Steel and carbon fiber hybrid cable cable-stayed bridge cable design method and device

Abstract

The application relates to the technical field of bridge design, in particular to a steel and carbon fiber mixed cable cable-stayed bridge cable design method and device, wherein the method comprises the following steps: determining basic geometric parameters and basic load parameters of a cable-stayed bridge, determining cable characteristic data of steel and carbon fiber mixed cables, and determining a maximum cable type quantity and a cable specification selection table of each type of cable; and performing optimization calculation based on a genetic algorithm and a deep learning mode to obtain the fitness of each individual in the tth generation population, thereby performing calculation until a preset iteration or a termination calculation condition is reached, obtaining an individual with the highest fitness of the population, and obtaining an optimized numerical solution. The application embodiment can reasonably set genetic algorithm parameters, and can predict by fusing a deep learning mode, so that the estimation efficiency of cable strength value is improved, the cable force calculation of the cable-stayed bridge is more accurate, and the automatic and efficient design of the cable is realized, and the applicability is stronger.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge design, in particular to a steel and carbon fiber mixed cable cable-stayed bridge cable design method and device. BACKGROUND

[0002] In bridge design, the tower, beam and cable are the main force components, the cable directly bears the gravity, the main beam bears the axial force and local bending moment, and the bridge is called a cable-stayed bridge. The cable-stayed bridge belongs to a multi-constrained statically indeterminate structure, there are many cables, the cable force can be adjusted, and there are many bridge force states that meet the requirements.

[0003] In related technologies, the current cable-stayed bridge cable generally uses steel as the main material, and there are also cable-stayed bridges that use carbon fiber composite cables and steel cables at the same time. The carbon fiber composite cable has the characteristics of high strength, light weight and small cable sag, so that the span of the steel and carbon fiber mixed cable cable-stayed bridge is larger.

[0004] However, in related technologies, the steel and carbon fiber mixed cable cable-stayed bridge has higher nonlinearity and more constraints, and when mixedly arranged, it may produce greater cable stiffness difference than single-material cable cable-stayed bridges, resulting in increased difficulty in adjusting the bridge cable force, reducing the calculation efficiency of the cable-stayed bridge cable design process, and unable to achieve rapid and efficient design of the steel and carbon fiber mixed cable cable-stayed bridge cable. It needs to be solved urgently. SUMMARY

[0005] The present application provides a steel and carbon fiber mixed cable cable-stayed bridge cable design method and device to solve the problems in related technologies that the steel and carbon fiber mixed cable cable-stayed bridge has higher nonlinearity and more constraints, and when mixedly arranged, it may produce greater cable stiffness difference than single-material cable cable-stayed bridges, resulting in increased difficulty in adjusting the bridge cable force, reducing the calculation efficiency of the cable-stayed bridge cable design process, and unable to achieve rapid and efficient design of the steel and carbon fiber mixed cable cable-stayed bridge cable.

[0006] The first aspect embodiment of the application provides a steel and carbon fiber mixed cable cable-stayed bridge cable design method, including the following steps: determining the basic geometric parameters and basic load parameters of the cable-stayed bridge, and determining the cable characteristic data of the steel and carbon fiber mixed cable and the maximum cable type quantity and cable specification selection table of each type of cable; based on a genetic algorithm and a deep learning method, according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum cable type quantity and the cable specification selection table, optimization calculation is performed to obtain the fitness of each individual in the tth generation population, t is a positive integer; based on the fitness of each individual in the tth generation population, the probability of selecting each individual is matched, and a crossover operator is applied to the population, and a mutation operator is applied to the population until a preset iteration or termination operation condition is reached, the individual with the highest fitness of the population is obtained, the chromosome of the highest individual is decoded, and an optimized numerical solution is obtained.

[0007] Optionally, in an embodiment of the application, the optimization calculation based on the genetic algorithm and the deep learning method according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum cable type quantity and the cable specification selection table to obtain the fitness of each individual in the tth generation population includes: selecting a cable force in a preset range of estimated cable force, forming an individual based on the cable force of all cables in the bridge, corresponding each individual to a chromosome, and setting the maximum evolution number, randomly generating a plurality of individuals as an initial population; calculate the initial fitness of each individual in the tth generation population.

[0008] Optionally, in an embodiment of the application, the calculation of the initial fitness of each individual in the tth generation population includes: estimating the initial dead load cable force of a plurality of cables according to the dead load; estimating the initial live load cable force according to the live load; calculating the estimated cable specification according to the initial dead load cable force and the initial live load cable force; calculating the estimated dead load cable stiffness according to the initial dead load cable force and the estimated cable specification; recalculating the live load maximum cable force according to the estimated dead load cable stiffness; recalculating the cable specification according to the initial dead load cable force and the live load maximum cable force; calculating the cable stiffness according to the initial dead load cable force and the cable specification; recalculating the final dead load cable force according to the dead load and the cable stiffness; based on the negative of the second norm of the error of the initial dead load cable force and the final dead load cable force, obtaining the initial fitness of each individual.

[0009] Optionally, in an embodiment of the application, the calculation formula of the initial live load cable force is:

[0010]

[0011] Wherein, F li is the estimated live load cable force of the ith cable, ΔLi is the cable spacing corresponding to the i-th cable, F lu is the uniform load of live load, F lc is the concentrated load of live load, θ i is the angle between the i-th cable and the horizontal plane, n is the number of cables, i = 1, 2, …, n.

[0012] Optionally, in an embodiment of the present application, the calculating the estimated cable specification according to the initial dead load cable force and the initial live load cable force comprises: calculating the bridge cable specification satisfying the force requirement according to the preset maximum cable type number and the preset minimum cable amount principle respectively, to obtain the estimated cable specification.

[0013] Optionally, in an embodiment of the present application, the expression of the preset minimum cable amount principle is:

[0014]

[0015] wherein, n is the number of cables, L i is the length of the i-th cable, N i is the number of the i-th cable, i = 1, 2, …, n.

[0016] The second aspect embodiment of the present application provides a steel and carbon fiber hybrid cable cable design device of a cable-stayed bridge, comprising: a determination module configured to determine basic geometric parameters and basic load parameters of the cable-stayed bridge, and determine cable characteristic data of the steel and carbon fiber hybrid cable and a maximum cable type number and a cable specification selection table of each type of cable; a calculation module configured to perform optimization calculation based on a genetic algorithm and a deep learning method according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum cable type number and the cable specification selection table, to obtain fitness of each individual in the t-th generation, t being a positive integer; an acquisition module configured to match a probability of each individual being selected based on the fitness of each individual in the t-th generation, and apply a crossover operator to the population and a mutation operator to the population until a preset iteration or a termination operation condition is reached, to obtain an individual with the highest fitness of the population, decode the chromosome of the highest individual, and obtain an optimized numerical solution.

[0017] Optionally, in an embodiment of the present application, the calculation module comprises: a generation unit configured to select a cable force within a preset range of estimated cable force, cable forces of all cables of the whole bridge form an individual, each individual corresponds to a chromosome, and a maximum evolution generation number is set, and a plurality of individuals are randomly generated as an initial population; a first calculation unit configured to calculate the initial fitness of each individual in the t-th generation.

[0018] Optionally, in an embodiment of the present application, the computing module further comprises: a first estimating unit configured to estimate initial dead cable forces of the plurality of cables according to dead loads; a second estimating unit configured to estimate initial live cable forces according to live loads; a second computing unit configured to compute estimated cable specifications according to the initial dead cable forces and the initial live cable forces; a third computing unit configured to compute estimated dead cable stiffnesses according to the initial dead cable forces and the estimated cable specifications; a fourth computing unit configured to recompute live maximum cable forces according to the estimated dead cable stiffnesses; a fifth computing unit configured to recompute cable specifications according to the initial dead cable forces and the live maximum cable forces; a sixth computing unit configured to compute cable stiffnesses according to the initial dead cable forces and the cable specifications; a seventh computing unit configured to recompute final dead cable forces according to the dead loads and the cable stiffnesses; and an obtaining unit configured to obtain the initial fitness of each individual based on a negative number of a second norm of errors between the initial dead cable forces and the final dead cable forces.

[0019] Optionally, in an embodiment of the present application, the initial live cable forces are computed according to the following formula:

[0020]

[0021] wherein, F li is the estimated live cable force of the ith cable, ΔL i is the cable spacing corresponding to the ith cable, F lu is the uniform load of the live loads, F lc is the concentrated load of the live loads, θ i is the angle between the ith cable and the horizontal plane, and n is the number of cables, i = 1, 2, …, n.

[0022] Optionally, in an embodiment of the present application, the second computing unit comprises: a first computing unit configured to compute cable specifications satisfying force requirements according to a preset maximum cable type number, to obtain the estimated cable specifications; and a second computing unit configured to compute the estimated cable specifications according to a preset minimum cable amount principle.

[0023] Optionally, in an embodiment of the present application, the preset minimum cable amount principle is expressed as:

[0024]

[0025] wherein, n is the number of cables, L i is the length of the ith cable, N i is the number of the ith cable, and i = 1, 2, …, n.

[0026] The third aspect of the application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the program to realize the cable design method of the steel and carbon fiber hybrid cable cable-stayed bridge as described in the above embodiments.

[0027] The fourth aspect of the application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the cable design method of the steel and carbon fiber hybrid cable cable-stayed bridge as described above.

[0028] The embodiments of the application can determine the basic geometric parameters and basic load parameters of the cable-stayed bridge, determine the cable characteristic data of the steel and carbon fiber hybrid cable, and the maximum cable type quantity and cable specification selection table of each type of cable, and perform optimization calculation based on the genetic algorithm and deep learning method to obtain the fitness of each individual in the t th generation population, thereby performing calculation until a preset iteration or termination operation condition is reached, obtaining the individual with the highest fitness of the population, obtaining the optimized numerical solution, improving the estimation efficiency of the cable strength value, and enabling the cable force calculation of the cable-stayed bridge to be more accurate, thereby realizing the automatic and efficient design of the cable, and having stronger applicability. Thus, the problems in the related art, such as the higher nonlinearity of the steel and carbon fiber hybrid cable cable-stayed bridge, more constraints, and greater cable stiffness difference between the hybrid arrangement than the single material cable cable-stayed bridge, leading to increased difficulty in adjusting the cable force of the completed bridge, reducing the calculation efficiency of the cable-stayed bridge cable design process, and being unable to realize the rapid and efficient design of the steel and carbon fiber hybrid cable cable-stayed bridge cable, are solved.

[0029] Additional aspects and advantages of the application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0030] The above and / or additional aspects and advantages of the application will become apparent and be readily appreciated from the following description, including the accompanying drawings, in which:

[0031] Figure 1 A flowchart of a steel and carbon fiber hybrid cable cable-stayed bridge cable design method according to an embodiment of the application is provided.

[0032] Figure 2 A process diagram of a steel and carbon fiber hybrid cable cable-stayed bridge cable design method based on a genetic algorithm and deep learning according to an embodiment of the application is provided.

[0033] Figure 3 A reference cable-stayed bridge schematic diagram according to an embodiment of the application is provided.

[0034] Figure 4Error curve chart of iterative calculation of the reference cable-stayed bridge of one embodiment of the present application;

[0035] Figure 5 Safety factor and reliability index broken line chart of the reference cable-stayed bridge of one embodiment of the present application after completion of design;

[0036] Figure 6 Cable force and cable specification broken line chart of the reference cable-stayed bridge of one embodiment of the present application after completion of design before and after iteration of cables;

[0037] Figure 7 Structure schematic diagram of the cable-stayed bridge cable design device of steel and carbon fiber hybrid cable according to the embodiment of the present application;

[0038] Figure 8 Structure schematic diagram of the electronic device according to the embodiment of the present application. DETAILED DESCRIPTION

[0039] Embodiments of the present application are described in detail below with reference to the attached drawings, which show by way of example, embodiments in which the same or similar elements or elements having the same or similar functions are denoted by the same or similar reference numerals throughout the drawings. The embodiments described below by reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0040] The steel and carbon fiber mixed cable cable-stayed bridge cable design method and device provided by the embodiment of the present application are described below with reference to the accompanying drawings. In view of the problems in the related art that the steel and carbon fiber mixed cable cable-stayed bridge has higher nonlinearity and more constraints, and when mixedly arranged, it can produce greater inter-cable stiffness difference than a single-material cable-stayed bridge, leading to increased difficulty in adjusting the cable force of the completed bridge, reducing the calculation efficiency of the cable-stayed bridge cable design process, and failing to achieve rapid and efficient design of the steel and carbon fiber mixed cable cable-stayed bridge cable, the present application provides a steel and carbon fiber mixed cable cable-stayed bridge cable design method, which determines the basic geometric parameters and basic load parameters of the cable-stayed bridge, determines the cable characteristic data of the steel and carbon fiber mixed cable and the maximum cable type quantity and cable specification selection table of each type of cable, and performs optimization calculation based on a genetic algorithm and deep learning method to obtain the fitness of each individual in the tth generation population. Thus, the operation is performed until the preset iteration or termination operation condition is reached, the individual with the highest fitness of the population is obtained, the optimized numerical solution is obtained, the estimation efficiency of the cable strength value is improved, the cable force calculation of the cable-stayed bridge is more accurate, and thus the automatic and efficient design of the cable is realized, and the applicability is stronger. Thus, the problems in the related art that the steel and carbon fiber mixed cable cable-stayed bridge has higher nonlinearity and more constraints, and when mixedly arranged, it can produce greater inter-cable stiffness difference than a single-material cable-stayed bridge, leading to increased difficulty in adjusting the cable force of the completed bridge, reducing the calculation efficiency of the cable-stayed bridge cable design process, and failing to achieve rapid and efficient design of the steel and carbon fiber mixed cable cable-stayed bridge cable are solved.

[0041] Specifically, Figure 1 A flowchart of a steel and carbon fiber mixed cable cable-stayed bridge cable design method provided by the embodiment of the present application is shown.

[0042] As Figure 1 shown, the steel and carbon fiber mixed cable cable-stayed bridge cable design method includes the following steps:

[0043] In step S101, the basic geometric parameters and basic load parameters of the cable-stayed bridge are determined, and the cable characteristic data of the steel and carbon fiber mixed cable and the maximum cable type quantity and cable specification selection table of each type of cable are determined.

[0044] It can be understood that in the embodiments of the present application, the basic geometric parameters of the cable-stayed bridge can clearly indicate the cable-stayed bridge cable-beam position relationship, and the basic load parameters of the cable-stayed bridge can clearly indicate the dead load and live load of the cable-stayed bridge, including the mean value and the variation coefficient. The cable characteristics data of the steel and carbon fiber hybrid cable can clearly indicate the type of each cable, which can be a steel cable or a carbon fiber composite cable, and the calculation method control parameters of each cable, which can be the material index and safety factor index of the steel cable, or the material index and reliability index of the carbon fiber composite cable. The cable specification selection table of each type of cable can include the specification, weight, cross-sectional area and other properties of each cable.

[0045] In actual execution process, when selecting relevant parameters, the cable material can be steel, carbon fiber composite material, steel and carbon fiber composite material, the cable surface form can be single cable surface, double cable surface, dense cable and sparse cable, and the tower form can be concrete tower, steel tower, single column tower and double column tower, etc.

[0046] The embodiments of the present application can determine the basic geometric parameters and basic load parameters of the cable-stayed bridge, and determine the cable characteristics data of the steel and carbon fiber hybrid cable and the maximum cable type quantity and cable specification selection table of each type of cable, through data preprocessing of cable design, to obtain relevant parameters required by the algorithm in the following steps, thereby providing a data basis for obtaining the cable design result of the cable-stayed bridge.

[0047] In step S102, based on the genetic algorithm and deep learning method, the basic geometric parameters, the basic load parameters, the cable characteristics data, the maximum cable type quantity and the cable specification selection table are calculated to obtain the fitness of each individual in the t th generation population, and t is a positive integer.

[0048] In actual execution process, based on the genetic algorithm, the relevant data obtained in the above steps can be processed, and the strength value of the carbon fiber cable can be predicted by deep learning prediction. The mean value and variation coefficient of the carbon fiber composite cable strength obtained from the unit strength index of the test data are used to realize the prediction of the carbon fiber cable strength value, and then the optimization calculation of the data is completed.

[0049] The embodiments of the present application can be based on the genetic algorithm and deep learning method, and the basic geometric parameters, the basic load parameters, the cable characteristics data, the maximum cable type quantity and the cable specification selection table are calculated to obtain the fitness of each individual in the t th generation population, and the deep learning method is used for prediction, which improves the corresponding calculation efficiency and makes the design process more efficient.

[0050] Optionally, in an embodiment of the present application, based on a genetic algorithm and deep learning method, according to basic geometric parameters, basic load parameters, cable characteristic data, the maximum cable type number and the cable specification selection table, an optimization calculation is performed to obtain the fitness of each individual in the t th generation population, including: selecting a cable force in a preset range of estimated cable force, forming an individual based on the cable force of all cables in the whole bridge, corresponding each individual to a chromosome, and setting the maximum evolution number, and randomly generating a plurality of individuals as an initial population; and calculating the initial fitness of each individual in the t th generation population.

[0051] It can be understood that in the embodiment of the present application, the cable force in the preset range of the estimated cable force can be calculated by calculating the estimated dead load cable force value of each cable in a certain range, forming an individual based on the cable force of all cables in the whole bridge, corresponding each individual to a chromosome, and the initial dead load cable force is,

[0052]

[0053] wherein, F di is the estimated dead load cable force of the i th cable, ΔL i is the cable spacing corresponding to the i th cable, F du is the constant uniform load, θ i is the angle between the i th cable and the horizontal plane, and p is the value range of the search cable force, i = 1, 2, …, n. Wherein, p can be taken in the range of 0.8-1.2.

[0054] For example, binary Gray coding can be used as the chromosome coding method, an individual is formed based on the cable force of all cables in the whole bridge, each individual corresponds to a chromosome, wherein the chromosome can cover the preset cable force range, the maximum evolution number T is set, N individuals are randomly generated as the initial population P(0), and the initial fitness of each individual in the population is calculated.

[0055] In the embodiment of the present application, the cable force in the preset range of the estimated cable force can be selected, an individual is formed based on the cable force of all cables in the whole bridge, each individual corresponds to a chromosome, and the maximum evolution number is set, a plurality of individuals are randomly generated as an initial population, and then the initial fitness of each individual in the t th generation population is calculated. By reasonably setting the genetic algorithm parameters, the computer parallel computing capability can be fully utilized, and the calculation speed is further improved.

[0056] Optionally, in an embodiment of the present application, the initial fitness of each individual in the t th generation is calculated, comprising: estimating the initial dead load cable force according to the dead load; estimating the initial live load cable force according to the live load; calculating the estimated cable specification according to the initial dead load cable force and the initial live load cable force; calculating the estimated dead load cable stiffness according to the initial dead load cable force and the estimated cable specification; recalculating the live load maximum cable force according to the estimated dead load cable stiffness; recalculating the cable specification according to the initial dead load cable force and the live load maximum cable force; calculating the cable stiffness according to the initial dead load cable force and the cable specification; recalculating the final dead load cable force according to the dead load and the cable stiffness; and obtaining the initial fitness of each individual based on the negative of the second norm of the error between the initial dead load cable force and the final dead load cable force.

[0057] It can be understood that the initial dead load cable force in the embodiment of the present application can be estimated according to the dead load in the geometric parameters and the load, and the initial live load cable force can be estimated according to the live load in the geometric parameters and the load.

[0058] In actual execution, when the genetic algorithm iterates, each individual can select an input value within a certain range, such as 0.8-1.2, of the estimated initial dead load cable force, and then obtain the initial live load cable force, and the next individual reselects an initial dead load cable force as an input value to estimate again. The initial fitness of each individual in the t th generation is calculated by individual evaluation, and the evaluation function takes all the input bridge cable forces as input parameters and outputs the error index of the input bridge cable force and the estimated bridge cable force based on the input bridge cable force.

[0059] For example, first, the dead load cable force of N cables can be estimated according to the dead load q to obtain the initial dead load cable force F d as an input parameter, and the live load cable force can be estimated according to the live load q l to obtain the initial live load cable force F l . Then, the estimated cable specification Ω is calculated according to the input initial dead load cable force F d and the estimated initial live load cable force F l . The estimated dead load cable stiffness K is calculated according to the input initial dead load cable force F d and the estimated cable specification Ω, the equivalent cable modulus of elasticity is calculated according to the catenary equation, the live load influence line is calculated by using the finite element calculation method of the truss structure, and then the live load cable force is calculated to obtain the recalculated live load maximum cable force F l '.

[0060] Then, the cable specification Ω' is recalculated according to the input initial dead load cable force F d and the recalculated live load maximum cable force F l ', and then the initial dead load cable force F dRecalculate the cable stiffness K', and use the zero-moment method to reduce the tower beam stiffness to p times the original stiffness, p is a positive value much smaller than 1, which can be taken as 0.001, and record the cable force at this time, which is the final constant load cable force F obtained by recalculation d ’.

[0061] Finally, output the initial constant load cable force F d and the error of the second norm of the maximum live load cable force F d ’ calculated by recalculation. The output value is taken as the fitness of the corresponding input constant load cable force F d sample. Wherein, the second norm is the arithmetic square root of the sum of squares of all data.

[0062] The embodiments of the application can estimate the initial constant load cable force of multiple cables, and then estimate the constant load cable stiffness, and recalculate the final constant load cable force according to the estimated constant load cable stiffness, to obtain the initial fitness of each individual. Through individual evaluation, the fitness function is reasonably set, the nonlinear factors of the cable-stayed bridge are fully considered at low calculation cost, and the calculation efficiency is effectively increased.

[0063] Specifically, in one embodiment of the application, the calculation formula of the initial live load cable force is:

[0064]

[0065] Wherein, F li is the estimated live load cable force of the i-th cable, ΔL i is the cable spacing corresponding to the i-th cable, F lu is the uniform load of the live load, F lc is the concentrated load of the live load, θ i is the angle between the i-th cable and the horizontal plane, n is the number of cables, and i=1, 2, …, n.

[0066] As can be seen from the above formula, the live load cable force of each cable can be estimated according to the cable arrangement of the cable-stayed bridge to obtain the corresponding live load cable force estimate.

[0067] In addition, in one embodiment of the application, the estimated cable specification is calculated according to the initial constant load cable force and the initial live load cable force, including: calculating the bridge cable specification that meets the force requirement according to the preset maximum cable type quantity and the preset minimum cable quantity principle respectively, to obtain the estimated cable specification.

[0068] It can be understood that in the embodiments of the present application, when calculating the specifications of the cables, the cables meeting the design requirements, i.e., meeting the safety factor index or the reliability index, can be selected according to the preset cable calculation method and cable specification selection table, the steel cables can be controlled by the safety factor, the carbon fiber composite cables can be controlled by the reliability index, and then the calculation is performed according to the preset maximum cable type quantity and the preset minimum cable quantity principle. Among them, the mean value and the coefficient of variation of the strength of the carbon fiber composite cable are obtained according to the unit strength index obtained from the test data, and are predicted by deep learning.

[0069] In actual execution, when recalculating the cable specifications according to the initial dead load and the maximum live load in calculating the initial fitness of each individual in the tth generation population, the cable specifications meeting the stress requirements can be calculated according to the preset maximum cable type quantity and the preset minimum cable quantity principle to obtain the recalculated cable specifications.

[0070] It should be noted that the preset maximum cable type quantity and the preset minimum cable quantity principle are set by a person skilled in the art according to the actual situation, and are not limited specifically herein.

[0071] The embodiments of the present application can calculate the cable specifications meeting the stress requirements according to the preset maximum cable type quantity and the preset minimum cable quantity principle, respectively, to obtain the estimated cable specifications, and further improve the data processing process of the genetic algorithm, so that the algorithm result is more accurate.

[0072] Specifically, in an embodiment of the present application, the expression of the preset minimum cable quantity principle is:

[0073]

[0074] Wherein, n is the number of cables, L i is the length of the ith cable, N i is the number of the ith cable, i = 1, 2, …, n.

[0075] It can be understood that the number of cable roots and the size of the cable in the embodiments of the present application need to be within the total range of the cable, i.e., N i ∈Ω j , j = 1, 2,

[0076] Wherein, Ω j is the set of cable roots, Ω1 is the set of steel cable roots, the number of elements of Ω1 is less than or equal to the set number of steel cable specifications P1, Ω2 is the set of carbon fiber cable roots, and the number of elements of Ω2 is less than or equal to the set number of carbon fiber cable specifications P2.

[0077] It can be seen from the above formula that the preset minimum cable amount principle expression of the embodiment of the application can be used to calculate the bridge completion cable specifications that meet the force requirement, thereby further providing an optimization processing mode for the operation of the genetic algorithm.

[0078] In step S103, based on the fitness of each individual in the tth generation population, the probability of each individual being selected is matched, and a crossover operator is applied to the population, and a mutation operator is applied to the population, until a preset iteration or a termination operation condition is reached, the individual with the highest fitness of the population is obtained, the chromosome of the highest individual is decoded, and the optimized numerical solution is obtained.

[0079] It can be understood that, in the embodiment of the application, the selection operation can be performed based on the fitness of each individual in the tth generation population obtained in the above steps, the probability of each individual being selected is matched according to the fitness of each individual in the tth generation population P(t), and the individuals genetically passed to the next generation are randomly selected, so that the next generation of excellent individuals has a greater genetic probability. For example, a roulette selection method can be selected, that is, the probability of each individual being selected is proportional to the size of its fitness, so as to ensure that the better individuals have a greater selection probability. The crossover operator can determine the crossover position and crossover probability of the chromosome of each selected individual, and the crossover operator is applied to the population through the crossover operation. The mutation operator can determine the probability of mutation at different positions in the chromosome of each individual, and the mutation operator is applied to the population through the mutation operation.

[0080] In the actual iteration process of the genetic algorithm, if the maximum evolution number reaches T, the evolution is terminated, the individual with the highest fitness of the final population is output, and the optimized numerical solution of the steel and carbon fiber hybrid cable cable-stayed bridge cable design is obtained by decoding the chromosome of the individual.

[0081] It should be noted that the preset iteration operation condition and the preset termination operation condition are set by a person skilled in the art according to the actual situation, and are not specifically limited herein.

[0082] In some embodiments, the genetic algorithm can be programmed, and a control language corresponding to a main structure design software is output to perform modeling calculation. A designer inputs the necessary key geometric parameters and load parameters of the cable-stayed bridge design, completes the full-automatic design of the cable specifications and cable forces, and the calculation error can meet the structural design requirements.

[0083] The embodiment of the application can sequentially perform selection, crossover and mutation operations based on the fitness of each individual in the tth generation population until a preset iteration or termination operation condition is reached, obtain the individual with the highest fitness of the population, decode the chromosome of the highest individual, and obtain the optimized numerical solution, thereby optimizing the design process, improving the design efficiency, and expanding the application range of the design process.

[0084] The following will be described in combination with Figures 2-6The working content of the embodiment of the present application is described in detail.

[0085] As shown in Figure 2 , it is a process diagram of the steel and carbon fiber hybrid cable cable-stayed bridge cable design method based on genetic algorithm and deep learning of an embodiment of the present application.

[0086] In the design process of the steel and carbon fiber hybrid cable cable-stayed bridge cable, first, based on the geometric parameters, load parameters, cable characteristics, maximum species number and cable specification table, the initialization processing is performed, the initial constant load cable force is input and the live load cable force is estimated, the estimated cable specification is obtained, the calculation of the live load cable force is obtained, the cable specification is recalculated, the cable stiffness is recalculated, and the constant load cable force is recalculated. The fitness is calculated, and the selection operation, crossover operation and mutation operation are performed in turn. If the maximum evolution generation i reaches T, the operation is terminated. If it has not reached, the operation is continued to perform the iteration process.

[0087] Through the above process, the reference cable-stayed bridge diagram as shown in Figure 3 is obtained. Among them, Figure 4 is the iteration calculation error curve diagram of the reference cable-stayed bridge, Figure 5 is the safety factor and reliability index broken line diagram of the reference cable-stayed bridge after the design is completed, Figure 6 is the cable force and cable specification broken line diagram of the reference cable-stayed bridge before and after the iteration after the design is completed, to further elaborate the design results of the steel and carbon fiber hybrid cable cable-stayed bridge cable.

[0088] According to the steel and carbon fiber hybrid cable cable-stayed bridge cable design method provided by the embodiment of the present application, by determining the basic geometric parameters and basic load parameters of the cable-stayed bridge, and determining the cable characteristic data of the steel and carbon fiber hybrid cable and the maximum cable species number and cable specification selection table of each type of cable, and based on the genetic algorithm and deep learning method for optimization calculation, the fitness of each individual in the t th generation population is obtained. The operation is performed until the preset iteration or termination operation condition is reached, the individual with the highest fitness of the population is obtained, the optimized numerical solution is obtained, the estimation efficiency of the cable strength value is improved, the cable force calculation of the cable-stayed bridge is more accurate, and the automatic and efficient design of the cable is realized. Stronger applicability. Therefore, the problems such as higher nonlinearity, more constraints of the steel and carbon fiber hybrid cable cable-stayed bridge, and greater cable stiffness difference between the mixed arrangement than the single material cable-stayed bridge, resulting in increased bridge cable force adjustment difficulty, reduced cable-stayed bridge cable design process calculation efficiency, and inability to realize rapid and efficient design of the steel and carbon fiber hybrid cable cable-stayed bridge cable in the related technology are solved.

[0089] Second, the steel and carbon fiber hybrid cable cable-stayed bridge cable design device according to the embodiment of the present application is described with reference to the accompanying drawings.

[0090] Figure 7 is a block schematic view of a steel and carbon fiber hybrid cable cable-stayed bridge cable design device of an embodiment of the present application.

[0091] As shown in Figure 7 the steel and carbon fiber hybrid cable cable-stayed bridge cable design device 10 includes a determination module 100, a calculation module 200, and an acquisition module 300.

[0092] The determination module 100 is configured to determine basic geometric parameters and basic load parameters of the cable-stayed bridge, and determine cable characteristic data of the steel and carbon fiber hybrid cable, and a maximum cable type quantity and a cable specification selection table of each type of cable.

[0093] The calculation module 200 is configured to perform optimization calculation based on a genetic algorithm and a deep learning method according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum cable type quantity, and the cable specification selection table, to obtain fitness of each individual in a t th generation population, t being a positive integer.

[0094] The acquisition module 300 is configured to match a selection probability of each individual based on the fitness of each individual in the t th generation population, and apply a crossover operator to the population and a mutation operator to the population until a preset iteration or a termination operation condition is reached, to obtain an individual with the highest fitness of the population, decode a chromosome of the individual with the highest fitness, and obtain an optimized numerical solution.

[0095] Optionally, in an embodiment of the present application, the calculation module 200 includes a generation unit and a first calculation unit.

[0096] The generation unit is configured to select a cable force in a preset range of estimated cable force, form an individual based on cable forces of all cables of the whole bridge, correspond each individual to a chromosome, set a maximum evolution generation number, and randomly generate a plurality of individuals as an initial population.

[0097] The first calculation unit is configured to calculate an initial fitness of each individual in the t th generation population.

[0098] Optionally, in an embodiment of the present application, the calculation module 200 further includes a first estimation unit, a second estimation unit, a second calculation unit, a third calculation unit, a fourth calculation unit, a fifth calculation unit, a sixth calculation unit, a seventh calculation unit, and an acquisition unit.

[0099] The first estimation unit is configured to estimate initial dead load cable forces of a plurality of cables according to dead loads.

[0100] The second estimation unit is configured to estimate initial live load cable forces according to live loads.

[0101] The second calculation unit is configured to calculate the estimated cable specification according to the initial constant load cable force and the initial live load cable force.

[0102] The third calculation unit is configured to calculate the estimated constant load cable stiffness according to the initial constant load cable force and the estimated cable specification.

[0103] The fourth calculation unit is configured to recalculate the live load maximum cable force according to the estimated constant load cable stiffness.

[0104] The fifth calculation unit is configured to recalculate the cable specification according to the initial constant load cable force and the live load maximum cable force.

[0105] The sixth calculation unit is configured to calculate the cable stiffness according to the initial constant load cable force and the cable specification.

[0106] The seventh calculation unit is configured to recalculate the final constant load cable force according to the constant load and the cable stiffness.

[0107] The acquisition unit is configured to acquire the initial fitness of each individual based on a negative number of a second norm of an error between the initial constant load cable force and the final constant load cable force.

[0108] Optionally, in an embodiment of the present application, the calculation formula of the initial live load cable force is as follows:

[0109]

[0110] wherein, F li is the estimated live load cable force of the ith cable, ΔL i is the cable spacing corresponding to the ith cable, F lu is the uniform load of the live load, F lc is the concentrated load of the live load, θ i is the angle between the ith cable and the horizontal plane, n is the number of cables, and i = 1, 2, …, n.

[0111] Optionally, in an embodiment of the present application, the second calculation unit comprises: a calculation unit configured to calculate the cable specification of the completed bridge that meets the force requirement according to the preset maximum cable type number and the preset minimum cable amount principle, respectively, to obtain the estimated cable specification.

[0112] Optionally, in an embodiment of the present application, the expression of the preset minimum cable amount principle is as follows:

[0113]

[0114] wherein, n is the number of cables, L i is the length of the ith cable, N i is the number of the ith cable, and i = 1, 2, …, n.

[0115] It should be noted that the aforementioned explanation of the steel and carbon fiber mixed cable cable-stayed bridge cable design method embodiment is also applicable to the steel and carbon fiber mixed cable cable-stayed bridge cable design device of this embodiment, which will not be repeated here.

[0116] The steel and carbon fiber mixed cable cable-stayed bridge cable design device provided by the embodiment of the application can determine the basic geometric parameters and basic load parameters of the cable-stayed bridge, determine the cable characteristic data of the steel and carbon fiber mixed cable and the maximum cable type quantity and cable specification selection table of each type of cable, and perform optimization calculation based on a genetic algorithm and a deep learning method to obtain the fitness of each individual in the t th generation population. The operation is performed until a preset iteration or termination operation condition is reached, the individual with the highest fitness of the population is obtained, the optimized numerical solution is obtained, the estimation efficiency of the cable strength value is improved, the cable force calculation of the cable-stayed bridge is more accurate, and the automatic and efficient design of the cable is realized, and the applicability is stronger. Therefore, the problems in the related art, such as the higher nonlinearity of the steel and carbon fiber mixed cable cable-stayed bridge, more constraints, and greater cable stiffness difference between the mixed arrangement than the single-material cable cable-stayed bridge, leading to increased difficulty in adjusting the cable force of the completed bridge, reducing the calculation efficiency of the cable-stayed bridge cable design process, and being unable to realize the rapid and efficient design of the steel and carbon fiber mixed cable cable-stayed bridge cable, are solved.

[0117] Figure 8 The structure schematic diagram of the electronic device provided by the embodiment of the application is shown. The electronic device can include:

[0118] The memory 801, the processor 802, and the computer program stored in the memory 801 and executable on the processor 802.

[0119] The processor 802 implements the steel and carbon fiber mixed cable cable-stayed bridge cable design method provided in the above embodiments when executing the program.

[0120] Further, the electronic device further includes:

[0121] The communication interface 803 is used for communication between the memory 801 and the processor 802.

[0122] The memory 801 is used to store the computer program executable on the processor 802.

[0123] The memory 801 can include a high-speed RAM memory, and can also include a non-volatile memory, such as at least one disk memory.

[0124] If the memory 801, the processor 802 and the communication interface 803 are implemented independently, the communication interface 803, the memory 801 and the processor 802 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 8 Only one thick line is used to represent the bus in the figure, but it does not mean that there is only one bus or only one type of bus.

[0125] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can complete communication between each other through an internal interface.

[0126] The processor 802 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0127] The embodiment also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steel and carbon fiber mixed cable cable-stayed bridge cable design method.

[0128] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example" or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0129] Moreover, the terms "first", "second", "third", etc. are used herein only to describe different steps or categories of steps in a claim for patent purposes, and are not to be construed as indicating or implying relative importance of one step to another or a quantity of times the steps are to be performed in use. Thus, features defined with "first", "second" or "third" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, for example, two, three, etc. unless explicitly specifically defined otherwise.

[0130] Any process or method descriptions or blocks in flow charts described herein and elsewhere can be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are possible. In some embodiments, the processes or methods described in flow charts can be substantially represented in computer readable medium that can be executed by a processing unit of a computer system.

[0131] Logic and / or steps represented in flow charts described herein and elsewhere can be embodied in computer readable medium, which can be executed by a processing unit of a computer system, or in combination with other instructions in software, firmware or hardware, for example. For the purposes of this description, a "computer readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can also be non-transitory. The computer readable medium can further include a computer storage medium. The computer storage medium can be a volatile or non-volatile memory, a floppy diskette, a compact disk, a tape, a solid state memory drive, a memory card, or a persistent memory. The computer storage medium can be a non-transitory computer readable medium. The computer storage medium can be a tangible or physical computer storage medium. The computer storage medium can be a computer readable storage medium. The computer storage medium can be a computer readable non-transitory storage medium. The computer storage medium can be a computer readable tangible non-transitory storage medium. The computer readable medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. The computer readable medium can be a non-transitory computer readable medium. The computer readable medium can be a computer readable tangible non-transitory medium. The computer readable medium can be a computer readable storage medium. The computer readable medium can be a computer readable non-transitory storage medium. The computer readable medium can be a computer readable tangible non-transitory storage medium.

[0132] It should be understood that portions of the application can be realized with a combination of hardware, software, firmware, or their combination. In the above-described embodiments, the N steps or methods can be realized with software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if realized with hardware, any one or their combination of the following technologies known in the art can be used: discrete logic circuit with logic gate circuit for implementing logic functions on data signals, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA), etc.

[0133] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0134] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0135] The above-mentioned storage medium can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A method for designing cables for a steel-carbon fiber hybrid cable-stayed bridge, characterized in that, Includes the following steps: Determine the basic geometric parameters and basic load parameters of the cable-stayed bridge, and determine the cable characteristic data of the steel and carbon fiber hybrid cables, the maximum number of cable types for each type, and the cable specification selection table; Based on genetic algorithms and deep learning, optimization calculations are performed according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum number of cable types, and the cable specification selection table to obtain the fitness of each individual in the t-th generation population, where t is a positive integer; as well as Based on the fitness of each individual in the t-th generation population, the probability of each individual being selected is matched, and the crossover operator and the mutation operator are applied to the population until the preset iteration or termination operation condition is reached, to obtain the individual with the highest fitness in the population, and the chromosome of the highest fitness individual is decoded to obtain the optimized numerical solution. The method, based on genetic algorithms and deep learning, optimizes the population by calculating the fitness of each individual in the t-th generation based on the basic geometric parameters, basic load parameters, cable characteristic data, maximum number of cable types, and cable specification selection table. Select the cable forces within the preset range of estimated cable forces, form an individual based on the cable forces of all cables in the entire bridge, assign each individual to a chromosome, set the maximum number of generations, and randomly generate multiple individuals as the initial population. Calculate the initial fitness of each individual in the t-th generation population; The calculation of the initial fitness of each individual in the t-th generation population includes: Estimate the initial dead load force of multiple cables based on the dead load; Estimate the initial live load cable force based on the live load; The cable specifications are estimated based on the initial dead load cable force and the initial live load cable force. The estimated stiffness of the dead load cable is calculated based on the initial dead load cable force and the estimated cable specifications; Recalculate the maximum live load cable force based on the estimated dead load cable stiffness; The cable specifications are recalculated based on the initial dead load cable force and the maximum live load cable force. Calculate the cable stiffness based on the initial dead load cable force and cable specifications; The final dead load cable force is recalculated based on the dead load and the cable stiffness. The initial fitness of each individual is obtained based on the negative of the second norm of the error between the initial constant load cable force and the final constant load cable force.

2. The method according to claim 1, characterized in that, The formula for calculating the initial live load cable force is: ， in, For the first Estimation of live load cable force in the root cable. For the first The cable spacing corresponding to the root cable, For live loads, For concentrated loads of live load, For the first The angle between the root and the horizontal plane, For the number of cables, .

3. The method according to claim 2, characterized in that, The calculation and estimation of cable specifications based on the initial dead load cable force and the initial live load cable force includes: Based on the preset maximum number of cable types and the preset minimum cable usage principle, the specifications of the completed bridge cables that meet the stress requirements are calculated to obtain the estimated cable specifications.

4. The method according to claim 3, characterized in that, The expression for the preset minimum amount of material used principle is: ， in, For the number of cables, For the first The root cable is long. For the first Number of roots of the root of the root, .

5. A cable design device for a steel and carbon fiber hybrid cable-stayed bridge, characterized in that, Includes the following steps: The determination module is used to determine the basic geometric parameters and basic load parameters of cable-stayed bridges, and to determine the cable characteristic data of steel and carbon fiber hybrid cables, the maximum number of cable types for each type of cable, and the cable specification selection table. The calculation module is used to perform optimization calculations based on genetic algorithms and deep learning, according to the basic geometric parameters, the basic load parameters, the cable characteristic data, the maximum number of cable types, and the cable specification selection table, to obtain the fitness of each individual in the t-th generation population, where t is a positive integer; as well as The acquisition module is used to match the probability of each individual being selected based on the fitness of each individual in the t-th generation population, and to apply the crossover operator and the mutation operator to the population until a preset iteration or termination operation condition is reached, to obtain the individual with the highest fitness in the population, to decode the chromosome of the highest fitness individual, and to obtain an optimized numerical solution. The computing module includes: The generation unit is used to select cable forces within a preset range of estimated cable forces, form an individual based on the cable forces of all cables in the entire bridge, assign each individual to a chromosome, set a maximum number of generations, and randomly generate multiple individuals as the initial population. The first calculation unit is used to calculate the initial fitness of each individual in the t-th generation population; The computing module also includes: The first estimation unit is used to estimate the initial dead load cable force of multiple cables based on the dead load. The second estimation unit is used to estimate the initial live load cable force based on the live load. The second calculation unit is used to calculate and estimate the cable specifications based on the initial dead load cable force and the initial live load cable force. The third calculation unit is used to calculate the estimated stiffness of the dead load cable based on the initial dead load cable force and the estimated cable specifications; The fourth calculation unit is used to recalculate the maximum live load cable force based on the estimated dead load cable stiffness. The fifth calculation unit is used to recalculate the cable specifications based on the initial dead load cable force and the maximum live load cable force; The sixth calculation unit is used to calculate the cable stiffness based on the initial dead load cable force and cable specifications; The seventh calculation unit is used to recalculate the final dead load cable force based on the dead load and the cable stiffness; The acquisition unit is used to acquire the initial fitness of each individual based on the negative of the second norm of the error between the initial constant load cable force and the final constant load cable force.

6. The apparatus according to claim 5, characterized in that, The formula for calculating the initial live load cable force is: ， in, For the first Estimation of live load cable force in the root cable. For the first The cable spacing corresponding to the root cable, For live loads, For concentrated loads of live load, For the first The angle between the root and the horizontal plane, For the number of cables, .

7. The apparatus according to claim 6, characterized in that, The second calculation unit includes: calculating the specifications of the bridge cables that meet the stress requirements based on the preset maximum number of cable types and the preset minimum cable usage principle, so as to obtain the estimated cable specifications.

8. The apparatus according to claim 7, characterized in that, The expression for the preset minimum amount of material used principle is: ， in, For the number of cables, For the first The root cable is long. For the first Number of roots of the root of the root, .

9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the cable design method for a steel and carbon fiber hybrid cable-stayed bridge as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the cable design method for a steel and carbon fiber hybrid cable-stayed bridge as described in any one of claims 1-4.

Images