CN-121997418-A - Retaining wall body type optimization method and device based on atomic search optimization algorithm

CN121997418ACN 121997418 ACN121997418 ACN 121997418ACN-121997418-A

Abstract

The invention relates to the technical field of data processing, and provides a retaining wall body type optimization method and device based on an atomic search optimization algorithm, wherein the method comprises the steps of constructing an objective function based on standard proportion of the retaining wall and with minimum retaining wall volume of unit width according to a predetermined key body type parameter of a plurality of retaining walls; generating a plurality of groups of key body type parameters under the same working condition at random to obtain initial body type parameters, calculating corresponding mechanical indexes based on each group of initial body type parameters and corresponding loads, obtaining preset constraints according to design specifications, generating fitness function values according to the mechanical indexes, the preset constraints and target functions, and performing iterative optimization on the fitness function values by adopting an atomic search optimization algorithm to obtain optimized body type parameters. The invention provides a standardized and reproducible technical path for optimizing the body shape of the retaining wall, reduces the dependence on personal experience, and ensures the stability of design quality and efficiency.

Inventors

DUAN XIAONING
HAN BIN
WANG XIAOPING
MA YAN
TIAN YING
HE JIANG
SHI XIAOWU
ZHOU HUAHUA
MEN BO

Assignees

中国电建集团西北勘测设计研究院有限公司

Dates

Publication Date: 20260508
Application Date: 20260116

Claims (10)

1. The method for optimizing the retaining wall body type based on the atomic search optimization algorithm is characterized by comprising the following steps of: constructing an objective function with a minimum retaining wall volume per unit width based on a standard proportion of the retaining wall according to a predetermined key body type parameter of a plurality of retaining walls; randomly generating a plurality of groups of key body type parameters under the same working condition to obtain initial body type parameters, calculating corresponding mechanical indexes based on each group of initial body type parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values according to the mechanical indexes, the preset constraints and the objective functions; and (3) adopting an atomic search optimization algorithm to carry out iterative optimization on the fitness function value to obtain optimized body type parameters.
2. The method for optimizing the size of a retaining wall based on an atomic search optimization algorithm according to claim 1, wherein the constructing an objective function based on a standard proportion of the retaining wall with a minimum retaining wall volume per unit width according to a predetermined key size parameter of a plurality of retaining walls comprises: Determining a plurality of vertex coordinates of the retaining wall based on the influence relation of the key body type parameters and the standard proportion by taking the wall bottom point of the retaining wall as an origin of coordinates; And calculating the cross-sectional area of the retaining wall according to the vertex coordinates, representing the unit-width retaining wall volume by using the cross-sectional area, and constructing an objective function for minimizing the unit-width retaining wall volume.
3. The method for optimizing a retaining wall body type based on an atomic search optimization algorithm according to claim 1, wherein the calculating a corresponding mechanical index based on each set of the initial body type parameters and the corresponding load, and obtaining a preset constraint according to a design specification, generating an fitness function value according to the mechanical index, the preset constraint and the objective function, includes: Selecting the corresponding load based on the working condition and the corresponding load combination rule, and calculating the corresponding mechanical index according to each group of initial body type parameters and the load; According to the design specification, an index limit value of the mechanical index corresponding to the working condition is called, and the preset constraint is generated based on the index limit value; And applying a punishment item according to a comparison result of the preset constraint and the mechanical index by using the retaining wall volume as a basic item of the using function by adopting an external punishment function method to obtain an adaptability function comprising the objective function and the constraint punishment, wherein the constraint punishment is obtained according to the preset constraint and the corresponding punishment item.
4. The method for optimizing a retaining wall body type based on atomic search according to claim 3, wherein the penalty term includes a penalty weight and a standard weight, the applying an external penalty function method to apply a penalty term to the retaining wall volume as a basic term of a usage function according to a comparison result of the preset constraint and the mechanical index, and obtaining an fitness function including the objective function and the constraint penalty includes: Setting the punishment weight and the standard weight for each mechanical index based on a preset design specification; Judging whether the mechanical index meets the preset constraint, if not, matching the corresponding punishment weight for the corresponding mechanical index, and if so, matching the corresponding standard weight for the corresponding mechanical index; And obtaining constraint punishment by using the external punishment function method according to the mechanical index, the preset constraint and the corresponding punishment weight or the standard weight, and summing the objective function and the constraint punishment to obtain the fitness function value.
5. The method for optimizing the body type of the retaining wall based on the atomic search optimization algorithm according to claim 1, wherein the iterative optimization of the fitness function value by using the atomic search optimization algorithm to obtain the optimized body type parameter comprises the following steps: Initializing the speed of each group of initial body type parameters, and setting the initial value of the global optimal fitness function value to be infinity; comparing the fitness function value corresponding to the current parameter set with the global optimal fitness function value, and if the fitness function value of the current parameter set is smaller than the global optimal fitness function value, updating the global optimal fitness function value and the optimal parameter corresponding to the global optimal fitness function value according to the fitness function values of the current parameter set and the current parameter set; Calculating the quality of the corresponding parameter group according to the fitness function value corresponding to each parameter group, wherein the smaller the fitness function value is, the higher the quality of the corresponding parameter group is; Calculating a K value based on the quality and the iteration times of the parameter set and updating a parameter set consisting of the previous K groups of initial body type parameters with the optimal fitness function value; Calculating interaction force between each group of initial body type parameters in the parameter set and geometric constraint force of the optimal parameters on the parameter set, and solving acceleration of the parameter set based on the interaction force and the geometric constraint force; updating the corresponding speed and parameter value of the parameter set according to the acceleration, calculating a corresponding fitness function value according to the updated body type parameter of the parameter set, taking the updated parameter set as the current parameter set, returning to the step of comparing the fitness function value corresponding to the current parameter set with the global optimal fitness function value, repeating iteration until the preset maximum iteration number is reached, and outputting the global optimal parameter corresponding to the global optimal fitness function value as the optimized body type parameter.
6. The method for optimizing the body type of a retaining wall based on an atomic search optimization algorithm according to claim 1, wherein the mechanical indexes include an anti-slip stability safety coefficient, an anti-capsizing stability safety coefficient, a maximum basal stress and a minimum basal stress; the preset constraint comprises: The anti-slip stable safety coefficient is not smaller than the corresponding standard anti-slip stable safety limit value under each working condition, the anti-capsizing stable safety coefficient calculated value is not smaller than the corresponding anti-capsizing safety limit value, the maximum base stress is not larger than the allowable bearing capacity of the foundation, the tensile stress does not occur under the non-earthquake working condition, the minimum base stress is not the tensile stress under the non-construction and earthquake working conditions, and the absolute value of the minimum base stress is not larger than the stress limit value if the minimum base stress is the tensile stress under the construction working condition and the earthquake working condition.
7. The method for optimizing a retaining wall body type based on an atomic search optimization algorithm according to claim 4, further comprising the steps of: After the optimized body type parameters are obtained, setting construction strategy parameters, wherein the construction strategy parameters comprise preset typical construction sequences, maximum allowable single excavation depth and layered pouring layer height range; Simulating each stage of construction according to the construction strategy parameters and the optimized body type parameters, and calculating temporary loads and temporary stability of each stage; updating the punishment weight according to the temporary load and the temporary stability, and updating the fitness function value according to the updated punishment weight; And performing iterative optimization again based on the updated fitness function value to obtain final body type parameters.
8. An atomic search optimization algorithm-based retaining wall type optimization device, which is characterized by comprising: The construction module is used for constructing an objective function based on the standard proportion of the retaining walls and the minimum retaining wall volume of unit width according to the predetermined key body type parameters of the retaining walls; The generation module is used for randomly generating a plurality of groups of key body type parameters under the same working condition to obtain initial body type parameters, calculating corresponding mechanical indexes based on each group of initial body type parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values according to the mechanical indexes, the preset constraints and the objective functions; and the iteration module is used for carrying out iteration optimization on the fitness function value by adopting an atomic search optimization algorithm to obtain optimized body type parameters.
9. An electronic device comprising a memory and a processor; The memory is used for storing a computer program; The processor is configured to implement the retaining wall body type optimization method based on the atomic search optimization algorithm according to any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, wherein a computer program is stored on the storage medium, which when executed by a processor, implements the retaining wall body type optimization method based on the atomic search optimization algorithm according to any one of claims 1 to 7.

Description

Retaining wall body type optimization method and device based on atomic search optimization algorithm Technical Field The invention relates to the technical field of data processing, in particular to a retaining wall body type optimization method and device based on an atomic search optimization algorithm. Background In the hydraulic and hydroelectric engineering, the retaining wall is used as a core structure and bears the key functions of retaining soil, preventing seepage, stabilizing slope and resisting water pressure, and the rationality of the body type design is directly related to the stable operation, safety performance and cost control of the whole engineering. The scientific retaining wall body type realizes the balance of structural economy and engineering practicability on the premise of meeting the standard requirements of anti-slip stability, anti-capsizing stability, foundation bearing capacity and the like, and has important significance for guaranteeing the long-term safe and reliable operation of hydraulic and hydroelectric engineering. At present, the design and optimization of the retaining wall body type mainly depend on a trial calculation method driven by traditional experience, and engineers gradually determine the section size by repeatedly adjusting key body type parameters such as wall top width, wall toe step size, slope gradient and the like according to engineering geological conditions, water level parameters and standard requirements. However, the traditional trial calculation method has longer design period, needs to take a large amount of time to carry out repeated iterative adjustment, is difficult to quickly respond to engineering design requirements, and has the defects that the design result highly depends on personal experience of engineers, and the technical accumulation difference of different practitioners can cause unstable design quality and efficiency, so that the best economic benefit is difficult to continuously achieve. Disclosure of Invention The invention solves the problem of how to improve the optimization efficiency and the quality stability of the retaining wall body type. In order to solve the problems, the invention provides a retaining wall type optimization method and device based on an atomic search optimization algorithm. In a first aspect, the present invention provides a method for optimizing a retaining wall body shape based on an atomic search optimization algorithm, including: constructing an objective function with a minimum retaining wall volume per unit width based on a standard proportion of the retaining wall according to a predetermined key body type parameter of a plurality of retaining walls; randomly generating a plurality of groups of key body type parameters under the same working condition to obtain initial body type parameters, calculating corresponding mechanical indexes based on each group of initial body type parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values according to the mechanical indexes, the preset constraints and the objective functions; and (3) adopting an atomic search optimization algorithm to carry out iterative optimization on the fitness function value to obtain optimized body type parameters. Optionally, the constructing the objective function with the minimum unit width of the retaining wall volume based on the standard proportion of the retaining wall according to the predetermined key body type parameters of the plurality of retaining walls comprises: Determining a plurality of vertex coordinates of the retaining wall based on the influence relation of the key body type parameters and the standard proportion by taking the wall bottom point of the retaining wall as an origin of coordinates; And calculating the cross-sectional area of the retaining wall according to the vertex coordinates, representing the unit-width retaining wall volume by using the cross-sectional area, and constructing an objective function for minimizing the unit-width retaining wall volume. Optionally, calculating a corresponding mechanical index based on each set of the initial body type parameters and the corresponding load, obtaining a preset constraint according to a design specification, and generating an fitness function value according to the mechanical index, the preset constraint and the objective function, including: Selecting the corresponding load based on the working condition and the corresponding load combination rule, and calculating the corresponding mechanical index according to each group of initial body type parameters and the load; According to the design specification, an index limit value of the mechanical index corresponding to the working condition is called, and the preset constraint is generated based on the index limit value; And applying a punishment item according to a comparison result of the preset constraint and the m