Gluing track design method, storage medium and electronic equipment

Abstract

According to the gluing track design method, the storage medium and the electronic equipment, the to-be-glued area is divided into the multiple period design domains, after the gluing starting position is selected, the multiple gluing tracks in each period design domain are planned according to the genetic optimization algorithm, and according to the fact that the coverage rate corresponding to the gluing result is not smaller than the target gluing coverage rate, the gluing track is designed. Under the conditions that the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, the optimal gluing track is selected from the multiple gluing tracks to serve as the final gluing track. According to the scheme, based on a genetic optimization algorithm framework, a gluing track parameterization expression method of a multi-cycle design domain is established, gene crossover and gene variation mechanisms are improved, and a gluing track planning method with the coverage rate, the gluing thickness and the gluing amount meeting target requirements is provided. According to the scheme, the gluing track meeting the requirements for the coverage rate and the glue amount can be obtained, and the advantages of being high in coverage rate and low in glue amount are achieved.

Description

Technical Field

[0001] The present application relates to a new energy power battery pack manufacturing process, and specifically to a glue coating track design method, a storage medium and an electronic device. Background Art

[0002] During the assembly of power battery packs, the gluing process typically requires applying a thermally conductive structural adhesive between the battery pack housing and the battery cells. This adhesive serves as a structural connection between the cell module and the housing and facilitates rapid heat transfer. As a heat transfer medium, this adhesive efficiently transfers heat generated by the battery during operation, ensuring the battery pack's thermal management performance in high-temperature environments and preventing performance degradation or safety hazards caused by heat accumulation. It also enhances the integrity and stability of the battery pack structure, effectively reducing the impact of mechanical vibration on the battery module, and improving the vibration resistance and durability of the battery pack.

[0003] The thermal conductivity of the thermally conductive structural adhesive is closely related to the coverage area of its contact surface. Therefore, the setting of the glue coating trajectory largely determines whether the coverage of the thermally conductive structural adhesive can meet the heat dissipation requirements required for stable operation of the battery pack. Appropriately increasing the coverage of the thermally conductive structural adhesive between the battery pack shell and the battery cell will be more helpful in meeting the thermal conductivity of the product. Therefore, the product design generally has high requirements for coverage. In view of the difference in contour between the battery shell and the bottom surface of the battery cell, the glue coating process requires a sufficient amount of glue to meet the coverage after coating, and the amount of glue used needs to balance the manufacturing cost and product performance, so the actual amount of glue used is crucial. During the process, the amount of glue used in the single battery pack should be reduced as much as possible while meeting the coverage requirements. Summary of the Invention

[0004] The present application aims to provide a gluing trajectory design method, storage medium and electronic device, which can obtain the optimal gluing trajectory design under actual gluing conditions, thereby reducing the amount of gluing while ensuring the gluing coverage.

[0005] In a first aspect, the technical solution of the present application provides a method for designing a gluing track, comprising:

[0006] Divide the area to be glued into multiple periodic design domains;

[0007] Determining a target glue coating coverage rate and a target glue coating thickness, and determining a target glue coating amount according to the target glue coating coverage rate and the target glue coating thickness;

[0008] After selecting the starting position for gluing, multiple gluing trajectories within each periodic design domain are planned according to the genetic optimization algorithm, and the optimal gluing trajectory is selected from the multiple gluing trajectories as the final gluing trajectory based on the conditions that the coverage corresponding to the gluing result is not less than the target gluing coverage, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount.

[0009] Preferably, in some embodiments of the gluing trajectory design method, after selecting the gluing starting position, planning multiple gluing trajectories within each of the periodic design domains according to a genetic optimization algorithm, selecting the optimal gluing trajectory as the final gluing trajectory from the multiple gluing trajectories based on the conditions that the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, includes:

[0010] Parameter definition, define the genetic optimization algorithm parameters, set the number of optimization trajectories k, number of iterations G, maximum number of repetitions R, initial population size N, gene crossover probability P1, gene mutation probability P2 and gene length L;

[0011] Gene encoding, taking the glue track of each cycle as a gene, encoding the gene in the form of unit coordinates; genes of different cycles are connected end to end;

[0012] Population initialization uses a random initial population method to generate an initial population by randomly initializing coordinates. The initial population consists of N genes.

[0013] Gene crossover, generate the first random number in the interval [0,1], and perform gene crossover when the first random number is less than the gene crossover probability P1: randomly select two genes from the current population and randomly select the crossover breakpoint according to the probability to perform gene crossover to generate new offspring genes;

[0014] Gene mutation: Generate a second random number in the interval [0,1]. When the second random number is less than the gene mutation probability P2, gene mutation is performed: random mutation operations are performed simultaneously on the odd and even bit trajectory segments of a gene in the current population.

[0015] Gene decoding: decoding the genes after population initialization, gene crossover, and gene mutation. In a periodic design domain, for a certain trajectory segment, if the projection distance d from any element point P in the periodic design domain to the trajectory segment is less than b / 2, then the element point is assigned an initial glue thickness h1, where b is the glue width. The decoded genes in each periodic design domain are arrayed according to the arrangement direction of the periodic design domain, and the initial trajectory matrix is output.

[0016] Glue diffusion simulation of the glue coating track: for each track segment in the initial track matrix output in the gene decoding step, glue diffusion simulation is performed;

[0017] Fitness function design, calculate the coverage rate and glue amount after the glue spreading simulation of the glue spreading track, and design a fitness function with coverage rate and glue amount as variables to evaluate the quality of the glue spreading track;

[0018] The optimal gluing trajectory is retained. In the genetic operation of each gene, the fitness function is used to calculate the fitness of the gene individuals before and after gene crossover and gene mutation. The fitness results of each gene individual in the genetic population are combined with the fitness results of each gene individual in the previous generation population, and then sorted according to the fitness value. The gene individuals ranked in the top N fitness values are selected to form the genetic population.

[0019] Iteration termination judgment: set the variable r to represent the number of times the current optimal solution has not changed continuously, and set the variable g to represent the number of iterations of the current algorithm; when r>R or g>G, the loop repetition stops;

[0020] Visualization: Output the coverage, glue amount, and endpoint coordinates of the optimal glue trajectory in each gene after the iteration to generate a visualization pattern.

[0021] The final gluing trajectory is confirmed, and the optimal gluing trajectory of each period design domain is summarized as the simulated gluing result. If the coverage corresponding to the gluing result is not less than the target gluing coverage, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, the optimal gluing trajectory is selected from multiple gluing trajectories as the final gluing trajectory.

[0022] Preferably, the gluing track design method described in some schemes:

[0023] In the gene crossover step, the abscissa of the starting point coordinate and the abscissa of the end point coordinate of the new offspring gene generated by the gene crossover are respectively in the first column and the last column in the cycle; the ordinate of the starting point coordinate and the ordinate of the end point coordinate are the same;

[0024] In the gene mutation step, the abscissa of the starting point coordinate and the abscissa of the end point coordinate of the mutated gene are respectively in the first column and the last column in the cycle; the ordinate of the starting point coordinate and the ordinate of the end point coordinate have the same value.

[0025] Preferably, in the method for designing a gluing track described in some embodiments, in the step of simulating the gluing diffusion of the gluing track:

[0026] Based on the eight-neighborhood diffusion model, the glue diffusion simulation is performed on the glue coating trajectory, including: selecting measuring points, detecting whether the glue thickness at each measuring point exceeds the upper limit of glue thickness, and if so, distributing the excess colloid to the eight neighborhoods of the measuring point according to different diffusion coefficients, where the eight neighborhoods refer to the neighborhoods in the eight directions of up, down, left, right, upper left, lower left, upper right, and lower right of the measuring point.

[0027] Preferably, in the method for designing the gluing track described in some embodiments, in the step of designing the fitness function:

[0028] The fitness function is expressed as: f=1-C+λmax{0,Q1-Q0};

[0029] Among them, λ is the penalty factor, C is the coverage, Q1 is the glue amount calculated after simulating the glue diffusion of the glue trajectory, and Q0 is the target glue amount.

[0030] Preferably, in the method for designing a gluing trajectory described in some embodiments, in the step of retaining the optimal gluing trajectory:

[0031] A temporary matrix is provided, wherein the temporary matrix is used to store gene individuals before gene crossover and gene mutation and gene individuals after gene crossover and gene mutation in the genetic operation of each gene;

[0032] After the top N gene individuals with the highest fitness values are selected to form a genetic population, the memory of the temporary matrix is released.

[0033] Preferably, the gluing track design method described in some schemes:

[0034] For different periodic design domains, the optimal gluing trajectory in each periodic design domain is planned according to a genetic optimization algorithm in a parallel computing manner.

[0035] In a second aspect, the technical solution of the present application provides a computer-readable storage medium, in which program information is stored. After a computer reads the program information, the computer executes the steps of the gluing trajectory design method described in any one of the first aspects.

[0036] In a third aspect, the technical solution of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the glue trajectory design method described in any one of the first aspects.

[0037] In a fourth aspect, the technical solution of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the glue trajectory design method described in any one of the first aspects.

[0038] Compared with the existing technology, the above technical solution provided by this application has the following technical effects:

[0039] The gluing trajectory design method, storage medium and electronic device provided in the present application divide the area to be glued into multiple periodic design domains, set the target glue coverage rate and target glue thickness to meet the gluing requirements, and determine the target glue amount. After selecting the starting position of gluing, after planning a variety of gluing trajectories in each periodic design domain according to the genetic optimization algorithm, the optimal gluing trajectory is selected from the multiple gluing trajectories as the final gluing trajectory based on the conditions that the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the glue thickness corresponding to the simulated gluing result is consistent with the target glue thickness, and the glue amount corresponding to the simulated gluing result does not exceed the target glue amount. The above scheme, based on the genetic optimization algorithm framework, establishes a parameterized expression method for gluing trajectories in multi-periodic design domains, improves the gene crossover and gene mutation mechanisms, and proposes a gluing trajectory planning method in which coverage rate, glue thickness and glue amount all meet the target requirements. The present application scheme can obtain a gluing trajectory that meets the coverage rate and glue amount requirements, and has the advantages of high coverage rate and low glue amount. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of a rectangular glue-coated area according to one embodiment of the present application;

[0041] Figure 2 This is a flow chart of a method for designing a gluing track according to an embodiment of the present application;

[0042] Figure 3 This is a schematic diagram of the periodic design domain division result and the gluing trajectory within each periodic design domain according to an embodiment of the present application;

[0043] Figure 4 A flowchart of various gluing trajectories within a design domain of a genetic optimization algorithm planning cycle according to one embodiment of the present application;

[0044] Figure 5 This is a schematic diagram of the glue coating according to one embodiment of the present application;

[0045] Figure 6 This is a structural diagram of an embodiment of the present application after the battery cell is arranged on the glue-coated surface;

[0046] Figure 7 This is a schematic diagram of the hardware connection relationship of an electronic device that executes the glue track design method described in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The specific implementation of this application is further described below with reference to the accompanying drawings.

[0048] It is easy to understand that according to the technical solution of this application, a variety of structural methods and implementation methods can be replaced with each other by those skilled in the art without changing the essential spirit of this application. Therefore, the following specific embodiments and drawings are only exemplary descriptions of the technical solution of this application and should not be regarded as the entire application or as a limitation or restriction of the technical solution of the application.

[0049] This embodiment provides a method for designing a gluing trajectory, which is applied to a control system of a gluing device, such as Figure 1 The rectangular glue application area shown is consistent with the shape of the actual glue application area of the battery pack shell. Its length is x and its width is y. The small rectangular areas inside correspond to the placement of the battery cells. The glue application trajectory design is performed on this design domain using the method of this application. Figure 1 The length and width of the glue-coated area described in the figure are the same as the length and width of the glue-coated plane area of the shell of the power battery pack of a specific model.

[0050] The selection of a periodic design domain for narrow-width gluing is crucial for both glue volume and coverage. In this embodiment, the entire rectangular area is divided into n periodic design domains along the horizontal direction (the x-direction in the figure). In specific implementation, n can be determined based on the equipment model and empirical values, typically ranging from 20 to 40. In this solution, n = 22 is used as an example. The lateral dimension corresponding to each periodic design domain is defined as e. Each periodic design domain is discretized into a number of unit grids, and the overall design domain is a superposition of n periodic units. The size of e is determined based on the length of the gluing area and the specific value of n, with a suitable range of 3 to 5 mm. In this solution, e = 3.5 mm is used as an example. Based on the actual gluing equipment model and the actual gluing conditions, the glue width during gluing is set to b, the initial glue thickness is set to h1, the glue thickness after gluing is set to h2, and the upper limit of glue thickness per grid is set to h3. The number of line segments per period is set to u, resulting in a total of m = u × n segments during the gluing process. As shown in the figure, the number of line segments per period is set to 2. When n = 22, m = 44. The theoretical glue amount Q0 of the entire rectangular area is calculated as follows: Q0 = h2×x×y / 1000. The scheme in the following embodiments of this application is to meet the coverage requirement under the premise that the glue amount does not exceed Q0. Specifically, Figure 2 As shown, the gluing track design method includes the following steps:

[0051] S100: Divide the area to be glued into multiple periodic design domains.

[0052] like Figure 1 As shown, the number of the periodic design domains can be selected as 22.

[0053] S200: Determine a target glue coating coverage rate and a target glue coating thickness, and determine a target glue coating amount according to the target glue coating coverage rate and the target glue coating thickness.

[0054] In a specific implementation, the target glue coating coverage can be 99.5%, or can be set separately according to the cell coverage and the overall coverage, such as the single cell coverage must be greater than 90%.

[0055] S300: After selecting the starting position for gluing, after planning multiple gluing trajectories within each periodic design domain according to the genetic optimization algorithm, the optimal gluing trajectory is selected as the final gluing trajectory from the multiple gluing trajectories based on the conditions that the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount.

[0056] The starting position of gluing can be selected as the corner position of the rectangular area, such as Figure 3 As shown, the lower left corner, the most corner that the glue coating equipment can touch, is used as the starting position.

[0057] The above-mentioned scheme of the present application divides the area to be glued into multiple periodic design domains, sets the target glue coverage rate and target glue thickness in order to meet the gluing requirements, and determines the target glue amount. After selecting the starting position of gluing, after planning a variety of gluing trajectories in each periodic design domain according to the genetic optimization algorithm, the optimal gluing trajectory is selected from the multiple gluing trajectories as the final gluing trajectory based on the conditions that the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the glue thickness corresponding to the simulated gluing result is consistent with the target glue thickness, and the glue amount corresponding to the simulated gluing result does not exceed the target glue amount. The above-mentioned scheme, based on the genetic optimization algorithm framework, establishes a parameterized expression method for the gluing trajectory of a multi-period design domain, improves the gene crossover and gene mutation mechanism, and proposes a gluing trajectory planning method in which the coverage rate, glue thickness and glue amount all meet the target requirements. The present application scheme can obtain a gluing trajectory that meets the coverage rate and glue amount requirements, and has the advantages of high coverage rate and low glue amount.

[0058] Preferably, in the embodiment of the present application, the gluing track in each cycle design domain is planned according to the genetic optimization algorithm in step S300, such as Figure 4 As shown, the following steps are included:

[0059] S301: Parameter definition, define the genetic optimization algorithm parameters, set the number of optimization trajectories k, number of iterations G, maximum number of repetitions R, initial population size N, gene crossover probability P1, gene mutation probability P2 and gene length L.

[0060] In this scheme, K=100, G=200, R=20, N=50, P1=1, and P2=0.8 can be set. The gene length L is determined by the number of line segments and endpoints in a cycle, including the endpoint coordinate information. The calculation formula is as follows: L=(u+1)×2. Taking u=2 as an example, L=6.

[0061] S302: Gene encoding, taking the glue track of each cycle as a gene, encoding the gene in the form of unit coordinates; wherein, genes of different cycles are connected end to end.

[0062] The glue track is used as the gene, and the glue track gene is encoded in the form of unit coordinates. The initial gene s=(x1,y1,...,x L ,y L ), used to represent the coordinates of all endpoints within the cycle.

[0063] On the basis of initializing the endpoint coordinates, the horizontal coordinates of the starting point coordinates and the ending point coordinates of each periodic trajectory can be constrained to be in the first and last columns in the period respectively; the vertical coordinates of the starting point coordinates and the ending point coordinates can be constrained to have the same values to ensure that the connection between the periodic trajectories is connected from beginning to end.

[0064] S303: Population initialization: using a random initial population method, generating an initial population by randomly initializing coordinates, and the initial population consists of N genes.

[0065] In this step, a random initial population is used to generate an initial population by randomly initializing coordinates. The initial population consists of multiple glued track genes, each of which consists of multiple continuous track segments. Finally, N L-dimensional glued tracks are generated as the initial population.

[0066] S304: Gene crossover, generate a first random number in the interval [0,1]. When the first random number is less than the gene crossover probability P1, perform gene crossover: randomly select two genes from the current population and randomly select crossover breakpoints according to probability to perform gene crossover to generate new offspring genes.

[0067] In this step, the new offspring genes also correspond to the glued tracks, so the unit coordinate position constraints in the previous step must be met: the horizontal coordinates of the starting coordinate and the ending coordinate are constrained to be in the first and last columns of the cycle, respectively; the vertical coordinates of the starting coordinate and the ending coordinate are constrained to be the same, ensuring that the tracks are connected at the connection between cycles. Except for the first and last coordinates, the remaining coordinates are crossovered using a randomly selected crossover breakpoint.

[0068] S305: Gene mutation, generating a second random number in the interval [0,1]. When the second random number is less than the gene mutation probability P2, gene mutation is performed: random mutation operations are performed simultaneously on the odd-numbered and even-numbered trajectory segments of a gene in the current population.

[0069] In this step, mutations are performed simultaneously on both odd- and even-numbered gene segments within a given gene population. Taking into account margins for gluing, the horizontal and vertical unit coordinates are randomly mutated within the corresponding single cycle. As previously mentioned, the mutated gene corresponds to the gluing trajectory, so the unit coordinate position constraints described in the previous step must be met: the horizontal coordinates of the starting and ending coordinates must be in the first and last columns within the cycle, respectively; the vertical coordinates of the starting and ending coordinates must be the same, ensuring that the trajectory is connected at the junction between cycles. All unit coordinates except the first and last coordinates can be mutated.

[0070] S306: Gene decoding, decoding the genes after the population initialization, gene crossover, and gene mutation; in the periodic design domain, for a certain trajectory segment, if the projection distance d from any element point P in the periodic design domain to the trajectory segment is less than b / 2, then the element point is assigned an initial glue thickness h1, where b is the glue width; the decoded genes in each periodic design domain are arrayed according to the arrangement direction of the periodic design domain, and the initial trajectory matrix is output;

[0071] Assuming that the starting coordinates of a certain glue-spreading trajectory segment are (x1, y1) and the ending coordinates are (x2, y2), for any element P(i, j) in the glue-spreading area, the projection distance d from point P to the trajectory can be calculated by the following formula:

[0072]

[0073] If the above result is less than b / 2, it can be considered as an area with thermal conductive structural adhesive in the adhesive coating track, and the element is given an initial adhesive thickness of h1. Otherwise, it is a blank area without thermal conductive structural adhesive. After completing the above judgment for all pixel points in the periodic design domain, the adhesive coating track gene is decoded.

[0074] S307: Glue spreading simulation of the glue trajectory, performing glue spreading simulation on each trajectory segment in the initial trajectory matrix output in the gene decoding step.

[0075] In specific implementation, this step preferably performs glue diffusion simulation on the glue coating trajectory based on the eight-neighborhood diffusion model. Check whether the glue thickness of each grid unit exceeds the capacity limit. If it exceeds the limit, the excess colloid is distributed to eight neighborhoods according to different diffusion coefficients, and the diffusion coefficients T1 for the upper, lower, left, and right directions of the glue coating trajectory are defined, and the diffusion coefficients T2 for the upper left, lower left, upper right, and lower right directions are defined. Traverse the grid units in the glue coating area. If there is no colloid in the neighborhood to continue to diffuse, the colloid continues to be distributed to the neighborhood. Otherwise, the overflow glue is counted to complete the diffusion simulation of the colloid. During the application process, the results obtained after the glue is executed in each cycle design domain are as follows Figure 5 As shown, the black part is the part covered by glue.

[0076] S308: Design of fitness function, calculating the coverage rate and glue amount after the glue spreading simulation of the glue spreading track, and designing a fitness function with coverage rate and glue amount as variables to evaluate the quality of the glue spreading track.

[0077] S309: The optimal gluing trajectory is retained. In the genetic operation of each gene, the fitness function is used to calculate the fitness of the gene individuals before gene crossover and gene mutation, and the fitness of the gene individuals after gene crossover and gene mutation. The fitness results of each gene individual in the genetic population are merged with the fitness results of each gene individual in the previous generation population, and then sorted according to the fitness value. The gene individuals ranked in the top N in fitness value are selected to form the genetic population.

[0078] S310: Iteration termination judgment, setting the variable r to represent the number of times the current optimal solution has not changed continuously, and setting the variable g to represent the number of current algorithm iterations; when r>R or g>G, the loop repetition stops;

[0079] In this step, when r≤R and g≤G, if the current optimal solution is the same as the previous optimal solution, r+1 is added; if they are different, r is reset to 0, the current iteration number is g+1, and step S304 is repeated. When r>R or g is greater than G, the loop stops and the process goes to step S311.

[0080] S311: Visualization, outputting the coverage rate, glue amount, and coordinates of the endpoints of the track segments in each gene corresponding to the optimal glue track after the iteration is completed, and generating a visualization pattern.

[0081] In practice, the visualization operation traverses each track in the aforementioned track matrix and determines whether its relevant parameter exceeds a preset upper limit, such as whether the glue thickness exceeds h3. Based on this determination, the color and transparency of the visualization are dynamically adjusted. If the track's value exceeds the limit, it is marked with a specific color and the transparency is set to the maximum value. If it does not exceed the limit, it is marked with a different color and the transparency is dynamically adjusted based on the ratio of the track's value to the limit.

[0082] S312: The final gluing trajectory is confirmed, and the optimal gluing trajectory of each period design domain is summarized as the simulated gluing result. If the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, the optimal gluing trajectory is selected from multiple gluing trajectories as the final gluing trajectory.

[0083] This step is to filter the summarized glue tracks and combine them with the visualized ones. Figure 6 The block diagram of the covered cell area is shown. The coverage of the area with obvious glue shortage at the edge is calculated, and the track that meets the single cell coverage ≥ 90% is selected. The overall coverage of this track is 99.5%. The cells in the upper left corner, lower left corner, upper right corner, and lower right corner are relatively glue-deficient areas, and the coverage meets the product requirement of ≥ 90%.

[0084] Furthermore, in the above scheme, in the fitness function design, the quality of the glue coating track is evaluated by calculating the coverage rate and effective glue coating amount after diffusion, so a function containing these two is used as the fitness function f to reflect the quality of the track. The fitness calculation formula is as follows:

[0085] f=1-C+λmax{0,Q1-Q0};

[0086] Where λ is the penalty factor, C is the overall coverage, and Q1 is the effective glue amount calculated from the diffusion glue trajectory matrix. The smaller the fitness function f, the better the trajectory. The calculation formulas for C and Q1 are as follows:

[0087]

[0088] α i,j is the effective glue thickness of each unit cell in the glue-coated area after diffusion, η is the side length of the square grid obtained by discretizing the periodic design domain, and ω and v represent the number of discrete square grids in the horizontal and vertical directions of the glue-coated area, respectively.

[0089] Furthermore, the optimal individual retention strategy is implemented in the optimal glue trajectory retention. That is, in each generation of genetic operations (including gene crossover and gene mutation), the individuals before the gene crossover and gene mutation, as well as the new individuals generated after the operation, are recorded and stored in a temporary matrix. By calculating the fitness of each individual in the next generation population, the results are merged with the previous generation population and sorted by fitness value. The top N individuals with the highest fitness are selected as the next generation population. At the same time, the poorer individuals with a ranking exceeding the population size N are discarded, freeing up the temporary matrix memory, ensuring that the best individuals in each generation population are retained, and avoiding the problem of fitness degradation caused by genetic operations.

[0090] Preferably, to improve computational efficiency, the above scheme employs large-scale parallel computing. For different periodic design domains, the optimal gluing trajectory within each periodic design domain is planned using a genetic optimization algorithm in parallel. Each step can be considered an overall computational process, a subtask. By utilizing multi-core processors or distributed computing resources to simultaneously execute k subtasks, each running independently without interfering with each other, the results of the k subtasks are ultimately aggregated.

[0091] An embodiment of the present application provides a computer-readable storage medium, in which program information is stored. After a computer reads the program information, the computer executes the steps of the gluing trajectory design method described in any one of the above method embodiments.

[0092] An embodiment of the present application provides a computer program product, including a computer program / instruction, characterized in that when the computer program / instruction is executed by a processor, the steps of the gluing trajectory design method described in any one of the above method embodiments are implemented.

[0093] The present application also provides an electronic device, such as Figure 7As shown, the electronic device includes at least one processor 71 and at least one memory 72. At least one of the memories 72 stores program information. After reading the program information, the at least one processor 71 executes the method for designing a gluing track described in any of the above method embodiments. The device may also include an input device 73 and an output device 74. The processor 71, memory 72, input device 73, and output device 74 are communicatively connected. Memory 72, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs, and modules. By running the non-volatile software programs, instructions, and modules stored in memory 72, the processor 71 executes various functional applications and data processing, thereby implementing the method for designing a gluing track provided in any of the above methods. Memory 72 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for the function; the data storage area may store data created by using the method for designing a gluing track. In addition, the memory 72 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 72 may optionally include a memory remotely located relative to the processor 71, and these remote memories may be connected to a device for executing the gluing track design method via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The input device 73 may receive input user clicks and generate signal inputs related to user settings and function controls of the gluing track design method. The output device 74 may include a display device such as a display screen. The one or more modules are stored in the memory 72, and when executed by the one or more processors 71, the gluing track design method in any of the above-mentioned method embodiments is executed.

[0094] As needed, the above technical solutions can be combined to achieve the best technical effect.

[0095] The above are only the principles and preferred embodiments of the present application. It should be noted that, for those skilled in the art, on the basis of the principles of the present application, several other modifications can be made, which should also be considered as the scope of protection of the present application.

Claims

1. A method for designing a gluing track, characterized in that: include: Divide the area to be glued into multiple periodic design domains; Determining a target glue coating coverage rate and a target glue coating thickness, and determining a target glue coating amount according to the target glue coating coverage rate and the target glue coating thickness; After selecting the starting position for gluing, multiple gluing trajectories within each periodic design domain are planned according to the genetic optimization algorithm, and the optimal gluing trajectory is selected from the multiple gluing trajectories as the final gluing trajectory based on the conditions that the coverage corresponding to the gluing result is not less than the target gluing coverage, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount.

2. The method for designing a gluing track according to claim 1, wherein: After selecting the gluing starting position, planning multiple gluing trajectories within each of the periodic design domains according to the genetic optimization algorithm, selecting the optimal gluing trajectory as the final gluing trajectory from the multiple gluing trajectories based on the conditions that the coverage rate corresponding to the gluing result is not less than the target gluing coverage rate, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, including: Parameter definition, define the genetic optimization algorithm parameters, set the number of optimization trajectories k, number of iterations G, maximum number of repetitions R, initial population size N, gene crossover probability P1, gene mutation probability P2 and gene length L; Gene encoding, taking the glue track of each cycle as a gene, encoding the gene in the form of unit coordinates; genes of different cycles are connected end to end; Population initialization uses a random initial population method to generate an initial population by randomly initializing coordinates. The initial population consists of N genes. Gene crossover, generate the first random number in the interval [0,1], and perform gene crossover when the first random number is less than the gene crossover probability P1: randomly select two genes from the current population and randomly select the crossover breakpoint according to the probability to perform gene crossover to generate new offspring genes; Gene mutation: Generate a second random number in the interval [0,1]. When the second random number is less than the gene mutation probability P2, gene mutation is performed: random mutation operations are performed simultaneously on the odd and even bit trajectory segments of a gene in the current population. Gene decoding: decoding the genes after population initialization, gene crossover, and gene mutation. In a periodic design domain, for a certain trajectory segment, if the projection distance d from any element point P in the periodic design domain to the trajectory segment is less than b / 2, then the element point is assigned an initial glue thickness h1, where b is the glue width. The decoded genes in each periodic design domain are arrayed according to the arrangement direction of the periodic design domain, and the initial trajectory matrix is output. Glue diffusion simulation of the glue coating track: for each track segment in the initial track matrix output in the gene decoding step, glue diffusion simulation is performed; Fitness function design, calculate the coverage rate and glue amount after the glue spreading simulation of the glue spreading track, and design a fitness function with coverage rate and glue amount as variables to evaluate the quality of the glue spreading track; The optimal gluing trajectory is retained. In the genetic operation of each gene, the fitness function is used to calculate the fitness of the gene individuals before and after gene crossover and gene mutation. The fitness results of each gene individual in the genetic population are combined with the fitness results of each gene individual in the previous generation population, and then sorted according to the fitness value. The gene individuals ranked in the top N fitness values are selected to form the genetic population. Iteration termination judgment: set the variable r to represent the number of times the current optimal solution has not changed continuously, and set the variable g to represent the number of iterations of the current algorithm; when r>R or g>G, the loop repetition stops; Visualization: Output the coverage, glue amount, and endpoint coordinates of the optimal glue trajectory in each gene after the iteration to generate a visualization pattern. The final gluing trajectory is confirmed, and the optimal gluing trajectory of each period design domain is summarized as the simulated gluing result. If the coverage corresponding to the gluing result is not less than the target gluing coverage, the gluing thickness corresponding to the simulated gluing result is consistent with the target gluing thickness, and the gluing amount corresponding to the simulated gluing result does not exceed the target gluing amount, the optimal gluing trajectory is selected from multiple gluing trajectories as the final gluing trajectory.

3. The method for designing a gluing track according to claim 2, wherein: In the gene crossover step, the abscissa of the starting point coordinate and the abscissa of the end point coordinate of the new offspring gene generated by the gene crossover are respectively in the first column and the last column in the cycle; the ordinate of the starting point coordinate and the ordinate of the end point coordinate are the same; In the gene mutation step, the abscissa of the starting point coordinate and the abscissa of the end point coordinate of the mutated gene are respectively in the first column and the last column in the cycle; the ordinate of the starting point coordinate and the ordinate of the end point coordinate have the same value.

4. The method for designing a gluing track according to claim 2, wherein: In the steps of simulating the diffusion of glue on the glue track: Based on the eight-neighborhood diffusion model, the glue diffusion simulation is performed on the glue coating trajectory, including: selecting measuring points, detecting whether the glue thickness at each measuring point exceeds the upper limit of glue thickness, and if so, distributing the excess colloid to the eight neighborhoods of the measuring point according to different diffusion coefficients, where the eight neighborhoods refer to the neighborhoods in the eight directions of up, down, left, right, upper left, lower left, upper right, and lower right of the measuring point.

5. The method for designing a gluing track according to claim 2, wherein: In the steps of fitness function design: The fitness function is expressed as: f=1-C+λmax{0,Q1-Q0}; Among them, λ is the penalty factor, C is the coverage, Q1 is the glue amount calculated after simulating the glue diffusion of the glue trajectory, and Q0 is the target glue amount.

6. The method for designing a gluing track according to claim 2, characterized in that: In the step of retaining the optimal gluing trajectory: A temporary matrix is provided, wherein the temporary matrix is used to store gene individuals before gene crossover and gene mutation and gene individuals after gene crossover and gene mutation in the genetic operation of each gene; After the top N gene individuals with the highest fitness values are selected to form a genetic population, the memory of the temporary matrix is released.

7. The method for designing a gluing track according to any one of claims 2 to 6, characterized in that: For different periodic design domains, the optimal gluing trajectory in each periodic design domain is planned according to a genetic optimization algorithm in a parallel computing manner.

8. A computer-readable storage medium, characterized in that The storage medium stores program information, and the computer reads the program information and executes the steps of the method for designing a gluing track according to any one of claims 1 to 7.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for designing a gluing track according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the gluing track design method according to any one of claims 1 to 7.

Images