A fabric layout optimization method and device

Abstract

The application provides a fabric layout optimization method and device, the method comprising: obtaining to-be-cut fabric data, to-be-laid paper sample data and pre-set layout constraint conditions; generating a certain number of initial layout schemes randomly according to the obtained information to form an initial population; calculating the fitness function value corresponding to each initial layout scheme according to a fitness function, selecting a plurality of initial layout schemes in the initial population as parent individuals according to the fitness function value, performing a crossover operation on the parent individuals to generate new child individuals; performing a mutation operation on the child individuals, iteratively updating a mutation population, and calculating the fitness function value of the individuals in the mutation population until the fitness function value improvement rate is less than a preset value, outputting the iteration result, taking the iteration result as an intermediate layout scheme and evaluating the intermediate layout scheme, and outputting an evaluation result; adjusting and optimizing the intermediate layout scheme according to the evaluation result and a pre-set evaluation benchmark to obtain a final layout scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of garment processing, and particularly relates to a fabric layout optimization method and device. BACKGROUND

[0002] Numerical control cutting beds are widely used in the field of textile and garment, especially in garment manufacturing and bag making. With the continuous progress of technology and the continuous expansion of the market, the performance and function of numerical control cutting beds are also improving and perfecting. At present, there are many powerful numerical control cutting bed manufacturing enterprises in China, and their products have shown strong competitiveness in the international market.

[0003] In the prior art, the layout kernel algorithm of the numerical control cutting bed mostly adopts the minimum envelope rectangle algorithm. This algorithm solves the minimum envelope rectangle of each paper pattern (or cutting piece), and optimizes the arrangement of these rectangles on the fabric to maximize the reduction of waste. Although this algorithm has fast calculation speed, it may not achieve the best layout effect when dealing with some special shapes or irregular fabrics, resulting in scattered layout and causing fabric waste in the actual cutting process. Therefore, in order to better adapt to complex pattern features and improve the utilization rate of fabric, designing a more advanced layout method has become an important research direction of layout optimization. SUMMARY

[0004] The present application provides a fabric layout optimization method and device to solve at least one of the above problems.

[0005] The present application provides a fabric layout optimization method, which comprises:

[0006] Obtaining cutting fabric data, paper pattern data to be laid out, and pre-set layout constraints;

[0007] According to the cutting fabric data and the paper pattern data to be laid out, and the pre-set layout constraints, a certain number of initial layout schemes are randomly generated to form an initial population;

[0008] According to the fitness function, the fitness function value corresponding to each initial layout scheme is calculated, and according to the fitness function value, several initial layout schemes in the initial population are selected as parent individuals, and the parent individuals are subjected to a cross operation to generate new child individuals;

[0009] The child individuals are subjected to a mutation operation, and the mutation population is iteratively updated, and the fitness function values of the individuals in the mutation population are calculated until the fitness function value improvement rate is less than a preset value, and the iteration result is output as an intermediate layout scheme;

[0010] The intermediate layout scheme is evaluated, and the evaluation result is output;

[0011] According to the evaluation result and a preset evaluation benchmark, the intermediate layout scheme is adjusted and optimized to obtain a final layout scheme.

[0012] Further, the to-be-cut fabric data includes fabric type, size, area, and coordinates of a cuttable area and coordinates of a defect area in a two-dimensional coordinate system.

[0013] The coordinates of the defect area are vertex coordinates of a defect area marked by a polygon.

[0014] The to-be-layout paper sample data includes a number of to-be-layout paper samples, numbers of the to-be-layout paper samples, polygon vertex coordinates of the to-be-layout paper samples, side lengths of the to-be-layout paper samples, and areas of the to-be-layout paper samples.

[0015] Further, before generating a certain number of initial layout schemes according to the to-be-cut fabric data and the to-be-layout paper sample data and preset layout constraint data to form an initial population, a unified coordinate system is established, and all polygon vertex coordinates of the to-be-layout paper samples are converted into absolute coordinates relative to a lower left corner (0, 0) of the to-be-cut fabric for normalization processing.

[0016] Further, the evaluation of the intermediate layout scheme includes:

[0017] Fabric utilization rate and cutting cost are calculated.

[0018]

[0019] Cutting cost = unit cutting cost × total cutting length + unit tool changing cost × tool changing times.

[0020] The total cutting length is a total side length of the to-be-layout paper samples participating in layout.

[0021] Further, a fitness function value of the layout scheme is calculated according to a fitness function, and a number of initial layout schemes are selected as parents according to the fitness function value, specifically including:

[0022] The calculated fitness is sorted from high to low, and the top 5% of the initial layout schemes are selected as the parents.

[0023] Further, the preset layout constraint condition is set according to historical layout data.

[0024] The preset layout constraint condition includes a layout direction, a spacing, a fabric utilization rate, and a rotatable angle of the paper sample.

[0025] Further, the fitness function is specifically:

[0026] Fit(x) = a x (total area of paper sample to be laid out / area of fabric to be cut) - b x cutting cost + g x constraint penalty term;

[0027] Wherein, x represents an initial layout scheme, a is the weight coefficient of fabric utilization rate; b is the weight coefficient of cutting cost, g is the weight coefficient of constraint penalty term.

[0028]

[0029] Wherein, Fit(x1) is the fitness function value of the tth generation, Fit(x2) is the fitness function value of the t+1th generation.

[0030] Further, the parent individuals are subjected to a crossover operation to generate new offspring individuals, specifically comprising:

[0031] Randomly selecting two parents, exchanging the paper sample position information in the two parents, and finally obtaining a plurality of crossover-transformed offspring individuals.

[0032] Further, the offspring individuals are subjected to a mutation operation, and the mutation population is iteratively updated, specifically comprising:

[0033] The paper samples in the offspring individuals are subjected to position fine-tuning and angle rotation to form a new mutation population.

[0034] On the other hand, the present application also provides a fabric layout optimization device, which comprises:

[0035] An information acquisition module is configured to acquire fabric data to be cut, paper sample data to be laid out, and pre-set layout constraints;

[0036] A control module is configured to randomly generate a certain number of initial layout schemes according to the fabric data to be cut and the paper sample data to be laid out, and the pre-set layout constraints, to form an initial population;

[0037] The control module is further configured to calculate the fitness function value corresponding to each initial layout scheme according to a fitness function, to select a plurality of initial layout schemes as parent individuals in the initial population according to the fitness function value, to generate new offspring individuals by subjecting the parent individuals to a crossover operation, and to calculate the fitness function value of the offspring individuals.

[0038] The control module is further configured to perform a mutation operation on the offspring individuals, to iteratively update the mutation population, to calculate the fitness function value of the individuals in the mutation population, and to output the iteration result as an intermediate layout scheme until the fitness function value improvement rate is less than a preset value.

[0039] The control module is further configured to evaluate the intermediate layout scheme and output an evaluation result.

[0040] The control module is further configured to adjust and optimize the intermediate layout scheme according to the evaluation result and a preset evaluation criterion, so as to obtain a final layout scheme.

[0041] Compared with the prior art, the present application has the following advantages:

[0042] The present application provides a fabric layout optimization method and device, which can obtain data of fabric to be cut, data of paper pattern to be laid out and preset layout constraint conditions; a certain number of initial layout schemes are randomly generated according to the data of fabric to be cut, the data of paper pattern to be laid out and the preset layout constraint conditions, so as to form an initial population; the fitness function value of the layout scheme is calculated according to a fitness function, and a plurality of initial layout schemes are selected as parents according to the fitness function value; a cross operation is performed on the parent individuals, so as to generate new child individuals; a mutation operation is performed on the child individuals, and the mutation population is iteratively updated until the fitness function value improvement rate is less than a preset value; the iteration result is output as an intermediate layout scheme; the intermediate layout scheme is evaluated, and an evaluation result is output; the intermediate layout scheme is adjusted and optimized as necessary according to the evaluation result and a preset evaluation criterion, so as to obtain a final layout scheme; and the final layout scheme is converted into a CAD file. The method of the present application not only improves fabric utilization, but also reduces cutting cost, greatly shortens layout time and improves production efficiency. In addition, due to the generalization ability of the genetic algorithm, the method has good adaptability to different types of fabric and paper pattern.

[0043] It can be seen that, compared with the prior art, the present application has outstanding and substantial characteristics and significant progress, and the beneficial effects of its implementation are also obvious. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 FIG. 1 is a flowchart of a fabric layout optimization method according to the present application.

[0045] Figure 2 FIG. 2 is a layout region diagram according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described in detail below with reference to the drawings.

[0047] Figure 1 FIG. 1 is a flowchart of a fabric layout optimization method according to the present application.

[0048] As shown in FIG. 1, the fabric layout optimization method provided by the present application includes the following steps. Figure 1

[0049] ​S1, obtain data of a fabric to be cut, data of a paper pattern to be laid out and a pre-set layout constraint condition.

[0050] S2, randomly generate a certain number of initial layout schemes according to the data of the fabric to be cut, the data of the paper pattern to be laid out and the pre-set layout constraint condition, and form an initial population.

[0051] S3, calculate a fitness function value corresponding to each initial layout scheme according to a fitness function, select a plurality of initial layout schemes in the initial population as parent individuals according to the fitness function value, and generate new child individuals by performing a crossover operation on the parent individuals.

[0052] S4, perform a mutation operation on the child individuals, iteratively update a mutation population, and calculate a fitness function value of an individual in the mutation population until a fitness function value improvement rate is less than a preset value, output an iteration result, and take the iteration result as an intermediate layout scheme.

[0053] S5, evaluate the intermediate layout scheme and output an evaluation result.

[0054] S6, adjust and optimize the intermediate layout scheme according to the evaluation result and a pre-set evaluation benchmark to obtain a final layout scheme.

[0055] The method of the application not only improves fabric utilization, but also reduces cutting cost, greatly shortens layout time and improves production efficiency. In addition, due to the generalization ability of the genetic algorithm, the method has good adaptability to different types of fabrics and paper patterns.

[0056] In an embodiment of the application,

[0057] S1, obtain data of a fabric to be cut, data of a paper pattern to be laid out and a pre-set layout constraint condition.

[0058] The data of the fabric to be cut includes fabric type, size, area, and coordinates of a cuttable area and coordinates of a defect area in a two-dimensional coordinate system.

[0059] The coordinates of the defect area are vertex coordinates of a defect area marked by a polygon.

[0060] The data of the paper pattern to be laid out includes the number of paper patterns to be laid out, the number of paper patterns to be laid out, the polygon vertex coordinates of the paper patterns to be laid out, the side length of the paper patterns to be laid out and the area of the paper patterns to be laid out.

[0061] The pre-set layout constraint condition is set according to historical layout data.

[0062] The pre-set layout constraint condition includes the layout direction, spacing, fabric utilization and rotatable angle of the paper pattern.

[0063] First, a unified coordinate system is established, and the coordinates of the polygon vertices of all the paper patterns to be laid out are converted into absolute coordinates relative to the lower left corner (0, 0) of the fabric to be cut, and normalized.

[0064] S2, randomly generate a certain number of initial layout schemes according to the data of the fabric to be cut and the data of the paper patterns to be laid out and the pre-set layout constraint conditions, and form an initial population.

[0065] S3, calculate the fitness function value corresponding to each initial layout scheme according to the fitness function, select a number of initial layout schemes as parent individuals in the initial population according to the fitness function value, and perform a crossover operation on the parent individuals to generate new offspring individuals. The crossover operation can simulate the process of gene recombination and increase the diversity of the population.

[0066] Preferably, the fitness function is specifically:

[0067] Fit(x) = a x (total area of paper patterns to be laid out / area of fabric to be cut) - b x cutting cost + g x constraint penalty term.

[0068] Where x represents an initial layout scheme, a is the weight coefficient of fabric utilization rate, b is the weight coefficient of cutting cost, and g is the weight coefficient of constraint penalty term.

[0069] a, b and g are used to adjust the relative importance of fabric utilization rate, cutting cost and constraint penalty term in the fitness function. The constraint penalty term is a penalty value set according to the layout constraint condition. If the constraint condition is not met, the penalty term is a very large negative number, otherwise it is 0.

[0070] Preferably, the fitness function value of the layout scheme is calculated according to the fitness function, and a number of initial layout schemes are selected as parents according to the fitness function value, specifically including:

[0071] Sort the calculated fitness from high to low, and select the top 5% of initial layout schemes as parents.

[0072] Preferably, the parent individuals are subjected to a crossover operation to generate new offspring individuals, specifically including:

[0073] Randomly select two parents, exchange the paper pattern position information in the two parents, and finally obtain a plurality of crossover transformed offspring individuals.

[0074] S4, performing a mutation operation on the offspring individuals, constantly iterating and updating the mutation population, and calculating the fitness function value of the individuals in the mutation population until the fitness function value improvement rate is less than a preset value, outputting the iteration result, and taking the iteration result as an intermediate layout scheme.

[0075] Preferably, the mutation operation on the offspring individuals constantly iterates and updates the mutation population, specifically including:

[0076] Position fine-tuning and angle rotation are performed on the paper samples in the offspring individuals to form a new mutation population.

[0077] The mutation operation on the offspring individuals can change the genes of the individuals with a certain probability, thereby introducing a new solution space region. The mutation operation helps to avoid the algorithm from falling into a local optimal solution.

[0078] Preferably,

[0079] Wherein, Fit(x1) is the tth generation fitness function value, and Fit(x2) is the t+1th generation fitness function value.

[0080] S5, evaluating the intermediate layout scheme and outputting an evaluation result.

[0081] The evaluation includes calculating the fabric utilization rate and the cutting cost.

[0082]

[0083] The cutting cost = unit length cutting cost x total cutting length + unit tool changing cost x tool changing times;

[0084] Wherein, the total cutting length is the total length of the paper samples to be laid out participating in the layout,

[0085] The unit length cutting cost, the unit tool changing cost and the tool changing times are obtained according to historical layout data.

[0086] S6, according to the evaluation result and a preset evaluation benchmark, performing necessary adjustment and optimization on the intermediate layout scheme to obtain a final layout scheme, as shown in Figure 2 for subsequent cutting and manufacturing.

[0087] On the other hand, the present application also provides a fabric layout optimization device, the device comprising:

[0088] An information acquisition module is configured to acquire data of the fabric to be cut, data of the paper samples to be laid out, and a pre-set layout constraint condition.

[0089] The control module is configured to generate a plurality of initial layout schemes according to the data of the fabric to be cut, the data of the paper pattern to be laid out, and preset layout constraint conditions, and form an initial population;

[0090] The control module is further configured to calculate a fitness function value corresponding to each of the initial layout schemes according to a fitness function, select a plurality of initial layout schemes as parent individuals from the initial population according to the fitness function values, and perform a crossover operation on the parent individuals to generate new child individuals.

[0091] The control module is further configured to perform a mutation operation on the child individuals, iteratively update a mutation population, and calculate fitness function values of the individuals in the mutation population until a fitness function value improvement rate is less than a preset value, output an iteration result, and take the iteration result as an intermediate layout scheme.

[0092] The control module is further configured to perform an evaluation on the intermediate layout scheme and output an evaluation result.

[0093] The control module is further configured to adjust and optimize the intermediate layout scheme according to the evaluation result and a preset evaluation benchmark to obtain a final layout scheme.

[0094] The same or similar parts among the various embodiments in the specification can be referred to each other.

[0095] The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for optimizing fabric layout, characterized in that, The methods include: Acquire the fabric data to be cut, the paper pattern data to be laid out, and the pre-set layout constraints; Based on the fabric data to be cut, the paper pattern data to be laid out, and the pre-set layout constraints, a certain number of initial layout schemes are randomly generated to form an initial population. Calculate the fitness function value corresponding to each initial layout scheme according to the fitness function value, select several initial layout schemes as parent individuals in the initial population according to the fitness function value, and perform crossover operation on the parent individuals to generate new offspring individuals; The offspring individuals are subjected to mutation operations, the mutated population is continuously updated iteratively, and the fitness function value of individuals in the mutated population is calculated until the fitness function value improvement rate is less than a preset value. The iteration result is then output and the iteration result is used as an intermediate layout scheme. The intermediate layout scheme is evaluated, and the evaluation results are output. Based on the evaluation results and the preset evaluation criteria, the intermediate layout scheme is adjusted and optimized to obtain the final layout scheme; The fitness function is specifically: Fit(x) = α × (total area of ​​paper patterns to be typed / area of ​​fabric to be cut) − β × cutting cost + γ × constraint penalty term; Where x represents an initial layout scheme, α is the weighting coefficient of fabric utilization, β is the weighting coefficient of cutting cost, and γ is the weighting coefficient of constraint penalty term. ； Where Fit(x1) is the fitness function value of generation t, and Fit(x2) is the fitness function value of generation t+1.

2. The fabric layout optimization method according to claim 1, characterized in that, The fabric data to be cut includes fabric type, size, area, and coordinates of the cuttable area and defective area in a two-dimensional coordinate system; The coordinates of the defective area are the vertex coordinates of the defective area marked with a polygon; The data of the paper pattern to be laid out includes the quantity of the paper pattern to be laid out, the paper pattern number, the vertex coordinates of the polygon of the paper pattern to be laid out, the side length of the paper pattern to be laid out, and the area of ​​the paper pattern to be laid out.

3. The fabric layout optimization method according to claim 2, characterized in that, Before generating a certain number of initial layout schemes based on the fabric data to be cut, the paper pattern data to be laid out, and the pre-set layout constraint data, and forming the initial population, a unified coordinate system is first established, and the coordinates of all the polygon vertices of the paper pattern to be laid out are converted into absolute coordinates relative to the lower left corner (0,0) of the fabric to be cut, and then normalized.

4. The fabric layout optimization method according to claim 3, characterized in that, The intermediate layout scheme is evaluated, including: Calculate fabric utilization and cutting costs; ； Cutting cost = Cutting cost per unit length × Total cutting length + Cutting cost per unit × Number of cuts; The total cutting length is the total side length of the paper pattern to be typed.

5. The fabric layout optimization method according to claim 3, characterized in that, The fitness function value of the typesetting scheme is calculated based on the fitness function, and several initial typesetting schemes are selected as parent schemes based on the fitness function value, specifically including: Sort the calculated fitness scores from high to low, and select the top 5% of initial layout schemes as the parent generation.

6. The fabric layout optimization method according to claim 1, characterized in that, The pre-set layout constraints are set based on historical layout data; Pre-set layout constraints include the layout direction of the paper pattern, spacing, fabric utilization, and rotation angle.

7. The fabric layout optimization method according to claim 1, characterized in that, The step of performing a crossover operation on the parent individual to generate a new child individual specifically includes: Two parent generations are randomly selected, and the position information of the paper patterns in the two parent generations is swapped to obtain multiple cross-transformed offspring individuals.

8. The fabric layout optimization method according to claim 1, characterized in that, The process of performing mutation operations on the offspring individuals and continuously iterating and updating the mutated population specifically includes: The paper patterns in the offspring individuals are slightly adjusted in position and rotated in angle to form a new variant population.

9. A fabric layout optimization device, employing the fabric layout optimization method according to any one of claims 1-8, characterized in that, The device includes: The information acquisition module is used to acquire data on the fabric to be cut, data on the paper pattern to be laid out, and pre-set layout constraints. The control module is used to randomly generate a certain number of initial layout schemes based on the fabric data to be cut, the paper pattern data to be laid out, and the pre-set layout constraints, forming an initial population. The control module is also used to calculate the fitness function value corresponding to each initial layout scheme according to the fitness function, select several initial layout schemes as parent individuals in the initial population according to the fitness function value, perform crossover operation on the parent individuals, and generate new offspring individuals; The control module is also used to perform mutation operations on the offspring individuals, continuously iterate and update the mutated population, and calculate the fitness function value of individuals in the mutated population until the fitness function value improvement rate is less than a preset value, output the iteration result, and use the iteration result as an intermediate layout scheme. The control module is also used to evaluate the intermediate layout scheme and output the evaluation results; The control module is also used to adjust and optimize the intermediate layout scheme according to the evaluation results and preset evaluation criteria to obtain the final layout scheme.

Images