Fabric cutting path planning method, device and equipment and storage medium

Abstract

The invention relates to the technical field of fabric processing, in particular to a fabric cutting path planning method and device, equipment and a storage medium. Performing enhancement processing on the historical cutting path data based on a multi-point crossing method to obtain an enhanced chromosome population; constructing a path planning model based on a preset genetics algorithm and the enhanced chromosome population; generating a cutting total path based on the path planning model, the fabric characteristic data and the fabric image; adjusting the total cutting path based on a preset bounding box algorithm, the fabric characteristic data, the cutting tool state data and the cutting table component coordinate data to obtain an optimized total cutting path; by combining the fabric characteristics and the equipment state to plan the path, the cutting efficiency and the fabric utilization rate can be effectively improved, the cost is reduced, the service life of a cutter is prolonged, the system environment adaptability is enhanced, the cutting accuracy and stability are guaranteed, and the intelligent and efficient development of the fabric cutting industry is promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fabric processing, and particularly relates to a fabric cutting path planning method, device, equipment and storage medium. BACKGROUND

[0002] In the field of fabric processing, efficient and accurate cutting path planning is a key link to improve production efficiency and reduce costs. Traditional fabric cutting path planning relies on manual experience design, which is not only time-consuming and labor-intensive, but also difficult to deal with complex cutting patterns, leading to low fabric utilization and low cutting efficiency. With the development of computer technology, some enterprises have introduced cutting path planning methods based on historical data, but such methods only simply reuse historical paths, lack deep mining and optimization of data, and are difficult to adapt to different fabrics and cutting requirements. At the same time, the existing path planning scheme based on genetic algorithm mostly uses single-point crossover in the crossover operation, which is difficult to fully integrate the excellent gene fragments in the historical data, resulting in insufficient adaptability of the generated path planning model. In addition, in the path adjustment link, most technologies only consider a single factor, such as not comprehensively considering the key factors such as fabric characteristics and cutting tool state, so that the final cutting path has defects such as high collision risk and poor cutting quality. Therefore, there is an urgent need for a fabric cutting path planning scheme that can deeply mine the value of historical data and comprehensively optimize multiple factors to solve the shortcomings of the existing technology. SUMMARY

[0003] To solve the above-mentioned shortcomings of the prior art, the present application provides a fabric cutting path planning method.

[0004] To solve the above-mentioned technical problems, the technical solutions adopted by the present application are as follows:

[0005] The application discloses a fabric cutting path planning method, which comprises the following steps: obtaining historical cutting path data; performing enhancement processing on the historical cutting path data based on a multi-point crossover method to obtain an enhanced chromosome population; constructing a path planning model based on a preset genetic algorithm and the enhanced chromosome population; obtaining fabric characteristic data and a fabric image; generating a total cutting path based on the path planning model, the fabric characteristic data and the fabric image; obtaining cutting tool state data and cutting table component coordinate data; and adjusting the total cutting path based on a preset bounding box algorithm, the fabric characteristic data, the cutting tool state data and the cutting table component coordinate data to obtain an optimized total cutting path.

[0006] Further, the enhancement processing on the historical cutting path data based on the multi-point crossover method to obtain the enhanced chromosome population comprises the following steps: generating a primary population based on a preset random function and the historical cutting path data; evaluating the primary population based on a preset fitness function to obtain reciprocal evaluation coefficients; performing feature selection on the primary population according to the reciprocal evaluation coefficients to obtain parent chromosomes; performing a crossover operation on the parent chromosomes based on the multi-point crossover method to obtain a child chromosome population; and performing a mutation operation on the child chromosome population to obtain the enhanced chromosome population.

[0007] Further, the mutation operation on the child chromosome population to obtain the enhanced chromosome population comprises the following steps: randomly selecting multiple site gene data from the child chromosome population; calculating a value set based on a preset minimum mutation probability and a preset maximum mutation probability; and performing a mutation operation on the child chromosome population according to the value set and the multiple site gene data to obtain the enhanced chromosome population.

[0008] Further, the generating the total cutting path based on the path planning model, the fabric characteristic data and the fabric image comprises: performing feature analysis on the fabric characteristic data to obtain physical features, mechanical features and chemical features; performing region division on the fabric image according to the physical features, the mechanical features and the chemical features to obtain a set of sub-image regions; planning a cutting path for each sub-region based on the path planning model to obtain a set of cutting sub-paths; and performing total path planning based on a preset depth-first search algorithm and the set of cutting sub-paths to obtain the total cutting path.

[0009] Further, the performing total path planning based on the preset depth-first search algorithm and the set of cutting sub-paths to obtain the total cutting path comprises: calculating a length of each cutting sub-path in the set of cutting sub-paths based on a preset Euclidean distance formula to obtain a set of cutting sub-path lengths; calculating a first index value and a second index value according to the set of cutting sub-paths; creating a two-dimensional array according to the first index value and the second index value; performing depth-first search on the set of cutting sub-path lengths based on the depth-first search algorithm and the two-dimensional array to obtain a path length combination search analysis result; and generating the total cutting path according to the path length combination search analysis result and the set of cutting sub-paths.

[0010] Further, the adjusting the total cutting path based on the preset bounding box algorithm, the fabric characteristic data, the cutting tool state data and the cutting table component coordinate data to obtain an optimized total cutting path comprises: analyzing a preset initial cutting speed according to the fabric characteristic data and the cutting tool state data to obtain a first adjustment coefficient and a second adjustment coefficient; adjusting the initial cutting speed according to the first adjustment coefficient and the second adjustment coefficient to obtain an updated cutting speed; adjusting the total cutting path based on the preset bounding box algorithm, the updated cutting speed and the cutting table component coordinate data to obtain a path adjustment offset; and adjusting the total cutting path according to the path adjustment offset to obtain the optimized total cutting path.

[0011] Further, the bounding box algorithm, the updated cutting speed, and the cutting table component coordinate data are used to adjust the cutting total path to obtain a path adjustment offset, including: analyzing the cutting table component coordinate data to obtain three-dimensional geometric information; analyzing the three-dimensional geometric information based on a preset reconfigurability constraint function to obtain an information domain score; determining whether the information domain score is less than a preset information domain score threshold; when the information domain score is less than the information domain score threshold, obtaining a viewpoint data group and calculating the viewpoint data group to obtain a constraint coefficient; modifying the three-dimensional geometric information based on a preset sampling normal vector, the constraint coefficient, and a preset adjustable coefficient to obtain modified three-dimensional geometric information; setting the modified three-dimensional geometric information as the three-dimensional geometric information, and returning to analyze the three-dimensional geometric information based on the reconfigurability constraint function until a preset iteration stop condition is met, to obtain corresponding modified three-dimensional geometric information; modeling according to the modified three-dimensional geometric information and a preset point cloud processing algorithm to obtain a cutting machine model; performing collision analysis based on the bounding box algorithm, the cutting machine model, and the cutting total path to obtain a collision node set and a node offset set; and generating the path adjustment offset based on a linear fitting method, the updated cutting speed, the collision node set, and the node offset set.

[0012] Further, a fabric cutting device includes a first data acquisition module configured to acquire historical cutting path data; a data enhancement processing module configured to enhance the historical cutting path data based on a multi-point intersection method to obtain an enhanced chromosome population; a model construction module configured to construct a path planning model based on a preset genetic algorithm and the enhanced chromosome population; a second data acquisition module configured to acquire fabric characteristic data and a fabric image; a path planning module configured to generate a cutting total path based on the path planning model, the fabric characteristic data, and the fabric image; and a third data acquisition module configured to acquire cutting tool state data and cutting table component coordinate data; and a path optimization module configured to adjust the cutting total path based on a preset bounding box algorithm, the fabric characteristic data, the cutting tool state data, and the cutting table component coordinate data to obtain an optimized cutting total path.

[0013] Further, a fabric cutting path planning device includes a memory and at least one processor, the memory storing instructions; and the at least one processor invoking the instructions in the memory to cause the fabric cutting path planning method to perform each step of the fabric cutting path planning method in any one of the above embodiments.

[0014] Further, a computer readable storage medium stores instructions, and the instructions are executed by a processor to implement each step of the fabric cutting path planning method in any one of the above embodiments.

[0015] The face fabric cutting path planning method has the beneficial effects that:

[0016] In the data processing and model construction layer, historical cutting path data is acquired and a multi-point intersection method is used for enhanced processing to fully tap the data value, increase the diversity of the chromosome population, and combine a path planning model constructed by a genetic algorithm to better adapt to various fabric cutting requirements and have strong generalization and optimization capabilities; in the path generation stage, fabric characteristic data and image information are fused to make the generated cutting total path fully conform to the actual situation of the fabric and greatly improve the rationality and feasibility of the path; in the path optimization link, based on a bounding box algorithm, the fabric characteristics, tool state, and cutting table component coordinate data are comprehensively considered to scientifically adjust the path, effectively avoid collision with the cutting table components, and reduce tool wear; overall, the scheme can improve cutting efficiency, reduce invalid cutting and equipment adjustment time, significantly improve fabric utilization, reduce production cost, prolong tool service life, reduce replacement cost, enhance the adaptability of the system to different fabrics and cutting environments, guarantee cutting accuracy and stability, improve cutting quality, and have important significance for promoting the intelligent and efficient development of the fabric cutting industry. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

[0018] Figure 1 A first flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0019] Figure 2 A second flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0020] Figure 3 A third flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0021] Figure 4 A fourth flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0022] Figure 5 A fifth flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0023] Figure 6 A sixth flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0024] Figure 7 A seventh flowchart of a fabric cutting path planning method provided for an embodiment of the present application;

[0025] Figure 8 A structural schematic diagram of a fabric cutting path planning device provided by an embodiment of the present application is shown in the figure.

[0026] Figure 9 A structural schematic diagram of a fabric cutting path planning device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0027] The technical solutions of the present application will be described clearly and completely below in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0028] The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprise" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0029] For the sake of understanding, the specific flow of the embodiments of the present application will be described below. Please refer to Figure 1 An embodiment of a fabric cutting path planning method of the present application comprises the following steps.

[0030] 101. Obtain historical cutting path data;

[0031] 102. Perform enhancement processing on the historical cutting path data based on a multi-point intersection method to obtain an enhanced chromosome population;

[0032] 103. Construct a path planning model based on a preset genetic algorithm and the enhanced chromosome population;

[0033] In this embodiment, historical cutting path data is acquired to provide an empirical basis for subsequent planning. The historical cutting path data is enhanced by a multi-point crossover method. Compared with single-point crossover, multi-point crossover can more fully combine excellent gene fragments in the historical path. By exchanging gene information at multiple locations, the diversity of the chromosome population is effectively increased, the potential value of the data is tapped, and a foundation is laid for constructing a high-quality path planning model. Genetic algorithms simulate the biological evolution process and continuously optimize the model through selection, crossover, mutation, and other operations. The chromosome population carries more abundant gene information, enabling the constructed path planning model to better adapt to different fabric cutting needs and have stronger generalization ability and optimization potential.

[0034] 104. Obtain fabric characteristic data and fabric image;

[0035] 105. Generate a total cutting path based on the path planning model, the fabric characteristic data, and the fabric image;

[0036] In this embodiment, fabric characteristic data (such as texture, elasticity, thickness, etc.) and image information can reflect the actual situation of the fabric. The model generates a path in combination with these data, fully considers the actual performance of the fabric during cutting, and makes the generated total cutting path more in line with actual production needs, improving the rationality and feasibility of the path.

[0037] 106. Obtain cutting tool state data and cutting table component coordinate data;

[0038] 107. Adjust the total cutting path based on a preset bounding box algorithm, fabric characteristic data, cutting tool state data, and cutting table component coordinate data to obtain an optimized total cutting path;

[0039] In this embodiment, the bounding box algorithm is used to detect the collision risk of the path and the cutting table components. In combination with fabric characteristics and tool states, the path can be adjusted more scientifically according to factors such as the vulnerability of the fabric and the sharpness of the tool, avoiding collisions and reducing tool wear, and ultimately obtaining an optimized total cutting path.

[0040] In the embodiment, at the data processing and model building level, the historical cutting path data is acquired and a multi-point cross method is used for enhanced processing to fully tap the data value, increase the chromosome population diversity, and combine a path planning model constructed by a genetic algorithm to better adapt to cutting requirements of various fabrics and have strong generalization and optimization capabilities. At the path generation stage, fabric characteristic data and image information are fused to make the generated cutting total path fully conform to the actual situation of the fabric and greatly improve the rationality and feasibility of the path. At the path optimization stage, based on the bounding box algorithm, the fabric characteristics, tool state and cutting table component coordinate data are comprehensively considered to scientifically adjust the path, effectively avoid collision with the cutting table components and reduce tool wear. Overall, the scheme can improve the cutting efficiency, reduce invalid cutting and equipment adjustment time, significantly improve the fabric utilization rate and reduce production costs, prolong the service life of the tool and reduce replacement costs, enhance the adaptability of the system to different fabrics and cutting environments, ensure cutting accuracy and stability, improve cutting quality, and have important significance for promoting the intelligent and efficient development of the fabric cutting industry.

[0041] Referring to Figure 2 In the second embodiment of the fabric cutting path planning method in the embodiment of the present application, the following steps are included.

[0042] 201. Generating a primary population based on a preset random function and historical cutting path data;

[0043] In the embodiment, historical experience and random exploration are combined. The random function ensures the initial diversity of the population and avoids the algorithm from falling into local search. The historical cutting path data gives the primary population certain prior knowledge, so that the population has a certain directionality at the initial stage of evolution and provides a basis for subsequent optimization.

[0044] 202. Evaluating the primary population based on a preset fitness function to obtain the reciprocal of the evaluation coefficient;

[0045] 203. Selecting features of the primary population according to the reciprocal of the evaluation coefficient to obtain parent chromosomes;

[0046] In the embodiment, the fitness function comprehensively considers key indicators (such as path length and fabric utilization rate) in cutting path planning, maps the chromosomes to the reciprocal of the evaluation coefficient, and the higher the numerical value, the better the performance of the chromosome in actual cutting. According to the reciprocal of the evaluation coefficient, features are selected to preferentially retain chromosomes with high fitness as parents to ensure that excellent genes are passed on and guide the population to evolve in a better direction.

[0047] 204. Cross-operating the parent chromosomes based on a multi-point cross method to obtain a population of child chromosomes;

[0048] In the embodiment, multiple-point crossover is performed on the parent chromosomes, compared with single-point crossover, gene fragments can be exchanged at multiple positions at the same time, which can more fully recombine the excellent characteristics of the parent chromosomes, break the linkage effect between genes, produce more diversified offspring chromosome combinations, and improve population diversity, which provides the possibility for the algorithm to explore a wider solution space;

[0049] 205, a mutation operation is performed on the offspring chromosome population to obtain an enhanced chromosome population;

[0050] In the embodiment, the mutation operation is performed on the offspring chromosome population to randomly change part of the genes of the chromosomes, which introduces new gene information into the population and avoids premature convergence of the algorithm to a local optimal solution;

[0051] In the embodiment, the initial population is generated by fusing a random function and historical cutting path data, which not only ensures the diversity of the initial population and avoids falling into a local optimum, but also provides prior knowledge and a clear evolution direction, thereby laying a solid foundation for subsequent optimization. The fitness function based on comprehensive consideration of key indicators such as path length and fabric utilization rate is used for evaluation and feature selection, so as to ensure that excellent genes with high fitness are retained and inherited, and the population is guided to evolve towards a better solution. The multi-point crossover operation breaks through the limitation of single-point crossover, exchanges gene fragments at multiple positions, fully recombines the excellent characteristics of the parent, enriches the offspring chromosome combinations, and expands the search space of the algorithm. The mutation operation randomly changes the genes, which introduces new information into the population and prevents the algorithm from converging too early. Overall, the scheme effectively improves the optimization accuracy of the path planning, enhances the adaptability and robustness of the algorithm to complex scenarios, improves the search efficiency, reduces invalid exploration, can quickly output a high-quality cutting path scheme, reduces production cost, and has important significance for improving the intelligent level of fabric cutting production.

[0052] Please refer to Figure 3 The third embodiment of the fabric cutting path planning method in the embodiment of the application comprises the following steps:

[0053] 301, a plurality of site gene data are randomly selected from the offspring chromosome population;

[0054] In the embodiment, this random selection method can ensure that the mutation operation covers different regions of the chromosomes, avoid the limitations caused by fixed position mutation, and introduce diversified gene combinations into the population by operating on multiple sites;

[0055] 302, a value set is calculated based on a preset minimum mutation probability and a preset maximum mutation probability;

[0056] In the embodiment, the process provides a probability regulation basis for the mutation operation, and the minimum mutation probability can prevent excessive mutation sparseness and ensure the algorithm to continuously introduce new gene information in the evolution process. The maximum mutation probability avoids excessive mutation frequency and maintains the stability of the excellent gene structure in the population. The calculation of the value set enables the mutation probability to be dynamically adjusted within a reasonable range, thereby enhancing the adaptability of the algorithm to different evolution stages.

[0057] 303. performing a mutation operation on the offspring chromosome population according to the value set and the plurality of locus gene data to obtain an enhanced chromosome population;

[0058] In the embodiment, in the specific implementation, for each selected locus gene, the mutation probability is determined according to the value set, and a random process is used to determine whether the locus gene is mutated. If the mutation occurs, the gene value is adjusted according to the problem characteristics (for example, the discrete gene is replaced by other legal values, and the continuous gene is changed within a certain range). This mutation method combining probability regulation and locus selection can ensure the randomness of the mutation and reasonably constrain the algorithm state, and finally obtain an enhanced chromosome population with better gene structure and stronger diversity.

[0059] In this embodiment, in the offspring chromosome population variation operation, a plurality of site gene data corresponding to key nodes in the cutting path, direction and fabric characteristic video parameters and other information are randomly selected, breaking the limitation of traditional fixed position variation, prompting the variation operation to widely cover each region of the chromosome, such as flexibly adjusting each link of the cutting path according to the texture, thickness and other characteristics of different fabrics, enriching the diversity of gene combination, providing the possibility for the algorithm to explore the solution space more in line with the actual fabric cutting demand; based on the minimum and maximum variation probability calculation value set, a dynamic probability regulation mechanism is constructed, which is particularly critical in the fabric cutting scene: when processing complex texture or high elasticity fabric, higher variation probability can quickly adjust the path planning to adapt to the fabric characteristics, while when processing regular fabric, lower variation probability can maintain the existing excellent path gene structure, this regulation not only ensures the continuous injection of new path planning ideas in the evolution process, but also effectively maintains the stability of the excellent gene structure in line with the fabric characteristics, enhances the adaptability of the algorithm to different fabric characteristics and cutting tasks, ensures the continuous injection of new gene information in the evolution process, effectively maintains the stability of the excellent gene structure, and enhances the adaptability of the algorithm to different evolution stages; in the specific variation operation, the value set is combined with the site gene data to determine whether the gene is varied according to the probability, and the gene value is flexibly adjusted according to the fabric characteristics (such as wear resistance, tensile strength, etc.), realizing the balance between randomness and constraint, for example, for fabrics with poor wear resistance, the variation operation will preferentially avoid repeated cutting of the same area in the path; the enhanced chromosome population generated by the scheme finally has more optimized gene structure and significantly enhanced diversity, which can effectively avoid the algorithm falling into local optimum, speed up the convergence speed, and improve the ability to obtain high-quality solutions in complex optimization problems, which has important significance for improving the efficiency of genetic algorithm in practical application of fabric processing.

[0060] Please refer to Figure 4 The fourth embodiment of the fabric cutting path planning method in the embodiment of the application comprises:

[0061] 401, performing feature analysis on the fabric characteristic data to obtain physical characteristics, mechanical characteristics and chemical characteristics;

[0062] In this embodiment, the physical characteristics (such as thickness, density, weight, etc.), mechanical characteristics (such as tensile strength, elasticity, wear resistance, etc.) and chemical characteristics (such as fiber composition, pH value, chemical stability, etc.) are extracted by in-depth analysis of the fabric characteristic data, which are the quantitative embodiment of the inherent properties of the fabric, providing a core basis for subsequent path planning, for example, the tensile strength of the fabric will affect the cutting intensity requirement;

[0063] 402, dividing the fabric image into regions according to the physical characteristics, mechanical characteristics and chemical characteristics to obtain a set of sub-image regions;

[0064] In the embodiment, since the fabric characteristics of different regions may be different, such as the thickness of the fabric edge and the center part may be different, the regions are divided according to the physical, mechanical and chemical characteristics, the parts with similar characteristics are classified into the same sub-image region, and different cutting strategies can be made for the characteristics of different regions, for example, a more gentle cutting method is used for the region with poor wear resistance.

[0065] 403, planning a cutting path for each sub-region based on the path planning model to obtain a set of cutting sub-paths;

[0066] In the embodiment, the path planning model can be constructed based on an optimization method such as genetic algorithm, and can plan efficient cutting sub-paths by combining the fabric characteristics and shape of the sub-region, for example, for a sub-region with irregular shape, the model can plan the shortest cutting path that conforms to the fabric texture direction, reducing fabric waste and cutting time.

[0067] 404, total path planning based on a preset depth-first search algorithm and the set of cutting sub-paths to obtain a total cutting path;

[0068] In the embodiment, the depth-first search algorithm is used to integrate the set of cutting sub-paths to obtain the total cutting path. The depth-first search algorithm can efficiently find the best connection order between sub-paths by preferentially exploring a path until it cannot continue or reaches the target, and then backtracking to explore other paths, avoiding path redundancy and repetition, and ensuring the efficiency and continuity of the total cutting path.

[0069] In the embodiment, the physical, mechanical and chemical characteristics of the fabric are analyzed in depth, and the inherent properties of the fabric are quantified to provide core data support for subsequent planning, ensuring that the cutting intensity and other parameters are adapted to the fabric characteristics; the fabric image is divided into regions based on the characteristic differences, and regions with similar characteristics are classified, which facilitates the development of exclusive cutting strategies for different regions and avoids fabric damage caused by uniform processing, such as gentle cutting for fragile areas, effectively ensuring cutting quality; the path planning model constructed by means of genetic algorithm combines the characteristics and shape of the sub-region to plan efficient sub-paths that meet actual needs, reducing fabric waste and cutting time; the depth-first search algorithm is used to integrate the sub-paths to connect the sub-paths in the optimal order, eliminating redundancy and ensuring the continuity and efficiency of the total path. The overall scheme realizes the whole-process optimization from data analysis to path generation, which not only improves fabric utilization, reduces costs, but also enhances cutting efficiency and product quality, effectively meeting diverse production needs.

[0070] Please refer to Figure 5 , the fifth embodiment of the fabric cutting path planning method in the embodiment of the application comprises:

[0071] 501. Calculate the length of each cutting sub-path in the cutting sub-path set based on the preset Euclidean distance formula to obtain a cutting sub-path length set;

[0072] In this embodiment, the length of the line segment composed of the node (x1, y1) and the node (x2, y2) can be calculated by the Euclidean distance formula Calculate the total length of the sub-path by summing up the lengths of all line segments in the sub-path;

[0073] 502. Calculate the first index value and the second index value according to the cutting sub-path set;

[0074] In this embodiment, the setting of the index value aims to assign a specific identification or location information to the sub-path, which may be related to the starting point, the ending point, the belonging area or other key attributes of the sub-path. Through the index value, the sub-path can be more conveniently located and managed, which provides support for subsequent construction of two-dimensional array and path search;

[0075] 503. Create a two-dimensional array according to the first index value and the second index value;

[0076] In this embodiment, the two-dimensional array stores the sub-path related information in the form of a matrix. The index value can be used as the row and column identification of the array, and the sub-path length or other attribute data can be filled into the corresponding position. This structured data storage method makes the relationship between sub-paths more clear, which facilitates subsequent algorithm to quickly access and process data;

[0077] 504. Perform a depth-first search on the cutting sub-path length set based on the depth-first search algorithm and the two-dimensional array to obtain a path length combination search analysis result;

[0078] In this embodiment, the depth-first search starts from a certain node, preferentially explores along a path, and then backtracks when it cannot continue or reaches the target, and tries other paths. By using this algorithm, all possible sub-path combinations are traversed, the total length of the path under different combinations is analyzed, and the path length combination search analysis result is obtained, and potential shorter path combinations are found;

[0079] 505. Generate a cutting total path according to the path length combination search analysis result and the cutting sub-path set;

[0080] In this embodiment, according to the path length combination search analysis result and the cutting sub-path set, the factors such as path length and connection order are comprehensively considered, and finally the cutting total path is determined and generated. This path is the optimal scheme selected from many sub-path combinations, which can meet the demand of efficient cutting;

[0081] In the embodiment, the cutting sub-path length is calculated by the Euclidean distance formula, which provides a quantitative basis for subsequent optimization, and makes the path planning based on accurate length data, avoiding low cutting efficiency caused by path length estimation error; the first index value, the second index value and the two-dimensional array are calculated and created to store the sub-path information, which not only can conveniently locate the sub-path, but also can clearly present the relationship between the sub-paths, improve the data processing efficiency, make the algorithm quickly access and process data, and speed up the path planning process; the sub-path combination is traversed by the depth-first search algorithm, the path length sum is analyzed, the potential shorter path combination is effectively found out, the invalid path is reduced, the path connection order is optimized, the cutting efficiency is improved, the tool wear and fabric waste are reduced, and finally, the cutting total path generated based on the path length combination search analysis result is the better scheme selected from many combinations, which can meet the efficient cutting demand, improve the production efficiency, reduce the production cost, enhance the adaptability and universality of the scheme in different cutting scenes, and has important significance for improving the overall quality and benefit of fabric cutting.

[0082] Please refer to Figure 6 In the sixth embodiment of the fabric cutting path planning method, the following steps are included:

[0083] 601. Analyze the preset initial cutting speed according to the fabric characteristic data and the cutting tool state data to obtain a first adjustment coefficient and a second adjustment coefficient;

[0084] 602. Adjust the initial cutting speed according to the first adjustment coefficient and the second adjustment coefficient to obtain an updated cutting speed;

[0085] In the embodiment, the initial cutting speed is v0, and the adjusted cutting speed v is: v=v0×(1-k1w-k2t), k1 is the first adjustment coefficient, k2 is the second adjustment coefficient, and the numerical value of the coefficient reflects the influence weight of the fabric characteristics and the tool state on the cutting speed. Through such adjustment, the cutting speed can better adapt to the fabric characteristics and the tool state, and the efficiency and quality of cutting are improved;

[0086] 603. Adjust the cutting total path based on the preset bounding box algorithm, the updated cutting speed and the cutting table component coordinate data to obtain a path adjustment offset;

[0087] In the embodiment, the bounding box algorithm is an algorithm for detecting the collision or proximity between objects. In this step, the cutting total path obtained before is adjusted and analyzed based on the updated cutting speed and the cutting table component coordinate data, and the path adjustment offset, i.e., the distance and direction of the cutting path that needs to be offset, is calculated;

[0088] 604、adjust the cutting total path according to the path adjustment offset to obtain an optimized cutting total path;

[0089] In the embodiment, the optimized cutting total path is obtained by offsetting part of the nodes on the path, which takes into account the requirements of fabric characteristics and tool state on speed, and avoids collision with the cutting table components, ensuring the smooth progress of the cutting process;

[0090] In the embodiment, the influence weight of factors such as fabric thickness and tool wear on cutting speed is quantified through the first adjustment coefficient and the second adjustment coefficient, and the initial cutting speed is dynamically adjusted through the formula, which can avoid cutting defects caused by high-speed cutting of hard and thick fabric, and reduce tool wear, thereby improving cutting quality and prolonging tool life. Secondly, using the bounding box algorithm, the cutting speed and the cutting table component coordinate data are combined to scientifically calculate the path adjustment offset, and the collision risk between the tool and the cutting table component is effectively avoided through the offset operation of the path nodes, thereby enhancing the production safety. The finally generated optimized cutting total path organically combines speed regulation and path optimization, which not only ensures smooth and efficient cutting process and reduces downtime adjustment time caused by improper speed or path conflict, but also adapts to various fabric and tool working conditions, significantly improves production efficiency, and reduces comprehensive cost, thereby providing a more intelligent and reliable solution for fabric cutting production.

[0091] Please refer to Figure 7 The seventh embodiment of the fabric cutting path planning method in the embodiment of the application comprises:

[0092] 701、analyze the cutting table component coordinate data to obtain three-dimensional geometric information;

[0093] In the embodiment, the coordinate data of the cutting table component contains the position and shape information of the component in space, and by analyzing these data, a three-dimensional model of the cutting table component can be accurately constructed, and its geometric features in three-dimensional space can be clearly presented, thereby providing an intuitive and specific data basis for subsequent analysis and processing;

[0094] 702、analyze the three-dimensional geometric information based on a preset reconfigurability constraint function to obtain an information domain score;

[0095] In the embodiment, the reconfigurability constraint function is a tool for evaluating the reconfigurability of three-dimensional geometric information under certain conditions, and by analyzing the three-dimensional geometric information through the function, an information domain score can be quantitatively obtained, which reflects the quality of the three-dimensional geometric information and its performance in reconfigurability, thereby providing an important reference index for subsequent judgment and processing;

[0096] 703、determine whether the information domain score is less than a preset information domain score threshold value;

[0097] 704、when the information domain score is less than the information domain score threshold value, obtain a viewpoint data set and calculate the viewpoint data set to obtain a constraint coefficient;

[0098] In this embodiment, the viewpoint data set can be flexibly set according to the structure characteristics of the cutting table and the analysis requirements. For example, in a gantry type cutting table, the center points of the bearing seats at both ends of the cross beam, the upper and lower limit position points of the vertical guide rail, and the center of the positioning pin hole of the tool holder clamp can be selected as key identification components, and the coordinate data thereof in the three-dimensional space is recorded. For a disc type cutting table, the coordinates of the center shaft of the disc, the coordinates of the positioning hole of the cutter disc edge, and the coordinates of the key support points of the protective cover can be used as key identification points. The viewpoint data set is constructed from different directions to provide accurate data basis for subsequent analysis and can reflect the constraint of three-dimensional geometric information under different viewing angles, thereby providing a basis for subsequent correction operations.

[0099] 705、based on the preset sampling normal vector, the constraint coefficient and the preset adjustable coefficient, the three-dimensional geometric information is corrected to obtain corrected three-dimensional geometric information;

[0100] In this embodiment, the sampling normal vector is used to describe the direction and characteristics of each face in the three-dimensional geometric information. Combined with the constraint coefficient and the adjustable coefficient, the three-dimensional geometric information can be adjusted and optimized, so that the corrected three-dimensional geometric information is improved in reconfigurability;

[0101] 706、set the corrected three-dimensional geometric information as the three-dimensional geometric information, and return to execute the analysis of the three-dimensional geometric information based on the reconfigurability constraint function until the preset iteration stop condition is met, and then obtain the corresponding corrected three-dimensional geometric information;

[0102] 707、modeling according to the corrected three-dimensional geometric information and the preset point cloud processing algorithm to obtain a cutting machine model;

[0103] In this embodiment, the iteration stop condition is that the information domain score is greater than or equal to the information domain score threshold value, so as to ensure that the three-dimensional geometric information meets the reconfigurability requirement, and finally a cutting machine model is obtained by modeling according to the three-dimensional geometric information and the preset point cloud processing algorithm. The model accurately reflects the structure and geometric characteristics of the overall fabric cutting mechanism;

[0104] 708、based on the bounding box algorithm, the cutting machine model and the cutting total path, collision analysis is performed to obtain a collision node set and a node offset set;

[0105] In this embodiment, for example, for two bounding box coordinate data in the cutting table component coordinate data, the minimum coordinates (x min1 , y min1 , zmin1 ), the maximum coordinate (x max1 , y max1 , z max1 ), by judging whether x min1 ≤x max2 , and x min1 ≥x max2 , y max1 ≤y min2 and y max1 ≥y min2 , z min1 ≤z max2 and z max1 ≥z min2 in three coordinate axis directions, to determine whether a collision occurs, and once a collision is detected, the offset amount set that needs to be adjusted, i.e. the node offset amount set, is obtained through the collision node set;

[0106] 709, generating path adjustment offsets based on the linear fitting method, the cutting speed, the collision node set and the node offset amount set;

[0107] In this embodiment, the analysis of the cutting table component coordinate data constructs a three-dimensional model (cutting machine model) to provide intuitive data basis for subsequent processing, ensures the accuracy of the cutting machine model, reflects its structure and geometric characteristics, and improves the model precision. Secondly, the reconstructability constraint function quantifies the information domain score to provide a reference index for judging the quality of three-dimensional geometric information, iteratively corrects the three-dimensional geometric information multiple times to meet the reconstructability requirement, and enhances the universality and adaptability of the model. The setting of the viewpoint data group provides data from different directions, combines the sampling normal vector, the constraint coefficient and the adjustable coefficient, and optimizes the three-dimensional geometric information; then, the collision analysis based on the bounding box algorithm can effectively detect the collision, generate path adjustment offsets based on the linear fitting method, avoid collision between devices during cutting, and improve the safety of the cutting process. Finally, through the above series of operations, the total cutting path is optimized, the path adjustment and equipment downtime caused by collision are reduced, the cutting efficiency is improved, the production cost is reduced, and detailed basis is provided for the decision-making of the cutting process, so that the cutting operation is more scientific and reasonable, and the overall production benefit and intelligent level are improved.

[0108] The above describes a fabric cutting path planning method in an embodiment of the present application, and the following describes a fabric cutting device in an embodiment of the present application, please refer to Figure 8 , an embodiment of a fabric cutting device in an embodiment of the present application, comprising:

[0109] The first data acquisition module 1 is used for acquiring historical cutting path data;

[0110] The data enhancement processing module 2 is configured to perform enhancement processing on the historical cutting path data based on a multi-point crossover method to obtain an enhanced chromosome population.

[0111] The model construction module 3 is configured to construct a path planning model based on a preset genetic algorithm and the enhanced chromosome population.

[0112] The second data acquisition module 4 is configured to acquire fabric characteristic data and fabric images.

[0113] The path planning module 5 is configured to generate a total cutting path based on the path planning model, the fabric characteristic data and the fabric images.

[0114] The third data acquisition module 6 is configured to acquire cutting tool state data and cutting table component coordinate data.

[0115] The path optimization module 7 is configured to adjust the total cutting path based on a preset bounding box algorithm, the fabric characteristic data, the cutting tool state data and the cutting table component coordinate data to obtain an optimized total cutting path.

[0116] In the embodiment, at the data processing and model construction level, the historical cutting path data is acquired and enhanced by using the multi-point crossover method, the data value is fully tapped, the diversity of the chromosome population is increased, and the path planning model constructed in combination with the genetic algorithm can better adapt to the cutting requirements of various fabrics and has strong generalization and optimization capabilities. In the path generation stage, the fabric characteristic data and image information are fused, the generated total cutting path is fully fitted to the actual situation of the fabric, and the rationality and feasibility of the path are greatly improved. In the path optimization stage, based on the bounding box algorithm, the fabric characteristics, the tool state and the cutting table component coordinate data are comprehensively considered, the path is scientifically adjusted, the collision with the cutting table components is effectively avoided, and the tool wear is reduced. Overall, the scheme can improve the cutting efficiency, reduce the invalid cutting and equipment adjustment time, significantly improve the fabric utilization rate and reduce the production cost, prolong the service life of the tool and reduce the replacement cost, enhance the adaptability of the system to different fabrics and cutting environments, ensure the cutting accuracy and stability, improve the cutting quality, and has important significance for promoting the intelligent and efficient development of the fabric cutting industry.

[0117] Figure 9is a structural schematic diagram of a fabric cutting path planning device provided by an embodiment of the present application. The fabric cutting path planning device 900 can be different in configuration or performance and can include one or more central processing units (CPUs) 913 (for example, one or more processors) and a memory 920, one or more media 930 (for example, one or more mass storage devices) storing application programs 933 or data 932. The memory 920 and the media 930 can be temporary storage or persistent storage. The programs stored in the media 930 can include one or more modules (not shown in the figure), each of which can include a series of instruction operations of the fabric cutting path planning device 900. Further, the processor 913 can be configured to communicate with the media 930 and execute the series of instruction operations in the media 930 on the fabric cutting path planning device 900 to implement the steps of the fabric cutting path planning method provided by each method embodiment described above.

[0118] The fabric cutting path planning device 900 can also include one or more power supplies 940, one or more wired or wireless network interfaces 950, one or more input / output interfaces 960, and / or one or more operating systems 931, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art can understand that the fabric cutting path planning device 900 can include more or fewer components than those shown in the figure, or some components can be combined, or different components can be arranged. Figure 9 The fabric cutting path planning device structure shown does not constitute a limitation on the fabric cutting path planning device 900, which can include more or fewer components than those shown in the figure, or some components can be combined, or different components can be arranged.

[0119] A computer readable medium having instructions stored thereon, the instructions being executed by a processor to implement each step of the fabric cutting path planning method described above.

[0120] The present application and its embodiments have been described above, and such description is not restrictive, and the embodiments shown in the figures are only one of the embodiments of the present application, and the actual content is not limited thereto. In general, if a person skilled in the art is inspired by it, without departing from the spirit of the present application, without creative design, similar structural forms and embodiments to the technical solution can be designed and belong to the protection scope of the present application.

Claims

1. A fabric cutting path planning method, characterized in that: include: Get historical cutting path data; The historical cutting path data is enhanced based on the multi-point crossover method to obtain the enhanced chromosome population; A path planning model is constructed based on a preset genetic algorithm and enhanced chromosome population; Obtain fabric property data and fabric images; Generate the total cutting path based on the path planning model, fabric property data and fabric image; Obtain cutting tool status data and cutting table component coordinate data; The total cutting path is adjusted based on the preset bounding box algorithm, fabric characteristic data, cutting tool status data and cutting table component coordinate data to obtain an optimized total cutting path.

2. A fabric cutting path planning method according to claim 1, characterized in that: The method of enhancing the historical cutting path data based on the multi-point crossover method to obtain an enhanced chromosome population includes: Generate the initial population based on the preset random function and historical cutting path data; Evaluate the initial population based on the preset fitness function to obtain the inverse of the evaluation coefficient; Perform feature selection on the primary population according to the inverse of the evaluation coefficient to obtain the parent chromosome; Perform crossover operation on parent chromosomes based on multi-point crossover method to obtain offspring chromosome population; The offspring chromosome population is mutated to obtain an enhanced chromosome population.

3. A fabric cutting path planning method according to claim 2, characterized in that: The step of performing a mutation operation on the offspring chromosome population to obtain an enhanced chromosome population includes: Multiple locus gene data are randomly selected from the offspring chromosome population; A value set is calculated based on a preset minimum mutation probability and a preset maximum mutation probability; The offspring chromosome population is mutated according to the value set and multiple site gene data to obtain an enhanced chromosome population.

4. A fabric cutting path planning method according to claim 1, characterized in that: The method of generating a total cutting path based on a path planning model, fabric property data, and a fabric image includes: Perform feature analysis on fabric property data to obtain physical, mechanical and chemical characteristics; Divide the fabric image into regions according to physical features, mechanical features and chemical features to obtain a sub-image region set; Plan the cutting path of each sub-region based on the path planning model to obtain a cutting sub-path set; The total path planning is performed based on the preset depth-first search algorithm and the cutting sub-path set to obtain the cutting total path.

5. A fabric cutting path planning method according to claim 4, characterized in that: The total path planning is performed based on a preset depth-first search algorithm and a set of cutting sub-paths to obtain a total cutting path, including: Calculating the length of each cutting sub-path in the cutting sub-path set based on a preset Euclidean distance formula to obtain a cutting sub-path length set; Calculate a first index value and a second index value according to the clipping sub-path set; Create a two-dimensional array according to the first index value and the second index value; Based on the depth-first search algorithm and two-dimensional array, a depth-first search is performed on the length set of the cut sub-path to obtain the path length combination search analysis results; The total cutting path is generated by combining the search analysis results and the cutting sub-path set according to the path length.

6. A fabric cutting path planning method according to claim 1, characterized in that: The adjusting of the total cutting path based on the preset bounding box algorithm, fabric property data, cutting tool status data and cutting table component coordinate data to obtain the optimized total cutting path includes: Analyzing the preset initial cutting speed according to the fabric property data and the cutting tool state data to obtain a first adjustment coefficient and a second adjustment coefficient; Adjusting the initial cutting speed according to the first adjustment coefficient and the second adjustment coefficient to obtain an updated cutting speed; Adjust the total cutting path based on the preset bounding box algorithm, updated cutting speed and cutting table component coordinate data to obtain a path adjustment offset; The total cutting path is adjusted according to the path adjustment offset to obtain an optimized total cutting path.

7. A fabric cutting path planning method according to claim 6, characterized in that: The method of adjusting the total cutting path based on a preset bounding box algorithm, updating the cutting speed and the cutting table component coordinate data to obtain a path adjustment offset includes: Analyze the coordinate data of cutting table components to obtain three-dimensional geometric information; Analyze the three-dimensional geometric information based on the preset reconfigurability constraint function to obtain the information domain score; Determine whether the information domain score is less than a preset information domain score threshold; When the information domain score is less than the information domain score threshold, a viewpoint data group is obtained, and the viewpoint data group is calculated to obtain a constraint coefficient; Correcting the three-dimensional geometric information based on a preset sampling normal vector, a constraint coefficient, and a preset adjustable coefficient to obtain corrected three-dimensional geometric information; The corrected 3D geometric information is set as the 3D geometric information, and the analysis of the 3D geometric information based on the reconfigurability constraint function is returned until a preset iteration stop condition is satisfied, thereby obtaining the corresponding corrected 3D geometric information; Modeling is performed based on the corrected three-dimensional geometric information and the preset point cloud processing algorithm to obtain a cutting machine model; Perform collision analysis based on bounding box algorithm, clipper model and total clipping path to obtain collision node set and node offset set; Generates path adjustment offsets based on a linear fitting method, updated clipping velocity, collision node set, and node offset set.

8. A fabric cutting device, characterized in that: A first data acquisition module is used to acquire historical cutting path data; A data enhancement processing module is used to enhance the historical cutting path data based on a multi-point crossover method to obtain an enhanced chromosome population; A model building module is used to construct a path planning model based on a preset genetic algorithm and an enhanced chromosome population; A second data acquisition module is used to acquire fabric characteristic data and fabric images; A path planning module is used to generate a total cutting path based on a path planning model, fabric property data, and fabric images; A third data acquisition module is used to obtain cutting tool status data and cutting table component coordinate data; The path optimization module is used to adjust the total cutting path based on a preset bounding box algorithm, fabric characteristic data, cutting tool status data and cutting table component coordinate data to obtain an optimized total cutting path.

9. A fabric cutting device comprising: a memory and at least one processor, wherein instructions are stored in the memory; At least one of the processors calls the instructions in the memory to enable the fabric cutting method to execute each step of the fabric cutting method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of the fabric cutting method according to any one of claims 1 to 7 are implemented.

Images