Automatic tape laying path planning method and system based on material utilization rate

Abstract

The invention belongs to the technical field of data processing, and particularly relates to an automatic tape laying path planning method and system based on the material utilization rate, and the method comprises the steps: employing a genetic algorithm, introducing a dynamic layout optimization operator in an iteration process, and calculating the geometric agility of a part and the local optimization degree of a plate through the operator, and a vacant area and a flexible part with optimization potential are identified, and the target part is finely adjusted to reduce the vacant area. The typesetting scheme is changed into an evolvable entity from a static constraint, and the material utilization rate can be improved on the premise that it is guaranteed that the machining time meets the constraint.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing. More particularly, the present application relates to a material utilization rate based automatic tape laying path planning method and system. BACKGROUND

[0002] In the fields of aerospace, automobile manufacturing, etc., automatic tape laying technology is the core process of manufacturing large and complex composite material components. This process usually involves laying and cutting multiple parts with different shapes from expensive pre-impregnated tape raw materials. Therefore, how to efficiently plan the layout scheme of parts on the plate and the processing path of the tape laying equipment to maximize material utilization is a key link to reduce manufacturing costs and improve production efficiency.

[0003] In order to solve this complex combinatorial optimization problem, the existing technology often uses intelligent optimization algorithms such as genetic algorithms to solve it. However, there are usually the following technical problems in the application of these algorithms: First, the traditional path planning method often regards the layout of the parts as a pre-existing, static hard constraint. That is, the layout is completed once, and the subsequent path optimization is completely based on this fixed layout, which greatly limits the optimization space of the algorithm. Once there is a slight defect or optimization space in the initial layout scheme, the subsequent algorithm cannot adjust it, so it is difficult to break through the bottleneck of material utilization. Secondly, the existing method often takes material utilization as a single target in optimization, ignoring the strict requirements of industrial production on processing time, and may plan a scheme with extremely high material utilization but long processing time, which is not practical for actual production.

[0004] Therefore, how to improve the algorithm to dynamically adjust the layout and consider multiple production constraints in the optimization process has become a technical problem to be solved in the field. SUMMARY

[0005] To solve the above technical problem of poor automatic tape laying path planning effect, the present application provides a scheme in the following aspects.

[0006] In a first aspect, the present application provides a material utilization rate based automatic tape laying path planning method, comprising: Obtain the geometric information of all parts to be processed and the performance parameters of the laying equipment; generate an initial layout scheme containing the position information of each part based on a heuristic algorithm, and construct an initial population of a genetic algorithm in combination with a random processing order and equipment allocation; in the iteration process of the genetic algorithm, adjust the initial layout scheme by executing a dynamic layout optimization operator to obtain an adjusted layout scheme, the dynamic layout optimization operator including: calculating the geometric agility of each part, the geometric agility being negatively correlated with the area of the part and positively correlated with the square of the perimeter of the part; dividing the plate into multiple local areas; calculating the local optimizable degree of each local area, the local optimizable degree being positively correlated with the average value of the vacant area of the corresponding local area and the geometric agility of the adjacent parts thereof; taking the local area with the largest local optimizable degree as a target area, and taking the adjacent part with the largest geometric agility in the target area as a target part; moving the target part within a set search range to reduce the vacant area of the target area; calculating the material utilization rate based on the adjusted layout scheme and obtaining the fitness value of each individual; operating the population based on the fitness value until a termination condition is met, and decoding the individual with the highest fitness value to obtain a final laying path.

[0007] The present application embeds the geometric information of the layout scheme as an evolvable entity in the iteration process of the genetic algorithm, intelligently identifies and fine-tunes the most convenient part and vacant area by using the geometric agility and local optimizable degree indicators through the dynamic layout optimization operator, and realizes the collaborative optimization of the layout and the laying path. This dynamic adjustment mechanism can search for a better solution in the global range, thereby improving the material utilization rate.

[0008] Preferably, the heuristic algorithm is specifically the best-fit method, including: Sort all parts to be processed in descending order of area; for each sorted part, traverse all available blank areas on the plate and place it in a position that minimizes the fragmentation degree of the remaining blank area; repeat the placement process until all parts are placed to obtain an initial layout scheme.

[0009] The present application generates an initial layout scheme by using the best-fit method, sorts the parts in descending order of area and places them in positions that minimize the fragmentation degree of the remaining blank area, which can obtain a high-quality initial layout, provides a better starting point for subsequent genetic algorithm optimization, helps to accelerate the convergence of the algorithm and find a globally better solution.

[0010] Preferably, the geometric agility satisfies the expression: ; In the formula, G i represents the geometric agility of the i th part; A i represents the area of the i th part; denotes the circumference of the i-th part; denotes the circumference of the i-th part.

[0011] The present application comprehensively considers the area and the complexity of the shape of the part to obtain the geometric agility of the part, provides a more accurate calculable basis for the dynamic layout optimization operator, enables it to more efficiently screen out the most suitable part for filling the irregular gap, and thus improves the accuracy and effectiveness of the layout optimization.

[0012] Preferably, the local optimizable degree satisfies the expression: ; In the formula, denotes the local optimizable degree of the r-th local area; denotes the vacant area of the r-th local area; denotes the number of all parts that are adjacent or partially overlapped with the local area ; denotes the geometric agility of the j-th adjacent part of the r-th local area; denotes a very small positive value.

[0013] The present application can identify the area that not only has a large gap, but also has agile parts around it that are easy to move and adjust by combining the vacant area in the area with the average geometric agility of the adjacent parts, thereby concentrating the computing resources in the most potential optimization location and improving the efficiency and success rate of dynamic layout adjustment.

[0014] Preferably, the division of the plate into multiple local areas comprises: Grid division is performed on the plate area, and each grid unit is taken as a local area.

[0015] Preferably, the grid division comprises: The side length of the grid unit is the minimum value of the short side length of the envelope rectangle of all parts to be processed.

[0016] Preferably, the movement of the target part within the set search range to reduce the vacant area of the target area comprises: A plurality of candidate fine-tuning disturbance vectors are generated within the set search range with the current position of the target part as the center, each vector containing a translation component and a rotation component; the candidate fine-tuning disturbance vectors are applied to the target part, and the reduction amount of the vacant area of the target area is calculated; the candidate fine-tuning disturbance vector that maximizes the reduction amount is selected as the final fine-tuning disturbance vector and the target part is adjusted.

[0017] The present application can realize accurate fine adjustment of the part position with low calculation cost, effectively fill local gaps, and avoid destructive impact on the overall layout, so that the dynamic optimization process is more stable and efficient.

[0018] Preferably, the search range comprises: a circular translational search range with a radius of , and a sectorial rotational search range with an included angle of .

[0019] Preferably, the obtaining of the fitness value of each individual comprises: calculating material utilization and total processing time based on the adjusted layout scheme; setting a total processing time threshold; taking the material utilization as the fitness value of the individual; and correcting the fitness value of the individual to a set minimum positive value when the total processing time of the individual exceeds the threshold.

[0020] In a second aspect, the present application provides an automatic tape laying path planning system based on material utilization, comprising a processor and a memory, wherein the memory stores computer program instructions which, when executed by the processor, implement the above-mentioned automatic tape laying path planning method based on material utilization.

[0021] By using the above technical solution, the above-mentioned automatic tape laying path planning method based on material utilization is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is manufactured according to the memory and the processor, and convenient use is achieved.

[0022] The present application has the advantages that the part layout scheme is taken as a dynamic gene and integrated into the iteration process of the genetic algorithm, the part layout is intelligently fine adjusted during optimization by using the geometric agility and local optimizable degree, and the layout and path are co-evolved, so that the utilization of expensive composite materials is improved under the premise that the processing time meets the actual production constraints. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a flowchart schematically showing an automatic tape laying path planning method based on material utilization in the present application; Figure 2 is a schematic diagram showing the relationship between area, shape factor and geometric agility. DETAILED DESCRIPTION

[0024] The present application discloses an automatic tape laying path planning method based on material utilization, which is described with reference toFigure 1 comprising steps S1-S4: S1: obtaining geometric information of parts to be processed and basic information of a tape laying device; generating an initial layout scheme based on a heuristic algorithm, and constructing an initial population of a genetic algorithm containing a hybrid coding structure.

[0025] It should be noted that in the path planning of the automatic tape laying process of composite materials, the pros and cons of the layout scheme directly determine the upper limit of the utilization rate of the expensive prepreg material. The traditional path planning method usually regards the layout as a preposed and static hard constraint. Once the layout is determined, the subsequent path optimization can only be carried out on the fixed part position, resulting in that the algorithm can only search for optimization in the local space and it is difficult to break through the bottleneck of material utilization rate. Therefore, the hybrid coding structure containing the layout scheme, the sequence in the scheme, the device allocation and the global processing sequence is adopted, the geometric information of the layout scheme is directly embedded into the chromosome of the genetic algorithm, so that it is changed from a static constraint to an evolvable entity. This design not only allows the algorithm to fine-tune the layout while searching for the path, but also provides a basic interface for data operation for the subsequent introduction of a dynamic layout optimization operator, so that the algorithm can adaptively adjust the layout of the layout according to the remaining space.

[0026] Specifically, the geometric information of the parts to be processed and the basic information of the tape laying device are obtained; an initial layout scheme is generated based on a heuristic algorithm, and an initial population of a genetic algorithm containing a hybrid coding structure is constructed, comprising: Obtaining the contour coordinates, area and perimeter of all parts to be processed; obtaining the specification information of the available plate and the number and performance parameters of the tape laying device.

[0027] An initial layout scheme is generated by using the best adaptation method, specifically: first, all parts to be processed are sorted in descending order of area; then, for each part to be processed, all blank areas on the plate where the part can be placed are traversed, and the fragmentation degree of the remaining space after the part is placed is calculated. For example, the minimum side length of the remaining rectangle is taken as the fragmentation degree, and the position with the minimum fragmentation degree of the remaining space is selected for placement; the process is repeated until all parts are placed, and an initial layout scheme is obtained.

[0028] Based on the initial layout scheme, an initial population of a genetic algorithm is randomly generated. It should be noted that each chromosome in the initial population copies the part position data in the initial layout scheme as the initial gene, and the processing sequence and device allocation gene are randomly generated. In the subsequent evolution process, the layout data of each body will evolve independently.

[0029] At this point, the data acquisition and population initialization are completed.

[0030] S2: in the iteration process of the genetic algorithm, a dynamic layout optimization operator is introduced; based on the geometric characteristics of any part, the geometric agility of the part is calculated; the plate area is divided into several local areas, based on the geometric agility of the neighborhood parts of any local area and the vacant area area of the local area, the local optimizable degree of the local area is obtained; based on the local optimizable degree, the final fine-tuning disturbance vector is generated to adjust the layout scheme of the current individual, and the adjusted layout scheme is obtained.

[0031] It should be noted that when the layout scheme is dynamically adjusted, not all parts are suitable as fillers to fill the gaps, and not all vacant areas have optimization value. If large-size or simple-shaped parts are moved blindly, it is often difficult to fill irregular small gaps, and new collisions are easily caused; at the same time, if a vacant area is surrounded by rigid large parts, the optimization feasibility is low. Therefore, the dynamic layout optimization operator is designed to first select flexible parts through geometric agility, and then locate the areas with optimization value combined with local optimization potential, so as to realize accurate layout fine-tuning.

[0032] Specifically, the geometric agility of any part is calculated based on the geometric characteristics of the part, including: It should be noted that the smaller the area of the part, the less space it occupies, and the easier it is to be inserted into the gap formed by other parts; at the same time, the more complex the shape of the part, the more concave and convex characteristics of its contour make it have more fitting possibilities when rotating, and it can enter irregular gaps like a puzzle. Figure 1 Therefore, the geometric agility index is constructed by combining the geometric characteristics of the part.

[0033] The geometric agility of any part satisfies the expression: ; In the formula, denotes the geometric agility of the i-th part; denotes the area of the i-th part; denotes the circumference of the i-th part; denotes the circumference of the i-th part.

[0034] In the formula, denotes the size factor, which increases with the decrease of , reflecting that the larger the part area, the weaker the mobility and the weaker the geometric agility; The ratio of the circumference and the area of the part represents the shape factor, which is 1 for a circular shape, and increases with the increase of the shape complexity, such as long strip, star, etc., the ratio of the circumference to the area increases, and the value increases; The larger, the more the i-th part has the characteristics of small size and complex shape, and the more likely it is to be filled as a filler in layout optimization.

[0035] It should be noted that, as Figure 2 The figure shows the area, shape factor and geometric agility of each part, and the combined value distribution of the geometric agility.

[0036] It should be noted that the geometric agility index can obtain the most suitable adjusted part, and if a global search is performed on the entire plate, the local area with both gaps and easy to be filled also needs to be further identified. Therefore, the present application combines spatial information and geometric agility to evaluate the optimization possibility of each local area on the plate.

[0037] Preferably, the plate area is divided into a plurality of local areas, and the local optimization degree of the local area is obtained based on the geometric agility of the neighborhood parts of the local area and the vacant area of the local area, including: The plate area is grid divided, and each grid cell is a local area. It should be noted that since the plate is a continuous space, it is difficult to define the boundary when evaluating the vacant area directly on the continuous domain. Therefore, the present application uses gridding processing to discretize the continuous space. Regarding the size setting of the grid cell, if the grid is too large, it cannot capture the small gap characteristics; if the grid is too small, it will generate a large calculation overhead. Therefore, the length of the grid cell is set to 10mm, for example, the smallest part of the envelope rectangle in the set of parts to be processed, to ensure that the grid has sufficient resolution to identify the available filling space.

[0038] It should be noted that after the local area is determined, in order to identify the most likely optimized area, not only the vacant area of the local area needs to be calculated, but also the effectiveness of the vacant area of the local area needs to be analyzed, that is, whether the part can be placed. Therefore, the optimization value of the local area is determined by the vacant area and the flexibility of the neighborhood parts. Only when a large vacant area is surrounded by small parts with high agility, it is the most effective to fill the area by fine-tuning the neighbors. Therefore, the local optimization degree of any local area is calculated.

[0039] The area of the region not covered by any part in any local area is obtained, which is recorded as the vacant area of the local area.

[0040] All parts with geometric overlap or boundary contact with any local area are obtained, which are recorded as the adjacent parts of the local area.

[0041] The local optimization degree of any local area satisfies the expression: ​ ; wherein, represents the local optimizability of the rth local region; represents the vacant area of the rth local region; represents the number of parts that are adjacent to or partially overlap with the local region ; represents the geometric agility of the jth adjacent part of the rth local region; represents a very small positive value, used to avoid division by zero when the number of parts that are adjacent to or partially overlap with the local region is 0; .

[0042] wherein, represents the average geometric agility of all adjacent parts of the rth local region, which reflects the mobilizability of parts around the rth local region; represents the weighted amplification of the vacant space by the mobilizability, and the larger the value is, the greater the rth local region is not only in a large vacant area, but also in a mobilizable adjacent part, which can be optimized in layout.

[0043] It should be noted that further, the local optimizability of the local region needs to be converted into specific optimization operations to calculate the degree of movement and rotation of the parts, so as to reduce the gap.

[0044] Preferably, based on the local optimizability, a final fine-tuning disturbance vector is generated to adjust the layout scheme of the current individual, including: The local region with the largest local optimizability is taken as the target region.

[0045] The part with the largest geometric agility in the adjacent parts of the target region is taken as the target part.

[0046] It should be noted that for specific movement instructions, the present application sets a search range for moving the target part to the target vacant region within the search range without collision.

[0047] The current position of the target part is taken as the center to perform a local search within the search range to generate a plurality of candidate fine-tuning disturbance vectors of the target part, and the search range includes a translation search range and a rotation search range. For example, the translation search range is set to be within a circular region with a radius of , and the rotation search range is set to be within a sector region with an included angle of . The candidate fine-tuning disturbance vectors are, for example, , .

[0048] The final fine-tuning disturbance vector of the target part satisfies the expression: ; In the formula, represents the final fine-tuning disturbance vector of the target part; represents the optimal translation component of the target part; represents the optimal rotation component of the target part; represents the set of candidate fine-tuning disturbance vectors of the target part; represents the reduction amount of the empty area in the target area after applying the final candidate fine-tuning disturbance vector to the target part; represents the candidate fine-tuning disturbance vector that maximizes the reduction amount of the empty area in the target area among all candidate fine-tuning disturbance vectors.

[0049] At this point, the dynamic optimization of the layout arrangement is completed.

[0050] S3: Based on the adjusted layout scheme and the machining path, the material utilization rate and the total machining time are calculated; the machining time threshold is set as a feasibility constraint, and the fitness function is constructed with the material utilization rate as the core to obtain the fitness value of each individual in the population.

[0051] It should be noted that in the industrial production environment, the optimization target is often not flat. For example, the production time of a shift is a fixed hard boundary, and any scheme that exceeds this time, no matter how much material is saved, is not executable. Therefore, the present application adopts a constrained optimization model, first ensures that the machining efficiency of the scheme meets the time constraint, and then finds the scheme with the highest material utilization rate among all feasible schemes. Convert the multi-objective problem into a single-objective problem with constraints, making the evaluation standard more objective and the logic clearer.

[0052] Specifically, based on the adjusted layout scheme and the machining path, the material utilization rate and the total machining time are calculated; the machining time threshold is set as a feasibility constraint, and the fitness function is constructed with the material utilization rate as the core to obtain the fitness value of each individual in the population, including: Based on the layout scheme of the current individual, the total area of all parts and the minimum envelope rectangle area of the plate are obtained, and the material utilization rate is calculated.

[0053] Based on the machining order and the equipment allocation scheme of the current individual, the strip laying process is simulated, the effective laying time and the empty travel time of the strip laying head are counted, and the total machining time is calculated.

[0054] The machining time threshold is set. It should be noted that the machining time threshold is determined based on the performance of the initial scheme. Exemplarily, the total machining time of the initial layout scheme is taken as the reference, and the machining time threshold is set to 1.1 times the total machining time of the initial layout scheme.

[0055] The fitness value of any individual satisfies the expression: ; In the formula, denotes the fitness value of the i-th individual; denotes the material utilization rate of the i-th individual; denotes the total processing time of the i-th individual; denotes the material utilization rate of the i-th individual; denotes the total processing time of the i-th individual; denotes the material utilization rate of the i-th individual; denotes the processing time threshold; denotes a very small positive value, for example, .

[0056] In the formula, A feasibility threshold is constructed, when the total processing time of an individual does not exceed the processing time threshold, the individual is determined as a feasible solution, and its fitness value is directly equal to its material utilization rate, in this case, the driving force of the algorithm is to select the highest material utilization rate among all time-qualified solutions; when the total processing time of an individual exceeds the processing time threshold, the individual is determined as an infeasible solution, and its fitness value is assigned to a very small positive value , which ensures that any processing timeout solution, no matter how high its material utilization rate is, will be eliminated with a high probability in the selection and elimination process of the genetic algorithm, thereby guiding the population to converge in the direction of meeting the time constraint.

[0057] At this point, the fitness value of each individual is obtained.

[0058] S4: Based on the fitness value of each individual, selection, crossover and mutation operations are performed, and the population is updated in combination with a dynamic layout optimization operator; it is judged whether the iteration termination condition is met, if met, the optimal individual is decoded, and the final tape laying path planning scheme is output.

[0059] It should be noted that the core of the genetic algorithm is to search for the optimal solution through the evolution mechanism of survival of the fittest. The present application retains excellent individuals with high fitness values through selection operation; the genetic fragments of different excellent individuals are recombined through crossover operation in order to produce better offspring; mutation operation introduces diversity to the population to prevent the algorithm from converging to a local optimal solution too early. In particular, the present application uses the dynamic layout optimization operator as a mutation operation, which cooperates with the conventional random mutation to jointly drive the population to evolve towards the global optimal solution.

[0060] Specifically, based on the fitness value of each individual, selection, crossover and mutation operations are performed, and the population is updated in combination with a dynamic layout optimization operator; it is judged whether the iteration termination condition is met, if met, the optimal individual is decoded, and the final tape laying path planning scheme is output, including: The roulette wheel selection method is used to select parent individuals from the current population.

[0061] The selected parent individuals are subjected to multi-point crossover operation and conventional mutation operation to generate a child population. Exemplarily, the conventional mutation includes applying Gaussian perturbation to the layout coordinate genes and performing random exchange on the processing order genes.

[0062] A portion of the individuals in the child population are selected with a preset probability, and a dynamic layout optimization operator is executed to perform deep optimization on the layout scheme of the individuals.

[0063] The child population generated after the above operation is combined with the parent population, and an elitist reservation strategy is adopted to select the individuals with the highest fitness to form a new generation population.

[0064] The above operation is repeatedly executed until a preset maximum iteration number is reached or the optimal fitness value of the population no longer has a significant improvement within a preset iteration number. Exemplarily, the maximum iteration number is 500 generations, and the preset iteration number is 50 generations.

[0065] The individual with the highest fitness value in the final population is selected as the optimal individual. Based on the chromosome data of the optimal individual, the final layout layout diagram, part processing order table and equipment allocation instruction are decoded, and the machining code directly used for numerical control equipment is generated accordingly.

[0066] At this point, the tape laying path planning is completed.

[0067] The embodiment of the application also discloses an automatic tape laying path planning system based on material utilization, which comprises a processor and a memory, and the memory stores computer program instructions which realize the automatic tape laying path planning method based on material utilization according to the application when executed by the processor.

[0068] The system also comprises other components such as a communication bus and a communication interface which are well known to those skilled in the art, and the settings and functions thereof are known in the art, so they will not be described here.

[0069] Although the present specification has shown and described several embodiments of the present application, it will be apparent to those skilled in the art that many modifications, changes and substitutions can be made without departing from the idea and spirit of the present application. It should be understood that various alternatives to the embodiments of the present application described herein can be employed in practicing the present application.

Claims

1. An automatic tape laying path planning method based on material utilization rate, characterized in that, include: Obtain the geometric information of all parts to be processed and the performance parameters of the tape laying equipment; generate an initial layout scheme containing the position information of each part based on a heuristic algorithm, and construct the initial population of the genetic algorithm by combining the random processing order and equipment allocation; During the iteration of the genetic algorithm, a dynamic layout optimization operator is executed to adjust the initial layout scheme to obtain the adjusted layout scheme. The dynamic layout optimization operator includes: calculating the geometric agility of each part, wherein the geometric agility is negatively correlated with the part area and positively correlated with the square of the part perimeter. The board material is divided into multiple local regions; the local optimizability of each local region is calculated, and the local optimizability is positively correlated with the average value of the vacant area of ​​the corresponding local region and the geometric agility of its adjacent parts; the local region with the highest local optimizability is selected as the target region, and the adjacent part with the highest geometric agility in the target region is selected as the target part; the target part is moved within a set search range to reduce the vacant area of ​​the target region; the material utilization rate is calculated based on the adjusted layout scheme, and the fitness value of each individual is obtained; the population is operated on based on the fitness value until the termination condition is met, and the individual with the highest fitness value is decoded to obtain the final tape laying path.

2. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, The heuristic algorithm is specifically the optimal fit method, including: Sort all parts to be processed in descending order of area; for each sorted part, traverse all available blank areas on the board and place it in the position that minimizes the fragmentation of the remaining blank areas; repeat the placement process until all parts have been placed to obtain the initial layout scheme.

3. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, The geometric agility satisfies the expression: ； In the formula, This represents the geometric agility of the i-th part; This represents the area of ​​the i-th part; Let represent the perimeter of the i-th part; It represents pi (π).

4. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, The degree of local optimizability satisfies the expression: ； In the formula, This represents the degree of local optimizability of the r-th local region; This represents the vacant area of ​​the r-th local region; Indicates all and local regions The number of adjacent or partially overlapping parts; This represents the geometric agility of the j-th adjacent part in the r-th local region; This indicates a very small positive value.

5. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, The process of dividing the board into multiple local areas includes: The board area is divided into grids, and each grid cell is treated as a local area.

6. The automatic tape laying path planning method based on material utilization rate according to claim 5, characterized in that, The grid division includes: The side length of the grid cell is the minimum value of the short side length of the envelope rectangle of all parts to be processed.

7. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, Moving the target part within the set search range to reduce the empty area of ​​the target region includes: Centered on the current position of the target part, multiple candidate fine-tuning perturbation vectors are generated within a set search range. Each vector contains translation and rotation components. Each candidate fine-tuning perturbation vector is applied to the target part, and the reduction in the empty area of ​​the target region is calculated. The candidate fine-tuning perturbation vector that maximizes the reduction is selected as the final fine-tuning perturbation vector, and the target part is adjusted accordingly.

8. The automatic tape laying path planning method based on material utilization rate according to claim 7, characterized in that, The search range includes: by The search range for circular translation with radius, and The search range is a sector-shaped rotation with an included angle.

9. The automatic tape laying path planning method based on material utilization rate according to claim 1, characterized in that, The process of obtaining the fitness values ​​of each individual includes: The material utilization rate and total processing time are calculated based on the adjusted layout scheme; a threshold for the total processing time is set; the material utilization rate is used as the fitness value of an individual; when the total processing time of an individual exceeds the threshold, its fitness value is corrected to the set minimum positive value.

10. An automatic tape laying path planning system based on material utilization, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement an automatic tape laying path planning method based on material utilization as described in any one of claims 1-9.

Images