution.

[0031] S3: Obtain the objective function value for generating a new solution in each iteration; based on the objective function value for generating a new solution in each iteration and the initial degree of destruction, obtain the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration; based on the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration, obtain the proportion of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration.

[0032] It should be noted that during the entire process of laser cutting the sheet material along an arbitrary cutting path, a larger temperature increment indicates a greater likelihood that the cutting path will induce thermal stress distortion, meaning a greater possibility of sheet material deformation. Therefore, the cutting path is less likely to be optimal, and its objective function value is larger. Conversely, a smaller path length during the entire process of laser cutting the sheet material along the chosen path indicates higher efficiency and a greater likelihood that the cutting path is optimal. Therefore, the objective function value of the cutting path is smaller. Thus, this invention obtains the objective function value of the cutting path based on the temperature increment and path length during the entire process of cutting the sheet material along an arbitrary cutting path. A larger objective function value indicates lower quality of the cutting path, while a smaller objective function value indicates higher quality.

[0033] In this embodiment of the invention, the objective function value for generating a new solution in each iteration is obtained: ; In the formula, This represents the objective function value used to generate a new solution in the i-th iteration. The path length during the entire cutting process represents the length of the laser when it generates a new solution based on the i-th iteration to cut a material identical to the material to be cut. exp() represents the temperature increment during the entire cutting process when the laser generates a new solution based on the i-th iteration and cuts a material identical to the material to be cut; norm() represents the normalization function; It should be noted that the temperature and number of cut points (problem size) of the SA algorithm are used to initially set the destruction ratio in the ALNS algorithm. This approach considers the approximate stage requirements, such as a larger destruction ratio when the temperature is higher in the early stage, and a lower destruction ratio when the temperature is lower in the later stage. However, the drawback of this setting method is that it only depends on the temperature change of the algorithm and the problem size, and ignores the quality of the solution in each iteration. Assuming that the temperature of the SA algorithm has decreased, the search range of the algorithm may be too limited, resulting in the inability to find a better solution and leading to getting stuck in a local optimum. Therefore, the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in each iteration is obtained based on the quality of the solution generated in each iteration of the SA algorithm. It should be further explained that if the quality of the new solutions generated in the previous iterations of the SA algorithm is poor or the changes are small in a certain iteration, then the destruction ratio of the ALNS algorithm should be increased in the current iteration in order to guide the search to a wider solution space. In this case, the destruction degree of the random removal operator in the ALNS algorithm should be greater when generating a new solution in the current iteration.

[0034] In this embodiment of the invention, the number of historical iterations before each iteration is preset to M=5, and the M iterations before each iteration are taken as the historical iterations before the i-th iteration; To determine the degree of disruption caused by randomly removing operators in the ALNS algorithm during each iteration to generate a new solution: ; In the formula, This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of previous iterations before the i-th iteration; This represents the objective function value used to generate a new solution in the m-th historical iteration prior to the i-th iteration. The objective function value represents the current solution of the historical iteration before the i-th iteration; The range represents the objective function values ​​generated from all previous iterations before the i-th iteration; || represents the absolute value sign; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base. This represents the preset adjustment coefficient, used to adjust... The value range is adjusted to [0.5-1.5]; The larger the value, the greater the degree of primary destruction of the random removal operator in the ALNS algorithm when generating a new solution in the i-th iteration. In this case, the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in the i-th iteration is greater. The larger the value of , the greater the objective function value of the new solution generated in the m-th iteration before the i-th iteration is compared to the objective function value of the current solution. This indicates that the quality of the new solution generated in the m-th iteration before the i-th iteration was worse. The larger the value, the better the iteration before the i-th iteration. The quality of the new solution generated in each subsequent historical iteration is worse, and The smaller the value, the more likely it is that the iteration before the i-th iteration... The quality change of the new solution generated in each iteration is small, therefore when The larger the value and The smaller the value, the more likely the current search strategy is to be trapped in a local optimum and unable to effectively explore the solution space. Therefore, the greater the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration, the more it attempts to escape the local optimum by "scrambling" the solution space over a larger range.

[0035] It should be noted that if the number of historical iterations before the i-th iteration is less than five, the initial degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in the i-th iteration is directly taken as the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in the i-th iteration.

[0036] It should be noted that the greater the degree of disruption caused by the random removal operator in the ALNS algorithm when generating a new solution in a certain iteration, the greater the proportion of disruption caused by the random removal operator in the ALNS algorithm should be when generating a new solution in the next iteration, so as to ensure that the search can be expanded to a wider solution space and obtain an accurate optimal solution.

[0037] In this embodiment of the invention, the destruction ratio of randomly removed operators in the ALNS algorithm is obtained when a new solution is generated in each iteration: ; In the formula, This represents the proportion of disruption caused by the random removal of operators in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. Representing the destruction ratio of the random removal operator in the preset ALNS algorithm, in this embodiment of the invention, the preset =25%, in other embodiments, the implementer may preset according to the specific implementation method. The greater the degree of destruction of the random removal operator in the ALNS algorithm when generating a new solution in the i-th iteration, the greater the proportion of destruction of the random removal operator in the ALNS algorithm should be when generating a new solution in the i-th iteration, so as to escape the local optimum by exploring the solution space over a larger range.

[0038] S4: The proportion of damage caused by randomly removing operators in the ALNS algorithm when generating a new solution in each iteration. The optimal path of the plate to be cut is obtained by combining the SA algorithm and the ALNS algorithm.

[0039] It should be noted that after obtaining the destruction ratio of the random removal operator in the ALNS algorithm when generating a new solution in each iteration, it is necessary to combine the SA algorithm and the ALNS algorithm to iteratively obtain the optimal solution (optimal path) for the plate to be cut.

[0040] In this embodiment of the invention, the specific operation of iteratively obtaining the optimal solution (optimal path) of the plate to be cut using the SA algorithm and the ALNS algorithm is as follows: The initial temperature value of the SA algorithm is set to 100℃, the temperature threshold is 1℃, the temperature cooling coefficient is 0.98, and the probability of accepting a new solution is 10%. A path is randomly generated based on the cutting point of the plate to be cut, which is used as the initial solution. The initial solution is used as the current solution for the first iteration. The steps to obtain the ALNS algorithm after the first iteration of optimization are as follows: The destruction operators include: random removal operator (randomly removes cut points in the current solution of the first iteration according to the destruction ratio of the random removal operator in the ALNS algorithm when generating a new solution in the first iteration), and distance-sensitive removal operator (removes the top 10% of cut points that contribute the most to the path distance in the current solution of the first iteration); the repair operators include: random insertion operator (randomly inserts the cut points removed by the destruction operator into any position in the path), and greedy insertion operator (inserts the cut points removed by the destruction operator into positions that result in a small increase in path distance); Set the first iteration score of each operator to 1. Based on the first iteration score of each operator, obtain the candidate probability of each operator in the first iteration (existing technical steps in the ALNS algorithm). Based on the candidate probability of each operator in the first iteration, use roulette to select any destruction operator and repair operator, and record them as the destruction operator and repair operator in the first iteration. The ALNS algorithm optimized in the first iteration is used to destroy and repair the current solution of the first iteration to obtain a new solution generated in the first iteration; the temperature of the SA algorithm in the first iteration is the initial temperature; Obtain the objective function value of the new solution generated in the first iteration and the objective function value of the current solution in the first iteration. If the objective function value of the new solution generated in the first iteration is greater than the objective function value of the current solution in the first iteration, decide whether to accept the new solution generated in the first iteration based on the acceptance probability. If accepted, the new solution generated in the first iteration is used as the current solution for the second iteration; otherwise, the current solution of the first iteration is used as the current solution for the second iteration. If the objective function value of the new solution generated in the first iteration is less than the objective function value of the current solution in the first iteration, the new solution generated in the first iteration is used as the current solution for the second iteration. The steps to obtain the ALNS algorithm after the second round of iteration optimization are as follows: The destruction operators include: random removal operator (randomly removes cut points from the current solution of the first iteration according to the destruction ratio of the random removal operator in the ALNS algorithm when generating a new solution in the second iteration), and distance-sensitive removal operator (removes the top 10% of cut points that contribute the most to the path distance in the current solution of the second iteration); the repair operators include: random insertion operator (randomly inserts the cut points removed by the destruction operator into any position in the path), and greedy insertion operator (inserts the cut points removed by the destruction operator into positions that result in a small increase in path distance); If the objective function value of the new solution generated in the first iteration is less than the current solution of the first iteration, then the score of the destruction operator and the repair operator in the first iteration is increased by one. If the objective function value of the new solution generated in the first iteration is greater than the objective function value of the current solution of the first iteration, and the new solution generated in the first iteration is used as the current solution of the second iteration, then the score of the destruction operator and the repair operator in the first iteration is increased by 0.5, and the score of each operator in the second iteration is obtained. Based on the second iteration score of each operator, obtain the candidate probability of each operator in the second iteration. Based on the candidate probability of each operator in the second iteration, use roulette to select any one of the destruction and repair operators as the destruction and repair operators in the second iteration. The ALNS algorithm optimized in the second round of iterations is used to destroy and repair the current solution of the second iteration, resulting in a new solution generated in the third iteration; the temperature of the SA algorithm in the second iteration is the product of the temperature of the SA algorithm in the second iteration and the temperature cooling coefficient. This process continues until the temperature of the SA algorithm is less than or equal to the temperature threshold during the Jth iteration. In this case, the current solution of the Jth iteration is taken as the optimal path for the plate to be cut.

[0041] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for optimizing the laser cutting path, characterized in that, include: Collect the cutting points of the material to be cut; During the process of iteratively obtaining the optimal path of the plate to be cut by the SA algorithm, the primary degree of destruction of the random removal operator in the ALNS algorithm is obtained according to the number of cutting points of the plate to be cut and the temperature value of the SA algorithm when a new solution is generated in each iteration. Obtain the objective function value for each iteration that generates a new solution; Based on the objective function value of the new solution generated in each iteration and the primary degree of destruction, the degree of destruction of the random removal operator in the ALNS algorithm is obtained when a new solution is generated in each iteration. Based on the degree of destruction caused by the random removal of operators in the ALNS algorithm during each iteration to generate a new solution, the destruction ratio of the random removal of operators in the ALNS algorithm during each iteration to generate a new solution is obtained; Based on the destruction ratio of the randomly removed operator in the ALNS algorithm when generating a new solution in each iteration, the optimal path of the plate to be cut is obtained by combining the SA algorithm and the ALNS algorithm.

2. The laser cutting path optimization method according to claim 1, characterized in that, The process of obtaining the initial degree of destruction of the random removal operator in the ALNS algorithm during each iteration to generate a new solution includes: ； In the formula, This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of cutting points on the material to be cut. This represents the temperature value of the SA algorithm when a new solution is generated in the i-th iteration; This represents the initial temperature value for the preset SA algorithm; norm() represents the normalization function.

3. The laser cutting path optimization method according to claim 1, characterized in that, The step of obtaining the objective function value for each iteration to generate a new solution includes: ； In the formula, This represents the objective function value used to generate a new solution in the i-th iteration. The path length during the entire cutting process represents the length of the laser when it generates a new solution based on the i-th iteration to cut a material identical to the material to be cut. exp() represents the temperature increment during the entire cutting process when the laser generates a new solution based on the i-th iteration and cuts a material identical to the material to be cut; exp() represents an exponential function with the natural constant as the base; norm() represents a normalization function.

4. The laser cutting path optimization method according to claim 1, characterized in that, The process of obtaining the degree of destruction caused by randomly removing operators in the ALNS algorithm during each iteration to generate a new solution includes: ； In the formula, This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. This represents the initial degree of destruction in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the number of previous iterations before the i-th iteration; This represents the objective function value used to generate a new solution in the m-th historical iteration prior to the i-th iteration. The objective function value represents the current solution of the historical iteration before the i-th iteration; The range represents the objective function values ​​generated from all previous iterations before the i-th iteration; || represents the absolute value sign; norm() represents the normalization function; exp() represents the exponential function with the natural constant as the base. This represents the preset adjustment coefficient.

5. The laser cutting path optimization method according to claim 4, characterized in that, Obtaining the number of historical iterations prior to the i-th iteration includes: The number of previous iterations before each iteration is set to M. The M iterations before each iteration are taken as the previous iterations before the i-th iteration.

6. The laser cutting path optimization method according to claim 1, characterized in that, The process of obtaining the destruction ratio of randomly removed operators in the ALNS algorithm during each iteration to generate a new solution includes: ； In the formula, This represents the proportion of disruption caused by the random removal of operators in the ALNS algorithm when a new solution is generated in the i-th iteration; This represents the degree of disruption caused by the random removal of operators in the ALNS algorithm when generating a new solution in the i-th iteration. This represents the proportion of disruption caused by randomly removing operators in the default ALNS algorithm.

7. The laser cutting path optimization method according to claim 2, characterized in that, The acquisition of the temperature value of the SA algorithm when generating a new solution in the i-th iteration includes: A preset temperature cooling coefficient is used. When a new solution is generated in the first iteration, the temperature value of the SA algorithm is the initial temperature value. When a new solution is generated in the second iteration, the temperature value of the SA algorithm is the product of the temperature value of the SA algorithm when a new solution is generated in the first iteration and the temperature cooling coefficient. And so on. When a new solution is generated in the i-th iteration, the temperature value of the SA algorithm is the product of the temperature value of the SA algorithm when a new solution is generated in the (i-1)-th iteration and the temperature cooling coefficient.

8. The laser cutting path optimization method according to claim 1, characterized in that, The process of collecting the cutting points of the material to be cut includes: The CAD drawing file of the board to be cut is imported into the API interface of the CAD software for loading, and the position coordinates of all cutting points in the board to be cut are extracted.

9. The laser cutting path optimization method according to claim 4, characterized in that, The acquisition of the range of the objective function values ​​generated from all previous iterations before the i-th iteration includes: The difference between the maximum and minimum values ​​of the objective function values ​​generated by all previous iterations before the i-th iteration is taken as the range of the objective function values ​​generated by all previous iterations before the i-th iteration.

10. A laser cutting path optimization system, characterized in that, include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement a laser cutting path optimization method according to any one of claims 1-9.

Images