Helmet internal structure design method based on fractal geometric model

Abstract

The invention discloses a helmet internal structure design method based on a fractal geometric model. The method comprises the following steps: S1, constructing an initial fractal geometric model; s2, defining a multi-objective optimization function; s3, performing preliminary planning of material distribution based on the fractal geometric model and the multi-objective optimization function, and generating an initial design scheme of the energy absorption structure of the helmet; s4, obtaining a final design scheme of the energy absorption structure of the helmet; s5, performing simulation verification on the final design scheme of the helmet energy absorption structure; and S6, adjusting a fractal geometric model and a material layout scheme according to a simulation result, including optimizing fractal dimensions, geometric unit sizes and porosity parameters, and forming an actual design scheme of the energy-absorbing structure of the helmet according with the optimization target. The helmet effectively solves the contradiction among the protection performance, the light weight and the air permeability in the existing helmet design, and has important technical value and application prospect in the field of helmet design.

Description

Technical Field

[0001] The invention relates to the technical field of special equipment, and in particular to a method for designing the internal structure of a helmet based on a fractal geometry model. Background Art

[0002] With the development of industrial design and safety technology, helmets have become an important protective equipment to protect personal safety and are widely used in transportation, construction, extreme sports and military fields. In these scenarios, helmets need to have good impact resistance to protect the head from injury, while also meeting the requirements of lightweight, breathability and comfort. Traditional helmet designs find it difficult to strike a balance between these performances.

[0003] At present, the internal structure of the helmet usually adopts an integrated buffer material design, such as polystyrene or other foam materials. The material protects the user's head by absorbing and dispersing impact energy, but there are obvious technical limitations. Traditional helmet design mainly relies on the physical properties of the material to improve protection capabilities, so it is necessary to increase the thickness of the material to improve the energy absorption effect, which directly leads to an increase in the weight of the helmet and affects the comfort of the wearer. In addition, the dense distribution of the material limits the breathability of the helmet, which can easily cause discomfort to the user when worn for a long time or in a high temperature environment.

[0004] In recent years, some improved helmet designs have attempted to optimize performance by introducing new materials, but the following problems have been exposed in practical applications: On the one hand, the manufacturing cost of new materials is high and it is difficult to promote them on a large scale; on the other hand, traditional geometric design methods are insufficient in optimizing complex mechanical properties, making it difficult to efficiently disperse impact energy and ensure lightweight and breathable structures. When facing multi-directional impacts or non-uniform force distribution, traditional designs have difficulty in achieving multi-level dispersion and absorption of energy.

[0005] In summary, the prior art has significant defects in the following aspects:

[0006] 1. The balance between protective performance and weight: Traditional helmets improve protective performance by increasing material thickness, but this also increases the weight of the helmet, affecting the comfort of long-term wearing.

[0007] 2. Insufficient breathability: The dense material distribution limits the air circulation performance of the helmet, which can easily cause discomfort when used in high temperature or high humidity environments.

[0008] 3. Insufficient optimization of complex mechanical properties: Existing design methods are difficult to cope with multi-directional impacts and non-uniform force distribution, and the energy absorption effect is limited.

[0009] In response to the above problems, there is an urgent need for a helmet design method that can combine advanced geometric modeling technology and algorithm optimization to achieve multi-objective comprehensive optimization of protective performance, lightweight and breathability, and solve the shortcomings of existing technologies. Summary of the invention

[0010] One purpose of the present invention is to propose a method for designing the internal structure of a helmet based on a fractal geometry model. The present invention effectively solves the contradiction between protective performance, lightness and breathability in existing helmet designs, and has important technical value and application prospects in the field of helmet design.

[0011] A method for designing the internal structure of a helmet based on a fractal geometry model according to an embodiment of the present invention comprises the following steps:

[0012] S1. Construct an initial fractal geometry model, select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet, set the initial parameters of the fractal geometry model according to the target protection requirements, and generate a three-dimensional geometry model with self-similarity and multi-level characteristics;

[0013] S2. Determine the performance optimization target of the internal structure design of the helmet based on the initial fractal geometry model, and define a multi-objective optimization function based on the requirements of energy absorption performance, structural weight and breathability performance;

[0014] S3. Preliminary planning of material distribution based on fractal geometry model and multi-objective optimization function. Combining geometric units of fractal geometry with the characteristics of cushioning materials to generate preliminary material layout. The material layout is configured according to the density and porosity of the geometric units to generate the initial design of the helmet energy absorption structure.

[0015] S4. Optimize the initial design of the helmet energy absorption structure using a deep ant colony algorithm to obtain a final design of the helmet energy absorption structure;

[0016] S5. Simulate and verify the final design of the helmet energy absorption structure. Use finite element simulation tools to simulate the energy absorption performance in different impact directions to verify the multi-level impact energy dispersion effect of the final design of the helmet energy absorption structure and the optimization effect of material distribution on the weight and breathability of the helmet;

[0017] S6. Adjust the fractal geometry model and material layout plan according to the simulation results, including optimizing the fractal dimension, geometric unit size and porosity parameters, to form an actual design plan for the helmet energy absorption structure that meets the optimization goals.

[0018] Optionally, S1 includes the following contents:

[0019] S11. Select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet. According to the protective performance requirements of the helmet, set the basic shape of the fractal geometry model. The geometry of Menger sponge has a cubic basic unit. A multi-level structure is generated through fractal iteration. The self-similarity of the multi-level structure disperses the impact energy step by step along the multi-level structure.

[0020] S12. Set the initial parameters of the fractal geometry model, including the fractal dimension , Geometry unit size And the number of iterations N:

[0021] Fractal dimension Indicates the complexity of the geometric model. The fractal dimension is set according to the energy absorption requirements of the helmet. The higher the fractal dimension, the stronger the energy dispersion ability of the fractal geometric model.

[0022] Geometry unit size is the side length of the basic cube unit, which is set according to the internal space limitation of the helmet and the material distribution accuracy;

[0023] The number of iterations N determines the number of levels of the fractal geometry, which is set based on the material distribution requirements and energy absorption capacity optimization. The value range of N is 1 to 5;

[0024] S13. Generate a three-dimensional Menger sponge model using recursion:

[0025] ;

[0026] in, represents the fractal geometry model after the nth iteration, is the i-th mapping function, through the fractal geometry model The scaling and displacement realize the replication and arrangement of geometric units. The initial state is the basic cubic unit, with a size of ;

[0027] S14. In each iteration, the position and size of the geometric unit of the fractal geometric model are adjusted according to the scaling and displacement rules:

[0028] ;

[0029] Among them, x, y, z are the coordinates of the initial cube, are the offsets of the i-th scaling unit in three directions, and the offset value range is {-1, 0, 1}, which satisfies the arrangement rule of Menger sponge;

[0030] S15. After completing N iterations, a three-dimensional Menger sponge fractal geometric model with multi-level characteristics is generated, wherein the geometric units of each level are arranged according to a recursive formula, and the volume to surface area ratio of the three-dimensional Menger sponge fractal geometric model satisfies the following relationship:

[0031] ;

[0032] in, represents the total volume of the three-dimensional Menger sponge fractal geometry model after the Nth iteration, Represents the surface area of ​​the three-dimensional Menger sponge fractal geometry model after the Nth iteration.

[0033] Optionally, S2 includes the following contents:

[0034] S21, based on the initial fractal geometry model , combined with the protective performance requirements of the helmet, determine the performance optimization goals of the helmet's internal structure design, including energy absorption performance, structural weight and breathability;

[0035] S22, improve energy absorption performance so that the impact energy in the fractal geometry model The energy absorption performance target is defined as maximizing the impact energy absorbed. :

[0036] ;

[0037] in, Fractal geometry model Absorbed impact energy, Fractal geometry model The local stress distribution function inside, V is the fractal geometry model The volume of Fractal geometry model The spatial position vector of the midpoint;

[0038] S23, realize lightweight structure and optimize fractal geometry model The distribution of materials in the system reduces the overall weight and the objective is defined as minimizing the total mass M:

[0039] ;

[0040] Among them, M is the fractal geometry model The total mass, is the density of the cushioning material, Fractal geometry model Volume;

[0041] S24, improve the air permeability, make the fractal geometry model The pore structure has good air circulation characteristics, and the air permeability target is defined as maximizing the porosity P:

[0042] ;

[0043] Among them, P is the fractal geometry model The porosity, Fractal geometry model The solid part volume;

[0044] S25, the optimization requirements of comprehensive energy absorption performance, structural weight and breathability define the multi-objective optimization function F(x):

[0045] ;

[0046] in, is the weight coefficient of the optimization objective.

[0047] Optionally, the S3 includes the following contents:

[0048] S31, based on fractal geometry model And the multi-objective optimization function F(x), combined with the mechanical properties of the buffer material, establish the material distribution rules of the geometric unit and calculate the material density of the geometric unit :

[0049] ;

[0050] in, Fractal geometry model The material density of geometric unit i, is the local stress of geometric unit i, is the porosity of geometric unit i, and is the weight coefficient, which is used to adjust the influence of stress and porosity on material distribution;

[0051] S32, fractal geometry model The multi-level structure is divided into different density regions, according to the local stress of the geometric units in the region. and porosity Distribution optimizes overall material utilization:

[0052] ;

[0053] in, For local area The average material density, is the volume of geometric unit i, Fractal geometry model The kth region in is determined by the geometric unit stress and position;

[0054] S33. Calculate the overall energy absorption performance of the helmet energy absorption structure based on material distribution rules :

[0055] ;

[0056] in, is the total energy absorption performance of the helmet energy absorption structure, K is the fractal geometry model The total number of partitions, is the material energy absorption coefficient function of unit i, which is determined according to the characteristics of the cushioning material;

[0057] And generate the initial design of the helmet energy absorption structure:

[0058] ;

[0059] Where i represents the fractal geometry model The i-th geometric unit in m represents the fractal geometry model The total number of geometric cells in .

[0060] Optionally, S4 includes the following contents:

[0061] S41. Initial design of helmet energy absorption structure Enter the deep ant colony algorithm to model fractal geometry Geometric unit parameters and energy absorption performance To optimize the target, construct the search space of the optimization problem:

[0062] ;

[0063] in, is the search space of design parameters, are the minimum and maximum densities of the cushioning material, are the minimum and maximum porosity of the geometric unit;

[0064] S42. Fractal geometry model Represented as a graph structure:

[0065] ;

[0066] in, is a set of geometric unit nodes, is the set of Edges connecting nodes. is a node feature set, each node feature Represent stress, porosity, and material density of geometric elements;

[0067] S43. Use graph neural network to embed node features, extract multi-level correlation information in fractal geometry, and define node embedding vectors :

[0068] ;

[0069] Among them, N(i) is the node The set of adjacent nodes of For edge The characteristic mapping function is based on the fractal geometry model The topological relationship of adjacent nodes is weighted. Represents the node characteristics after embedding, integrating the stress, porosity and density information of each adjacent node;

[0070] S44. Model the solution construction process of the ant colony algorithm as a Markov decision process (S, A, P, R):

[0071] The state S contains the fractal parameters Distribution of materials , action A represents the adjustment of fractal parameters and material distribution, and the transition probability P is distributed through the strategy Determine that the reward R is determined by the objective function F(x), and define the action selection probability as:

[0072] ;

[0073] in, is the strategy parameter, is the set of optional actions in state S, Embedding vector for the combined node Feature mapping function with the target function F(x);

[0074] S45. Optimize strategy parameters using policy gradient method Improve optimization efficiency:

[0075] ;

[0076] in, is the objective function of the expected return of the strategy, Performance index value of the path;

[0077] S46. Update the pheromone matrix to make the search process tend to the path with good performance. The pheromone update rules are as follows:

[0078] ;

[0079] in, For edge The original pheromone concentration, is the pheromone volatility coefficient, is the objective function value of the current optimal path, is the feature similarity function based on the node embedding vector;

[0080] S47. After multiple iterations of path selection and pheromone updating, the optimal path that maximizes the objective function F(x) is selected from the path set to determine the final design of the helmet energy absorption structure:

[0081] ;

[0082] in, is the adjustment coefficient, which is used to balance the impact of the objective function value and pheromone distribution on path selection.

[0083] Optionally, S5 includes the following contents:

[0084] S51, Final design scheme based on helmet energy absorption structure Construct a finite element analysis model to transform the fractal geometry of the helmet's energy-absorbing structure , Material density distribution Input the material characteristic parameters into the simulation tool to establish a simulation model;

[0085] S52, setting the boundary conditions of the impact simulation, simulating the energy dispersion and absorption performance of the helmet under multi-directional impact forces, and defining the moment and force in the impact direction;

[0086] S53, finite element meshing for fractal geometry model of helmet energy absorption structure Perform multi-level grid division to refine the grid units in the impact force action area. The grid division rules are as follows:

[0087] A high-density mesh is used in the impact area, with a cell size of ;

[0088] A low-density grid is used in other areas, with a cell size of ;

[0089] The meshing meets the convergence conditions of the overall calculation:

[0090] ;

[0091] in, is the energy absorption value calculated for the nth simulation, is the convergence threshold;

[0092] S54. Use finite element simulation tools to dynamically simulate and analyze the multi-level impact energy dispersion performance of the helmet energy absorption structure, and calculate the energy absorption efficiency of the structure in various impact directions. ;

[0093] S55. Evaluate the optimization effect of material distribution on the weight of the helmet and calculate the total mass ;

[0094] S56. Verify the air permeability of the helmet's energy-absorbing structure and evaluate the air circulation effect by calculating the porosity P;

[0095] S57. Based on the simulation results, a comprehensive evaluation report of multi-level impact energy dispersion performance, total mass optimization effect and air permeability performance is output. If the simulation results do not meet the optimization requirements of the objective function F(x), the optimization step S4 is returned to readjust the fractal parameters or material distribution.

[0096] The beneficial effects of the present invention are:

[0097] (1) The present invention applies fractal geometry models to the design of helmet energy absorption structures, and uses the self-similarity and multi-level characteristics of fractal geometry to construct a three-dimensional energy absorption structure in the form of a Menger sponge. The energy absorption structure of traditional helmets is usually designed with uniformly distributed materials, while the present invention uses fractal geometry to achieve the gradual dispersion and dissipation of impact energy in a multi-level network, thereby greatly improving the energy absorption performance. Simulation results show that compared with the traditional helmet design with uniformly distributed materials, the present invention improves the multi-directional impact energy dispersion efficiency by more than 22%, while significantly reducing the risk of injury to the head caused by single-point impact.

[0098] (2) The present invention introduces graph neural network and reinforcement learning policy gradient method into the ant colony algorithm, models the design problem of the helmet energy absorption structure as a Markov decision process, and realizes efficient optimization of material distribution and structural parameters by extracting the correlation information of multi-level nodes in the fractal geometry model through the graph neural network. Compared with the traditional topology optimization method, the present invention significantly improves the design efficiency and optimization effect. Experimental results show that the total mass of the optimized helmet is reduced by 18%, and lightweight design is achieved while ensuring energy absorption performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0100] Figure 1 A flowchart of a method for designing the internal structure of a helmet based on a fractal geometry model proposed by the present invention;

[0101] Figure 2This is a schematic diagram of the optimization process of optimizing the energy absorption structure of a helmet by using a deep ant colony algorithm in a helmet internal structure design method based on a fractal geometry model proposed in the present invention. DETAILED DESCRIPTION

[0102] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0103] refer to Figure 1-Figure 2 , a method for designing the internal structure of a helmet based on a fractal geometry model, comprising the following steps:

[0104] S1. Construct an initial fractal geometry model, select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet, set the initial parameters of the fractal geometry model according to the target protection requirements, and generate a three-dimensional geometry model with self-similarity and multi-level characteristics;

[0105] S2. Determine the performance optimization target of the internal structure design of the helmet based on the initial fractal geometry model, and define a multi-objective optimization function based on the requirements of energy absorption performance, structural weight and breathability performance;

[0106] S3. Preliminary planning of material distribution based on fractal geometry model and multi-objective optimization function. Combining geometric units of fractal geometry with the characteristics of cushioning materials to generate preliminary material layout. The material layout is configured according to the density and porosity of the geometric units to generate the initial design of the helmet energy absorption structure.

[0107] S4. Optimize the initial design of the helmet energy absorption structure using a deep ant colony algorithm to obtain a final design of the helmet energy absorption structure;

[0108] S5. Simulate and verify the final design of the helmet energy absorption structure. Use finite element simulation tools to simulate the energy absorption performance in different impact directions to verify the multi-level impact energy dispersion effect of the final design of the helmet energy absorption structure and the optimization effect of material distribution on the weight and breathability of the helmet;

[0109] S6. Adjust the fractal geometry model and material layout plan according to the simulation results, including optimizing the fractal dimension, geometric unit size and porosity parameters, to form an actual design plan for the helmet energy absorption structure that meets the optimization goals.

[0110] In this implementation, S1 includes the following contents:

[0111] S11. Select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet. According to the protective performance requirements of the helmet, set the basic shape of the fractal geometry model. The geometry of Menger sponge has a cubic basic unit. A multi-level structure is generated through fractal iteration. The self-similarity of the multi-level structure disperses the impact energy step by step along the multi-level structure.

[0112] S12. Set the initial parameters of the fractal geometry model, including the fractal dimension , geometric unit size And the number of iterations N:

[0113] Fractal dimension Indicates the complexity of the geometric model. The fractal dimension is set according to the energy absorption requirements of the helmet. The higher the fractal dimension, the stronger the energy dispersion ability of the fractal geometric model.

[0114] Geometry unit size is the side length of the basic cube unit, which is set according to the internal space limitation of the helmet and the material distribution accuracy;

[0115] The number of iterations N determines the number of levels of the fractal geometry, which is set based on the material distribution requirements and energy absorption capacity optimization. The value range of N is 1 to 5;

[0116] S13. Generate a three-dimensional Menger sponge model using recursion:

[0117] ;

[0118] in, represents the fractal geometry model after the nth iteration, is the i-th mapping function, through the fractal geometry model The scaling and displacement realize the replication and arrangement of geometric units. The initial state is the basic cubic unit, with a size of ;

[0119] S14. In each iteration, the position and size of the geometric unit of the fractal geometric model are adjusted according to the scaling and displacement rules:

[0120] ;

[0121] Among them, x, y, z are the coordinates of the initial cube, are the offsets of the i-th scaling unit in three directions, and the offset value range is {-1, 0, 1}, which satisfies the arrangement rule of Menger sponge;

[0122] S15. After completing N iterations, a three-dimensional Menger sponge fractal geometric model with multi-level characteristics is generated, wherein the geometric units of each level are arranged according to a recursive formula, and the volume to surface area ratio of the three-dimensional Menger sponge fractal geometric model satisfies the following relationship:

[0123] ;

[0124] in, represents the total volume of the three-dimensional Menger sponge fractal geometry model after the Nth iteration, Represents the surface area of ​​the three-dimensional Menger sponge fractal geometry model after the Nth iteration.

[0125] In this implementation, S2 includes the following contents:

[0126] S21, based on the initial fractal geometry model , combined with the protective performance requirements of the helmet, determine the performance optimization goals of the helmet's internal structure design, including energy absorption performance, structural weight and breathability;

[0127] S22, improve energy absorption performance so that the impact energy in the fractal geometry model The energy absorption performance target is defined as maximizing the impact energy absorbed. :

[0128] ;

[0129] in, Fractal geometry model Absorbed impact energy, Fractal geometry model The local stress distribution function inside, V is the fractal geometry model The volume of Fractal geometry model The spatial position vector of the midpoint;

[0130] S23, realize lightweight structure and optimize fractal geometry model The distribution of materials in the system reduces the overall weight and the objective is defined as minimizing the total mass M:

[0131] ;

[0132] Among them, M is the fractal geometry model The total mass, is the density of the cushioning material, Fractal geometry model Volume;

[0133] S24, improve the air permeability, make the fractal geometry model The pore structure has good air circulation characteristics, and the air permeability target is defined as maximizing the porosity P:

[0134] ;

[0135] Among them, P is the fractal geometry model The porosity, Fractal geometry model The solid part volume;

[0136] S25, the optimization requirements of comprehensive energy absorption performance, structural weight and breathability define the multi-objective optimization function F(x):

[0137] ;

[0138] in, is the weight coefficient of the optimization objective.

[0139] In this implementation, S3 includes the following contents:

[0140] S31, based on fractal geometry model And the multi-objective optimization function F(x), combined with the mechanical properties of the buffer material, establish the material distribution rules of the geometric unit and calculate the material density of the geometric unit :

[0141] ;

[0142] in, Fractal geometry model The material density of geometric unit i, is the local stress of geometric unit i, is the porosity of geometric unit i, and is the weight coefficient, which is used to adjust the influence of stress and porosity on material distribution;

[0143] S32, fractal geometry model The multi-level structure is divided into different density regions, according to the local stress of the geometric units in the region. and porosity Distribution optimizes overall material utilization:

[0144] ;

[0145] in, For local area The average material density, is the volume of geometric unit i, Fractal geometry model The kth region in is determined by the geometric unit stress and position;

[0146] S33. Calculate the overall energy absorption performance of the helmet energy absorption structure based on material distribution rules :

[0147] ;

[0148] in, is the total energy absorption performance of the helmet energy absorption structure, K is the fractal geometry model The total number of partitions, is the material energy absorption coefficient function of unit i, which is determined according to the characteristics of the cushioning material;

[0149] And generate the initial design of the helmet energy absorption structure:

[0150] ;

[0151] Where i represents the fractal geometry model The i-th geometric unit in m represents the fractal geometry model The total number of geometric cells in .

[0152] In this implementation, S4 includes the following contents:

[0153] S41. Initial design of helmet energy absorption structure Enter the deep ant colony algorithm to model fractal geometry Geometric unit parameters and energy absorption performance To optimize the target, construct the search space of the optimization problem:

[0154] ;

[0155] in, is the search space of design parameters, are the minimum and maximum densities of the cushioning material, are the minimum and maximum porosity of the geometric unit;

[0156] S42. Fractal geometry model Represented as a graph structure:

[0157] ;

[0158] in, is a set of geometric unit nodes, is the set of Edges connecting nodes. is a node feature set, each node feature Represent stress, porosity, and material density of geometric elements;

[0159] S43. Use graph neural network to embed node features, extract multi-level correlation information in fractal geometry, and define node embedding vectors :

[0160] ;

[0161] Among them, N(i) is the node The set of adjacent nodes of For edge The characteristic mapping function is based on the fractal geometry model The topological relationship of adjacent nodes is weighted. Represents the node characteristics after embedding, integrating the stress, porosity and density information of each adjacent node;

[0162] S44. Model the solution construction process of the ant colony algorithm as a Markov decision process (S, A, P, R):

[0163] The state S contains the fractal parameters Distribution of materials , action A represents the adjustment of fractal parameters and material distribution, and the transition probability P is distributed through the strategy Determine that the reward R is determined by the objective function F(x), and define the action selection probability as:

[0164] ;

[0165] in, is the strategy parameter, is the set of optional actions in state S, Embedding vector for the combined node Feature mapping function with the target function F(x);

[0166] S45. Optimize strategy parameters using policy gradient method Improve optimization efficiency:

[0167] ;

[0168] in, is the objective function of the expected return of the strategy, Performance index value of the path;

[0169] S46. Update the pheromone matrix to make the search process tend to the path with good performance. The pheromone update rules are as follows:

[0170] ;

[0171] in, For edge The original pheromone concentration, is the pheromone volatility coefficient, is the objective function value of the current optimal path, is the feature similarity function based on the node embedding vector;

[0172] S47. After multiple iterations of path selection and pheromone updating, the optimal path that maximizes the objective function F(x) is selected from the path set to determine the final design of the helmet energy absorption structure:

[0173] ;

[0174] in, is the adjustment coefficient, which is used to balance the impact of the objective function value and pheromone distribution on path selection.

[0175] In this implementation, S5 includes the following contents:

[0176] S51, Final design scheme based on helmet energy absorption structure Construct a finite element analysis model to transform the fractal geometry of the helmet's energy-absorbing structure , Material density distribution Input the material characteristic parameters into the simulation tool to establish a simulation model;

[0177] S52, setting the boundary conditions of the impact simulation, simulating the energy dispersion and absorption performance of the helmet under multi-directional impact forces, and defining the moment and force in the impact direction;

[0178] S53, finite element meshing for fractal geometry model of helmet energy absorption structure Perform multi-level grid division to refine the grid units in the impact force action area. The grid division rules are as follows:

[0179] A high-density mesh is used in the impact area, with a cell size of ;

[0180] A low-density grid is used in other areas, with a cell size of ;

[0181] The meshing meets the convergence conditions of the overall calculation:

[0182] ;

[0183] in, is the energy absorption value calculated for the nth simulation, is the convergence threshold;

[0184] S54. Use finite element simulation tools to dynamically simulate and analyze the multi-level impact energy dispersion performance of the helmet energy absorption structure, and calculate the energy absorption efficiency of the structure in various impact directions. ;

[0185] S55. Evaluate the optimization effect of material distribution on the weight of the helmet and calculate the total mass ;

[0186] S56. Verify the air permeability of the helmet's energy-absorbing structure and evaluate the air circulation effect by calculating the porosity P;

[0187] S57. Based on the simulation results, a comprehensive evaluation report of multi-level impact energy dispersion performance, total mass optimization effect and air permeability performance is output. If the simulation results do not meet the optimization requirements of the objective function F(x), the optimization step S4 is returned to readjust the fractal parameters or material distribution.

[0188] Embodiment 1:

[0189] Embodiment In an extreme sports event in August 2023, a helmet manufacturing company conducted a practical application test on the helmet designed based on the fractal geometry model and the deep ant colony algorithm of the present invention. The goal of the event was to verify the protective performance, lightweight and breathability of the helmet under extreme conditions. The event was located in the desert terrain with an ambient temperature of up to 40°C. The athletes needed to wear helmets continuously for long-term mountain riding and rock climbing challenges.

[0190] One day before the competition, the technical team registered the equipment of all contestants, including helmets of traditional design and helmets designed according to the present invention. 50 contestants were randomly selected for the test, 25 of whom wore traditional helmets and 25 wore helmets designed according to the present invention. The groups were numbered as Group A (traditional design) and Group B (designed according to the present invention).

[0191] During the test, the temperature, humidity, and impact force sensor data inside each athlete’s helmet are recorded in real time. The equipment numbers are sensors ID001 to ID050. The data is uploaded to the cloud database at a frequency of 10 times per second for real-time analysis.

[0192] Event 1: Air permeability test under high temperature conditions

[0193] In the third hour of the cycling challenge, athlete ID013 (Group B) reported that the temperature inside the helmet was significantly lower than usual. Through sensor data analysis, it was found that under the conditions of an ambient temperature of 40°C and a humidity of 50%, the internal temperature of the helmet designed by the present invention worn by athlete ID013 was 37.2°C and the humidity was 65%, which was significantly improved compared to the internal temperature (41.8°C) and humidity (78%) of the traditional helmet worn by athlete ID005 in Group A.

[0194] Further analysis of the data showed that the porosity distribution of athlete ID013's helmet showed that the porosity of the top area of ​​the helmet was 42%, and the porosity of the forehead area was 36%, which effectively promoted air circulation inside the helmet and reduced heat accumulation under high temperature conditions. After the event, athlete ID013 reported that the helmet maintained good comfort throughout the entire ride, and there was no stuffiness or excessive sweating on the head.

[0195] Event 2: Impact performance verification

[0196] During the rock climbing challenge, contestant ID026 (Group B) fell from a height of 2.5 meters due to a mistake in his footwork, and the top of his helmet collided with hard rock. Sensor data showed that the instantaneous impact force on the top of the helmet reached 1568 N, while the dispersed impact force recorded by the sensor inside the helmet was 362 N, which is far below the safety threshold of the human head (800 N). In comparison, contestant ID018 from Group A fell under similar conditions with an impact force of 1896 N, and the dispersed impact force recorded by the sensor inside the helmet was 735 N. Although it did not exceed the safety threshold, it caused obvious shock to the head.

[0197] Subsequent inspection found that the helmet worn by athlete ID026 still maintained the integrity of its overall structure after the collision. The multi-level energy-absorbing structure of the fractal geometry model effectively dispersed the impact energy to each level of the helmet network, while traditionally designed helmets experienced local material compression and deformation under high impact forces, resulting in reduced energy absorption efficiency.

[0198] Event 3: Long-term wearing comfort test

[0199] The final stage of the event was a 6-hour high-temperature off-road challenge, during which the contestants needed to wear helmets continuously to complete the race. Through real-time data monitoring, it was found that the internal temperature of the helmets of Group B contestants was maintained at an average of 38°C and the humidity was 70% during the entire process. Compared with the internal temperature (43°C) and humidity (82%) of the helmets of Group A contestants, the helmets designed by the present invention had significant advantages.

[0200] Player ID034 (Group B) said in an interview after the game that the lightweight design of the helmet made it possible to wear it for a long time without noticeable fatigue, and there was no discomfort in the head and neck after the game. Analysis showed that the total weight of the helmet designed by the present invention was 425 g, while the average weight of the traditional helmet of Group A was 560 g. The lightweight design significantly reduced the burden on the players.

[0201] In the test, 50 players were randomly selected, 25 of whom wore traditional helmets and 25 wore helmets designed based on the present invention. The comparative data analysis of the groups numbered as Group A (traditional design) and Group B (design of the present invention) is shown in Table 1 below:

[0202] Table 1 Comparison data of test indicators

[0203] Test indicators Traditional Helmets (Group A) Helmets of the present invention (Group B) Average internal temperature (℃) 42.5 37.8 Average internal humidity (%) 78 68 Collision impact force dispersion (N) 735 362 Total weight (g) 560 425 Long-term wearing comfort score (out of 10) 7.2 9.1

[0204] Through the application in real extreme sports events, this embodiment verifies the feasibility and effectiveness of the design method of the present invention. The test results show that the helmet designed by the present invention is significantly better than the traditional design in terms of energy absorption performance, light weight and breathability, especially in extreme conditions of high temperature, long-term wear and sudden impact, and shows excellent performance, providing higher safety and comfort experience for extreme sports enthusiasts.

[0205] The present invention applies fractal geometry models to the design of helmet energy absorption structures, and utilizes the self-similarity and multi-level characteristics of fractal geometry to construct a three-dimensional energy absorption structure in the form of a Menger sponge. The energy absorption structure of traditional helmets is usually designed with uniformly distributed materials, while the present invention uses fractal geometry to achieve the gradual dispersion and dissipation of impact energy in a multi-level network, thereby greatly improving the energy absorption performance. Simulation results show that compared with the traditional helmet design with uniformly distributed materials, the present invention improves the multi-directional impact energy dispersion efficiency by more than 22%, while significantly reducing the risk of injury to the head from a single-point impact.

[0206] The present invention introduces graph neural network and reinforcement learning policy gradient method into the ant colony algorithm, models the design problem of the helmet energy absorption structure as a Markov decision process, and realizes efficient optimization of material distribution and structural parameters by extracting the correlation information of multi-level nodes in the fractal geometry model through the graph neural network. Compared with the traditional topology optimization method, the present invention significantly improves the design efficiency and optimization effect. Experimental results show that the total mass of the optimized helmet is reduced by 18%, and lightweight design is achieved while ensuring energy absorption performance.

[0207] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for designing the internal structure of a helmet based on a fractal geometry model, characterized in that: The steps include: S1. Construct an initial fractal geometry model, select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet, set the initial parameters of the fractal geometry model according to the target protection requirements, and generate a three-dimensional geometry model with self-similarity and multi-level characteristics; S2. Determine the performance optimization target of the internal structure design of the helmet based on the initial fractal geometry model, and define a multi-objective optimization function based on the requirements of energy absorption performance, structural weight and breathability performance; S3. Preliminary planning of material distribution based on fractal geometry model and multi-objective optimization function. Combining geometric units of fractal geometry with the characteristics of cushioning materials to generate preliminary material layout. The material layout is configured according to the density and porosity of the geometric units to generate the initial design of the helmet energy absorption structure. S4. Optimize the initial design of the helmet energy absorption structure using a deep ant colony algorithm to obtain a final design of the helmet energy absorption structure; S5. Simulate and verify the final design of the helmet energy absorption structure. Use finite element simulation tools to simulate the energy absorption performance in different impact directions to verify the multi-level impact energy dispersion effect of the final design of the helmet energy absorption structure and the optimization effect of material distribution on the weight and breathability of the helmet; S6. Adjust the fractal geometry model and material layout plan according to the simulation results, including optimizing the fractal dimension, geometric unit size and porosity parameters, to form an actual design plan for the helmet energy absorption structure that meets the optimization goals.

2. A method for designing the internal structure of a helmet based on a fractal geometry model according to claim 1, characterized in that: The S1 includes the following contents: S11. Select Menger sponge as the basic fractal geometry of the internal energy absorption structure of the helmet. According to the protective performance requirements of the helmet, set the basic shape of the fractal geometry model. The geometry of Menger sponge has a cubic basic unit. A multi-level structure is generated through fractal iteration. The self-similarity of the multi-level structure disperses the impact energy step by step along the multi-level structure. S12. Set the initial parameters of the fractal geometry model, including the fractal dimension , geometric unit size And the number of iterations N: Fractal dimension Indicates the complexity of the geometric model. The fractal dimension is set according to the energy absorption requirements of the helmet. The higher the fractal dimension, the stronger the energy dispersion ability of the fractal geometric model. Geometry unit size is the side length of the basic cube unit, which is set according to the internal space limitation of the helmet and the material distribution accuracy; The number of iterations N determines the number of levels of the fractal geometry, which is set based on the material distribution requirements and energy absorption capacity optimization. The value range of N is 1 to 5; S13. Generate a three-dimensional Menger sponge model using recursion: ； in, represents the fractal geometry model after the nth iteration, is the i-th mapping function, through the fractal geometry model The scaling and displacement realize the replication and arrangement of geometric units. The initial state is the basic cubic unit, with a size of ; S14. In each iteration, the position and size of the geometric unit of the fractal geometric model are adjusted according to the scaling and displacement rules: ； Among them, x, y, z are the coordinates of the initial cube, are the offsets of the i-th scaling unit in three directions, and the offset value range is {-1, 0, 1}, which satisfies the arrangement rule of Menger sponge; S15. After completing N iterations, a three-dimensional Menger sponge fractal geometric model with multi-level characteristics is generated, wherein the geometric units of each level are arranged according to a recursive formula, and the volume to surface area ratio of the three-dimensional Menger sponge fractal geometric model satisfies the following relationship: ； in, represents the total volume of the three-dimensional Menger sponge fractal geometry model after the Nth iteration, Represents the surface area of ​​the three-dimensional Menger sponge fractal geometry model after the Nth iteration.

3. The method for designing the internal structure of a helmet based on a fractal geometry model according to claim 1, characterized in that: The S2 includes the following contents: S21, based on the initial fractal geometry model , combined with the protective performance requirements of the helmet, determine the performance optimization goals of the helmet's internal structure design, including energy absorption performance, structural weight and breathability; S22, improve energy absorption performance so that the impact energy in the fractal geometry model The energy absorption performance target is defined as maximizing the impact energy absorbed. : ； in, Fractal geometry model Absorbed impact energy, Fractal geometry model The local stress distribution function inside, V is the fractal geometry model The volume of Fractal geometry model The spatial position vector of the midpoint; S23, realize lightweight structure and optimize fractal geometry model The distribution of materials in the system reduces the overall weight and the objective is defined as minimizing the total mass M: ； Among them, M is the fractal geometry model The total mass, is the density of the cushioning material, Fractal geometry model Volume; S24, improve the air permeability, make the fractal geometry model The pore structure has good air circulation characteristics, and the air permeability target is defined as maximizing the porosity P: ； Among them, P is the fractal geometry model The porosity, Fractal geometry model The solid part volume; S25, the optimization requirements of comprehensive energy absorption performance, structural weight and breathability define the multi-objective optimization function F(x): ； in, is the weight coefficient of the optimization objective.

4. The method for designing the internal structure of a helmet based on a fractal geometry model according to claim 1, characterized in that: The S3 includes the following: S31, based on fractal geometry model And the multi-objective optimization function F(x), combined with the mechanical properties of the buffer material, establish the material distribution rules of the geometric unit and calculate the material density of the geometric unit : ； in, Fractal geometry model The material density of geometric unit i, is the local stress of geometric unit i, is the porosity of geometric unit i, and is the weight coefficient, which is used to adjust the influence of stress and porosity on material distribution; S32, fractal geometry model The multi-level structure is divided into different density regions, according to the local stress of the geometric units in the region. and porosity Distribution optimizes overall material utilization: ； in, For local area The average material density, is the volume of geometric unit i, Fractal geometry model The kth region in is determined by the geometric unit stress and position; S33. Calculate the overall energy absorption performance of the helmet energy absorption structure based on material distribution rules : ； in, is the total energy absorption performance of the helmet energy absorption structure, K is the fractal geometry model The total number of partitions, is the material energy absorption coefficient function of unit i, which is determined according to the characteristics of the cushioning material; And generate the initial design of the helmet energy absorption structure: ； Where i represents the fractal geometry model The i-th geometric unit in m represents the fractal geometry model The total number of geometric cells in .

5. The method for designing the internal structure of a helmet based on a fractal geometry model according to claim 1, characterized in that: The S4 includes the following: S41. Initial design of helmet energy absorption structure Enter the deep ant colony algorithm to model fractal geometry Geometric unit parameters and energy absorption performance To optimize the target, construct the search space of the optimization problem: ； in, is the search space of design parameters, are the minimum and maximum densities of the cushioning material, are the minimum and maximum porosity of the geometric unit; S42. Fractal geometry model Represented as a graph structure: ； in, is a set of geometric unit nodes, is the set of Edges connecting nodes. is a node feature set, each node feature Represent stress, porosity, and material density of geometric elements; S43. Use graph neural network to embed node features, extract multi-level correlation information in fractal geometry, and define node embedding vectors : ； Among them, N(i) is the node The set of adjacent nodes of For edge The characteristic mapping function is based on the fractal geometry model The topological relationship of adjacent nodes is weighted. Represents the node characteristics after embedding, integrating the stress, porosity and density information of each adjacent node; S44. Model the solution construction process of the ant colony algorithm as a Markov decision process (S, A, P, R): The state S contains the fractal parameters Distribution of materials , action A represents the adjustment of fractal parameters and material distribution, and the transition probability P is distributed through the strategy Determine that the reward R is determined by the objective function F(x), and define the action selection probability as: ； in, is the strategy parameter, is the set of optional actions in state S, Embedding vector for the combined node Feature mapping function with the target function F(x); S45. Optimize strategy parameters using policy gradient method Improve optimization efficiency: ； in, is the objective function of the expected return of the strategy, Performance index value of the path; S46. Update the pheromone matrix to make the search process tend to the path with good performance. The pheromone update rules are as follows: ； in, For edge The original pheromone concentration, is the pheromone volatility coefficient, is the objective function value of the current optimal path, is the feature similarity function based on the node embedding vector; S47. After multiple iterations of path selection and pheromone updating, the optimal path that maximizes the objective function F(x) is selected from the path set to determine the final design of the helmet energy absorption structure: ； in, is the adjustment coefficient, which is used to balance the impact of the objective function value and pheromone distribution on path selection.

6. The method for designing the internal structure of a helmet based on a fractal geometry model according to claim 1, characterized in that: The S5 includes the following contents: S51, Final design scheme based on helmet energy absorption structure Construct a finite element analysis model to transform the fractal geometry of the helmet's energy-absorbing structure , Material density distribution Input the material characteristic parameters into the simulation tool to establish a simulation model; S52, setting the boundary conditions of the impact simulation, simulating the energy dispersion and absorption performance of the helmet under multi-directional impact forces, and defining the moment and force in the impact direction; S53, finite element meshing for fractal geometry model of helmet energy absorption structure Perform multi-level grid division to refine the grid units in the impact force action area. The grid division rules are as follows: A high-density mesh is used in the impact area, with a cell size of ; A low-density grid is used in other areas, with a cell size of ; The meshing meets the convergence conditions of the overall calculation: ； in, is the energy absorption value calculated for the nth simulation, is the convergence threshold; S54. Use finite element simulation tools to dynamically simulate and analyze the multi-level impact energy dispersion performance of the helmet energy absorption structure, and calculate the energy absorption efficiency of the structure in various impact directions. ; S55. Evaluate the optimization effect of material distribution on the weight of the helmet and calculate the total mass ; S56. Verify the air permeability of the helmet's energy-absorbing structure and evaluate the air circulation effect by calculating the porosity P; S57. Based on the simulation results, a comprehensive evaluation report of multi-level impact energy dispersion performance, total mass optimization effect and air permeability performance is output. If the simulation results do not meet the optimization requirements of the objective function F(x), the optimization step S4 is returned to readjust the fractal parameters or material distribution.

Images