Framework bridge and culvert size optimization method, device and equipment based on improved genetic algorithm

Abstract

The invention discloses a frame bridge and culvert size optimization method, device and equipment based on an improved genetic algorithm, and relates to the technical field of civil engineering, and the method comprises the steps: determining a plurality of section normal stresses of each initial individual according to a design variable and a design constraint condition of a target frame bridge and culvert, and constructing a penalty function of each initial individual; determining the fitness value of each initial individual according to the penalty function of each initial individual, the plurality of section normal stress values and the section area; determining a population target individual according to a dynamic crossover probability calculation strategy, a dynamic mutation probability calculation strategy, a population reduction strategy and the fitness value of each initial individual; and determining section design parameters of the target frame bridge and culvert according to the population target individuals, and optimizing the size of the target frame bridge and culvert. By means of the mode, the applicability is improved, the optimization efficiency and the size optimization precision are improved, the mechanical safety of the frame bridge and culvert can be met, and meanwhile economic optimum design is achieved.

Description

Technical Field

[0001] The present application relates to the field of civil engineering technology, and in particular to a method, device and equipment for optimizing the size of a frame bridge and culvert based on an improved genetic algorithm. Background Art

[0002] At present, the design of frame bridge culvert dimensions is often based on experience. The cross-sectional dimensions of frame bridge culverts are estimated according to the stress characteristics, span, clear height, etc. of the frame bridge culvert. The refined design requires finite element analysis and stress strength calculations, and then the cross-sectional dimensions are constantly modified and recalculated. The appropriate cross-sectional dimensions are determined through repeated trial calculations. The above method requires repeated trial calculations, which is time-consuming and labor-intensive, and the designed dimensions are mainly to meet the structural bearing capacity, without considering material savings and the optimal stress state. Summary of the invention

[0003] The main purpose of this application is to provide a method, device and equipment for optimizing the size of frame bridges and culverts based on an improved genetic algorithm, aiming to solve the technical problems in the prior art that the optimization methods for the size of frame bridges and culverts are of low accuracy and efficiency and cannot achieve the optimal design.

[0004] To achieve the above objectives, the present application proposes a frame bridge and culvert size optimization method based on an improved genetic algorithm, and the frame bridge and culvert size optimization method based on an improved genetic algorithm includes:

[0005] Determine multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert;

[0006] Constructing the penalty function of each initial individual according to multiple cross-sectional normal stresses of each initial individual;

[0007] Determine the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual;

[0008] According to the dynamic crossover probability calculation strategy, dynamic mutation probability calculation strategy, population reduction strategy and the fitness value of each initial individual, the population is updated to determine the target individual of the population;

[0009] The cross-sectional design parameters of the target frame bridge and culvert are determined according to the target individuals of the population, and the size of the target frame bridge and culvert is optimized according to the cross-sectional design parameters.

[0010] In one embodiment, the step of determining a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert comprises:

[0011] Determine the size range of each design variable according to the design information of the target frame bridge and culvert;

[0012] According to the size range of each design variable, a random combination is performed to obtain multiple cross-sectional parameter combinations;

[0013] Each section parameter combination is used as a plurality of initial individuals, and stress calculation is performed based on each initial individual and a target finite element model to determine a plurality of section normal stresses of each initial individual.

[0014] In one embodiment, the step of constructing a penalty function for each initial individual according to a plurality of cross-sectional normal stresses of each initial individual comprises:

[0015] Determine the extreme normal stress of each initial individual according to multiple cross-sectional normal stresses of each initial individual;

[0016] When the extreme normal stress of each initial individual is within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to a preset value;

[0017] When the first normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to the first normal stress of each initial individual and the first function construction method;

[0018] When the second normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to the second normal stress of each initial individual and the second function construction method.

[0019] In one embodiment, the step of updating the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy, and the fitness value of each initial individual to determine the population target individual includes:

[0020] Sorting the fitness values ​​of the initial individuals, and screening the initial individuals based on the sorting results to obtain a plurality of first updated individuals;

[0021] Randomly selecting individuals from a plurality of first updated individuals to determine a plurality of groups of crossover individuals and a plurality of mutation individuals;

[0022] According to multiple groups of crossover individuals and dynamic crossover probability calculation strategy, a group is updated to obtain multiple second updated individuals;

[0023] According to each mutation individual and the dynamic mutation probability calculation strategy, the population is updated to obtain multiple third updated individuals;

[0024] According to each first updated individual, each second updated individual, each third updated individual and the population reduction strategy, the population is updated to obtain a fourth updated individual;

[0025] Based on the fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy, the population is iteratively updated to determine the target individual of the population.

[0026] In one embodiment, the step of performing population updating according to multiple groups of crossover individuals and dynamic crossover probability calculation to obtain multiple second updated individuals includes:

[0027] Determine the population extreme fitness value according to the fitness value of each initial individual;

[0028] Determine the dynamic crossover probability of each group of crossover individuals according to the extreme fitness value of the population, the target fitness value of each group of crossover individuals, the preset crossover rate and the dynamic crossover probability calculation strategy;

[0029] The group is updated according to the dynamic crossover probability of each group of crossover individuals and each group of crossover individuals to obtain a plurality of second updated individuals.

[0030] In one embodiment, the step of performing population updating according to each first updated individual, each second updated individual, each third updated individual and the population reduction strategy to obtain a fourth updated individual includes:

[0031] Determine the initial population size based on each initial individual;

[0032] Calculate the coefficient according to the preset population number, the preset evolutionary generation and the initial population data to determine the target update coefficient;

[0033] Calculate the current population size based on the target update coefficient, the current evolutionary generation, and the preset evolutionary generation;

[0034] When each first updated individual, each second updated individual and each third updated individual satisfy the section normal stress constraint condition, individual screening is performed according to the fitness value of each first updated individual, the fitness value of each second updated individual, the fitness value of each third updated individual and the current population number to obtain multiple fourth updated individuals.

[0035] In one embodiment, the step of performing iterative updating of a population based on the fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, and the population reduction strategy to determine the population target individual includes:

[0036] Performing iterative update of the population based on each fourth updated individual, a dynamic crossover probability calculation strategy, a dynamic mutation probability calculation strategy, and a population reduction strategy;

[0037] When the current iteration information meets the iteration termination condition, the target population is obtained;

[0038] The fitness values ​​of a plurality of iteration-suspended individuals in the target population are sorted, and a population target individual is determined from the plurality of iteration-suspended individuals based on the sorting result.

[0039] In addition, to achieve the above purpose, the present application also proposes a frame bridge culvert size optimization device based on an improved genetic algorithm, and the frame bridge culvert size optimization device based on the improved genetic algorithm includes:

[0040] A processing module, used for determining a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to design variables and design constraints of a target frame bridge and culvert;

[0041] A construction module, used for constructing a penalty function of each initial individual according to multiple cross-sectional normal stresses of each initial individual;

[0042] The processing module is used to determine the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual;

[0043] An updating module is used to update the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual, and determine the target individual of the population;

[0044] The optimization module is used to determine the cross-sectional design parameters of the target frame bridge and culvert according to the target individuals of the population, and optimize the size of the target frame bridge and culvert according to the cross-sectional design parameters.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a frame bridge and culvert size optimization device based on an improved genetic algorithm, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the frame bridge and culvert size optimization method based on the improved genetic algorithm as described above.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the frame bridge culvert size optimization method based on the improved genetic algorithm as described above are implemented.

[0047] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the frame bridge and culvert size optimization method based on the improved genetic algorithm as described above.

[0048] The present application determines multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert; constructs the penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual; determines the fitness value of each initial individual according to the penalty function of each initial individual, the multiple cross-sectional normal stress values ​​of each initial individual and the cross-sectional area corresponding to each initial individual; updates the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual to determine the population target individual; determines the cross-sectional design parameters of the target frame bridge and culvert according to the population target individual, and optimizes the size of the target frame bridge and culvert according to the cross-sectional design parameters. In the above manner, the improved genetic algorithm is used to solve the population target individual, thereby optimizing the size of the target frame bridge and culvert, which not only improves the applicability, but also improves the optimization efficiency and the accuracy of the optimized size, and can meet the mechanical safety of the frame bridge and culvert while achieving economic optimal design. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0051] Figure 1 A flow chart of the first embodiment of the frame bridge and culvert size optimization method based on the improved genetic algorithm provided in this application;

[0052] Figure 2 A schematic diagram of a cross-section of a double-hole frame bridge culvert according to a frame bridge culvert size optimization method based on an improved genetic algorithm provided in Example 1 of the present application;

[0053] Figure 3 A flow chart of the second embodiment of the frame bridge and culvert size optimization method based on the improved genetic algorithm provided in this application;

[0054] Figure 4 A brief flow chart of a frame bridge and culvert size optimization method based on an improved genetic algorithm provided in Example 2 of the present application;

[0055] Figure 5 This is a schematic diagram of the module structure of a frame bridge and culvert size optimization device based on an improved genetic algorithm according to an embodiment of the present application;

[0056] Figure 6Schematic diagram of the equipment structure of the hardware operating environment involved in the frame bridge and culvert size optimization method based on the improved genetic algorithm in the embodiment of the present application.

[0057] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0059] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0060] The main solution of the embodiment of the present application is: determine multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert; construct a penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual; determine the fitness value of each initial individual according to the penalty function of each initial individual, the multiple cross-sectional normal stress values ​​of each initial individual and the cross-sectional area corresponding to each initial individual; update the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual to determine the population target individual; determine the cross-sectional design parameters of the target frame bridge and culvert according to the population target individual, and optimize the size of the target frame bridge and culvert according to the cross-sectional design parameters.

[0061] At present, the design of frame bridge and culvert dimensions is often based on experience, and the cross-sectional dimensions of frame bridge and culvert are estimated according to the stress characteristics, span, clear height, etc. of the frame bridge and culvert. A more refined design requires finite element analysis and stress strength calculations, and then the cross-sectional dimensions are constantly modified and recalculated, and the appropriate cross-sectional dimensions are determined through repeated trial calculations. The above method requires repeated trial calculations, which is time-consuming and labor-intensive, and the designed dimensions mainly meet the structural bearing capacity, without considering material savings and the optimal stress state.

[0062] In addition, there is also a method in the prior art to calculate the structural dimensions of frame bridges and culverts through experience and a unified calculation model. However, since the above method is an empirical formula, its applicability is not wide and the results lack verification. Generally, it is difficult to achieve the optimal design under different functions and different structural forms. It is only used as a feasible design method.

[0063] The present application provides a solution, which constructs penalty functions of multiple initial individuals through the positive stress of each section of each initial individual, and determines the fitness value of each initial individual based on the penalty function of each initial individual, the positive stress value of each section and the cross-sectional area, and determines the target individual of the population through a dynamic crossover probability calculation strategy, a dynamic mutation probability calculation strategy, a population reduction strategy and the fitness value of each initial individual, thereby optimizing the size of a target frame bridge and culvert, which not only improves the applicability, but also improves the optimization efficiency and the accuracy of the optimized size, and can achieve economic optimal design while meeting the mechanical safety of the frame bridge and culvert.

[0064] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a frame bridge and culvert size optimization device based on an improved genetic algorithm that can achieve the above functions. The following takes the frame bridge and culvert size optimization device based on an improved genetic algorithm as an example of the execution subject to illustrate this embodiment and the following embodiments.

[0065] Based on this, the embodiment of the present application provides a frame bridge culvert size optimization method based on an improved genetic algorithm, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the frame bridge and culvert size optimization method based on the improved genetic algorithm of this application.

[0066] In this embodiment, the frame bridge and culvert size optimization method based on the improved genetic algorithm includes steps S10 to S50:

[0067] Step S10, determining a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert.

[0068] It should be noted that the target frame bridge culvert refers to the frame bridge culvert that needs to be optimized in cross-sectional size. The frame bridge culvert is a commonly used structure in railway, highway and urban infrastructure construction, mainly used to cross obstacles such as rivers, roads, ditches or pipelines. Frame bridges and culverts are widely used due to their strong integrity, convenient construction and good durability. The types of frame bridges and culverts can be divided into many types according to their structural form, span, number of holes and other factors, such as: single-hole frame bridges and culverts, multi-hole frame bridges and culverts, and separated frame bridges and culverts.

[0069] It can be understood that the design variables refer to multiple cross-sectional size parameters of the target frame bridge culvert, including but not limited to wall thickness ds, middle wall thickness dm, top plate thickness dt, bottom plate thickness db, total width dl, and total height dh. In this embodiment, a double-hole frame bridge culvert is taken as an example. Figure 2 The figure shows a schematic diagram of the cross section of a double-hole frame bridge culvert, which displays multiple cross-sectional size parameters.

[0070] In a specific implementation, the design constraints include, but are not limited to, the value range of the cross-sectional normal stress and the value range of each design variable. In this embodiment, the value range of the cross-sectional normal stress c is set to c∈[0,10]MPa, and the value range of each design variable is [0.1,2.5]m.

[0071] It should be noted that, based on the design variables and design constraints of the target frame bridge and culvert, multiple initial individuals can be created, each of which represents a combination of a set of cross-sectional size parameters, and ensures that each cross-sectional size parameter in all individuals is within the value range of the design variables. At the same time, this embodiment relies on an independent finite element analysis kernel, which can quickly call finite element analysis and stress detection methods to calculate the cross-sectional normal stress of each initial individual.

[0072] In a feasible implementation, step S10 may include steps A11 to A13:

[0073] Step A11, determining the size range of each design variable according to the design information of the target frame bridge and culvert.

[0074] It should be noted that, according to the design information of the target frame bridge and culvert, the total width dl, total height dh, boundary constraints, external effects, material strength, value range of cross-sectional normal stress c and value range of each design variable of the target frame bridge and culvert can be clarified. In this embodiment, the value range of each design variable is [0.1, 2.5] m, that is, the size range of each design variable.

[0075] Step A12, performing random combinations according to the size ranges of the design variables to obtain a plurality of cross-sectional parameter combinations.

[0076] It should be noted that, in this embodiment, the total width dl and total height dh of the target frame bridge culvert are known parameters, so the optimization variable of the target frame bridge culvert is X = [ds, dm, dt, db]. An initial population consisting of random initial individuals is created based on the design variables of the target frame bridge culvert. Each initial individual represents a combination of a set of cross-sectional size parameters [ds, dm, dt, db, dl, dh], and ensures that each cross-sectional size parameter in all individuals is within the value range of the design variables, wherein the total width dl and total height dh are known parameters. In this embodiment, the total length dl = 10m and the total height dh = 6m, which can also be set to other values, and this embodiment does not limit this.

[0077] Step A13: Combining the cross-sectional parameters as a plurality of initial individuals, and performing stress calculation based on the initial individuals and the target finite element model to determine a plurality of cross-sectional normal stresses of the initial individuals.

[0078] It should be noted that in this embodiment, the boundary constraints, external effects, and material strength of the target frame bridge culvert are known conditions, and the boundary and action conditions in general are used. At this time, the stress c is a function only about X, and the intermediate process includes a complete set of matrix displacement and cross-sectional normal stress calculation methods. Therefore, this embodiment needs to rely on an independent finite element analysis kernel, which can quickly call finite element analysis and stress detection methods. According to the target finite element model, the cross-sectional normal stress under the main force and main + additional force combination is calculated: f(X) = c, thereby obtaining multiple cross-sectional normal stresses of each initial individual.

[0079] Step S20, constructing a penalty function of each initial individual according to a plurality of cross-sectional normal stresses of each initial individual.

[0080] It should be noted that after calculating the multiple cross-sectional normal stresses of each initial individual, the penalty function of each initial individual can be constructed through the relationship between the multiple cross-sectional normal stresses of each initial individual and the value range of the cross-sectional normal stress c.

[0081] In a feasible implementation manner, step S20 may include steps B11 to B13:

[0082] Step B11, determining the extreme normal stress of each initial individual according to multiple cross-sectional normal stresses of each initial individual.

[0083] It should be noted that the extreme normal stress refers to the maximum stress value f(X)max and the minimum stress value f(X)min among the multiple cross-sectional normal stresses of the initial individual. After obtaining the multiple cross-sectional normal stresses of each initial individual, the multiple cross-sectional normal stresses of each initial individual are sorted respectively to determine the extreme normal stress of each initial individual.

[0084] Step B12, when the extreme normal stress of each initial individual is within the cross-sectional normal stress range, construct a penalty function for each initial individual according to a preset value.

[0085] It should be noted that the cross-sectional normal stress range refers to the value range of the cross-sectional normal stress c∈[0,10]MPa. When the extreme normal stress of the initial individual is within the cross-sectional normal stress range, it means that the maximum stress value of the initial individual does not exceed the upper limit of c∈[0,10]MPa, and the minimum stress value of the initial individual does not exceed the lower limit of c∈[0,10]MPa. At this time, each cross-sectional normal stress of the initial individual is within the range of c∈[0,10]MPa. At this time, the penalty function ef of the initial individual is constructed based on the preset value. In this embodiment, the preset value is 0, and it can also be set to other values ​​according to requirements. This embodiment is not limited to this. However, in this embodiment, when multiple cross-sectional normal stresses of the initial individual are within the range of c∈[0,10]MPa, the penalty function ef of the initial individual is 0.

[0086] Step B13, when the first normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, constructing a penalty function of each initial individual according to the first normal stress of each initial individual and the first function construction method.

[0087] Step B14, when the second normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, constructing a penalty function of each initial individual according to the second normal stress of each initial individual and the second function construction method.

[0088] It should be noted that the first normal stress refers to the maximum stress value f(X)max among the multiple cross-sectional normal stresses of the initial individual; the second normal stress refers to the minimum stress value f(X)min among the multiple cross-sectional normal stresses of the initial individual; the first function construction method refers to the construction method of the penalty function corresponding to when the maximum stress value exceeds the upper limit of c∈[0,10]MPa; the second function construction method refers to the construction method of the penalty function corresponding to when the minimum stress value exceeds the lower limit of c∈[0,10]MPa.

[0089] It can be understood that when the first normal stress of the initial individual is not within the cross-sectional normal stress range, it means that the maximum stress value of the initial individual exceeds the upper limit of c∈[0,10]MPa, that is, f(X)max>10MPa. At this time, the penalty function of the initial individual is constructed based on the first normal stress of the initial individual and the first function construction method: ef=100×(f(X)max-10).

[0090] In the specific implementation, when the second normal stress of the initial individual is not within the cross-sectional normal stress range, it means that the minimum stress value of the initial individual exceeds the lower limit of c∈[0,10]MPa, that is, f(X)min<0MPa. At this time, the penalty function of the initial individual is constructed based on the second normal stress of the initial individual and the second function construction method: ef=-100×f(X)min.

[0091] Step S30, determining the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual.

[0092] It should be noted that the cross-sectional area refers to the cross-sectional area of ​​the target frame bridge culvert, and its expression is g(X)=dl×dh-(dh-dt-db)×(dl-2ds-dm)=S. In this embodiment, the optimization target is to minimize S.

[0093] It is understandable that the fitness value corresponding to each initial individual is calculated by the penalty function of each initial individual, multiple cross-sectional normal stress values, and cross-sectional area. When the cross-sectional normal stress value of the initial individual exceeds the cross-sectional normal stress range, the penalty function is used to increase the fitness value, indicating the unfitness of the initial individual. In this embodiment, when the cross-sectional normal stress of the initial individual does not exceed the cross-sectional normal stress range, since the penalty function ef=0, the unfitness of the initial individual will not be increased at this time.

[0094] Step S40, updating the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual, and determining the target individual of the population.

[0095] It should be noted that, in this embodiment, in the improved genetic algorithm, the crossover of the population adopts a dynamic crossover probability P c To achieve gene exchange between individuals; the population mutation adopts the dynamic mutation probability P m To achieve the diversity of the group; the number of groups is gradually reduced in an exponential manner, that is, the population reduction strategy N t The population is updated through dynamic crossover probability calculation strategy, dynamic mutation probability calculation strategy, population reduction strategy and the fitness value of each initial individual, and the genetic operation is repeated until the termination condition is met.

[0096] It can be understood that after the iteration is terminated, the individual with the best fitness is selected from the final population formed. This individual is the target individual of the population and represents the optimal combination of cross-sectional size parameters.

[0097] Step S50, determining the cross-sectional design parameters of the target frame bridge and culvert according to the target individuals of the population, and optimizing the size of the target frame bridge and culvert according to the cross-sectional design parameters.

[0098] It should be noted that the cross-sectional size parameter combination [ds, dm, dt, db, dl, dh] corresponding to the target individuals in the population is used as the cross-sectional design parameters of the target frame bridge and culvert to optimize the size of the target frame bridge and culvert.

[0099] It can be understood that in this embodiment, for the optimization scenario of the cross-sectional size of the frame bridge, the objective function and the variable X are simple linear, and the cross-variation with dynamic adjustment is adopted, which generally does not fall into the situation of local optimal solution. According to the penalty function constructed in this embodiment, there is generally no multi-modal situation. When constructing the offspring population, the precision of the population X is limited to 0.1. Under the constraints of the upper limit Xmax and the lower limit Xmin, the number of possible values ​​is greatly reduced, which can effectively improve the convergence and stability of the algorithm.

[0100] This embodiment determines multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert; constructs the penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual; determines the fitness value of each initial individual according to the penalty function of each initial individual, the multiple cross-sectional normal stress values ​​of each initial individual and the cross-sectional area corresponding to each initial individual; updates the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual to determine the population target individual; determines the cross-sectional design parameters of the target frame bridge and culvert according to the population target individual, and optimizes the size of the target frame bridge and culvert according to the cross-sectional design parameters. In the above manner, the improved genetic algorithm is used to solve the population target individual, thereby optimizing the size of the target frame bridge and culvert, which not only improves the applicability, but also improves the optimization efficiency and the accuracy of the optimized size, and can meet the mechanical safety of the frame bridge and culvert while achieving economic optimal design.

[0101] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 In the frame bridge and culvert size optimization method based on the improved genetic algorithm, step S40 further includes steps S41 to S46:

[0102] Step S41, sorting the fitness values ​​of the initial individuals, and screening the initial individuals based on the sorting results to obtain a plurality of first updated individuals.

[0103] It should be noted that excellent individuals are selected based on the sorting selection and elite retention strategy, the fitness values ​​of all initial individuals are sorted, and individuals with high fitness values ​​are replaced with individuals with low fitness values ​​based on the sorting results, thereby filtering out individuals with high fitness values, and the remaining initial individuals are the first updated individuals. In this embodiment, the genetic selection elite retention ratio is 0.8, which can also be set to other values, and this embodiment is not limited to this.

[0104] Step S42: randomly selecting individuals from a plurality of first updated individuals to determine a plurality of groups of crossover individuals and a plurality of mutation individuals.

[0105] It should be noted that individuals are randomly selected from multiple first update individuals to create multiple groups of crossover individuals, each group of crossover individuals includes two first update individuals for gene exchange between individuals; and multiple first update individuals are randomly selected as mutation individuals for individual mutation to maintain population diversity.

[0106] Step S43, performing population update according to multiple groups of crossover individuals and a dynamic crossover probability calculation strategy to obtain multiple second updated individuals.

[0107] It should be noted that the dynamic crossover probability calculation strategy refers to the calculation method of the dynamic crossover probability, specifically: Among them, P cm ,f,f min 、f max They are the preset crossover rate, the larger fitness value of the two crossover individuals, the minimum fitness value of the contemporary population, and the maximum fitness value of the contemporary population.

[0108] It is understandable that the dynamic crossover probability corresponding to each group of crossover individuals is determined based on multiple groups of crossover individuals and the dynamic crossover probability calculation strategy, and the crossover between two individuals in each group of crossover individuals is performed based on the dynamic crossover probability corresponding to each group of crossover individuals to achieve gene exchange between individuals. In this embodiment, the new individual formed after the crossover of each group of crossover individuals is completed is the second updated individual.

[0109] In a feasible implementation, step S43 may include steps C11 to C13:

[0110] Step C11, determining the population extreme fitness value according to the fitness value of each initial individual.

[0111] It should be noted that the population extreme fitness value refers to the minimum fitness value and the maximum fitness value of the contemporary population. In the initial population, the fitness value of each initial individual is sorted, and the population extreme fitness value f corresponding to the initial population is selected. min 、f max .

[0112] Step C12, determining the dynamic crossover probability of each group of crossover individuals according to the population extreme fitness value, the target fitness value of each group of crossover individuals, the preset crossover rate and the dynamic crossover probability calculation strategy.

[0113] It should be noted that the target fitness value of each group of crossover individuals refers to the larger fitness value among the groups of crossover individuals. The dynamic crossover probability of each group of crossover individuals can be determined by the population extreme fitness value, the target fitness value of each group of crossover individuals, the preset crossover rate and the dynamic crossover probability calculation strategy. In this embodiment, the preset crossover rate P cm =0.6, and may also be set to other values, which are not limited in this embodiment.

[0114] Step C13, performing population update according to the dynamic crossover probabilities of each group of crossover individuals and each group of crossover individuals to obtain a plurality of second updated individuals.

[0115] It should be noted that the gene exchange of each group of crossover individuals is achieved through the dynamic crossover probability of each group of crossover individuals. When the individual fitness value is low, a smaller dynamic crossover probability can be selected to protect these excellent individuals. At the same time, based on the dynamic crossover probability of each group of crossover individuals and the group update of each group of crossover individuals, the specific process of obtaining the second updated individuals corresponding to each group of crossover individuals is: the crossover operation of the two individuals in each group of crossover individuals is multiplied by P c and (1-P c ) coefficients, and finally add them together to construct a new crossover individual. The new crossover individual is the second updated individual. At the same time, the second updated individual must also be within the value range of the design variable [0.1,2.5]m.

[0116] Step S44, updating the population according to each mutated individual and the dynamic mutation probability calculation strategy to obtain a plurality of third updated individuals.

[0117] It should be noted that the dynamic mutation probability calculation strategy refers to the calculation method of the dynamic mutation probability, specifically: Among them, P mm are preset mutation rates. In this embodiment, the preset mutation rate P mm =0.2, and may also be set to other values, which are not limited in this embodiment.

[0118] It is understandable that, based on the dynamic mutation probability, each mutant individual is randomly mutated. When the individual fitness is low, a smaller dynamic mutation probability can be selected to balance the diversity of the population. In this embodiment, each mutant individual is mutated by random assignment to obtain a third updated individual, and the third updated individual must also be within the value range of the design variable [0.1, 2.5] m.

[0119] Step S45, performing population update according to each first updated individual, each second updated individual, each third updated individual and the population reduction strategy to obtain a fourth updated individual.

[0120] It should be noted that, a plurality of first update individuals, second update individuals and third update individuals are screened through a population reduction strategy to obtain a plurality of fourth update individuals.

[0121] In a feasible implementation, step S45 may include steps D11 to D14:

[0122] Step D11, determining the initial population size based on each initial individual.

[0123] Step D12, performing coefficient calculation according to the preset population number, the preset evolutionary generation and the initial population data to determine the target update coefficient.

[0124] It should be noted that the initial population size N0 of the first generation is determined based on each initial individual. The preset population size refers to the minimum possible population size N at the end of the evolution based on the improved genetic algorithm. end ; The preset evolutionary number refers to the set maximum evolutionary number T max In this embodiment, the initial population number N0=100, the preset population number N end =20, preset evolutionary number T max =100, the above parameters can also be set to other values, which are not limited in this embodiment. The target update coefficient can be obtained by calculating the coefficient by presetting the population number, the presetting evolutionary generation and the initial population data.

[0125] Step D13, performing calculations based on the target update coefficient, the current evolutionary generation, and the preset evolutionary generation to determine the current population size.

[0126] It should be noted that based on the target update coefficient, the current evolutionary number t, the preset evolutionary number T max By performing disease analysis, the current population size N can be determined t =C(tT max ) 2 +N end , the current population size is the number of individuals contained in the population after the population is updated.

[0127] Step D14, when each first updated individual, each second updated individual and each third updated individual all satisfy the section normal stress constraint condition, individual screening is performed according to the fitness value of each first updated individual, the fitness value of each second updated individual and, the fitness value of each third updated individual and the current population number to obtain multiple fourth updated individuals.

[0128] It should be noted that when the cross-sectional normal stress constraint condition is met, the penalty function ef<0.001. Therefore, by judging whether the penalty function of each updated individual is less than 0.001, it can be determined whether each updated individual meets the cross-sectional normal stress constraint condition. t , which is the population reduction strategy. At this time, if multiple first updated individuals, second updated individuals, and third updated individuals do not violate the cross-sectional normal stress constraint condition, it means that neither the parent generation nor the offspring generation violates the constraint. At this time, the generation with the smallest fitness is selected from multiple first updated individuals, second updated individuals, and third updated individuals. At the same time, the current population size should satisfy N t =C(tT max ) 2 +N end , thereby obtaining multiple fourth updated individuals.

[0129] It can be understood that if the offspring of multiple first updated individuals, second updated individuals, and third updated individuals violate the cross-sectional normal stress constraint condition while the parents do not violate the constraint, then the parents are selected, and the current population size should satisfy N t =C(tT max ) 2 +N end , thereby obtaining multiple fourth updated individuals; if the parents of multiple first updated individuals, second updated individuals, and third updated individuals violate the section normal stress constraint condition and the offspring do not violate the constraint, then the offspring is taken, and the current population size should satisfy N t =C(tT max ) 2 +N end , thereby obtaining multiple fourth updated individuals; if the parents and offspring of multiple first updated individuals, second updated individuals, and third updated individuals all violate the cross-sectional normal stress constraint, then the fitness value with the smaller value is selected, and the current population size should satisfy N t =C(tT max ) 2 +N end , thereby obtaining multiple fourth updated individuals.

[0130] Step S46, performing iterative update of the population based on the fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy to determine the population target individual.

[0131] It should be noted that after obtaining the fourth updated individual, the genetic operation is repeatedly performed based on multiple fourth updated individuals, dynamic crossover probability calculation strategy, dynamic mutation probability calculation strategy and population reduction strategy until the termination condition is met. After the iteration is terminated, the individual with the best fitness is selected from the final population formed to obtain the population target individual.

[0132] In a feasible implementation, step S46 may include steps E11 to E13:

[0133] Step E11, performing iterative update of the population based on each fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy.

[0134] It should be noted that the plurality of fourth updated individuals, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy repeatedly perform the genetic operation, ie the process of the above steps S41 to S45.

[0135] Step E12, when the current iteration information meets the iteration termination condition, obtain the target population.

[0136] It should be noted that the current iteration information includes but is not limited to the current evolutionary generation (i.e., the current genetic generation), the current population size, and the fitness value of each individual in the current population. The iteration termination conditions include but are not limited to the current evolutionary generation reaching the preset maximum evolutionary generation T. max ; Or, there are individuals in the current population whose fitness values ​​reach a sufficiently small standard, that is, there are individuals whose fitness values ​​are less than the preset fitness value.

[0137] It can be understood that when the current evolutionary generation in the current iteration information reaches the preset maximum evolutionary generation; or when the fitness value of an individual in the current population in the current iteration information reaches a sufficiently small standard, the iteration is stopped, and the population obtained at this time is the target population.

[0138] Step E13, sorting the fitness values ​​of multiple iteration-terminated individuals in the target population, and determining a population target individual from the multiple iteration-terminated individuals based on the sorting result.

[0139] It should be noted that the individuals included in the target population are the iteration-terminated individuals. The fitness values ​​of the iteration-terminated individuals are sorted, and based on the sorting result, the individual with the smallest fitness value is selected from multiple iteration-terminated individuals as the population target individual.

[0140] This embodiment sorts the fitness values ​​of each initial individual, and screens each initial individual based on the sorting result to obtain multiple first update individuals; randomly selects individuals from multiple first update individuals to determine multiple groups of crossover individuals and multiple variant individuals; updates the population according to multiple groups of crossover individuals and dynamic crossover probability calculation strategies to obtain multiple second update individuals; updates the population according to each variant individual and dynamic mutation probability calculation strategy to obtain multiple third update individuals; updates the population according to each first update individual, each second update individual, each third update individual and population reduction strategy to obtain a fourth update individual; iterates and updates the population based on the fourth update individual, dynamic crossover probability calculation strategy, dynamic mutation probability calculation strategy and population reduction strategy to determine the population target individual. Through the above method, the number of iterations of the genetic algorithm is effectively reduced and the optimization efficiency is improved.

[0141] For example, in order to help understand the implementation process of the frame bridge culvert size optimization method based on the improved genetic algorithm obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 4 , Figure 4 A brief schematic diagram of a frame bridge and culvert size optimization method based on an improved genetic algorithm is provided. Specifically:

[0142] The method of this embodiment uses an improved genetic algorithm to solve the optimization equation. Under the strategy of exponentially reducing the number of populations, a specific penalty strategy is constructed based on the cross-sectional normal stress. During population iteration, precision control conditions are applied to the optimization variables. The dynamic crossover probability and dynamic mutation probability are adaptively adjusted to make it easier to converge to the global optimal solution, effectively reducing the number of iterations of the genetic algorithm and improving the optimization efficiency. At the same time, an optimization equation for the cross-sectional size of the frame bridge and culvert is established. The optimization variable is the cross-sectional size of the frame bridge and culvert, the optimization target is the minimum cross-sectional area, and the constraint condition is the cross-sectional normal stress. The cross-sectional area of ​​the frame bridge and culvert designed in this way is small, which saves the amount of concrete while meeting the bearing capacity requirements.

[0143] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the frame bridge and culvert size optimization method based on the improved genetic algorithm of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0144] This application also provides a frame bridge culvert size optimization device based on an improved genetic algorithm, please refer to Figure 5 The frame bridge and culvert size optimization device based on the improved genetic algorithm includes:

[0145] The processing module 10 is used to determine a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert.

[0146] The construction module 20 is used to construct the penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual.

[0147] The processing module 10 is used to determine the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual.

[0148] The updating module 30 is used to update the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual, and determine the target individual of the population.

[0149] The optimization module 40 is used to determine the cross-sectional design parameters of the target frame bridge and culvert according to the target individuals of the population, and optimize the size of the target frame bridge and culvert according to the cross-sectional design parameters.

[0150] Optionally, the processing module 10 is further used for:

[0151] The size range of each design variable is determined according to the design information of the target frame bridge and culvert; a plurality of cross-sectional parameter combinations are obtained by performing random combinations according to the size range of each design variable; each cross-sectional parameter combination is used as a plurality of initial individuals, and stress calculation is performed based on each initial individual and the target finite element model to determine a plurality of cross-sectional normal stresses of each initial individual.

[0152] Optionally, the construction module 20 is further used for:

[0153] The extreme normal stress of each initial individual is determined according to multiple cross-sectional normal stresses of each initial individual; when the extreme normal stress of each initial individual is within the cross-sectional normal stress range, the penalty function of each initial individual is constructed according to a preset value; when the first normal stress among the extreme normal stresses of each initial individual is not within the cross-sectional normal stress range, the penalty function of each initial individual is constructed according to the first normal stress and the first function construction method of each initial individual; when the second normal stress among the extreme normal stresses of each initial individual is not within the cross-sectional normal stress range, the penalty function of each initial individual is constructed according to the second normal stress and the second function construction method of each initial individual.

[0154] Optionally, the updating module 30 is further used for:

[0155] The fitness values ​​of the initial individuals are sorted, and the initial individuals are screened based on the sorting results to obtain multiple first updated individuals; individuals are randomly selected from the multiple first updated individuals to determine multiple groups of crossover individuals and multiple mutant individuals; the population is updated according to the multiple groups of crossover individuals and the dynamic crossover probability calculation strategy to obtain multiple second updated individuals; the population is updated according to the mutant individuals and the dynamic mutation probability calculation strategy to obtain multiple third updated individuals; the population is updated according to the first updated individuals, the second updated individuals, the third updated individuals and the population reduction strategy to obtain the fourth updated individuals; the population is iteratively updated based on the fourth updated individuals, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy to determine the population target individuals.

[0156] Optionally, the updating module 30 is further used for:

[0157] The extreme fitness value of the population is determined according to the fitness value of each initial individual; the dynamic crossover probability of each group of crossover individuals is determined according to the extreme fitness value of the population, the target fitness value of each group of crossover individuals, the preset crossover rate and the dynamic crossover probability calculation strategy; the population is updated according to the dynamic crossover probability of each group of crossover individuals and each group of crossover individuals to obtain multiple second updated individuals.

[0158] Optionally, the updating module 30 is further used for:

[0159] Determine the initial population number according to each initial individual; perform coefficient calculation according to the preset population number, the preset evolutionary generation and the initial population data to determine the target update coefficient; perform calculation according to the target update coefficient, the current evolutionary generation and the preset evolutionary generation to determine the current population number; when each first updated individual, each second updated individual and each third updated individual all meet the cross-sectional normal stress constraint condition, perform individual screening according to the fitness value of each first updated individual, the fitness value of each second updated individual, the fitness value of each third updated individual and the current population number to obtain multiple fourth updated individuals.

[0160] Optionally, the updating module 30 is further used for:

[0161] Iterative update of the population is performed based on each fourth updated individual, a dynamic crossover probability calculation strategy, a dynamic mutation probability calculation strategy, and a population reduction strategy; when the current iteration information meets the iteration termination condition, a target population is obtained; the fitness values ​​of multiple iteration termination individuals in the target population are sorted, and the population target individual is determined from the multiple iteration termination individuals based on the sorting result.

[0162] The frame bridge culvert size optimization device based on the improved genetic algorithm provided by the present application adopts the frame bridge culvert size optimization method based on the improved genetic algorithm in the above-mentioned embodiment, which can solve the technical problem that the optimization method of the frame bridge culvert size in the prior art has low accuracy and efficiency and cannot achieve the optimal design. Compared with the prior art, the beneficial effects of the frame bridge culvert size optimization device based on the improved genetic algorithm provided by the present application are the same as the beneficial effects of the frame bridge culvert size optimization method based on the improved genetic algorithm provided by the above-mentioned embodiment, and the other technical features of the frame bridge culvert size optimization device based on the improved genetic algorithm are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0163] The present application provides a frame bridge and culvert size optimization device based on an improved genetic algorithm, and the frame bridge and culvert size optimization device based on the improved genetic algorithm includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the frame bridge and culvert size optimization method based on the improved genetic algorithm in the above-mentioned embodiment one.

[0164] Reference below Figure 6, which shows a schematic diagram of the structure of a frame bridge and culvert size optimization device based on an improved genetic algorithm suitable for implementing the embodiment of the present application. The frame bridge and culvert size optimization device based on an improved genetic algorithm in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The frame bridge and culvert size optimization device based on the improved genetic algorithm shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0165] like Figure 6 As shown, the frame bridge culvert size optimization device based on the improved genetic algorithm may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the frame bridge culvert size optimization device based on the improved genetic algorithm are also stored. The processing device 1001, the ROM 1002 and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the frame bridge and culvert size optimization device based on the improved genetic algorithm to communicate wirelessly or wired with other devices to exchange data. Although the frame bridge and culvert size optimization device based on the improved genetic algorithm with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0166] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0167] The frame bridge culvert size optimization device based on the improved genetic algorithm provided by the present application adopts the frame bridge culvert size optimization method based on the improved genetic algorithm in the above embodiment, which can solve the technical problem that the optimization method of the frame bridge culvert size in the prior art has low accuracy and efficiency and cannot achieve the optimal design. Compared with the prior art, the beneficial effects of the frame bridge culvert size optimization device based on the improved genetic algorithm provided by the present application are the same as the beneficial effects of the frame bridge culvert size optimization method based on the improved genetic algorithm provided by the above embodiment, and the other technical features of the frame bridge culvert size optimization device based on the improved genetic algorithm are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0168] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0169] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0170] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the frame bridge culvert size optimization method based on the improved genetic algorithm in the above-mentioned embodiment.

[0171] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0172] The above-mentioned computer-readable storage medium may be included in the frame bridge and culvert size optimization device based on the improved genetic algorithm; or it may exist independently without being assembled into the frame bridge and culvert size optimization device based on the improved genetic algorithm.

[0173] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the frame bridge culvert size optimization device based on the improved genetic algorithm, the frame bridge culvert size optimization device based on the improved genetic algorithm: determines multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge culvert; constructs a penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual; determines the fitness value of each initial individual according to the penalty function of each initial individual, the multiple cross-sectional normal stress values ​​of each initial individual and the cross-sectional area corresponding to each initial individual; performs population update according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual to determine the population target individual; determines the cross-sectional design parameters of the target frame bridge culvert according to the population target individual, and optimizes the size of the target frame bridge culvert according to the cross-sectional design parameters.

[0174] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0175] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0176] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0177] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned frame bridge and culvert size optimization method based on the improved genetic algorithm, and can solve the technical problem that the optimization method of the frame bridge and culvert size in the prior art has low accuracy and efficiency and cannot achieve the optimal design. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the frame bridge and culvert size optimization method based on the improved genetic algorithm provided by the above-mentioned embodiment, and will not be repeated here.

[0178] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned frame bridge and culvert size optimization method based on the improved genetic algorithm.

[0179] The computer program product provided by the present application can solve the technical problem that the optimization method of the size of the frame bridge and culvert in the prior art has low accuracy and efficiency and cannot achieve the optimal design. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the frame bridge and culvert size optimization method based on the improved genetic algorithm provided in the above embodiment, and will not be repeated here.

[0180] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A frame bridge and culvert size optimization method based on an improved genetic algorithm, characterized in that: The frame bridge and culvert size optimization method based on the improved genetic algorithm includes: Determine multiple initial individuals and multiple cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert; Constructing the penalty function of each initial individual according to multiple cross-sectional normal stresses of each initial individual; Determine the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual; According to the dynamic crossover probability calculation strategy, dynamic mutation probability calculation strategy, population reduction strategy and the fitness value of each initial individual, the population is updated to determine the target individual of the population; The cross-sectional design parameters of the target frame bridge and culvert are determined according to the target individuals of the population, and the size of the target frame bridge and culvert is optimized according to the cross-sectional design parameters.

2. The method according to claim 1, characterized in that The step of determining a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to the design variables and design constraints of the target frame bridge and culvert comprises: Determine the size range of each design variable according to the design information of the target frame bridge and culvert; According to the size range of each design variable, a random combination is performed to obtain multiple cross-sectional parameter combinations; Each section parameter combination is used as a plurality of initial individuals, and stress calculation is performed based on each initial individual and a target finite element model to determine a plurality of section normal stresses of each initial individual.

3. The method according to claim 1, characterized in that The step of constructing the penalty function of each initial individual according to the multiple cross-sectional normal stresses of each initial individual comprises: Determine the extreme normal stress of each initial individual according to multiple cross-sectional normal stresses of each initial individual; When the extreme normal stress of each initial individual is within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to a preset value; When the first normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to the first normal stress of each initial individual and the first function construction method; When the second normal stress in the extreme normal stress of each initial individual is not within the cross-sectional normal stress range, a penalty function of each initial individual is constructed according to the second normal stress of each initial individual and the second function construction method.

4. The method according to claim 1, characterized in that The step of updating the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual to determine the population target individual includes: Sorting the fitness values ​​of the initial individuals, and screening the initial individuals based on the sorting results to obtain a plurality of first updated individuals; Randomly selecting individuals from a plurality of first updated individuals to determine a plurality of groups of crossover individuals and a plurality of mutation individuals; According to multiple groups of crossover individuals and dynamic crossover probability calculation strategy, a group is updated to obtain multiple second updated individuals; According to each mutation individual and the dynamic mutation probability calculation strategy, the population is updated to obtain multiple third updated individuals; According to each first updated individual, each second updated individual, each third updated individual and the population reduction strategy, the population is updated to obtain a fourth updated individual; Based on the fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy, the population is iteratively updated to determine the target individual of the population.

5. The method according to claim 4, characterized in that The step of performing population updating according to multiple groups of crossover individuals and dynamic crossover probability calculation to obtain multiple second updated individuals comprises: Determine the population extreme fitness value according to the fitness value of each initial individual; Determine the dynamic crossover probability of each group of crossover individuals according to the extreme fitness value of the population, the target fitness value of each group of crossover individuals, the preset crossover rate and the dynamic crossover probability calculation strategy; The group is updated according to the dynamic crossover probability of each group of crossover individuals and each group of crossover individuals to obtain a plurality of second updated individuals.

6. The method according to claim 4, characterized in that The step of updating the population according to each first updated individual, each second updated individual, each third updated individual and the population reduction strategy to obtain a fourth updated individual comprises: Determine the initial population size based on each initial individual; Calculate the coefficient according to the preset population number, the preset evolutionary generation and the initial population data to determine the target update coefficient; Calculate the current population size based on the target update coefficient, the current evolutionary generation, and the preset evolutionary generation; When each first updated individual, each second updated individual and each third updated individual satisfy the section normal stress constraint condition, individual screening is performed according to the fitness value of each first updated individual, the fitness value of each second updated individual and, the fitness value of each third updated individual and the current population number to obtain multiple fourth updated individuals.

7. The method according to claim 4, characterized in that The step of performing iterative updating of the population based on the fourth updated individual, the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy and the population reduction strategy to determine the population target individual comprises: Performing iterative update of the population based on each fourth updated individual, a dynamic crossover probability calculation strategy, a dynamic mutation probability calculation strategy, and a population reduction strategy; When the current iteration information meets the iteration termination condition, the target population is obtained; The fitness values ​​of a plurality of iteration-suspended individuals in the target population are sorted, and a population target individual is determined from the plurality of iteration-suspended individuals based on the sorting result.

8. A frame bridge and culvert size optimization device based on an improved genetic algorithm, characterized in that: The frame bridge and culvert size optimization device based on the improved genetic algorithm comprises: A processing module, used for determining a plurality of initial individuals and a plurality of cross-sectional normal stresses of each initial individual according to design variables and design constraints of a target frame bridge and culvert; A construction module, used for constructing a penalty function of each initial individual according to multiple cross-sectional normal stresses of each initial individual; The processing module is used to determine the fitness value of each initial individual according to the penalty function of each initial individual, multiple cross-sectional normal stress values ​​of each initial individual, and the cross-sectional area corresponding to each initial individual; An updating module is used to update the population according to the dynamic crossover probability calculation strategy, the dynamic mutation probability calculation strategy, the population reduction strategy and the fitness value of each initial individual, and determine the target individual of the population; The optimization module is used to determine the cross-sectional design parameters of the target frame bridge and culvert according to the target individuals of the population, and optimize the size of the target frame bridge and culvert according to the cross-sectional design parameters.

9. A frame bridge and culvert size optimization device based on improved genetic algorithm, characterized in that: The frame bridge and culvert size optimization device based on the improved genetic algorithm comprises: a memory, a processor, and a frame bridge and culvert size optimization program based on the improved genetic algorithm stored in the memory and executable on the processor, wherein the frame bridge and culvert size optimization program based on the improved genetic algorithm is configured to implement the frame bridge and culvert size optimization method based on the improved genetic algorithm as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a frame bridge and culvert size optimization program based on an improved genetic algorithm. When the frame bridge and culvert size optimization program based on the improved genetic algorithm is executed by a processor, the frame bridge and culvert size optimization method based on an improved genetic algorithm as described in any one of claims 1 to 7 is implemented.

Images