Ant colony optimization algorithm-based layout method for wear-resistant materials of labor protection shoes

Abstract

The application discloses an ant colony optimization algorithm-based layout method for wear-resistant materials of safety shoes, S1, a safety shoe wear data set is constructed; S2, a surface of the safety shoes is divided into multiple priority areas; S3, initial concentrations of pheromones are distributed according to priority area distribution of fractal characteristic values; S4, an optimization objective function is established; S5, an optimal material layout path of a high-priority area is gradually selected; S6, fitness values of each path are calculated according to path search results and the optimization objective function, and path pheromone concentrations are updated by using the fitness values; S7, a final global optimal path is obtained through multiple rounds of iterations of S1-S6; S8, a final optimal layout scheme of the wear-resistant materials of the safety shoes is output; and S9, the final optimal layout scheme is verified. The application can provide an efficient and scientific optimization scheme in the layout design of the wear-resistant materials of the safety shoes, and brings remarkable technical values and economic benefits for actual applications.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of special equipment, in particular to a layout method of wear-resistant materials for safety shoes based on an ant colony optimization algorithm. BACKGROUND

[0002] With the rapid development of material science and optimization algorithms, as an important personal protective equipment, the wear resistance and economic benefits of safety shoes have attracted widespread attention. The wear resistance of safety shoes is directly related to the safety of users and the service life of shoes. The reasonable distribution and optimized layout of wear-resistant materials are key factors to improve the overall performance. However, the current design method for the layout of wear-resistant materials of safety shoes still has many deficiencies, and it is difficult to meet the needs of multi-objective optimization while considering performance and cost.

[0003] Currently, the layout design of wear-resistant materials of safety shoes mainly relies on experience and simple rule distribution. Designers select high-wear-resistant materials in high-wear areas and low-cost ordinary materials in low-wear areas according to the stress and wear characteristics of different parts of safety shoes. Although this experience-based design method can improve wear resistance to some extent, it has obvious limitations. In recent years, some research has tried to introduce optimization algorithms for material layout optimization. Optimization algorithms improve material use efficiency through certain mathematical models. However, due to the simplicity of the model and the failure to fully consider the specific use scenarios and multi-objective requirements of safety shoes, the optimization effect is limited.

[0004] The existing technology has the following significant defects in the layout design of wear-resistant materials of safety shoes:

[0005] In summary, the existing technology lacks comprehensiveness, delicacy, and adaptability in the layout design of wear-resistant materials, and cannot effectively balance multi-objective requirements. At the same time, the efficiency and quality of the optimization process also cannot meet the requirements of practical applications. Therefore, a new technical solution is needed to overcome the above-mentioned defects, improve wear resistance, and optimize material use efficiency and overall performance. SUMMARY

[0006] One object of the present application is to provide a layout method of wear-resistant materials for safety shoes based on an ant colony optimization algorithm. The present application can provide an efficient and scientific optimization scheme in the layout design of wear-resistant materials for safety shoes, bringing significant technical value and economic benefits to practical applications.

[0007] According to an embodiment of the present application, a layout method of wear-resistant materials for safety shoes based on an ant colony optimization algorithm includes the following steps:

[0008] S1, experimental testing and use feedback collection of wear characteristics data of different parts of safety shoes are performed to construct a safety shoe wear data set including wear intensity, frequency distribution, and stress distribution;

[0009] S2, based on the labor shoes wear data set, using spatial fractal algorithm to construct the fractal feature model of labor shoes surface, calculate the fractal feature value of each part of the labor shoes surface, the fractal feature value represents the area wear complexity and intensity distribution, according to the size of fractal feature value distribution map is generated, the labor shoes surface is divided into multiple priority areas, wherein the higher the fractal feature value of the area priority is higher;

[0010] S3, based on the fractal feature value distribution map initialization ant colony optimization algorithm parameters, including the number of ants, pheromone evaporation coefficient, heuristic factor and iteration times, according to the priority area distribution of fractal feature value distribution of initial concentration of pheromone, the higher the fractal feature value of the area pheromone concentration is greater, to guide the ant search path priority covering high wear area;

[0011] S4, the optimization objective function is established, the optimization objective function considers the wear resistance of labor shoes, production cost, weight distribution and comfort, the priority area generated by fractal algorithm is used as the constraint condition of ant path search, that is, high priority area needs to be covered in path search;

[0012] S5, the layout problem of wear-resistant materials in different parts of labor shoes is converted into ant path search problem, the node in the ant path represents the type, thickness and arrangement of different materials, each ant in the path search follows the principle of the joint action of pheromone concentration and heuristic factor, and gradually selects the optimal material layout path of high priority area;

[0013] S6, according to the path search result and the optimization objective function, the fitness value of each path is calculated, and the pheromone concentration of the path is updated by using the fitness value, the higher the fitness value, the greater the pheromone concentration, when the fractal feature value distribution changes in the optimization process, the fractal priority area and the corresponding pheromone concentration distribution are updated dynamically;

[0014] S7, through the multiple iterations of S1-S6, gradually converging to the global optimal path, the optimal material layout scheme of the current path is recorded in each iteration, and the final global optimal path is obtained;

[0015] S8, according to the final global optimal path, the optimal layout scheme of labor shoes wear-resistant materials is output, including the material type, thickness configuration and arrangement of different areas, so that the labor shoes wear-resistant materials meet the wear resistance performance requirements, while considering the production process feasibility and cost control;

[0016] S9, the optimal material layout scheme is input to the material performance test platform to verify the wear resistance, comfort and production feasibility, according to the verification result, the material distribution of the area which does not meet the requirements in the scheme is adjusted, and the fractal feature value is updated and re-iterated.

[0017] Optionally, the S1 comprises the following steps:

[0018] S11, performing experimental testing on the wear characteristics data of different parts of the safety shoes, selecting test samples and dividing the surface of the safety shoes into measurement regions according to actual use scenarios ;

[0019] S12, measuring the wear depth and wear area of each measurement region using standard wear testing equipment, and calculating the wear intensity of the measurement region ; ;

[0020] wherein, is the wear depth of the measurement region , is the wear area of the measurement region ;

[0021] S13, statistically analyzing the wear frequency of each measurement region through long-term use feedback, and recording the wear frequency of each measurement region ;

[0022] S14, measuring the stress distribution of each measurement region based on the wear experiment and material stress analysis, and collecting the corresponding stress value ;

[0023] S15, normalizing the collected data of the wear intensity , wear frequency and stress distribution respectively;

[0024] S16, constructing a safety shoe wear data set according to the normalized data:

[0025] ;

[0026] wherein, N is the total number of divided measurement regions, is the normalized wear intensity of the measurement region , is the normalized wear frequency of the measurement region , is the normalized stress value of the measurement region .

[0027] Optionally, the S2 comprises the following steps:

[0028] S21, calculating the comprehensive wear index of each measurement region based on the safety shoe wear data set:

[0029] ;

[0030] wherein, , , are weight coefficients, respectively, for balancing the influence of wear intensity, wear frequency and stress on the comprehensive wear index ;

[0031] S22, calculating the fractal characteristic value of each measurement area using a multi-scale fractal analysis method; , taking the comprehensive wear index as a spatial distribution function M(x, y) in the measurement area , wherein x, y are the positions of the measurement area in the safety shoe surface coordinate system, setting a series of scales s, dividing the measurement area into equal-area sub-regions at each scale s, and calculating the cumulative value of the comprehensive wear index in each sub-region :

[0032] ;

[0033] wherein, is the area of the sub-region k;

[0034] calculating the total cumulative comprehensive wear index S(s) at each scale s:

[0035] ;

[0036] wherein q is a multi-fractal order parameter, used to emphasize wear features of different intensities;

[0037] calculating the generalized fractal dimension of the measurement area according to the total cumulative comprehensive wear index S(s) at different scales s:

[0038] ;

[0039] by linear fitting the relationship between and , the slope equals , and the fractal characteristic value is expressed as:

[0040] ;

[0041] wherein, characterizes the wear complexity and intensity distribution of the measurement area ;​

[0042] S23, normalizing the fractal feature value to obtain a normalized fractal feature value ;

[0043] S24, dividing the safety shoe surface into a plurality of priority areas according to the size of the normalized fractal feature value

[0044] ;

[0045] wherein, and and are priority threshold values, satisfying , the high-priority area corresponds to a part with high wear complexity and which needs to be highlighted in wear-resistant material configuration;

[0046] S25, generating a fractal feature value distribution map, and marking the priority areas of the measurement area on the safety shoe surface map to represent different priority areas with different colors or symbols.

[0047] Optionally, the S3 comprises the following steps:

[0048] S31, initializing the number of ants m, the pheromone evaporation coefficient , the heuristic factor and the iteration number T of the ant colony optimization algorithm based on the fractal feature value distribution map:

[0049] S32, distributing the initial pheromone concentration according to the priority area distribution of the fractal feature value , the initial pheromone concentration increases with the increase of the area wear complexity, so that the ants prefer to select the area with high wear complexity for path search;

[0050] S33, further strengthening the initial pheromone concentration of the high-priority area according to the difference between the fractal feature value and the threshold value by a power relationship:

[0051] ;

[0052] wherein, is a pheromone strengthening factor, is a strengthening index;

[0053] S34, generating an initial pheromone distribution map, and marking the initial pheromone concentration of the measurement area on the safety shoe surface map to represent the high and low of the pheromone concentration with different color depths or symbol sizes.

[0054] ​​Optionally, the number of ants m, the pheromone evaporation coefficient , the heuristic factor and the iteration number T are set as follows:

[0055] The number of ants m is set based on the number of priority areas and the overall wear complexity, so that the number of ants covers the areas with high wear complexity:

[0056] ;

[0057] Where N is the total number of priority areas divided, is the ant number adjustment coefficient, is the average value of all normalized fractal feature values , represents rounding up to x;

[0058] The pheromone evaporation coefficient is calculated as follows: The pheromone evaporation coefficient reflects the decay rate of pheromone, which is adjusted based on the degree of dispersion of wear complexity, The greater the value, the more uneven the wear complexity distribution:

[0059] ;

[0060] Where, is the pheromone evaporation adjustment coefficient, is the standard deviation of the normalized fractal feature ;

[0061] The heuristic factor measures the expected degree of ant transfer from area to area , which takes into account the wear complexity of the target area and the distance between areas;

[0062] The iteration number T is determined according to the logarithm of the number of ants and the number of priority areas.

[0063] Optionally, the S4 includes the following steps:

[0064] S41, the wear performance, production cost, weight distribution and comfort of the labor protection shoe wear-resistant material are integrated to establish a comprehensive optimization objective function F(x):

[0065] ;

[0066] Where, , , , is a weight coefficient, P(x) is a wear performance objective function, C(x) is a production cost objective function, W(x) is a weight distribution objective function, and S(x) is a comfort objective function;

[0067] The wear performance objective function P(x) is defined as follows:

[0068]

[0069] wherein N is the total number of measurement areas, is a path coverage indicator function, when a path covers a measurement area , , otherwise , is a wear performance adjustment coefficient;

[0070] The production cost objective function C(x) is defined as follows:

[0071]

[0072] wherein M is the total number of material types, is the unit area cost of the kth material, is the total use area of the kth material in the layout scheme, is a material utilization rate coefficient, is a cost adjustment coefficient;

[0073] The weight distribution objective function W(x) is defined as follows:

[0074]

[0075] wherein is the weight of the measurement area ; is the average value of the weights of all measurement areas, is a weight distribution adjustment coefficient;

[0076] The comfort objective function S(x) is defined as follows:

[0077]

[0078] wherein L is the total number of comfort indicators, is the score of the jth comfort indicator, is the weight coefficient of the jth comfort indicator, is a comfort enhancement coefficient, is a comfort adjustment coefficient;

[0079] S42, the priority area generated by the fractal algorithm is taken as a constraint condition for the ant path search, a high-priority area needs to be covered preferentially in the path search, and the path search constraint condition is defined as follows:​​​​

[0080] .

[0081] Optionally, the S5 comprises the following steps:

[0082] S51, initialize the ant colony, generate the initial solution set according to the initial concentration of pheromone and the constraint conditions of priority areas;

[0083] S52, in each iteration, the ant selects the measurement area for the next movement according to the transition probability , and constructs the complete material layout path:

[0084] ;

[0085] wherein, is the probability of the ant moving from the measurement area to in the tth iteration, is the pheromone concentration on the path (i, j), is the heuristic factor, is the distance between the measurement area and , and are importance factors, is the accessible neighborhood set of the measurement area ;

[0086] S53, after the path construction is completed, the comprehensive optimization objective value F(x) of each ant is calculated, and the solution set is evaluated according to the optimization objective function;

[0087] S54, update the pheromone concentration and the path search constraint condition, and strengthen the coverage of the high-priority area:

[0088] ;

[0089] wherein, is the pheromone evaporation coefficient, is the pheromone increment left by the kth ant on the path (i, j) in the tth iteration, and is defined as:

[0090] ;

[0091] wherein, Q is a constant, representing the total amount of pheromone released by the ant, is the path length of the kth ant in the tth iteration;

[0092] ​The pheromone reinforcement amount for high-priority areas is defined as:

[0093] ;

[0094] wherein, is a pheromone reinforcement coefficient, used to strengthen the pheromone concentration of paths between high-priority areas.

[0095] Optionally, the S7 comprises the following steps:

[0096] S71, based on path transfer probability In each iteration, the paths of all ants are constructed, and the fitness value of each ant path is calculated :

[0097] ;

[0098] wherein, , , , are the objective function values corresponding to the path k, , , , are weight coefficients;

[0099] Select the optimal material layout path of the current iteration :

[0100] ;

[0101] S72, for each path (i, j) in the optimal material layout path , the pheromone reinforcement amount of the high-priority area and the current fitness value update the reinforcement pheromone increment:

[0102] ;

[0103] wherein, is a reinforcement coefficient, is a reinforcement index, is the current path length of the kth ant in the tth iteration;

[0104] and add the updated reinforcement pheromone increment to the path pheromone concentration;

[0105] S73, define the global convergence criterion, when one of the following conditions is met, end the iteration:

[0106] reach the maximum number of iterations T;

[0107] continuous In the next iteration, the optimal path target value change amplitude satisfies:

[0108] ;

[0109] Wherein, is a convergence threshold, represents the optimal path corresponding to the comprehensive optimization target value in the tth iteration;

[0110] S74, output the global optimal path scheme :

[0111] .

[0112] Optionally, the S8 comprises the following steps:

[0113] S81, according to the global optimal path scheme, determine the corresponding measurement area and material layout requirement of each section in the path, combine the fractal characteristic value of the path coverage area, and determine the wear complexity and performance requirement of each area.

[0114] S82, based on the wear characteristics, fractal characteristic value and cost factor of the path coverage area, select the material type that best matches the area requirement, preferentially select the material with high wear resistance and economy, and comprehensively consider its easy processability in actual production.

[0115] S83, according to the wear intensity, frequency distribution and stress characteristics of the area, set the thickness configuration of the material, and use thicker material in high wear area, and appropriately thin in low wear area, so as to reduce the amount of material used, while maintaining the balance of overall performance.

[0116] S84, combine the stress distribution characteristics of the area and the grid division result of the fractal model to design the arrangement mode of the material, use regular arrangement in high stress area to enhance the mechanical properties, and use flexible distribution in low stress area to improve the comfort and adaptability.

[0117] S85, comprehensively consider the material type, thickness configuration and arrangement mode of each area, form the optimal layout scheme of the wear-resistant material of safety shoes, and evaluate the scheme to ensure that it meets the requirements of wear-resistant performance, production process feasibility and cost control.

[0118] The beneficial effects of the present application are:

[0119] (1) The fractal feature model of the labor protection shoe surface is constructed by introducing a spatial fractal algorithm, and the complex wear characteristics are accurately quantified as fractal feature values, which are used to guide the initial pheromone distribution and path search strategy of the ant colony optimization algorithm. Compared with the traditional single optimization algorithm, the present application distributes more initial concentration of pheromone in the high wear complexity area and significantly improves the coverage rate of high priority areas through the reinforcement of the pheromone update mechanism, effectively avoiding the limitation of the ant colony algorithm falling into local optimum due to the randomness of path search.

[0120] (2) The present application establishes a multi-objective optimization model by comprehensively considering the wear performance, material cost, weight distribution and comfort of the labor protection shoes, and realizes the effective balance of wear resistance and cost control through the weight adjustment of the path objective function and the setting of dynamic constraint conditions. The joint optimization of fractal feature value and fitness value in the high wear area ensures the reasonable distribution of high-quality materials, and reduces the material waste in the low wear area.

[0121] (3) The present application introduces a dynamic reinforcement mechanism in the path pheromone update process to adaptively enhance the pheromone in the high priority area with high fractal feature value, ensuring the global adaptability and flexibility of path search. Through the dynamic adjustment of the comprehensive optimization target value and the application of global convergence criterion, the change of wear characteristics can be adapted in real time in different use scenarios, and the global optimal performance of the optimized layout is always maintained. BRIEF DESCRIPTION OF DRAWINGS

[0122] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, together with the embodiments of the present application, to explain the present application, and do not constitute a limitation of the present application. In the drawings:

[0123] Figure 1 A flow chart of a labor protection shoe wear-resistant material layout method based on an ant colony optimization algorithm is proposed for the present application;

[0124] Figure 2 A path fitness value convergence trend chart in the multi-round iteration process of a labor protection shoe wear-resistant material layout method based on an ant colony optimization algorithm is proposed for the present application. DETAILED DESCRIPTION

[0125] The present application will now be further described in detail in conjunction with the drawings. These drawings are simplified schematic diagrams, and only illustrate the basic structure of the present application in a schematic manner, and therefore only show the components related to the present application.

[0126] REFERENCE Figures 1-2 A labor protection shoe wear-resistant material layout method based on an ant colony optimization algorithm, comprising the following steps:

[0127] S1, experimental test and use feedback collection of wear characteristics data of different parts of labor shoes, to build a labor shoe wear data set including wear intensity, frequency distribution and stress distribution;

[0128] S2, based on the labor shoe wear data set, use spatial fractal algorithm to build the fractal feature model of the surface of the labor shoe, calculate the fractal feature value of each part of the labor shoe surface, the fractal feature value represents the area wear complexity and intensity distribution, generate a fractal feature value distribution map according to the size of the fractal feature value, and divide the labor shoe surface into multiple priority areas, wherein the higher the fractal feature value, the higher the priority of the area;

[0129] S3, initialize the parameters of the ant colony optimization algorithm based on the fractal feature value distribution map, including the number of ants, the evaporation coefficient of pheromone, the heuristic factor and the iteration number, and distribute the initial concentration of pheromone according to the priority area distribution of the fractal feature value, the higher the fractal feature value, the greater the pheromone concentration in the area, to guide the ant search path to cover the high wear area preferentially;

[0130] S4, establish an optimization objective function, which comprehensively considers the wear performance, production cost, weight distribution and comfort of the wear-resistant material of the labor shoe, and takes the priority area generated by the fractal algorithm as the constraint condition of the ant path search, that is, the high priority area needs to be covered preferentially in the path search;

[0131] S5, convert the wear-resistant material layout problem of different parts of the labor shoe into an ant path search problem, the nodes in the ant path represent the type, thickness and arrangement of different materials, each ant in the path search follows the principle of the joint action of pheromone concentration and heuristic factor, and gradually selects the optimal material layout path of the high priority area;

[0132] S6, calculate the fitness value of each path according to the path search result and the optimization objective function, update the path pheromone concentration using the fitness value, the higher the fitness value, the greater the pheromone concentration, and when the fractal feature value distribution changes in the optimization process, dynamically update the fractal priority area and its corresponding pheromone concentration distribution;

[0133] S7, through multiple iterations of S1-S6, gradually converge to the global optimal path, record the optimal material layout scheme of the current path in each iteration, and obtain the final global optimal path;

[0134] S8, according to the final global optimal path, output the optimal layout scheme of the wear-resistant material of the labor shoe, including the material type, thickness configuration and arrangement of different areas, so that the wear-resistant material of the labor shoe meets the wear-resistant performance requirements while considering the production process feasibility and cost control;

[0135] S9, input the optimal material layout scheme to the material performance test platform to verify the wear resistance, comfort and production feasibility, adjust the material distribution in the scheme that does not meet the requirements according to the verification result, and re-iterate optimization through fractal characteristic value update.

[0136] In this embodiment, S1 includes the following steps:

[0137] S11, experimental test of wear characteristic data of different parts of safety shoes, selection of test samples and division of measurement areas on the surface of safety shoes according to actual use scenarios ;

[0138] S12, measurement of wear depth and wear area of each measurement area using standard wear test equipment, calculation of wear intensity of measurement area ; ;

[0139] wherein, is the wear depth of measurement area , and is the wear area of measurement area ;

[0140] S13, statistics of wear frequency of each measurement area through long-term use feedback, recording of wear frequency of each measurement area ;

[0141] S14, measurement of stress distribution of each measurement area based on wear test and material stress analysis, collection of corresponding stress values ;

[0142] S15, normalization processing of the collected wear intensity , wear frequency and stress distribution data respectively;

[0143] S16, construction of safety shoe wear data set according to the normalized data:

[0144] ;

[0145] wherein, N is the total number of divided measurement areas, is the normalized wear intensity of measurement area , is the normalized wear frequency of measurement area , is the normalized stress value of measurement area .

[0146] In this embodiment, S2 includes the following steps:

[0147] S21, calculating the comprehensive wear index of each measurement area based on the labor shoe wear dataset :

[0148] ;

[0149] wherein, , , are weight coefficients respectively used to balance the influence of wear intensity, wear frequency and stress on the comprehensive wear index ;

[0150] S22, calculating the fractal characteristic value of each measurement area by using a multi-scale fractal analysis method ; , taking the comprehensive wear index as a spatial distribution function M(x, y) in the measurement area , wherein x, y are the positions of the measurement area in the labor shoe surface coordinate system, setting a series of scales s, dividing the measurement area into equal-area sub-regions at each scale s, and calculating the cumulative value of the comprehensive wear index in each sub-region :

[0151] ; wherein,

[0152] is the area of the sub-region k; calculating the total cumulative comprehensive wear index S(s) at each scale s:

[0153]

[0154] ; wherein q is a multi-fractal order parameter used to emphasize wear characteristics of different intensities;

[0155] calculating the generalized fractal dimension of the measurement area

[0156] based on the total cumulative comprehensive wear index S(s) at different scales s: ;

[0157] by linear fitting the relationship between and

[0158] , the slope equals , and the fractal characteristic value is expressed as: ​​​

[0159] ;

[0160] wherein, characterizing the wear complexity and intensity distribution of the measurement region;

[0161] S23, normalizing the fractal feature value to obtain a normalized fractal feature value

[0162] S24, dividing the safety shoes surface into multiple priority regions according to the size of the normalized fractal feature value

[0163]

[0164] wherein, and are priority threshold values, satisfying , and the high-priority region corresponds to a part with high wear complexity and which needs to be highlighted in wear-resistant material configuration;

[0165] S25, generating a fractal feature value distribution map, and marking the priority regions of the measurement region on the safety shoes surface map to represent different priority regions in different colors or symbols.

[0166] The embodiment utilizes a spatial fractal algorithm to construct a fractal feature model of the safety shoes surface and generate a priority region distribution map. The fractal algorithm is used for modeling the wear characteristics of the safety shoes, the complex wear characteristics are quantified as fractal feature values, and the priority of the region is divided based on the fractal feature values to guide the subsequent optimization, thereby breaking through the limitations of traditional experience-based region division, making the material distribution more scientific and accurate, and providing a reasonable basis for pheromone initialization of the ant colony optimization algorithm.

[0167] In the embodiment, S3 includes the following steps:

[0168] S31, initializing the number of ants m, the pheromone evaporation coefficient , the heuristic factor and the iteration number T of the ant colony optimization algorithm based on the fractal feature value distribution map:

[0169] S32, distributing the initial concentration of pheromone according to the priority region distribution of the fractal feature value , and the initial concentration of pheromone increases with the increase of the wear complexity of the region, so that the ants preferentially select the region with high wear complexity for path search;

[0170] ​​​​​S33, further strengthening the pheromone initial concentration in the high priority area according to the difference between the fractal characteristic value and the threshold value in a power relationship;

[0171] ;

[0172] wherein, is a pheromone strengthening factor, is a strengthening index;

[0173] S34, generating a pheromone initial distribution map, marking the pheromone initial concentration of the measurement area on the labor protection shoe surface map, and representing the high and low pheromone concentrations by different color depths or symbol sizes.

[0174] In the embodiment, the number of ants m, the pheromone volatilization coefficient , the heuristic factor and the iteration number T are set as follows:

[0175] The number of ants m is set based on the number of priority areas and the overall wear complexity, so that the number of ants covers the areas with high wear complexity:

[0176] ;

[0177] wherein N is the total number of priority areas divided, is an ant number adjustment coefficient, is the average value of all normalized fractal characteristic values , and represents rounding up to x;

[0178] The pheromone volatilization coefficient is calculated, and the pheromone volatilization coefficient reflects the decay rate of the pheromone, which is adjusted based on the dispersion degree of the wear complexity, and the greater the value, the more uneven the wear complexity distribution:

[0179] ;

[0180] wherein, is a pheromone volatilization adjustment coefficient, is the standard deviation of the normalized fractal characteristic ;

[0181] The heuristic factor measures the expected degree of the ant moving from area to area , which is a comprehensive consideration of the wear complexity of the target area and the distance between the areas;

[0182] ​The iteration number T is determined according to the logarithm of the number of ants and the number of priority areas.

[0183] The embodiment is based on the fractal characteristic value distribution map to initialize the parameters of the ant colony optimization algorithm, and the creativity is embodied in that the initial concentration of pheromone is dynamically adjusted according to the fractal characteristic value priority distribution, so that the high-priority area obtains higher pheromone attraction, and the ants are guided to preferentially cover the key area.

[0184] In the embodiment, S4 includes the following steps:

[0185] S41, the wear performance, production cost, weight distribution and comfort of the wear-resistant material of the labor protection shoe are comprehensively optimized to establish a comprehensive optimization objective function F(x):

[0186] ;

[0187] Wherein, , , , is a weight coefficient, P(x) is a wear performance objective function, C(x) is a production cost objective function, W(x) is a weight distribution objective function, and S(x) is a comfort objective function;

[0188] The wear performance objective function P(x) is defined as:

[0189] ;

[0190] Wherein, N is the total number of measurement areas, is a path coverage indication function, when the path covers the measurement area , , otherwise , is a wear performance adjustment coefficient;

[0191] The production cost objective function C(x) is defined as:

[0192] ;

[0193] Wherein, M is the total number of material types, is the unit area cost of the kth material, is the total use area of the kth material in the layout scheme, is a material utilization rate coefficient, is a cost adjustment coefficient;

[0194] The weight distribution objective function W(x) is defined as:

[0195] ;

[0196] Wherein, the weight of the measurement area; the average of the weights of all measurement areas, the weight distribution adjustment coefficient;

[0197] Define the comfort objective function S(x):

[0198] ;

[0199] wherein L is the total number of comfort indicators, is the score of the jth comfort indicator, is the weight coefficient of the jth comfort indicator, is the comfort enhancement coefficient, is the comfort adjustment coefficient;

[0200] S42, the priority area generated by the fractal algorithm is used as a constraint condition for ant path search, and high priority areas need to be covered preferentially in path search, and the path search constraint condition is defined as:

[0201] .

[0202] In this embodiment, S5 includes the following steps:

[0203] S51, initialize the ant colony, and generate an initial solution set according to the initial concentration of pheromone and the constraint condition of the priority area;

[0204] S52, in each iteration, the ants select the measurement area for the next step according to the transition probability to build a complete material layout path:

[0205] ;

[0206] wherein, is the probability of the ant moving from the measurement area to in the tth iteration, is the pheromone concentration on the path (i, j), is the heuristic factor, is the distance between the measurement area and , and are importance factors, is the accessible neighborhood set of the measurement area ;

[0207] ​S53, after the path construction is completed, the comprehensive optimization target value F(x) of each ant is calculated and the solution set is evaluated according to the optimization target function;

[0208] S54, update pheromone concentration and path search constraints, strengthen the coverage of high priority areas:

[0209] ;

[0210] wherein, is the pheromone evaporation coefficient, is the pheromone increment left by the kth ant on the path (i, j) in the tth iteration, defined as:

[0211] ;

[0212] wherein Q is a constant, representing the total amount of ant pheromone release, is the path length of the kth ant in the tth iteration;

[0213] is the pheromone reinforcement amount of the high priority area, defined as:

[0214] ;

[0215] wherein, is the pheromone reinforcement coefficient, used to strengthen the pheromone concentration of the path between high priority areas.

[0216] In this embodiment, S7 includes the following steps:

[0217] S71, based on the path transfer probability construct the path of all ants in each iteration, and calculate the fitness value of each ant path :

[0218] ;

[0219] wherein, , , , respectively, the objective function value corresponding to the path k, , , , is the weight coefficient;

[0220] select the optimal material layout path of the current iteration :

[0221] ;

[0222] S72, for each path (i, j) in the optimal material layout path , according to the pheromone reinforcement amount of the high-priority area and the current fitness value Update the reinforcement pheromone increment:

[0223] ;

[0224] wherein, is a reinforcement coefficient, is a reinforcement index, is the current path length of the kth ant in the tth iteration;

[0225] and superimpose the updated reinforcement pheromone increment on the path pheromone concentration;

[0226] S73, define a global convergence criterion, when one of the following conditions is met, end the iteration:

[0227] The maximum number of iterations T is reached;

[0228] Consecutive iterations, the optimal path target value changes by:

[0229] ;

[0230] wherein, is a convergence threshold, represents the optimal path corresponding to the comprehensive optimization target value, which is calculated by the comprehensive optimization objective function, and the results of the multi-objective weight of the comprehensive wear resistance, material cost, weight distribution and comfort, etc.

[0231] The judgment formula is used to judge whether the ant colony optimization algorithm has reached the convergence state. When the relative change rate of the optimal path target value is less than the preset threshold , it means that the optimization effect of multiple iterations tends to be stable, and the improvement brought by subsequent iterations is not significant. The optimization process can be terminated in advance, thereby improving the calculation efficiency. In the labor protection shoe wear-resistant material layout optimization, it can avoid wasting computing resources in unnecessary iterations, while ensuring that the final output optimization scheme has sufficient stability and reliability.

[0232] S74, output the global optimal path scheme :

[0233] .

[0234] The embodiment improves the global optimization ability of the algorithm by dynamically adjusting the path search result and strengthening the pheromone distribution of the optimal path through the strategy of recording the optimal path and strengthening the pheromone concentration in multiple iterations, sets a multi-objective fitness convergence criterion, guarantees the stability and high efficiency of the algorithm under complex target constraints, significantly improves the optimization efficiency and scientificity of the wear-resistant material layout, and embodies the practical applicability and intelligent characteristics of the algorithm.

[0235] In the embodiment, S8 comprises the following steps:

[0236] S81, according to the global optimal path scheme, determine the corresponding measurement area and material layout requirement of each section in the path, and combine the fractal characteristic value of the path coverage area to determine the wear complexity and performance requirement of each area.

[0237] S82, based on the wear characteristics, fractal characteristic value and cost factors of the path coverage area, select the material type that best matches the area requirement, preferentially select the material with high wear resistance and economy, and comprehensively consider its ease of processing in actual production.

[0238] S83, according to the wear intensity, frequency distribution and stress characteristics of the area, set the thickness configuration of the material, use thicker material in high wear areas, and select appropriate thinning in low wear areas to reduce material usage while maintaining overall performance balance.

[0239] S84, combine the stress distribution characteristics of the area and the grid division result of the fractal model to design the arrangement of the material, use regular arrangement in high stress areas to enhance the mechanical properties, and use flexible distribution in low stress areas to improve comfort and adaptability.

[0240] S85, comprehensively consider the material type, thickness configuration and arrangement of each area to form the optimal layout scheme of the wear-resistant material of safety shoes, and evaluate the scheme to ensure that it meets the requirements of wear-resistant performance, production process feasibility and cost control.

[0241] Embodiment:

[0242] In the safety shoe manufacturing project of a certain mine, in view of the problem that the shoe sole is seriously worn in the complex scene of workers working on sandstone pavement, high humidity environment and gravel slope for a long time, the implementer decides to use the method of the present application to optimize the wear-resistant material layout of safety shoes.

[0243] In June 2024, a mine quarry safety shoe manufacturing project was launched. The first phase of the project tested the safety shoes currently used by workers and found that the wear and tear on different parts of the shoe soles was significantly different. For example, the shoe of worker A101, after 45 days of continuous use, the wear depth of the outer edge of the forefoot was 5.6 mm, while the heel area was only 1.2 mm. This difference in wear and tear led to early failure of the shoe sole, with an average service life of only 90 days and significant material waste.

[0244] To solve this problem, the implementer collected wear and tear data from the safety shoes of 20 consecutive workers. The test method included installing intelligent sensors on the shoe soles to record the force and wear of each step. The final data set included wear depth, wear area, and stress values. In the example, the average wear depth of the forefoot of shoe A101 was 5.4 mm, the heel was 1.0 mm, and the middle part was evenly worn with an average of 3.2 mm. Combined with the fractal algorithm, a fractal characteristic value distribution graph of different parts of the shoe sole was generated. The graph showed that the fractal characteristic values of the outer edge (number R4) and the inner edge (number R3) of the forefoot were 1.52 and 1.48, which were high priority areas, while the fractal characteristic values of the middle and heel areas were lower, averaging 1.20.

[0245] In the optimization phase, the implementer input the data into the ant colony optimization algorithm model, initialized the ant colony parameters (100 ants, 50 maximum iterations), and assigned the initial concentration of pheromone according to the priority of the fractal characteristic values. Each ant generated a material layout path in the simulated environment according to the path transition probability. In the example, the path selected by Ant-07 in the 3rd iteration covered the key areas of the forefoot and heel, but did not consider the middle area, with an adaptability value of 0.65. Ant-18, on the other hand, covered all high-priority areas in its path, with an adaptability value of 0.88.

[0246] By the 28th iteration, the model converged and generated the optimal path, outputting the distribution scheme of the wear-resistant material. Specifically, the outer edge (R4) and the inner edge (R3) of the forefoot used high-wear-resistant material with a thickness of 5 mm; the middle area (R2, R5) used medium-wear-resistant material with a thickness of 3 mm; and the heel area (R6) used ordinary material with a thickness of 2 mm. The entire optimization process took 3 hours, which was about 60% shorter than the traditional experience-based design method.

[0247] The implementer then manufactured 10 pairs of safety shoes according to the optimization scheme and conducted a 30-day mine field test, the average wear depth of the forefoot of shoe No. A102 was reduced to 1.8 mm at the end of the test, and the wear depths of the heel and the middle part were 0.5 mm and 1.2 mm respectively, the sole remained good functionality, compared with the safety shoes designed by the traditional method, the service life of the sole was significantly improved, and the material use cost was reduced.

[0248] By comparison with the traditional method, the specific data are as follows in Table 1:

[0249] Table 1 Comparison of key performances of the present application and the traditional method in the optimization process of wear-resistant material layout of safety shoes

[0250] Indicator Method of the invention Conventional method Average service life (days) 150 90 Material cost saving rate (%) 20 0 High priority area coverage 98% 70% Optimization time (hours) 3 7

[0251] In the whole embodiment, the implementer solves not only the problems of short service life and high cost caused by serious wear of the sole, but also improves the optimization efficiency, realizes scientific design and efficient production of wear-resistant material layout of safety shoes.

[0252] The present application introduces a spatial fractal algorithm to construct a fractal feature model of the surface of the safety shoes, accurately quantifies the complex wear characteristics into a fractal feature value, and uses the fractal feature value to guide the initial pheromone distribution and path search strategy of the ant colony optimization algorithm, compared with the traditional single optimization algorithm, the present application distributes more initial concentration of pheromone in the high wear complexity area and significantly improves the coverage rate of the high priority area through the reinforcement of the pheromone update mechanism, effectively avoids the limitation of the ant colony algorithm falling into local optimum due to the randomness of path search.

[0253] The present application establishes a multi-objective optimization model by comprehensively considering the wear performance, material cost, weight distribution and comfort according to the actual application requirements of the safety shoes, realizes effective balance of wear-resistant performance and cost control through weight adjustment of the path objective function and setting of dynamic constraint conditions, ensures reasonable distribution of high-quality materials through joint optimization of the fractal feature value and the fitness value in the high wear area, and reduces the material waste in the low wear area.

[0254] The present application introduces a dynamic reinforcement mechanism in the path pheromone update process to adaptively enhance the pheromone of the high priority area with high fractal feature value, ensures the global adaptability and flexibility of the path search, and through dynamic adjustment of the comprehensive optimization target value and application of the global convergence criterion, can adapt to the changes of the wear characteristics in different use scenarios in real time, and always maintains the global optimal performance of the optimized layout.

[0255] The above merely describes preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art, according to the technical solution and inventive concept of the present application, makes equivalent replacement or change within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for laying out wear-resistant materials for safety shoes based on an ant colony optimization algorithm, characterized in that, Comprise the following steps: S1, the wear characteristics data of different parts of safety shoes are tested and collected by using feedback, and a safety shoe wear data set is constructed; S2, based on the safety shoe wear data set, a fractal feature model of the surface of the safety shoe is constructed using a spatial fractal algorithm, the fractal feature values of each part of the surface of the safety shoe are calculated, a fractal feature value distribution map is generated according to the size of the fractal feature values, and the surface of the safety shoe is divided into multiple priority areas; The S2 comprises the following steps: S21, select the test sample and divide the surface of the safety shoes into measurement regions according to the actual use scene , calculate the comprehensive wear index of each measurement region based on the safety shoes wear dataset : ;​ wherein, are weight coefficients for balancing the influence of the wear intensity, the wear frequency and the stress on the overall wear indicator, is the normalized wear intensity of the measurement area is the normalized wear frequency of the measurement area is the normalized stress value of the measurement area ​​​​ S22, calculating the fractal characteristic value of each measuring area by using the multi-scale fractal analysis method , taking the comprehensive wear index as the spatial distribution function M(x, y) in the measuring area , where x, y are the positions of the measuring area in the safety shoe surface coordinate system, setting a series of scales s, dividing the measuring area into sub-areas with equal area at each scale s, and calculating the cumulative value of the comprehensive wear index in each sub-area : ;​​​ wherein Ak is the area of sub-region k; The total cumulative composite wear indicator S(s) is calculated at each scale s: ; Wherein, q is a multi-fractal order parameter, which is used to emphasize different intensity of wear characteristics; The measurement area is calculated according to the total cumulative comprehensive wear index S(s) under different scales s The generalized fractal dimension of the measurement area : ; By linear fitting the relationship between and , the slope equals , and the fractal characteristic value is expressed as: ; wherein characterizing the measurement region of the wear complexity and intensity distribution; S23, the fractal characteristic value S23, the fractal characteristic value ; S24、according to the normalized fractal characteristic value The size of the normalized fractal characteristic value divides the surface of the labor protection shoes into multiple priority areas: ; wherein, and is a priority threshold, satisfying , the high-priority area corresponds to a part with high wear complexity and which needs to be highlighted for wear-resistant material configuration. S25, generating a fractal feature value distribution map, marking the priority areas of the measurement area on the surface map of the labor protection shoes, and representing different priority areas with different colors or symbols; S25, generating a fractal feature value distribution map, marking the priority areas of the measurement area on the surface map of the labor protection shoes, and representing different priority areas with different colors or symbols; S3, initialize the parameters of the ant colony optimization algorithm based on the fractal feature value distribution map, and distribute the initial concentration of pheromone according to the priority area distribution of the fractal feature values; S4, establish an optimization objective function, and take the priority areas generated by the fractal algorithm as the constraint condition of the ant path search; S5, convert the wear-resistant material layout problem of different parts of safety shoes into an ant path search problem, and gradually select the optimal material layout path of the high-priority area; S6, calculate the fitness value of each path according to the path search result and the optimization objective function, update the path pheromone concentration using the fitness value, and the path pheromone concentration of the path with higher fitness value is larger, and when the fractal feature value distribution changes in the optimization process, the fractal priority area and the corresponding pheromone concentration distribution are dynamically updated; S7, through multiple iterations of S1-S6, gradually converge to the global optimal path, record the optimal material layout scheme of the current path in each iteration, and obtain the final global optimal path; S8, output the final optimal layout scheme of the wear-resistant material of the safety shoes according to the final global optimal path; S9, input the final optimal layout scheme into the material performance test platform to verify the wear resistance, comfort and production feasibility.

2. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The S1 comprises the following steps: S11, experimental test of wear characteristic data of different parts of the safety shoes, selection of test samples and division of measurement areas on the surface of the safety shoes according to actual use scenarios ; S12, measuring the wear depth and wear area of each measurement area using a standard wear test equipment, calculating the wear intensity of the measurement area ;​​ S13, statistically analyze the wear frequency of each measurement area through long-term use feedback, and record the wear frequency of each measurement area ; S14, measuring the stress distribution of each measurement area based on the wear test and material stress analysis, collecting the corresponding stress value ; S15, normalizing the collected data of wear intensity , wear frequency and stress distribution , respectively; S16, constructing the labor protection shoes wear data set according to the normalized data: ; Wherein, N is the total number of measurement areas.

3. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The S3 comprises the following steps: S31, initialize the number of ants m, pheromone evaporation coefficient p, heuristic factor and iteration number T of the ant colony optimization algorithm based on the fractal characteristic value distribution map; and iteration number T. S32, distributing initial pheromone concentration according to priority area distribution of fractal characteristic value initial pheromone concentration increasing with the increase of area wear complexity, so that the ants prefer to select the area with high wear complexity for path search; S33, the initial pheromone concentration in the high-priority area is further strengthened according to the difference between the fractal characteristic value and the threshold value in a power relationship: ; wherein is a pheromone reinforcement factor, is a reinforcement index; S34, generate pheromone initial distribution map, mark the measured area with different color depth or symbol size to represent the high and low of pheromone concentration Mark on the surface map of safety shoes, with different color depth or symbol size to represent the high and low of pheromone concentration.

4. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The number of ants m, the pheromone evaporation coefficient p, the heuristic factor and the number of iterations T are set as follows: The number of ants m is set based on the number of priority zones and the overall wear complexity such that the number of ants covers the zones of high wear complexity: ; Wherein, N is the total number of priority areas divided, is the ant quantity adjustment coefficient, is the average value of all normalized fractal characteristic values , represents rounding up; The pheromone volatilization coefficient p is calculated, and the pheromone volatilization coefficient p reflects the decay speed of the pheromone, and is adjusted based on the discrete degree of the wear complexity, The greater the wear complexity distribution is more uneven: ; wherein, is a pheromone volatility adjustment factor, is a standard deviation of normalized fractal features ; Heuristic factor Measuring ants from the region Transfer to the region The expected level, taking into account the wear complexity of the target area and the distance between areas; The number of iterations T is determined according to the logarithm of the number of ants and the number of priority areas.

5. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The S4 comprises the following steps: S41, the wear resistance of the comprehensive labor protection shoes, the production cost, the weight distribution and the comfort are combined to establish a comprehensive optimization objective function F(x): ; wherein are weight coefficients, P(x) is a wear performance objective function, C(x) is a production cost objective function, W(x) is a weight distribution objective function, and S(x) is a comfort objective function. Defining the wear performance objective function P(x): ; wherein N is the total number of measurement regions, is a path coverage indicator function when the path covers a measurement region , , otherwise , is a wear performance adjustment coefficient; Define the production cost objective function C(x): ; Wherein, M is the total number of material types, is the unit area cost of the k1th material, is the total use area of the k1th material in the layout scheme, is the material utilization coefficient, and β1 is the cost adjustment coefficient. Define the weight distribution objective function W(x): ; where w i is the weight of the measurement area ; is the average of the weights of all measurement areas, and γ1is a weight distribution adjustment coefficient. Define the comfort objective function S(x): ; wherein L is the total number of comfort indicators, s j is the score of the jth comfort indicator, φ j is the weight coefficient of the jth comfort indicator, θ j is the comfort enhancement coefficient, is the comfort adjustment coefficient; S42, the priority area generated by the fractal algorithm is taken as a constraint condition for the ant path search, the high priority area needs to be covered preferentially in the path search, and the path search constraint condition is defined: .

6. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The S5 comprises the following steps: S51, initialize the ant colony, and initialize the pheromone concentration and the constraint conditions of the priority area to generate an initial solution set; S52, in each iteration the ants follow the transition probabilities selecting the measurement region for the next move, building a complete material layout path: ; wherein, is the probability that an ant moves from a measurement region to at the t-th iteration, is the pheromone concentration on the path (i, j), is a heuristic factor, is the distance between a measurement region and , a2and b2are importance factors, N i is the set of accessible neighbors of a measurement region ; S53, after the path is constructed, calculate the comprehensive optimization objective value F(x) of each ant and evaluate the solution set according to the optimization objective function; S54, update pheromone concentration and path search constraints, reinforcing coverage of high priority areas: ; wherein p is pheromone evaporation coefficient, is the pheromone increment left by the k2th ant on path (i, j) in the tth iteration, defined as: ; wherein Q is a constant, representing the total amount of pheromone released by ants, is the path length of the k2th ant in the tth iteration. The pheromone reinforcement quantity for the high-priority area is defined as: ; wherein, is a pheromone reinforcement factor, used to reinforce the pheromone concentration of paths between high priority areas.

7. The ant colony optimization algorithm-based layout method of wear-resistant materials for safety shoes according to claim 1, characterized in that, The S7 comprises the following steps: S71、based on path transition probability In each iteration, the paths of all ants are constructed and the fitness value of each ant path is calculated : ; wherein, respectively are the objective function values corresponding to path k3, is a weight coefficient; selecting an optimal material layout path for the current iteration : ; S72, for each path (i, j) in the optimal material layout path the amount of pheromone reinforcement of the high priority area and the current fitness value update the reinforcement pheromone increment: ; wherein, is a reinforcement coefficient, is a reinforcement exponent, is the current path length of the k3rd ant in the tth iteration; And add the updated reinforced pheromone increment to the path pheromone concentration; S73, define a global convergence criterion, and end the iteration when one of the following conditions is met: The maximum number of iterations T is reached; Consecutive n c In the sub-iteration, the variation range of the optimal path target value satisfies: ; wherein, is a convergence threshold, denotes the optimal path in the tth iteration corresponds to the integrated optimization objective value; S74, output global optimal path scheme : .

Images