Panel furniture workpiece typesetting method based on improved genetic algorithm

Abstract

The invention relates to the technical field of panel processing, in particular to a panel furniture workpiece typesetting method based on an improved genetic algorithm, which comprises the following steps: acquiring parameter information of a to-be-typeset workpiece; and performing classification based on the parameter information of all the workpieces to be typeset to obtain a plurality of workpiece categories, endowing each workpiece category with a unique type code, constructing an initial population according to the category and the number of the workpieces to be typeset, and inputting the initial population into the improved genetic algorithm to obtain an optimal chromosome. According to the method, the workpieces with the same size and shape are classified into workpieces with the same specification, and a repeated gene coding mode is adopted, so that the defect that actual repeated chromosomes are generated when a plurality of workpieces with the same specification are processed in a traditional unique coding mode is effectively avoided, and the algorithm efficiency is improved. And secondly, in the gene crossover operation, an improved ordered crossover and order crossover strategy is introduced, and a random deletion mechanism is combined, so that the algorithm population diversity and the solution space coverage are effectively improved, and the search divergence and convergence efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of sheet metal processing technology. More specifically, this invention relates to a method for layout of panel furniture workpieces based on an improved genetic algorithm. Background Technology

[0002] With the continuous advancement of "whole-plant intelligent" construction in modern furniture factories, processes such as cutting, drilling, edge banding, labeling, and sorting in panel furniture manufacturing have gradually achieved equipment automation and information system linkage, forming a continuous, efficient, and low-manual-intervention flexible production line. In this highly collaborative manufacturing environment, the processing sequence of workpieces at each stage is no longer a local optimization goal, but has become a key factor affecting the cycle time and collaborative efficiency of the entire production line. In the actual production process, a common phenomenon is that multiple workpieces with the same size and shape will appear in a single layout task. The reasons are as follows: the symmetry of workpieces in panel furniture order splitting (such as left and right side panels, upper and lower shelves, etc., which will generate multiple workpieces with completely identical geometric dimensions during order splitting); customers produce the same specifications of products in batches with engineering orders. As the production scale expands and the processing of the same product orders from different customers becomes concentrated, even if there are workpieces of the same specifications in different work orders.

[0003] Due to the factors mentioned above, a typical typesetting task often involves hundreds or thousands of workpieces, a significant proportion of which are repetitive workpieces with the same size and shape. However, in the chromosome encoding structure of traditional genetic algorithms, to maintain gene uniqueness, it is usually required that each gene (i.e., each workpiece) in the chromosome must not appear repeatedly. The repeated independent encoding of a large number of workpieces of the same specification creates the drawback of actual duplicate chromosomes. Furthermore, traditional crossover operations are prone to crossover failure or require extensive backtracking corrections when processing workpiece sequences with high repetition rates, impacting processing efficiency. Summary of the Invention

[0004] This invention provides a workpiece layout method for panel furniture based on an improved genetic algorithm, aiming to solve the problem that crossover operations in related technologies are prone to failure due to repetition conflicts or require a large amount of backtracking correction when processing workpiece sequences with high repetition, thus affecting processing efficiency.

[0005] This invention provides a method for layout of panel furniture workpieces based on an improved genetic algorithm, comprising: acquiring parameter information of the workpieces to be laid out; classifying all workpieces based on their parameter information to obtain multiple workpiece categories, assigning a unique type code to each workpiece category, constructing an initial population according to the category and quantity of the workpieces to be laid out, and inputting it into a genetic algorithm to obtain the optimal chromosome, wherein the optimal chromosome is the optimal layout scheme; wherein the gene crossover method in the genetic algorithm includes: ordered crossover and sequential crossover; ordered crossover refers to randomly selecting a gene segment as a retained segment from two parent chromosomes, and sequentially filling the empty spaces with the remaining genes after removing duplicate genes from the other parent to generate offspring; sequential crossover refers to selecting several gene positions from the parent chromosomes, deleting duplicate genes, and sequentially inserting the crossover point genes into the other chromosome to generate offspring. By classifying workpieces of the same size and shape into the same type and encoding them with duplicate genes, the coding redundancy of chromosomes is significantly reduced, and the execution efficiency of genetic operations is improved. Meanwhile, in the crossover operation, the traditional ordered crossover and sequential crossover methods were improved, and a strategy of randomly removing duplicate genes was introduced to enhance chromosome diversity and the algorithm's ability to explore the solution space.

[0006] Furthermore, the process includes: constructing the fitness function in the genetic algorithm; performing selection operations based on the fitness function values ​​of each chromosome to select chromosomes for the next generation; iterating through crossover, mutation, and population updates until a set number of generations or fitness convergence is achieved; and then outputting the optimal chromosome, which is the optimal typesetting scheme. The typesetting optimization process based on the genetic algorithm, evaluating scheme quality through the fitness function, and iteratively evolving through selection, crossover, and mutation operations, effectively improves the overall utilization and computational efficiency of the typesetting scheme.

[0007] Furthermore, the fitness function in the genetic algorithm is constructed, including: the fitness function reflecting the material utilization factor, batch dispersion, and hole position disorder factor of each chromosome; wherein, the batch dispersion of the chromosome reflects the concentration of similar workpieces to be laid out, and the hole position disorder factor of the chromosome reflects the continuity of hole positions of adjacent workpieces to be laid out. By comprehensively considering material utilization, workpiece concentration, and hole position continuity, the processing efficiency, delivery consistency, and production stability of the layout scheme are effectively improved.

[0008] Furthermore, the calculation method for the fitness function value of each chromosome includes: assigning corresponding weights to the plate utilization factor, batch dispersion degree, and hole position disorder factor of each chromosome; weighting the chromosome with its own weights; and finally using the weighted sum as the fitness function value of each chromosome. Different production scenarios have different focuses on the layout objectives. By adjusting the weights corresponding to each factor, the genetic algorithm can be flexibly guided to favor improving material utilization, reducing batch disorder, or optimizing the drilling process, thereby enhancing the algorithm's adaptability to actual process constraints and management strategies.

[0009] Furthermore, the formula for calculating the fitness function value includes: In the formula, This represents the fitness function value of the i-th chromosome. This represents the plate utilization factor of the i-th chromosome. This indicates the weight corresponding to the board utilization factor. This indicates the batch dispersion of the i-th chromosome. The weights representing the degree of batch dispersion This represents the pore location disorder factor of the i-th chromosome. This represents the weight corresponding to the hole position disorder factor.

[0010] Furthermore, the board utilization factor includes: calculating the ratio of the total area of ​​all workpieces to be laid out in the chromosome to the total area of ​​the board, and using the normalized ratio as the board utilization factor of the chromosome.

[0011] Furthermore, the batch dispersion of the chromosome is calculated by sequentially traversing the batches of each workpiece to be laid out in the chromosome based on binary pairs. If the batches of workpieces to be laid out in a binary pair belong to the same batch, the value of that binary pair is 0; otherwise, the value of the binary pair is 1. The cumulative value of all binary pairs is calculated, and the normalized cumulative value is used as the batch dispersion of the chromosome. By traversing the binary pairs composed of workpiece batches in the chromosome, the dispersion between different batches is evaluated, and the normalized result is used as a metric. This effectively controls the concentrated arrangement of workpiece batches, thereby improving production efficiency and the orderliness of subsequent management.

[0012] Furthermore, achieving convergence of a set number of generations or fitness includes: the genetic iteration reaching a preset maximum number of generations or the change in the optimal fitness function value for several consecutive generations being less than a preset threshold.

[0013] Furthermore, chromosomes that will enter the next generation can be selected, including chromosomes selected based on roulette or tournaments.

[0014] Furthermore, clustering is performed based on the parameter information of all workpieces to be laid out, including: using the DBSCAN clustering algorithm to cluster the parameter information of all workpieces to be laid out.

[0015] Beneficial effects (i) By grouping workpieces of the same size and shape into workpieces of the same specification and adopting a repetitive gene encoding method, the drawback of the traditional unique encoding method in processing multiple workpieces of the same specification, which produces actual duplicate chromosomes, is effectively avoided, thus improving the efficiency of the algorithm. Secondly, in the gene crossover operation, an improved ordered crossover and sequential crossover strategy is introduced, combined with a random deletion mechanism, which effectively improves the diversity of the algorithm population and the coverage of the solution space, and enhances the divergence and convergence efficiency of the search.

[0016] (ii) By constructing a multi-objective fitness function that integrates the material utilization factor, batch dispersion degree and hole position disorder factor, and supports flexible weighting according to the layout objective, it can achieve multi-dimensional comprehensive optimization of material utilization, production cycle and processing path smoothness. It can intelligently and efficiently output the optimal layout scheme with high material utilization, reasonable workpiece grouping and good process continuity, thereby improving the overall intelligence level of the layout system and the operating efficiency of the production line. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the optimal typesetting scheme obtained according to an embodiment of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0019] like Figure 1 As shown, S101: Obtain parameter information of the workpiece to be laid out.

[0020] In one embodiment, the workpiece to be laid out refers to furniture panels that have not yet been arranged on the board and are awaiting layout optimization and cutting. Then, the parameter information of the workpiece to be laid out is obtained. For example, as shown in the figure, the smart factory supports retrieving workpiece data (parameter information) by scanning CAD QR codes or ERP system codes. The parameter information includes workpiece dimensions, workpiece shape, and number of holes. The workpiece dimensions include the length, width, and thickness, usually in millimeters (mm), and are the basis for calculating the board area and layout position during layout. The workpiece shape refers to the boundary contour shape of the workpiece, such as rectangular, L-shaped, or T-shaped, used to determine whether it can be classified as a workpiece of the same specification. The number of holes refers to the total number of preset processing holes on the workpiece. Obtaining the parameter information of each workpiece to be laid out facilitates subsequent classification.

[0021] In one embodiment, in actual panel furniture production, a layout task often involves a large number of workpieces to be laid out. These workpieces are automatically generated by the design and order splitting system based on user customization requirements, product structure, and process parameters. According to actual statistics, in the case of large-scale engineering orders or multiple small orders being combined for production, a single layout task may contain hundreds to thousands of workpieces to be laid out, and many of these workpieces are identical in size and shape. These identical workpieces may come from symmetrical structures within the same work order (such as left and right door panels, upper and lower shelves), or they may come from identical components across multiple different work orders (such as standard shelves or back panels shared by multiple wardrobes). This repetitiveness directly reflects the increased standardization and modularity of panel furniture product structures.

[0022] However, in traditional typesetting optimization systems, genetic algorithms often construct chromosomes using a "workpiece-by-workpiece independent encoding" approach. This means that each workpiece to be typed, regardless of whether it is repeated, is assigned a unique gene position. While this method has some expressive power for small-scale problems, it suffers from the drawback of having virtually duplicate chromosomes when dealing with typesetting tasks involving tens of thousands of workpieces. This leads to an exponential increase in the algorithm's search space, making crossover and mutation operations redundant and inefficient, significantly reducing the algorithm's convergence speed, and severely impacting the overall optimization performance.

[0023] In one embodiment, to solve the above problem, it is necessary to classify the parameter information of all workpieces to be typed to obtain multiple workpiece categories, assign a unique type code to each workpiece category, construct an initial population based on the category and quantity of the workpieces to be typed, and input it into the improved genetic algorithm to obtain the optimal chromosome, where the optimal chromosome is the optimal typesetting scheme.

[0024] S102: Classify all workpieces to be typed to obtain multiple workpiece categories.

[0025] In one embodiment, after obtaining parameter information, feature extraction and classification are performed on the size and shape characteristics of the workpieces to be laid out. All workpieces with the same size and shape (or approximately the same within a set tolerance range) are grouped into the same category using a clustering algorithm or rule matching, forming several categories of workpieces of the same specification. The clustering algorithm can utilize the DBSCAN clustering algorithm, which, through density analysis and tolerance control, can automatically divide a large number of workpieces to be laid out into multiple categories of workpieces of the same specification.

[0026] S103: Construct the initial population.

[0027] After obtaining the parameter information, feature extraction and classification are performed on the size and shape characteristics of the workpieces. Using clustering algorithms or rule matching, all workpieces with the same size and shape (or approximately the same within a set tolerance range) are grouped into the same category, forming several "workpiece categories of the same specification". Each category is assigned a unique type code, which serves as the basic unit of chromosome genes in the subsequent genetic algorithm.

[0028] After classifying the workpieces and determining the number of workpieces in each category, an initial population is constructed. Specifically, initial chromosome sequences are generated according to the coding and quantity of each workpiece category. Each chromosome represents a layout scheme, and the number of repetitions of the same gene in the sequence corresponds to the number of workpieces in that category. For example, with 12 workpieces to be layoutd, they are divided into 6 categories, with 2 workpieces of the same specification in each category. We encode genes 1 to 6 for each workpiece category, resulting in the initial chromosome coding gene "112233445566". This repetitive gene expression method, compared to the traditional "single workpiece unique gene" structure, effectively avoids the drawback of the traditional unique coding method generating actual duplicate chromosomes when dealing with multiple workpieces of the same specification, reduces unnecessary genetic operation computation, and improves the stability and evolutionary efficiency of the population structure.

[0029] S104: Improve the gene crossover method in the genetic algorithm.

[0030] In one embodiment, the gene crossover method in the genetic algorithm is improved, including improvements to both the ordered crossover method and the sequential crossover method. Specifically, a random deletion strategy is introduced, that is, when deleting duplicate genes that already exist in the crossover segment, one gene is randomly selected from all candidates for removal, thereby expanding the search space and enhancing the divergence and diversity of the algorithm.

[0031] In one embodiment, the ordered crossover method is improved by: obtaining two parent chromosomes, randomly selecting two crossover points in the two parent chromosomes, retaining the genes in the segment (the genes between the two crossover points) as the retained segment of the initial offspring; in another parent chromosome, finding and deleting the same genes as in the retained segment, and filling the remaining genes into the empty spaces of the offspring in sequence to generate a new chromosome.

[0032] For example, the two parent chromosomes are P1 and P2, where P1 is "112233445566" and P2 is "654321654321". Two intersection points are selected, and genes within those segments are retained. For P1, the retained gene segment is "23344", resulting in the initialized offspring chromosome C1 as "---23344----". Then, genes identical to "23344" are deleted from P2 (P2 has two genes with the number "2", randomly deleting one "2" increases the search's divergence), resulting in P2 as "65---165--21". The genes from "65---165--21" are then sequentially inserted into the empty gene slot of "---23344----", resulting in the offspring chromosome C1 as "651233446521". Similarly, another offspring chromosome C2 can be obtained.

[0033] In one embodiment, the improved crossover method includes: obtaining two parent chromosomes, randomly selecting four gene loci from the two parent chromosomes to obtain crossover genes for each parent chromosome; for any gene in a parent chromosome, deleting genes that are duplicated at the crossover loci of the other parent chromosome, and filling the empty spaces of the deleted genes with the crossover genes of the other parent chromosome in sequence to obtain a daughter chromosome; similarly, another daughter chromosome can be obtained.

[0034] For example, the two parent chromosomes are P1 and P2, where P1 is "112233445566" and P2 is "654321654321". The crossover gene in P1 is "2255", and the crossover gene in P2 is "4343". The crossover positions correspond to those in P1 and P2. In P1, the crossover genes from P2 are sequentially deleted to obtain the initial C1, which is "1122----5566". The gaps in C1 are then filled with "4343" according to the crossover gene sequence from P2, resulting in the offspring chromosome C1 being "112243435566". Similarly, by deleting the crossover gene "2255" from P1 in P2, we obtain the initial C2 as "6-43-16-43-1". Then, we fill the empty C2 with "2255" according to the crossover gene sequence of P1, resulting in another offspring chromosome C2 as "624321654351".

[0035] In summary, by structurally improving the ordered and sequential crossover methods in genetic algorithms and combining them with a random deletion strategy, the problems of crossover failure and lack of diversity in traditional algorithms when dealing with chromosomes containing duplicate genes are solved, significantly improving the solution space coverage and convergence performance in typesetting optimization tasks.

[0036] S105: Obtain the optimal typesetting scheme.

[0037] In one embodiment, a fitness function is constructed in the genetic algorithm. Based on the fitness function value of each chromosome, a selection operation is performed to screen out chromosomes that will enter the next generation (using roulette or tournament methods). After crossover, mutation, and population update, the algorithm iterates until a set number of generations or fitness convergence is reached. Then, the optimal chromosome is output, which is the optimal layout scheme. The conditions for outputting the optimal chromosome include: the genetic iteration reaches a preset maximum number of generations or the change in the optimal fitness function value for several consecutive generations is less than a preset threshold.

[0038] Specifically, the fitness function in the genetic algorithm is constructed as follows: the fitness function reflects the size of the board utilization factor, batch dispersion degree, and hole position disorder factor of each chromosome; wherein, the board utilization factor of the chromosome reflects the board utilization rate of the workpiece to be laid out, the batch dispersion degree of the chromosome reflects the concentration of similar workpieces to be laid out, and the hole position disorder factor of the chromosome reflects the continuity of the hole positions of adjacent workpieces to be laid out.

[0039] In one embodiment, the plate utilization factor, batch dispersion degree, and pore location disorder factor of each chromosome are added together, and the sum is used as the fitness function value of each chromosome.

[0040] In one embodiment, calculating the board utilization factor of a chromosome includes: calculating the ratio of the total area of ​​all workpieces to be laid out in the chromosome to the total area of ​​the board, and using the normalized ratio as the board utilization factor of the chromosome. Calculating the batch dispersion of a chromosome includes: sequentially traversing the batches of each workpiece to be laid out in the chromosome using binary pairs; if the batches of the workpieces to be laid out in a binary pair belong to the same batch, the value of that binary pair is 0; otherwise, the value of the binary pair is 1. The sum of the values ​​of all binary pairs is calculated, and the normalized sum is used as the batch dispersion of the chromosome. The smaller the batch dispersion value, the more concentrated and uniform the similar workpieces are, which is beneficial for assembly line or batch packaging. The hole position disorder factor of the chromosome is calculated by: sequentially traversing the information of each workpiece to be typed in the chromosome using binary pairs. If all workpieces to be typed in the binary pair need to be punched, the value of the binary pair is 0; otherwise, the value of the binary pair is 1. The sum of the values ​​of all binary pairs is calculated, and the normalized sum is used as the hole position disorder factor of the chromosome. The smaller the hole position disorder factor, the better the continuity of the hole position process, which reduces the frequency of subsequent tool changes and improves the processing efficiency.

[0041] In another embodiment, the plate utilization factor, batch dispersion degree, and pore location disorder factor of each chromosome are assigned corresponding weights. Each chromosome is then weighted using its own weights, and the weighted sum is used as the fitness function value for each chromosome. The calculation formula is as follows: In the formula, This represents the fitness function value of the i-th chromosome. This represents the plate utilization factor of the i-th chromosome. This indicates the weight corresponding to the board utilization factor. This indicates the batch dispersion of the i-th chromosome. The weights representing the degree of batch dispersion This represents the pore location disorder factor of the i-th chromosome. This represents the weight corresponding to the hole position disorder factor.

[0042] The specific weighting method is as follows: If you want to prioritize the utilization rate of the board material during the layout process, and secondly, the batch concentration of the workpieces to be laid out, then you can set the weight corresponding to the board material utilization factor to the maximum, making the weight of the board material utilization factor greater than the weight corresponding to the batch dispersion, and the weight corresponding to the batch dispersion greater than the weight corresponding to the hole position disorder factor. For example: the weight corresponding to the board material utilization factor is 0.5, the weight corresponding to the batch dispersion is 0.3, and the weight corresponding to the hole position disorder factor is 0.2.

[0043] Ultimately, after multiple rounds of evolution and iteration, the chromosome with the maximum fitness function value was selected as the optimal typesetting scheme for the current typesetting task. Its corresponding typesetting scheme has comprehensive advantages such as high material utilization, reasonable work order grouping, and smooth punching path.

[0044] The embodiments described above are merely examples of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A method for layout of panel furniture workpieces based on an improved genetic algorithm, characterized in that, include: Obtain the parameter information of the workpiece to be laid out; Based on the parameter information of all workpieces to be laid out, multiple workpiece categories are obtained, and each workpiece category is assigned a unique type code. An initial population is constructed according to the category and quantity of the workpieces to be laid out, and then input into a genetic algorithm to obtain the optimal chromosome, where the optimal chromosome is the optimal layout scheme. The gene crossover methods in the genetic algorithm include: ordered crossover and sequential crossover. Ordered crossover refers to randomly selecting a gene segment from two parent chromosomes as a retained segment, and then filling the gaps in the other parent chromosome with the remaining genes after removing duplicate genes in order to generate offspring. Sequential crossover refers to selecting several gene sites in the parent chromosomes, deleting duplicate genes, and then inserting the crossover site genes into the other chromosome in order to generate offspring.

2. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 1, characterized in that, Also includes: The fitness function in the genetic algorithm is constructed, and a selection operation is performed based on the fitness function value of each chromosome to select chromosomes to enter the next generation. After crossover, mutation and population update, the algorithm is iterated until the set number of generations or fitness convergence is reached, and then the optimal chromosome is output. The optimal chromosome is the optimal layout scheme.

3. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 1, characterized in that, Constructing the fitness function in the genetic algorithm includes: The fitness function reflects the plate utilization factor, batch dispersion, and pore location disorder factor of each chromosome. Among them, the material utilization factor of chromosomes reflects the material utilization rate of the workpiece to be laid out, the batch dispersion of chromosomes reflects the concentration of similar workpieces to be laid out, and the hole position disorder factor of chromosomes reflects the continuity of hole positions of adjacent workpieces to be laid out.

4. The panel furniture workpiece layout method based on an improved genetic algorithm according to claim 3, characterized in that, Methods for calculating fitness function values ​​include: Each chromosome is assigned a corresponding weight for its plate utilization factor, batch dispersion degree, and pore location disorder factor. Each chromosome is then weighted using its own weight, and the weighted sum is used as the fitness function value of each chromosome.

5. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 4, characterized in that, The formula for calculating the fitness function value includes: ； In the formula, This represents the fitness function value of the i-th chromosome. This represents the plate utilization factor of the i-th chromosome. This indicates the weight corresponding to the board utilization factor. This indicates the batch dispersion of the i-th chromosome. The weights representing the degree of batch dispersion This represents the pore location disorder factor of the i-th chromosome. This represents the weight corresponding to the hole position disorder factor.

6. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 5, characterized in that, The utilization factors of the board material include: Calculate the ratio of the total area of ​​all workpieces to be laid out in the chromosome to the total area of ​​the board material, and use the normalized ratio as the board material utilization factor of the chromosome.

7. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 5, characterized in that, Calculate the batch dispersion of chromosomes, including: Based on the binary tuple approach, the batches of each workpiece to be typed in the chromosome are traversed sequentially. If the batches of the workpieces to be typed in the binary tuple are from the same batch, the value of the binary tuple is 0; otherwise, the value of the binary tuple is 1. The cumulative value of all binary tuples is calculated, and the normalized cumulative value is used as the batch dispersion of the chromosome.

8. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 2, characterized in that, Achieving convergence at a predetermined algebraic or fitness level includes: Genetic iteration reaches a preset maximum number of generations or the change in the optimal fitness function value is less than a preset threshold after several consecutive generations.

9. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 2, characterized in that, Chromosomes that are selected to proceed to the next generation include: Chromosomes are selected for the next generation based on roulette or tournament selection.

10. The method for layout of panel furniture workpieces based on an improved genetic algorithm according to claim 1, characterized in that, Clustering is performed based on the parameter information of all workpieces to be laid out, including: The DBSCAN clustering algorithm is used to cluster the parameter information of all workpieces to be typed.

Images