A method, device and equipment for generating acupuncture path and implementing a process

Abstract

The present invention relates to the technical field of needle punching automation, and discloses a method, device and equipment for generating and implementing a needle punching path. The method comprises: determining the overall needle punching area based on the shape information of the target needle punched fabric, and dividing the overall needle punching area into N minimum units, searching within the minimum unit based on the preset needle punching process parameters using a reinforcement learning algorithm with a preset reward function as the target, generating a minimum unit needle punching path composed of multiple needle punching coordinate points, using a heuristic search algorithm with a preset fitness function as the target, splitting and distributing multiple needle punching coordinate points of the minimum unit needle punching path to each layer, obtaining each single-layer needle punching path within the minimum unit, and obtaining the target needle punched fabric by controlling the moving needle plate according to each single-layer needle punching path based on the preset needle punching process parameters. The method provided by the present invention can generate uniform, discrete and low-repetition needle punching paths to improve the interlayer performance of needle punched fabrics.

Description

Technical Field

[0001] The invention relates to the technical field of acupuncture molding automation, and in particular to a method, device and equipment for generating acupuncture paths and implementing a process. Background Art

[0002] Carbon fiber reinforced composite materials (such as C / C, C / C-SiC, etc.) show excellent comprehensive properties at room temperature and high temperature, with high specific stiffness and specific strength, able to withstand thermal shock and anti-oxidation. They are ideal high-temperature composite structural materials and functional materials, and can be used in aviation, aerospace, biomedicine, sports goods and other fields. Needle punching technology can efficiently produce various complex shapes of needle-punched carbon fiber preforms. It uses needles to relay needle punches on fiber composites such as carbon fiber cloth and mesh tires, introduces part of the in-plane fibers into the thickness direction of the layer (z direction), produces vertical fiber clusters, and makes the carbon fiber cloth and mesh tires closely combined to form a preform with a certain strength in the plane and between layers. It is a three-dimensional preform with a unique mesh structure, with the characteristics of uniform pore distribution, easy dense molding, and low production cost.

[0003] The needle-punched preform forming process has been realized in an automated, assembly-line production process. The needle-punching process mainly includes the following three steps: (1) alternately stacking fiber composites such as 0° non-woven fabric, mesh tire and 90° non-woven fabric to achieve a certain thickness; (2) needle-punching the surface of the non-woven fabric / mesh tire laminate. During the needling process, the carbon fiber composite moves horizontally with the conveyor belt, and the needle plate reciprocates up and down at a certain frequency; (3) rotating the composite laminate horizontally by 90° and repeating the needling to ensure the uniformity of the needle-punched holes in the material in the x and y directions.

[0004] The existing needle-punched preform forming process has a regular needling process, which only forms relatively irregularly distributed needling holes by horizontally rotating the composite stack. However, the needling preform preparation process requires multiple layering and needling to achieve the predetermined needling density. The fixed regular needling of each layer will inevitably lead to the appearance of repeated needling areas. The repeated needling area is actually a man-made defect, which will cause the fibers near the needling holes to lose their geometric continuity, and it is easy to produce defects such as holes and microcracks during the densification process. The strength of the needle-punched composite material is very sensitive to the needling area, especially the repeated needling area. Tensile, shear and compression specimens are prone to damage at the needling position. Therefore, when performing the needling process, it should be as uniform as possible and avoid the appearance of repeated needling areas between layers. Summary of the invention

[0005] In view of this, the present invention provides a method, device and equipment for generating and implementing a needle punching path to solve the problem in the prior art that the needle punching position performance of the fabric is poor due to poor uniformity operations such as repeated needle punching and crack voids during the needle punching process.

[0006] In a first aspect, the present invention provides a method for generating acupuncture paths and implementing a process, the method comprising:

[0007] Determine the overall needling area based on the shape information of the target needling fabric, and divide the overall needling area into N minimum units, where the minimum unit is the needling area assigned to each needle;

[0008] In the minimum unit, based on the preset needling process parameters, a reinforcement learning algorithm is used to search with a preset reward function as the target, and a minimum unit needling path composed of multiple needling coordinate points is generated. The minimum unit needling path is a multi-layer needling path generated in the minimum unit, which is equivalent to the superposition of the multi-layer needling paths in a two-dimensional plane. The total number of needling coordinate points in the minimum unit is equal to the product of the needling density, the number of fabric forming layers and the minimum unit area.

[0009] A heuristic search algorithm is used with a preset fitness function as the target, and multiple needle coordinate points of the minimum unit needle path are split and distributed to each layer to obtain the needle paths of each single layer in the minimum unit. The overall needle path of each layer is the total needle path of each layer of the target needle-punched fabric, which is equivalent to the sum of N repetitions of the minimum unit needle path.

[0010] Based on the preset needling process parameters, the target needle-punched fabric is obtained by controlling the moving needle plate to perform needling forming according to each single-layer needling path.

[0011] The needle punching path generation and process implementation method provided in this embodiment generates a minimum unit needle punching path based on a reinforcement learning algorithm, divides the minimum unit needle punching path into a single-layer path using a heuristic search algorithm, and achieves coverage of all needle punching positions in a continuous space by moving the needle plate. Needle punching forming is completed according to the generated path, and a uniform, discrete and low-repetition needle punching path can be generated to improve the interlayer performance of the needle punched fabric.

[0012] In an optional embodiment, the preset needling process parameters include: overall needling area, needle spacing, needle arrangement method, number of needles, diameter of needle barb parts, minimum unit, needling density and number of fabric forming layers.

[0013] In an optional embodiment, the method of searching based on preset acupuncture process parameters using a reinforcement learning algorithm with a preset reward function as a target to generate a minimum unit acupuncture path consisting of a plurality of acupuncture coordinate points includes:

[0014] Obtaining preset needling process parameters determined according to the target needling fabric;

[0015] According to the preset acupuncture process parameters, an intelligent agent for generating paths and an acupuncture simulation environment for interaction are established. The interaction between the intelligent agent and the acupuncture simulation environment is completed based on the proximal strategy search algorithm, and the Ripley's K function, the overlap of the acupuncture paths in the minimum unit and the Voronoi Figure 3 A reward function is used to search for the target and generate multi-layer acupuncture paths that meet the target discreteness, uniformity, and overlap within the smallest unit.

[0016] The embodiment of the present invention adopts the proximal strategy search algorithm for interaction because the algorithm is a reinforcement learning algorithm based on policy gradient. The core of the algorithm is to update the difference between the new and old strategies of the strategy time limit value, avoid performance degradation due to excessive updates, have good convergence and stability, and can ensure that the global optimal solution is found. Therefore, the application of the algorithm can obtain better interaction results based on setting target discreteness, uniformity, and overlap.

[0017] In an optional embodiment, the heuristic search algorithm is used with a preset fitness function as the target, multiple acupuncture coordinate points of the minimum unit acupuncture path are split and allocated to each layer to obtain each single-layer acupuncture path in the minimum unit, including:

[0018] Indexing the acupuncture coordinate points in the minimum unit acupuncture path according to a preset order, and assigning an index value to each coordinate point;

[0019] Based on the multi-objective genetic algorithm, the order of indexes is changed through selection, crossover and mutation operations, and the overlap of single-layer acupuncture paths, the overlap between layers and Voronoi Figure 3 The fitness function is taken as the target, and the acupuncture coordinates are allocated by slicing according to the number of layers to obtain the acupuncture paths of each single layer in the minimum unit.

[0020] The embodiment of the present invention adopts a multi-objective genetic algorithm to allocate acupuncture coordinates, wherein NSGA-II selection, ordered crossover and shuffle mutation operations are used to ensure the integrity of the coordinate sorting process and ensure that there will be no duplication or missing of coordinates, thereby effectively completing the task of allocating acupuncture coordinates.

[0021] In an optional embodiment, Ripley's K function is used to evaluate the discreteness of the acupuncture path in the smallest unit, different K values ​​are calculated by different search radii d, and different K values ​​are compared with the complete space randomness to determine the degree of aggregation and dispersion of the acupuncture points.

[0022] The embodiment of the present invention uses Ripley's K function to evaluate the degree of aggregation and dispersion of acupuncture points to obtain acupuncture coordinate points based on target discreteness.

[0023] In an optional embodiment, the process of using the Voronoi diagram to evaluate the uniformity of the acupuncture path in the minimum unit and the uniformity of each single-layer acupuncture path in the minimum unit is:

[0024] The uniformity of acupuncture coordinates was evaluated by calculating the mean square error between the Voronoi cell area when the point coordinates were uniformly distributed and the Voronoi cell area used to generate the acupuncture point coordinates. The calculation formula is as follows:

[0025]

[0026] Where A is the Voronoi cell area when the point coordinates are uniformly distributed, R i is the area of ​​the Voronoi cell of the i-th generated acupuncture point coordinate, n is the total number of point data, and β is a scaling factor used to adjust the weight of uniformity among the three reward functions.

[0027] The embodiment of the present invention is based on a preset target uniformity, and evaluates the needling path within the minimum unit of the Voronoi diagram and the needling path of each single layer within the minimum unit, and obtains a fabric with good uniformity after the process is implemented.

[0028] In an optional embodiment, the process of calculating the overlap of the acupuncture paths in the minimum unit is as follows: calculating the distance between the generated acupuncture points, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of the acupuncture paths in the minimum unit is obtained by counting;

[0029] The process of calculating the overlap of a single-layer acupuncture path is as follows: the distance between the generated acupuncture points is calculated, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of the single-layer acupuncture path is obtained by counting;

[0030] The process of calculating the interlayer overlap between single-layer acupuncture paths is as follows: calculate the distance between the acupuncture points of adjacent layers in two-dimensional space. If the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is judged as overlap. The interlayer overlap of the generated acupuncture path is obtained by counting.

[0031] The embodiment of the present invention is based on a preset overlap target, by evaluating the overlap of the needle paths in the total minimum unit, the overlap of the needle paths in a single layer, and the overlap between layers, and a fabric with low overlap is obtained after the process is implemented.

[0032] In a second aspect, the present invention provides a device for generating acupuncture paths and implementing a process, the device comprising:

[0033] A minimum unit determination module, used to determine the overall needling area based on the shape information of the target needling fabric, and divide the overall needling area into N minimum units, wherein the minimum unit is the needling area allocated to each needle;

[0034] A minimum unit acupuncture path generation module is used to search within the minimum unit based on preset acupuncture process parameters using a reinforcement learning algorithm with a preset reward function as a target, and generate a minimum unit acupuncture path composed of multiple acupuncture coordinate points, wherein the minimum unit acupuncture path is a multi-layer acupuncture path generated within the minimum unit, which is equivalent to the superposition of multi-layer acupuncture paths in a two-dimensional plane, and the total number of acupuncture coordinate points within the minimum unit is equal to the product of acupuncture density, the number of fabric forming layers, and the minimum unit area;

[0035] A minimum unit single-layer acupuncture path generation module is used to use a heuristic search algorithm with a preset fitness function as the target, split multiple acupuncture coordinate points of the minimum unit acupuncture path and distribute them to each layer, so as to obtain each single-layer acupuncture path in the minimum unit. The overall acupuncture path of each layer is the total acupuncture path of each layer of the target acupuncture fabric, which is equivalent to the sum of N repetitions of the minimum unit acupuncture path;

[0036] The process implementation module is used to obtain the target needle-punched fabric by controlling the moving needle plate to perform needle-punching forming according to each single-layer needling path based on the preset needling process parameters.

[0037] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the acupuncture path generation and process implementation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the acupuncture path generation and process implementation method of the first aspect or any corresponding embodiment thereof.

[0039] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the acupuncture path generation and process implementation method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 is a flow chart of a method for generating acupuncture paths and implementing a process according to an embodiment of the present invention;

[0042] Figure 2 is a flow chart of another method for generating acupuncture paths and implementing a process according to an embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of generating an overall acupuncture path through interaction between an intelligent agent and a simulation environment according to an embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of a process of assigning acupuncture coordinates using a multi-objective genetic algorithm according to an embodiment of the present invention;

[0045] Figure 5 is a schematic diagram of allocating the overall acupuncture path to two layers of acupuncture paths according to an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of integrally moving the needle plate to complete acupuncture forming according to an embodiment of the present invention;

[0047] Figure 7 is a structural block diagram of a device for generating acupuncture paths and implementing processes according to an embodiment of the present invention;

[0048] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0050] According to an embodiment of the present invention, an embodiment of a method for generating a needle path and implementing a process is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer device such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, a method for generating acupuncture paths and implementing a process is provided, which can be used in the above-mentioned computer device. Figure 1 is a flow chart of a method for generating acupuncture paths and implementing a process according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0052] Step S101, determining the overall needling area based on the shape information of the target needling fabric, and dividing the overall needling area into N minimum units, wherein the minimum unit is the needling area allocated to each needle.

[0053] In this embodiment, when the unit cell of the target needle-punched fabric is a triangle, the minimum unit is a triangle. For example, when the unit cell of the target needle-punched fabric is a quadrilateral, the minimum unit is a quadrilateral, such as a square, which is only used as an example. In actual applications, the minimum unit is determined according to the specific shape of the target needle-punched fabric.

[0054] Step S102, within the minimum unit, based on the preset needling process parameters, a reinforcement learning algorithm is used to search with a preset reward function as the target, and a minimum unit needling path composed of multiple needling coordinate points is generated, wherein the minimum unit needling path is a multi-layer needling path generated within the minimum unit, which is equivalent to the superposition of the multi-layer needling paths in a two-dimensional plane, and the total number of needling coordinate points within the minimum unit is equal to the product of the needling density, the number of fabric forming layers and the minimum unit area.

[0055] In the embodiment of the present invention, the needling path is the needling points at different positions in the needling area, the holes left by the needling are abstracted into a circle, the diameter of the circle is equal to the diameter of the needle working area, and the needling process parameters are preset, including: the overall needling area, the needle spacing, the needle arrangement method, the number of needles, the diameter of the needle barb part, the needling area (minimum unit) assigned to each needle, the needling density and the number of fabric forming layers. The reinforcement learning algorithm is used to search and generate a uniform, discrete and low-overlapping needling path in the minimum unit with the Voronoi diagram, Ripley's K function, the overlap of the needling path in the minimum unit and three reward functions as the target.

[0056] Step S103, using a heuristic search algorithm with a preset fitness function as the target, splitting the multiple needle coordinate points of the minimum unit needle path and distributing them to each layer, obtaining the needle paths of each single layer in the minimum unit, and the overall needle path of each layer is the total needle path of each layer of the target needle-punched fabric, which is equivalent to the sum of N repetitions of the minimum unit needle path.

[0057] Specifically, since the minimum unit acupuncture path is a superposition of multiple paths in a two-dimensional plane, the minimum unit acupuncture path splitting is to distribute the generated acupuncture coordinate points to each layer to form each single-layer acupuncture path in the minimum unit. Figure 3 The fitness function is used as the target, and the overall acupuncture coordinate points are split and allocated to each layer.

[0058] Step S104, based on the preset needling process parameters, the needling forming is completed by controlling the moving needle plate according to each single-layer needling path.

[0059] Specifically, the embodiment of the present invention uses a square array of needles on the needle plate as an example, and divides the acupuncture area into multiple basic cells. The length and width of the cell are equal to the distance between the needles, and each needle is n apart. Each needle is responsible for an n×n acupuncture area, which is arranged in a square array. By moving the needle plate, coverage of all acupuncture positions in a continuous space is achieved, and acupuncture forming is completed according to the final acupuncture path.

[0060] The needling path generation and process implementation method provided in this embodiment generates a minimum unit needling path based on a reinforcement learning algorithm, splits the minimum unit needling path into single-layer paths using a heuristic search algorithm, and achieves coverage of all needling positions in a continuous space by moving the needle plate. Needling forming is completed according to the generated path, and a uniform, discrete and low-repetition needling path can be generated to improve the interlayer performance of the needle-punched fabric.

[0061] In this embodiment, a method for generating acupuncture paths and implementing processes is provided, which is applied to the above-mentioned computer device, such as Figure 2 As shown, the process includes the following steps:

[0062] Step S201, determining the overall needling area based on the shape information of the target needle-punched fabric, and dividing the overall needling area into N minimum units, wherein the minimum unit is the needling area assigned to each needle. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0063] Step S202, in the minimum unit, based on the preset needling process parameters, a reinforcement learning algorithm is used to search with a preset reward function as the target, and a minimum unit needling path composed of multiple needling coordinate points is generated. The minimum unit needling path is a multi-layer needling path generated in the minimum unit, which is equivalent to the superposition of multi-layer needling paths in a two-dimensional plane. The total number of needling coordinate points in the minimum unit is equal to the product of the needling density, the number of fabric forming layers, and the minimum unit area. Specifically, step S201 includes the following processes:

[0064] Step S2021, obtaining preset needling process parameters determined according to the target needling fabric.

[0065] For example, the total puncture area is 50 mm × 50 mm, the puncture interval is 10 mm, the puncture pattern is a square array, the number of punctures is 5 × 5, the diameter of the barbed part of the puncture needle is 0.77 mm, the minimum unit (puncture area allocated to each puncture needle) is 10 mm × 10 mm, and the puncture density is 11 needles / cm 2 , fabric molding layers: 2.

[0066] Step S2022: establish an intelligent agent for generating a path and an acupuncture simulation environment for interaction with the intelligent agent according to the preset acupuncture process parameters, complete the interaction between the intelligent agent and the acupuncture simulation environment based on the proximal strategy search algorithm, and use Ripley's K function, the overlap of the acupuncture paths in the minimum unit and the Voronoi Figure 3 A reward function is used to search for the target and generate multi-layer acupuncture paths that meet the target discreteness, uniformity, and overlap within the smallest unit.

[0067] like Figure 3 What is shown is a schematic diagram of the interaction between the agent and the simulation environment to generate an overall needling path that meets the target discreteness, uniformity, and overlap within the smallest unit. The present invention adopts a proximal strategy search algorithm for interaction because the algorithm is a reinforcement learning algorithm based on policy gradient, and its core lies in updating the difference between the new and old strategies of the strategy time limit value to avoid performance degradation due to excessive updates. It has good convergence and stability and can ensure that the global optimal solution is found. Therefore, the application of this algorithm can obtain better interaction results based on setting the target discreteness, uniformity, and overlap, wherein the target discreteness, uniformity, and overlap are determined according to the requirements of the actual target needle-punched fabric and are not specifically limited here.

[0068] The Ripley's K function in this embodiment is:

[0069]

[0070] Where n is the total number of acupuncture points, K is the number of nearest neighbors, and x i and i is the two-dimensional coordinate of the i-th acupuncture point, x j and j is the two-dimensional coordinate of the jth nearest neighbor. Different K values ​​are calculated by different search radius d. These values ​​are compared with the complete space randomness to determine the degree of clustering and dispersion of the acupuncture points. For non-randomly distributed points, positive values ​​indicate clustering and negative values ​​indicate dispersion. In this embodiment, the search radius d is set to 4.5 mm based on experience.

[0071] The Voronoi diagram is used to describe the uniformity of a given set of data points in space. It divides the space into multiple regions, and the points in each region are closest to a specific point in the point set to which it belongs. These regions are called Voronoi cells, and the diagram composed of Voronoi cells is called a Voronoi diagram. The embodiment of the present invention evaluates the uniformity of acupuncture coordinates by calculating the mean square error between the Voronoi cell area when the point coordinates are uniformly distributed and the Voronoi cell area used to generate the acupuncture point coordinates. The calculation formula is as follows:

[0072]

[0073] Where A is the Voronoi cell area when the point coordinates are uniformly distributed, R i is the area of ​​the Voronoi cell of the i-th generated acupuncture point coordinate, n is the total number of point data, and β is a scaling factor used to adjust the weight of uniformity among the three reward functions. β = 1000 was selected through experimental testing.

[0074] The process of calculating the overlap of acupuncture paths in the minimum unit in the embodiment of the present invention is as follows: the distance between the generated acupuncture points is calculated, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapped, and the overlap of acupuncture paths in the minimum unit is obtained by counting. The overlap obtained by calculation is used to evaluate whether the overlap of acupuncture paths in the minimum unit meets the requirements.

[0075] Step S203, using a heuristic search algorithm with a preset fitness function as the target, splitting the multiple needle coordinate points of the minimum unit needle path and assigning them to each layer, obtaining the needle paths of each single layer in the minimum unit, and the overall needle path of each layer is the total needle path of each layer of the target needle-punched fabric, which is equivalent to the sum of N repetitions of the minimum unit needle path. Specifically, the above step S203 includes:

[0076] Step S2031, indexing the acupuncture coordinate points in the overall acupuncture path according to a preset order, and assigning an index value to each coordinate point. Specifically, each coordinate point is assigned an index value according to the order in which the acupuncture coordinate points are generated.

[0077] Step S2032, based on the multi-objective genetic algorithm, the order of the indexes is changed through selection, crossover and mutation operations, and the overlap of single-layer acupuncture paths, the overlap between layers and Voronoi Figure 3 The fitness function is taken as the target, and the acupuncture coordinates are allocated by slicing according to the number of layers to obtain the acupuncture paths of each single layer in the minimum unit.

[0078] like Figure 4 As shown, a flowchart of acupuncture coordinate allocation using a multi-objective genetic algorithm is shown in an embodiment of the present invention, wherein NSGA-II selection, ordered crossover and shuffle mutation operations are used to ensure the integrity of the coordinate sorting process and to ensure that there will be no duplication or missing of coordinates, thereby effectively completing the task of acupuncture coordinate allocation.

[0079] The process of calculating the overlap of a single-layer acupuncture path in the embodiment of the present invention is: calculating the distance between the generated acupuncture points, if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapped, and the overlap of the single-layer acupuncture path is obtained by counting. The process of calculating the inter-layer overlap between single-layer acupuncture paths is: calculating the distance between the acupuncture points of adjacent layers in two-dimensional space, if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapped, and the inter-layer overlap of the generated acupuncture paths is obtained by counting. The method for evaluating the uniformity of a single-layer acupuncture path in the embodiment of the present invention is the same as the method for evaluating the uniformity of acupuncture paths in the minimum unit, both using Voronoi diagrams, which will not be repeated here.

[0080] like Figure 5 As shown, in one embodiment, the overall acupuncture path includes 22 acupuncture coordinate points. Finally, a multi-objective genetic algorithm is used to allocate the 22 acupuncture coordinate points to two units, with 11 acupuncture points allocated to each unit, thereby completing the overall path splitting.

[0081] Step S204, based on the preset needling process parameters, the needling forming is completed by controlling the moving needle plate according to each single-layer needling path.

[0082] In a specific embodiment, if Figure 6 As shown, the needle arrangement mode is set to 5×5, the distance between needles is 10mm, the needle punching area is 50mm×50mm, each cell has the same path, and the needle punching process in the smallest unit is repeated until the overall needle punching path is completed to obtain the target needle punched fabric.

[0083] In this embodiment, a device for generating acupuncture paths and implementing processes is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made are omitted. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0084] This embodiment provides a device for generating acupuncture paths and implementing a process, such as Figure 7 As shown, including:

[0085] A minimum unit determination module 701 is used to determine the overall needling area based on the shape information of the target needling fabric, and divide the overall needling area into N minimum units, where the minimum unit is the needling area allocated to each needle;

[0086] A minimum unit acupuncture path generation module 702 is used to search within the minimum unit based on preset acupuncture process parameters using a reinforcement learning algorithm with a preset reward function as a target, and generate a minimum unit acupuncture path composed of multiple acupuncture coordinate points, wherein the minimum unit acupuncture path is a multi-layer acupuncture path generated within the minimum unit, which is equivalent to the superposition of multi-layer acupuncture paths on a two-dimensional plane, and the total number of acupuncture coordinate points within the minimum unit is equal to the product of acupuncture density, the number of fabric forming layers, and the minimum unit area;

[0087] The minimum unit single layer acupuncture path generation module 703 is used to use a heuristic search algorithm with a preset fitness function as a target, split the multiple acupuncture coordinate points of the minimum unit acupuncture path and distribute them to each layer, so as to obtain each single layer acupuncture path in the minimum unit. The overall acupuncture path of each layer is the total acupuncture path of each layer of the target acupuncture fabric, which is equivalent to the sum of N repetitions of the minimum unit acupuncture path;

[0088] The process implementation module 704 is used to obtain the target needle-punched fabric by controlling the moving needle plate to perform needle-punching forming according to each single-layer needling path based on the preset needling process parameters.

[0089] In some optional embodiments, the preset needling process parameters include: overall needling area, needle spacing, needle arrangement method, number of needles, diameter of needle barb parts, minimum unit, needling density and number of fabric forming layers.

[0090] In some optional embodiments, the minimum unit acupuncture path generation module 702 includes:

[0091] A process parameter determination unit, used for obtaining preset needling process parameters determined according to the target needling fabric;

[0092] The acupuncture path generation unit in the minimum unit is used to establish an intelligent agent for generating paths and an acupuncture simulation environment that interacts with it according to the preset acupuncture process parameters. The interaction between the intelligent agent and the acupuncture simulation environment is completed based on the proximal strategy search algorithm, and the Ripley's K function, the overlap of the acupuncture paths in the minimum unit and the Voronoi Figure 3 A reward function is used to search for the target and generate multi-layer acupuncture paths that meet the target discreteness, uniformity, and overlap within the smallest unit.

[0093] In some optional embodiments, the minimum unit single-layer acupuncture path generation module 703 includes:

[0094] A coordinate indexing unit is used to index the acupuncture coordinate points in the overall acupuncture path according to a preset order and assign an index value to each coordinate point;

[0095] The acupuncture path allocation unit is used to change the order of indexes through selection, crossover and mutation operations based on a multi-objective genetic algorithm, and to select and allocate the indexes according to the overlap of single-layer acupuncture paths, the overlap between layers and Voronoi Figure 3 The fitness function is taken as the target, and the acupuncture coordinates are allocated by slicing according to the number of layers to obtain each single-layer acupuncture path.

[0096] In some optional embodiments, Ripley's K function is used to evaluate the discreteness of the acupuncture path in the smallest unit, different K values ​​are calculated by different search radii d, and the different K values ​​are compared with the complete space randomness to determine the degree of aggregation and dispersion of the acupuncture points.

[0097] In some optional implementations, the process of using the uniformity of the acupuncture path in the minimum unit of the Voronoi diagram and the uniformity of each single-layer acupuncture path in the minimum unit is:

[0098] The uniformity of acupuncture coordinates was evaluated by calculating the mean square error between the Voronoi cell area when the point coordinates were uniformly distributed and the Voronoi cell area used to generate the acupuncture point coordinates. The calculation formula is as follows:

[0099]

[0100] Where A is the Voronoi cell area when the point coordinates are uniformly distributed, R i is the area of ​​the Voronoi cell of the i-th generated acupuncture point coordinate, n is the total number of point data, and β is a scaling factor used to adjust the weight of uniformity among the three reward functions.

[0101] In some optional embodiments, the process of calculating the overlap of acupuncture paths in the minimum unit is as follows: calculating the distance between the generated acupuncture points, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of the acupuncture paths in the minimum unit is obtained by counting;

[0102] The process of calculating the overlap of a single-layer acupuncture path is as follows: the distance between the generated acupuncture points is calculated, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of the single-layer acupuncture path is obtained by counting;

[0103] The process of calculating the interlayer overlap between single-layer acupuncture paths is as follows: calculate the distance between the acupuncture points of adjacent layers in two-dimensional space. If the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is judged as overlap. The interlayer overlap of the generated acupuncture path is obtained by counting.

[0104] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0105] The acupuncture path generation and process implementation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0106] The embodiment of the present invention also provides a computer device having the above Figure 7 The needle puncture path generation and process implementation device shown.

[0107] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 8A processor 10 is taken as an example.

[0108] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0109] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0110] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0111] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0112] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0113] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0114] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0115] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for generating acupuncture paths and implementing a process, characterized in that: The method comprises: Determine the overall needling area based on the shape information of the target needling fabric, and divide the overall needling area into N minimum units, where the minimum unit is the needling area assigned to each needle; In the smallest unit, based on the preset acupuncture process parameters, a reinforcement learning algorithm is used to search with a preset reward function as the target, and a minimum unit acupuncture path consisting of multiple acupuncture coordinate points is generated, including: Obtaining preset needling process parameters determined according to the target needling fabric; According to the preset needling process parameters, an intelligent agent for generating a path and a needling simulation environment for interacting with the intelligent agent are established. The interaction between the intelligent agent and the needling simulation environment is completed based on the proximal strategy search algorithm. The search is performed with three reward functions, namely, Ripley's K function, the overlap of the needling path in the minimum unit, and the Voronoi diagram, as the target, to generate a multi-layer needling path in the minimum unit that meets the target discreteness, uniformity, and overlap. The minimum unit needling path is a multi-layer needling path generated in the minimum unit, which is equivalent to the superposition of the multi-layer needling path in a two-dimensional plane. The total number of needling coordinate points in the minimum unit is equal to the product of the needling density, the number of fabric forming layers, and the minimum unit area. A heuristic search algorithm is used with a preset fitness function as the target to split multiple acupuncture coordinate points of the minimum unit acupuncture path and distribute them to each layer to obtain each single-layer acupuncture path in the minimum unit, including: Indexing the acupuncture coordinate points in the minimum unit acupuncture path according to a preset order, and assigning an index value to each coordinate point; Based on the multi-objective genetic algorithm, the order of index arrangement is changed through selection, crossover and mutation operations. The three fitness functions of single-layer acupuncture path overlap, inter-layer overlap and Voronoi diagram are taken as the targets. The acupuncture coordinates are allocated by slicing operations according to the number of layers to obtain the acupuncture paths of each single layer in the minimum unit; the overall acupuncture path of each layer is the total acupuncture path of each layer of the target acupuncture fabric, which is equivalent to the sum of N repetitions of the minimum unit acupuncture path; Based on the preset needling process parameters, the target needle-punched fabric is obtained by controlling the moving needle plate to perform needling forming according to each single-layer needling path.

2. The method according to claim 1, characterized in that The preset needling process parameters include: overall needling area, needle spacing, needle arrangement method, number of needles, diameter of needle barb parts, minimum unit, needling density and number of fabric forming layers.

3. The method according to claim 1, characterized in that Ripley's K function was used to evaluate the discreteness of the acupuncture path in the smallest unit. Different K values ​​were calculated by different search radii d. The different K values ​​were compared with the complete space randomness to determine the degree of aggregation and dispersion of the acupuncture points.

4. The method according to claim 1, characterized in that The process of using the Voronoi diagram to evaluate the uniformity of the acupuncture path within the minimum unit and the uniformity of each single-layer acupuncture path within the minimum unit is: The uniformity of acupuncture coordinates was evaluated by calculating the mean square error between the Voronoi cell area when the point coordinates were uniformly distributed and the Voronoi cell area used to generate the acupuncture point coordinates. The calculation formula is as follows: Where A is the Voronoi cell area when the point coordinates are uniformly distributed, R i is the area of ​​the Voronoi cell of the i-th generated acupuncture point coordinate, n is the total number of point data, and β is a scaling factor used to adjust the weight of uniformity among the three reward functions.

5. The method according to claim 1, characterized in that The process of calculating the overlap of acupuncture paths in the minimum unit is as follows: the distance between the generated acupuncture points is calculated, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of acupuncture paths in the minimum unit is obtained by counting; The process of calculating the overlap of a single-layer acupuncture path is as follows: the distance between the generated acupuncture points is calculated, and if the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is determined to be overlapping, and the overlap of the single-layer acupuncture path is obtained by counting; The process of calculating the interlayer overlap between single-layer acupuncture paths is as follows: calculate the distance between the acupuncture points of adjacent layers in two-dimensional space. If the distance between the acupuncture points is less than twice the radius of the acupuncture points, it is judged as overlap. The interlayer overlap of the generated acupuncture path is obtained by counting.

6. An acupuncture path generation and process implementation device, based on the acupuncture path generation and process implementation method according to claim 1, characterized in that: The device comprises: A minimum unit determination module, used to determine the overall needling area based on the shape information of the target needling fabric, and divide the overall needling area into N minimum units, wherein the minimum unit is the needling area allocated to each needle; A minimum unit acupuncture path generation module is used to search within the minimum unit based on preset acupuncture process parameters using a reinforcement learning algorithm with a preset reward function as a target, and generate a minimum unit acupuncture path composed of multiple acupuncture coordinate points, wherein the minimum unit acupuncture path is a multi-layer acupuncture path generated within the minimum unit, which is equivalent to the superposition of multi-layer acupuncture paths in a two-dimensional plane, and the total number of acupuncture coordinate points within the minimum unit is equal to the product of acupuncture density, the number of fabric forming layers, and the minimum unit area; A minimum unit single-layer acupuncture path generation module is used to use a heuristic search algorithm with a preset fitness function as the target, split multiple acupuncture coordinate points of the minimum unit acupuncture path and distribute them to each layer, so as to obtain each single-layer acupuncture path in the minimum unit. The overall acupuncture path of each layer is the total acupuncture path of each layer of the target acupuncture fabric, which is equivalent to the sum of N repetitions of the minimum unit acupuncture path; The process implementation module is used to obtain the target needle-punched fabric by controlling the moving needle plate to perform needle-punching forming according to each single-layer needling path based on the preset needling process parameters.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the acupuncture path generation and process implementation method according to any one of claims 1 to 5 by executing the computer instructions.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the acupuncture path generation and process implementation method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the needle path generation and process implementation method according to any one of claims 1 to 5.

Images