Retaining wall shape optimization method and device based on atomic search optimization algorithm

Abstract

The invention relates to the technical field of data processing, and provides a retaining wall shape optimization method and device based on an atomic search optimization algorithm, and the method comprises the steps: building a target function through the volume of a retaining wall with the minimum unit width based on the standard proportion of the retaining wall according to the predetermined key shape parameters of a plurality of retaining walls; randomly generating a plurality of groups of key body shape parameters under the same working condition to obtain initial body shape parameters, calculating corresponding mechanical indexes based on each group of initial body shape 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 a target function; and carrying out iterative optimization on the fitness function value by adopting an atomic search optimization algorithm to obtain an optimized body type parameter. According to the method, a standardized and reproducible technical path is provided for optimizing the shape of the retaining wall, the dependence on personal experience is reduced, and the design quality and the efficiency stability are guaranteed.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically, to a method and apparatus for optimizing the shape of retaining walls based on an atomic search optimization algorithm. Background Technology

[0002] In water conservancy and hydropower projects, retaining walls, as core structures, bear the crucial functions of retaining soil, preventing seepage, stabilizing slopes, and resisting water pressure. The rationality of their design directly affects the overall stable operation, safety performance, and cost control of the project. A scientifically designed retaining wall must achieve a balance between structural economy and engineering practicality while meeting the specifications for anti-sliding stability, anti-overturning stability, and foundation bearing capacity. This is of great significance for ensuring the long-term safe and reliable operation of water conservancy and hydropower projects.

[0003] Currently, the design and optimization of retaining wall shapes mainly rely on traditional experience-driven trial-and-error methods. Engineers determine the cross-sectional dimensions by repeatedly adjusting key shape parameters such as the top width of the wall, the size of the toe step, and the slope gradient, based on engineering geological conditions, water level parameters, and specification requirements. However, traditional trial-and-error methods have a long design cycle, requiring a significant amount of time for multiple iterative adjustments, making it difficult to quickly respond to engineering design needs. The design results are highly dependent on the individual experience of engineers, and differences in the technical accumulation of different practitioners may lead to unstable design quality and efficiency, making it difficult to consistently achieve optimal economic benefits. Summary of the Invention

[0004] The problem addressed by this invention is how to improve the efficiency and quality stability of retaining wall shape optimization.

[0005] To address the aforementioned problems, this invention provides a method and apparatus for optimizing the shape of retaining walls based on an atomic search optimization algorithm.

[0006] In a first aspect, the present invention provides a method for optimizing the shape of a retaining wall based on an atomic search optimization algorithm, comprising: Based on the key shape parameters of multiple pre-determined retaining walls, an objective function is constructed to minimize the volume of the retaining wall per unit width, according to the standard proportion of the retaining walls. Multiple sets of key body shape parameters under the same working conditions are randomly generated to obtain initial body shape parameters. Based on each set of initial body shape parameters and the corresponding load, the corresponding mechanical index is calculated, and the preset constraints are obtained according to the design specifications. The fitness function value is generated according to the mechanical index, the preset constraints and the objective function. An atomic search optimization algorithm is used to iteratively optimize the fitness function value to obtain the optimized body shape parameters.

[0007] Optionally, the step of constructing an objective function based on the standard proportions of the retaining walls and minimizing the volume of the retaining wall per unit width, according to the predetermined key shape parameters of multiple retaining walls, includes: Using the bottom point of the retaining wall as the origin of the coordinate system, the coordinates of multiple vertices of the retaining wall are determined based on the influence relationship of the key shape parameters and the standard proportion. The cross-sectional area of ​​the retaining wall is calculated based on the vertex coordinates, and the cross-sectional area is used to characterize the volume of the retaining wall per unit width. An objective function is then constructed to minimize the volume of the retaining wall per unit width.

[0008] Optionally, the step of calculating the corresponding mechanical indices based on each set of initial body shape parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values ​​based on the mechanical indices, the preset constraints, and the objective function includes: Based on the working conditions and the corresponding load combination rules, select the corresponding load, and calculate the corresponding mechanical index according to each set of initial body parameters and the load; According to the design specifications, retrieve the limit values ​​of the mechanical indicators corresponding to the working conditions, and generate the preset constraints based on the limit values. The external penalty function method is adopted, and the volume of the retaining wall is used as the basic term of the functional degree function. A penalty term is applied according to the comparison result of the preset constraints and the mechanical index to obtain a fitness function that includes the objective function and the constraint penalty, wherein the constraint penalty is obtained according to the preset constraints and the corresponding penalty term.

[0009] Optionally, the penalty term includes a penalty weight and a standard weight; the external penalty function method uses the retaining wall volume as the basis term of the usability function, and applies a penalty term based on the comparison results of the preset constraints and the mechanical indicators to obtain a fitness function that includes the objective function and the constraint penalty, including: Based on the preset design specifications, the penalty weight and the standard weight are set for each mechanical index; Determine whether the mechanical index meets the preset constraint. If not, match the corresponding penalty weight for the corresponding mechanical index. If yes, match the corresponding standard weight for the corresponding mechanical index. Based on the mechanical index, the preset constraints, and the corresponding penalty weights or standard weights, the constraint penalty is obtained using the external penalty function method. The fitness function value is obtained by summing the objective function and the constraint penalty.

[0010] Optionally, the step of employing an atomic search optimization algorithm to iteratively optimize the fitness function value to obtain optimized body shape parameters includes: The initial velocity of each set of initial body size parameters is initialized, and the initial value of the global optimal fitness function is set to infinity; Compare the fitness function value corresponding to the current parameter group with the global optimal fitness function value. If the fitness function value of the current parameter group is less than the global optimal fitness function value, then update the global optimal fitness function value and the optimal parameters corresponding to the global optimal fitness function value according to the current parameter group and the fitness function value of the current parameter group. The quality of the corresponding parameter group is calculated based on the fitness function value corresponding to each parameter group, wherein the smaller the fitness function value, the higher the quality of the corresponding parameter group; Calculate the K value based on the quality and number of iterations of the parameter set, and update the parameter set consisting of the top K initial body shape parameters with the best fitness function values; Calculate the interaction force between each set of initial body shape parameters in the parameter set, and the geometric constraint force of the optimal parameters on the parameter set; and solve for the acceleration of the parameter set based on the interaction force and the geometric constraint force. The velocity and parameter values ​​corresponding to the parameter group are updated according to the acceleration, and the corresponding fitness function value is calculated according to the body shape parameters of the updated parameter group. The updated parameter group is used as the current parameter group. The step of comparing the fitness function value corresponding to the current parameter group with the global optimal fitness function value is returned and iterated repeatedly until the preset maximum number of iterations is reached. The global optimal parameter corresponding to the global optimal fitness function value is output as the optimized body shape parameter.

[0011] Optionally, the mechanical properties include the anti-slip stability safety factor, the anti-overturning stability safety factor, the maximum base stress, and the minimum base stress; The preset constraints include: Under each working condition, the anti-sliding stability safety factor shall not be less than the anti-sliding stability safety limit of the corresponding specification, the calculated value of the anti-overturning stability safety factor shall not be less than the corresponding anti-overturning safety limit, the maximum base stress shall not be greater than the allowable bearing capacity of the foundation, and no tensile stress shall occur under non-earthquake working conditions, and the minimum base stress under non-construction and earthquake working conditions shall not be the tensile stress. If the minimum base stress under construction working conditions and earthquake working conditions is the tensile stress, then the absolute value of the minimum base stress shall not be greater than the stress limit.

[0012] Optionally, the retaining wall shape optimization method based on atomic search further includes the following steps: After obtaining the optimized body shape parameters, construction strategy parameters are set, including preset typical construction sequence, maximum allowable single excavation depth, and layer height range for layered pouring. Simulate each stage of construction according to the construction strategy parameters and the optimized body shape parameters, and calculate the temporary load and temporary stability of each stage; The penalty weights are updated based on the temporary loads and the temporary stability, and the fitness function value is updated according to the updated penalty weights. Secondly, the present invention provides a retaining wall shape optimization device based on an atomic search optimization algorithm, comprising: The module is used to construct an objective function based on the standard proportions of the retaining walls and the key shape parameters of multiple pre-determined retaining walls, in order to minimize the volume of the retaining wall per unit width. The generation module is used to randomly generate multiple sets of key body shape parameters under the same working conditions to obtain initial body shape parameters, calculate the corresponding mechanical index based on each set of initial body shape parameters and corresponding load, obtain preset constraints according to design specifications, and generate fitness function values ​​according to the mechanical index, the preset constraints and the objective function. The iterative module is used to iteratively optimize the fitness function value using an atomic search optimization algorithm to obtain the optimized body shape parameters.

[0013] Thirdly, the present invention provides an electronic device, including a memory and a processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the retaining wall shape optimization method based on atomic search as described in the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the retaining wall shape optimization method based on atomic search as described in the first aspect.

[0015] The beneficial effects of the retaining wall shape optimization method based on atomic search of the present invention are as follows: By clearly defining the key shape parameters of the retaining wall, minimizing the volume of the retaining wall per unit width is taken as the core objective. An objective function is constructed by combining the standard proportions of the retaining wall, directly focusing on the core of engineering cost optimization. This avoids redundant design caused by ambiguous objectives in traditional methods, ensuring that the optimization direction is highly consistent with the economic requirements of the project, providing a clear and precise target guidance for subsequent optimization, and reducing ineffective design iterations from the source. By randomly generating multiple sets of initial shape parameters, a wide coverage of the design space is achieved, breaking the limitations of traditional empirical calculations. Mechanical indices are accurately calculated based on each set of parameters and corresponding loads, and strictly compared with the preset constraints of the design specifications to ensure that all candidate schemes pass safety verification. The fitness function value is generated by integrating the objective function and constraints, achieving a quantitative balance between safety and economy, avoiding the design defect of solely pursuing the smallest volume while ignoring safety requirements, significantly improving the reliability and compliance of candidate schemes, and also providing an operational foundation for subsequent atomic search optimization methods. The Atomic Search optimization algorithm is used to iteratively optimize the fitness function value. The Atomic Search optimization algorithm has the advantages of strong global search capability, good local development effect and few control parameters. It can quickly converge to the optimal solution. Compared with the traditional iterative trial and error method, it significantly shortens the design cycle, reduces human intervention, avoids the problem of unstable design quality caused by differences in personal experience, and accurately discovers the minimum volume solution that satisfies all safety constraints, thus achieving a dual improvement in optimization efficiency and design accuracy.

[0016] This invention addresses the technical problems of low efficiency, reliance on experience, insufficient balance between safety and economy, and lack of construction adaptability in traditional retaining wall shape optimization by establishing a complete technical chain from precise objective function construction to quantitative fusion of fitness function and efficient optimization by intelligent algorithm. On the one hand, the application of the atomic search optimization algorithm completely changes the traditional experience-driven design mode, significantly improving optimization efficiency and rapidly responding to engineering design needs. On the other hand, by comprehensively considering load combinations and multi-condition constraints, combined with the goal of minimizing volume, it ensures that the optimized shape parameters not only meet the specifications for anti-sliding stability, anti-overturning stability, and foundation bearing capacity, but also achieve optimal engineering cost. Simultaneously, this method provides a standardized and replicable technical path for retaining wall shape optimization, reducing reliance on individual experience, ensuring the stability of design quality and efficiency, providing reliable technical support for the refined design and cost control of water conservancy and hydropower projects, and realizing a technical leap from safe and feasible to safe and economically optimal retaining wall shape design. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the retaining wall shape optimization method based on the atomic search optimization algorithm according to an embodiment of the present invention. Figure 2 This is a cross-sectional schematic diagram of a gravity retaining wall according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a retaining wall shape optimization device based on an atomic search optimization algorithm according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the accompanying drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0019] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0020] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to"; the term "based on" means "at least partially based on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; and the term "optionally" means "optional embodiments". Definitions of other terms will be given in the following description. It should be noted that the concepts of "first," "second," etc., mentioned in this invention are used only to distinguish different devices, modules, or units, and are not intended to limit the order of functions performed by these devices, modules, or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0023] like Figure 1 As shown in the figure, an embodiment of the present invention provides a method for optimizing the shape of a retaining wall based on an atomic search optimization algorithm, comprising: Step S1: Based on the predetermined key shape parameters of multiple retaining walls, construct an objective function that minimizes the volume of the retaining wall per unit width, according to the standard proportion of the retaining walls.

[0024] Specifically, this embodiment uses a gravity retaining wall as an example. The key shape parameters of the retaining wall are the core geometric parameters that determine the shape and structure of the gravity retaining wall, including the top width *a*, the toe step width *b*, the toe step height *h*, the face slope inclination *m1*, the back slope inclination *m2*, the toe step slope *m3*, and the bottom step slope *n*. The retaining wall height *H* needs to be predetermined based on the retaining height and the water levels before and after the retaining wall before shape design, and is not used as an optimization variable in this step. Based on the standard proportions of the retaining wall, such as the length-to-width ratio, the standard proportion requirements of the retaining wall must be strictly followed to ensure that the matching relationship between the key shape parameters conforms to the conventional principles of hydraulic engineering design, avoiding unreasonable geometric structures. The objective function for minimizing the retaining wall volume Vub per unit width is constructed as follows: MinVub=Min(A(a,b,h,m1,m2,m3,n)), where A is the cross-sectional area of ​​the retaining wall and Vub is the volume of the retaining wall per unit width.

[0025] The process involves constructing an objective function based on predetermined key shape parameters of multiple retaining walls, taking into account the standard proportions of the retaining walls, and minimizing the volume of the retaining wall per unit width. This includes: Using the bottom point of the retaining wall as the origin of the coordinate system, the coordinates of multiple vertices of the retaining wall are determined based on the influence relationship of the key shape parameters and the standard proportion.

[0026] Specifically, such as Figure 2 As shown, with point O at the bottom of the wall as the origin, the coordinates of each vertex of the retaining wall are derived based on the aforementioned key shape parameters: O(0,0), B(B1,B1*n), C(B1-h*m3,h+B1*n), D(B1-h*m3-b,h+B1*n), E(B1-h*m3-b-(Hh)*m1,H+B1*n), F(m2*(H+B1*n),H+B1*n), where H is the height of the retaining wall, which is predetermined by the height of the retaining soil and the water levels before and after the retaining wall.

[0027] The cross-sectional area of ​​the retaining wall is calculated based on the vertex coordinates, and the cross-sectional area is used to characterize the volume of the retaining wall per unit width. An objective function is then constructed to minimize the volume of the retaining wall per unit width.

[0028] Specifically, the area A of the retaining wall section is calculated based on the coordinates of each vertex using the polygon area calculation formula, and then the objective function is constructed.

[0029] Step S2: Randomly generate multiple sets of key body shape parameters under the same working conditions to obtain initial body shape parameters. Calculate the corresponding mechanical indices based on each set of initial body shape parameters and the corresponding load, and obtain preset constraints according to design specifications. Generate fitness function values ​​based on the mechanical indices, the preset constraints, and the objective function.

[0030] Specifically, retaining walls face various working conditions in practical applications, encompassing the operational and construction scenarios they may encounter throughout their entire lifecycle. Different working conditions correspond to different load combination rules. Based on the value range of key shape parameters, multiple sets of initial shape parameters are generated using a uniform random sampling method. Each set of parameters includes specific values ​​for a, b, h, m1, m2, m3, and n. Based on each set of initial shape parameters, and in conjunction with preset working conditions, the loads under the corresponding working conditions are calculated according to the calculation methods specified in relevant load standards and specifications such as the "Design Code for Hydraulic Retaining Walls" (SL379-2007), the "Seismic Design Code for Hydraulic Structures of Hydropower Projects" (NB35047-2015), and the "Load Standard for Hydraulic Structures" (GB / T51394-2020). Then, based on the loads, the corresponding mechanical indices are calculated, such as the anti-sliding stability safety factor, the anti-overturning stability safety factor, the maximum base stress, and the minimum base stress. Simultaneously, preset constraints are obtained according to construction specifications, and fitness function values ​​are generated based on the mechanical indices, preset constraints, and objective function.

[0031] It should be noted that load calculation requires retaining wall design parameters, including water level parameters (water levels in front of and behind the wall in each calculation case); geological parameters (coefficient of shear friction between the retaining wall base surface and the rock foundation, shear bond strength between the retaining wall base surface and the rock foundation, and allowable bearing stress of the foundation); and basic design parameters (wall top elevation, backfill elevation, uniformly distributed load acting on the backfill surface, unit weight of the wall material, unit weight of water, unit weight and internal friction angle of the backfill, and slope of the backfill surface, etc.).

[0032] Optionally, the mechanical properties include the anti-slip stability safety factor, the anti-overturning stability safety factor, the maximum base stress, and the minimum base stress; The preset constraints include: Under each working condition, the anti-sliding stability safety factor shall not be less than the anti-sliding stability safety limit of the corresponding specification, the calculated value of the anti-overturning stability safety factor shall not be less than the corresponding anti-overturning safety limit, the maximum base stress shall not be greater than the allowable bearing capacity of the foundation, and no tensile stress shall occur under non-earthquake working conditions, and the minimum base stress under non-construction and earthquake working conditions shall not be the tensile stress. If the minimum base stress under construction working conditions and earthquake working conditions is the tensile stress, then the absolute value of the minimum base stress shall not be greater than the stress limit.

[0033] Optionally, the step of calculating the corresponding mechanical indices based on each set of initial body shape parameters and corresponding loads, and obtaining preset constraints according to design specifications, and generating fitness function values ​​based on the mechanical indices, the preset constraints, and the objective function, includes: Based on the working conditions and the corresponding load combination rules, the corresponding load is selected, and the corresponding mechanical index is calculated according to each set of initial body parameters and the load.

[0034] Specifically, the working condition type and corresponding load combination rules are first clarified as shown in Table 1. The loads include the wall's self-weight, calculated based on the retaining wall's cross-sectional area and the unit weight of the wall material; and the hydrostatic pressure, calculated according to formula P. w =1 / 2γ v L 2 Calculate, where γ v The unit weight of water is taken as 10 kN / m3, and L is the water head acting at the calculation point; the uplift pressure is determined based on the combination of water levels in front of and behind the wall; the earth pressure is calculated according to the active earth pressure formula, and the active earth pressure coefficient is determined in combination with the internal friction angle of the fill and the included angle of the wall surface; the seismic load includes seismic inertial force, seismic water pressure, and seismic earth pressure, which are calculated according to the corresponding standard formulas. The operating conditions include construction status, completion status, full-load water level of the unit, design flood level, check flood level, sudden drop in water level, and earthquake status. The load combinations are divided into basic combinations and special combinations. The basic combination corresponds to the completion status, normal water level, and design flood level, and includes the self-weight of the retaining wall, earth pressure, earth weight, water weight, hydrostatic pressure, and uplift pressure. Special combination one corresponds to the construction status, check flood level, and sudden drop in water level. The construction status only includes self-weight, earth pressure, and earth weight, while the other two statuses include self-weight, earth pressure, earth weight, water weight, hydrostatic pressure, and uplift pressure. Special combination two corresponds to the earthquake status and includes all loads (including seismic action).

[0035] Table 1. Working Condition-Load Correspondence Table

[0036] For each set of randomly generated initial body shape parameters, select the corresponding load based on the above load combination rules, and calculate the mechanical properties according to the following specifications: The anti-skid stability safety factor Kc is expressed as: , Where ∑G represents all loads perpendicular to the horizontal plane acting on the retaining wall; ∑H represents all loads parallel to the base surface acting on the retaining wall; f' represents the friction coefficient between the base surface of the retaining wall and the foundation; and c' represents the bond force between the base surface of the retaining wall and the foundation.

[0037] The overturning stability safety factor K0 is expressed as: , Where, ∑M v The overturning moment at the front toe of the retaining wall foundation; ∑M H This refers to the overturning moment at the front toe of the retaining wall foundation.

[0038] Maximum base stress P max Represented as: , Where ∑G is all the loads acting on the retaining wall perpendicular to the horizontal plane; ∑M is the sum of the moments of all the loads acting on the retaining wall about the centroidal axis of the horizontal plane parallel to the front wall surface; A is the area of ​​the base surface of the retaining wall; and W is the section moment of the base surface of the retaining wall about the centroidal axis of the base surface parallel to the front wall surface.

[0039] Maximum base stress P min Represented as: .

[0040] According to the design specifications, the limit values ​​of the mechanical indicators corresponding to the working conditions are retrieved, and the preset constraints are generated based on the limit values.

[0041] Specifically, the index limits for the corresponding working conditions are retrieved according to the "Design Code for Hydraulic Retaining Walls" (SL379-2007), as shown in Table 2: Table 2. Correspondence between the limits of mechanical indicators under working conditions.

[0042] Generate corresponding preset constraints based on the indicator limits, including: Anti-sliding stability constraint: The calculated value of the anti-sliding stability safety factor Kc should not be less than the limit value of the anti-sliding stability safety factor specified in the code, expressed as: Kc≥[Kc], where [Kc] is the limit value of the anti-sliding stability safety factor of the retaining wall along the base surface under each calculation condition; Overturning stability constraint: The calculated value of the overturning stability safety factor K0 should not be less than the overturning stability safety factor limit specified in the code, expressed as: K0≥[K0], where [K0] is the overturning stability safety factor limit of the retaining wall under each calculation condition; Maximum base stress constraint: The calculated maximum base stress Pmax should not exceed the allowable bearing capacity of the foundation, nor should it generate tensile stress. Positive base stress is compressive stress, and negative base stress is tensile stress, expressed as: 0<Pmax≤[Pmax], where [Pmax] is the allowable bearing capacity of the foundation under each calculation condition; Minimum base stress constraint: The minimum base stress should not be tensile stress, expressed as: 0 < Pmin0 ≤ [Pmax], where Pmin0 is the calculated value of the minimum base stress of the retaining wall under the following conditions: completion, full-load water level, design flood level, check flood level, and sudden drop in water level. During construction and under seismic conditions, if the minimum base stress of the retaining wall is tensile stress, it should not exceed 100 kPa. Furthermore, the minimum base stress should not exceed the allowable bearing capacity of the foundation, expressed as: -100 < Pmin1 ≤ [Pmax], where Pmin1 is the calculated value of the minimum base stress of the retaining wall under construction and seismic conditions.

[0043] The external penalty function method is adopted, and the volume of the retaining wall is used as the basic term of the functional degree function. A penalty term is applied according to the comparison result of the preset constraints and the mechanical index to obtain a fitness function that includes the objective function and the constraint penalty, wherein the constraint penalty is obtained according to the preset constraints and the corresponding penalty term.

[0044] Optionally, the penalty term includes a penalty weight and a standard weight; the external penalty function method uses the retaining wall volume as the basis term of the usability function, and applies a penalty term based on the comparison results of the preset constraints and the mechanical indicators to obtain a fitness function that includes the objective function and the constraint penalty, including: The penalty weight and the standard weight are set for each mechanical index based on the preset design specifications.

[0045] The penalty items are set according to the logic that there is no penalty when the constraints are met, and a significant penalty is imposed when the constraints are violated, so as to ensure that the algorithm prioritizes the compliant solution. Based on preset design specifications such as the "Design Code for Hydraulic Retaining Walls" (SL379-2007) and engineering practice experience, penalty weights and standard weights are set for each mechanical index. For example: the penalty weight for the anti-sliding stability safety factor is μ1=105, and the standard weight is μ0=0; the penalty weight for the anti-overturning stability safety factor is η1=105, and the standard weight is η0=0; the penalty weight for the maximum base stress is ζ1=105, and the standard weight is ζ0=0; the penalty weight for the minimum base stress is ξ1=105, and the standard weight is ξ0=0.

[0046] It should be noted that the corresponding penalty items are different for each working condition.

[0047] Determine whether the mechanical index meets the preset constraint. If not, match the corresponding penalty weight to the corresponding mechanical index. If yes, match the corresponding standard weight to the corresponding mechanical index.

[0048] Specifically, for Kc: if Kc ≥ [Kc], then the matching standard weight μ0 = 0; if Kc < [Kc], then the matching penalty weight μ1 = 10. 5For K0: if K0 ≥ [K0], then the matching standard weight η0 = 0; if K0 < [K0], then the matching penalty weight η1 = 10. 5 For P max If P max ≤[P max And it meets the tensile stress limit (non-earthquake condition P) max >0, earthquake condition P max If the standard weight ζ0 is 0 (≥-100kPa), then the matching weight ζ0 = 0; if any condition is violated, then the matching penalty weight ζ1 = 10. 5 For P min If not construction and seismic conditions P min ≥0, Construction and seismic conditions P min ≥-100kPa and P min ≤[P max If the condition is met, the matching standard weight ξ0 = 0; if any condition is violated, the matching penalty weight ξ1 = 10. 5 .

[0049] Based on the mechanical index, the preset constraints, and the corresponding penalty weights or standard weights, the constraint penalty is obtained using the external penalty function method. The fitness function value is obtained by summing the objective function and the constraint penalty.

[0050] Specifically, the constraint penalty is calculated using the external penalty function method. The constraint penalty is the sum of the products of the weights corresponding to each mechanical index and the degree of constraint violation. Constraints and penalties are represented as follows: |min(0,Kc-[Kc])|+ |min(0,K0-[K0])|+

[0051] |min(0,[P max ]-P max )|+ |min(0,P min0 )|+ |min(-100,P min1 )|, Where μ, , , These are the weights (standard weights or penalty weights) after matching the corresponding mechanical indicators. i=1, 2, 3, 4, 5, 6, 7 represent the completion status, normal water level, design flood level, construction status, check flood level, sudden drop in water level, and earthquake status, respectively. The penalty weights are different for each working condition.

[0052] Finally, the objective function is summed with the constraint penalty to obtain the fitness function value F = V + constraint penalty. The fitness function value is specifically expressed as: F=MinV ub + |min(0,Kc-[Kc])|+ |min(0,K0-[K0])|+

[0053] |min(0,[P max ]-P max )|+ |min(0,P min0 )|+ |min(-100,P min1 )|.

[0054] Step S3: Use the atomic search optimization algorithm to iteratively optimize the fitness function value to obtain the optimized body shape parameters.

[0055] Optionally, the step of employing an atomic search optimization algorithm to iteratively optimize the fitness function value to obtain optimized body shape parameters includes: The initial velocity of each set of initial body size parameters is initialized, and the initial value of the global optimal fitness function is set to infinity; Compare the fitness function value corresponding to the current parameter group with the global optimal fitness function value. If the fitness function value of the current parameter group is less than the global optimal fitness function value, then update the global optimal fitness function value and the corresponding optimal parameters according to the current parameter group and the fitness function value of the current parameter group. The quality of each parameter group is calculated based on the fitness function value corresponding to each parameter group, and is expressed as follows: m i (t) = M i (t) = , Where t is the iteration number; N is the number of initial body size parameter sets; mi(t) is the quality of initial body size parameter set i in the t-th iteration; Fiti(t) is the fitness function value of initial body size parameter set i in the t-th iteration; for minimum optimization, Fitbest(t) and Fittworst(t) are the minimum and maximum fitness function values ​​in the t-th iteration, respectively. The smaller the fitness function value, the greater the quality of the corresponding parameter set; Calculate the K value based on the quality of the parameter set and the number of iterations, and update the parameter set K consisting of the top K sets of parameters with the best fitness function values. best The value of K is represented as: K(t) = N - (N - 2) , where T is the maximum number of iterations.

[0056] Select the first K groups of parameter groups with the largest quality and construct the parameter set K best .

[0057] Calculate the mutual force F between each group of the initial body shape parameters in the parameter set i and the geometric binding force G of the optimal parameters on the parameter group i , and solve the acceleration a of the parameter group based on the mutual force and the geometric binding force, expressed as: , , , , , , where, in this algorithm, it can be understood that an initial body shape parameter group is used as an atom, then F ij (t) is the mutual force between the i-th atom and the j-th atom at the t-th iteration; is the depth weight; h ij (t) is the ratio of the distance between atoms to the collision diameter of atoms. When 0.9 < h < 1.12, the mutual force shows repulsive force. When h = 1.12, the gravitational force and the repulsive force are in balance. When 1.12 < h < 1.24, the mutual force shows gravitational force, h min and h max are the lower limit of the repulsive force and the upper limit of the gravitational force of h respectively. g, as a drift factor, can make the algorithm achieve the transformation from global exploration to local development; r ij (t) is the distance between the i-th atom and the j-th atom; σ(t) is the length scale representing the collision radius; rand j is a random number in [0, 1]; F i (t) represents the total mutual force of atom i exerted by all other relevant atoms at the t-th iteration; G i (t) is the geometric binding force of atom i exerted by the atom with the best fitness at the t-th iteration; β is the multiplier weight; K best is the set composed of the first K atoms with the best fitness function values, x i1 to x i3 respectively represent the decision variables in atom i, x j1 to x j3 respectively represent the decision variables in atom j, for example xi1 Let a and x represent the top width of the wall in the i-th set of initial body shape parameters. j1 Let 'a' represent the top width of the wall in the j-th initial body shape parameters; g(t) represents the drift factor in iteration t; g0 is the initial value of the drift factor g; x best (t) represents the globally optimal atom position in the t-th iteration, corresponding to the parameter values ​​of the globally optimal initial size parameter set; x i (t) represents the current position of the i-th atom in the t-th iteration, corresponding to the parameter value of the current initial body size parameter group i.

[0058] The acceleration 'a' is expressed as: , Among them, a i (t) represents the acceleration of atom i in the t-th iteration.

[0059] The velocity and parameter values ​​corresponding to the parameter group are updated according to the acceleration, and the corresponding fitness function value is calculated according to the body shape parameters of the updated parameter group. The updated parameter group is used as the current parameter group. The step of comparing the fitness function value corresponding to the current parameter group with the global optimal fitness function value is returned and iterated repeatedly until the preset maximum number of iterations is reached. The global optimal parameter corresponding to the global optimal fitness function value is output as the optimized body shape parameter.

[0060] Specifically, update the speed and parameter values ​​corresponding to the parameter group: , , Among them, v i (t) and x i (t) represents the velocity and position of atom i in the t-th iteration; rand i Let v be a random number in the range [0,1]. i (t+1) represents the new velocity of the i-th atom in the (t+1)-th iteration, x i (t+1) The new position of the i-th atom in the (t+1)-th iteration corresponds to the parameter value of the initial body size parameter group i in the (t+1)-th iteration.

[0061] This invention, by clearly defining the key shape parameters of the retaining wall and taking the minimization of the retaining wall volume per unit width as the core objective, constructs an objective function based on the standard proportions of the retaining wall. This directly focuses on the core of engineering cost optimization, avoiding redundant design caused by ambiguous objectives in traditional methods. It ensures that the optimization direction is highly aligned with the economic requirements of the project, providing a clear and precise objective guide for subsequent optimization and reducing ineffective design iterations from the outset. By randomly generating multiple sets of initial shape parameters, it achieves broad coverage of the design space, breaking the limitations of traditional empirical calculations. Based on each set of parameters and corresponding loads, it accurately calculates mechanical indices and rigorously compares them with pre-set constraints in design specifications, ensuring that all candidate solutions pass safety verification. By using a method that integrates the objective function and constraints to generate fitness function values, it achieves a quantitative balance between safety and economy, avoiding the design flaw of solely pursuing minimum volume while neglecting safety requirements. This significantly improves the reliability and compliance of candidate solutions and also provides a foundation for subsequent atomic search optimization methods. The Atomic Search optimization algorithm is used to iteratively optimize the fitness function value. The Atomic Search optimization algorithm has the advantages of strong global search capability, good local development effect and few control parameters. It can quickly converge to the optimal solution. Compared with the traditional iterative trial and error method, it significantly shortens the design cycle, reduces human intervention, avoids the problem of unstable design quality caused by differences in personal experience, and accurately discovers the minimum volume solution that satisfies all safety constraints, thus achieving a dual improvement in optimization efficiency and design accuracy.

[0062] This invention addresses the technical problems of low efficiency, reliance on experience, insufficient balance between safety and economy, and lack of construction adaptability in traditional retaining wall shape optimization by establishing a complete technical chain from precise objective function construction to quantitative fusion of fitness function and efficient optimization by intelligent algorithm. On one hand, the application of the atomic search optimization algorithm completely changes the traditional experience-driven design mode, significantly improving optimization efficiency and rapidly responding to engineering design needs. On the other hand, by comprehensively considering load combinations and multi-condition constraints, combined with the goal of minimizing volume, it ensures that the optimized shape parameters meet the specifications for anti-sliding stability, anti-overturning stability, and foundation bearing capacity, while also achieving optimal engineering cost. Simultaneously, this method provides a standardized and replicable technical path for retaining wall shape optimization, reducing reliance on personal experience, ensuring the stability of design quality and efficiency, providing reliable technical support for the refined design and cost control of water conservancy and hydropower projects, and realizing a technical leap from safe and feasible to safe and economically optimal retaining wall shape design.

[0063] Optionally, the retaining wall shape optimization method based on atomic search further includes the following steps: After obtaining the optimized body shape parameters, construction strategy parameters are set, including preset typical construction sequence, maximum allowable single excavation depth, and layered pouring height range. Simulate each stage of construction according to the construction strategy parameters and the optimized body shape parameters, and calculate the temporary load and temporary stability of each stage; The penalty weights are updated based on the temporary loads and the temporary stability, and the fitness function value is updated according to the updated penalty weights. Based on the updated fitness function value, iterative optimization is performed again to obtain the final body shape parameters.

[0064] Specifically, after obtaining the initial optimized shape parameters through the atomic search optimization algorithm, and combining the structural characteristics of gravity retaining walls (such as height H, cross-sectional dimensions, and foundation conditions) and conventional construction techniques for hydraulic engineering, three types of construction strategy parameters are set, and typical construction sequences are preset: three industry-standard construction sequence options are provided, including ① top-down layered excavation → layered wall pouring → simultaneous backfilling of the soil behind the wall; ② segmented excavation → segmented pouring → overall backfilling; ③ overall excavation of the foundation pit → temporary support → overall wall pouring → backfilling. Users can choose according to the actual engineering scenario, or the module can optimize the shape parameters based on the actual shape parameters. The geometric complexity of the shape parameters is automatically matched and recommended; the maximum allowable single excavation depth is set to 1.5m-3.0m based on geological parameters such as the internal friction angle and cohesion of the foundation soil, and must not exceed 1 / 5 of the retaining wall height H to ensure the temporary stability of the foundation pit slope during excavation; the layer height range for layered pouring is set to 1.2m-2.5m, combined with the concrete pouring process requirements and the stress characteristics of the wall structure, and the pouring height of each layer must not exceed 1.2 times the height h of the wall toe step to avoid cracking of the wall structure or construction quality defects due to excessive pouring height. All construction strategy parameters must be boundary-checked in the module to ensure compliance with construction specifications and actual engineering feasibility. The module divides the construction process into four key stages according to the set construction strategy parameters and optimized shape parameters: foundation pit excavation stage, temporary support installation stage, layered wall pouring stage, and backfilling stage, and performs simulation calculations for each stage. Based on the maximum permissible single excavation depth, simulate the layered / segmented excavation process, calculate the temporary loads for this stage, including the active earth pressure on the unsupported slope (calculated according to the recommended formula in the "Technical Specification for Foundation Pit Engineering" JGJ120-2012) and the self-weight load of construction machinery (based on the standard self-weight of commonly used excavators and cranes, taking 200kN-500kN); use the Swedish slice method to calculate the temporary stability of the slope and assess the risk of slope sliding; if the excavation depth exceeds the maximum permissible single excavation depth or the slope stability does not meet the requirements (safety factor less than 1.2), simulate the installation process of temporary supports (such as anchor bolts, soil nailing walls), calculate the stress loads on the support structure (anchor bolt tension, soil nailing wall pull-out force), and verify the strength and stability of the support structure; simulate the concrete pouring process according to the layer height range, calculate the temporary loads for this stage, including the self-weight of the poured wall and the formwork support reaction force (calculated according to the concrete lateral pressure formula, taking 25kN / m2-35kN / m2). 2The finite element method was used to calculate the anti-sliding stability safety factor, overturning stability safety factor, and base stress of the partially formed wall to assess the temporary structural stability during the construction phase. The layered backfilling process was simulated to calculate the self-weight load of the backfill soil and its lateral pressure on the wall, verifying the temporary stability of the wall under backfill load. All temporary load and stability calculation results were stored in real-time in the module database as the basis for subsequent penalty weight updates. Based on the temporary load calculation results and temporary stability assessment results at each construction stage, penalty weight update rules were established. For example, if the temporary stability of a certain construction stage meets the requirements (slope stability safety factor ≥ 1.2, anti-sliding stability safety factor of partially formed wall ≥ [Kc] construction condition, overturning stability safety factor ≥ [K0] construction condition, base stress meets the constraint requirements), and the temporary load does not exceed the bearing capacity of conventional construction, then the original penalty weight is maintained (anti-sliding stability penalty weight μ = 10). 5 Anti-overturning stability penalty weight η=10 5 Maximum base stress penalty weight ζ=10 5 Minimum base stress penalty weight ξ=10 5 If the temporary stability of a certain construction stage does not meet the requirements, but can be compensated for by adding temporary support measures (such as slope stability safety factor 1.0≤K<1.2), then the penalty weight is updated according to the proportion of support cost: μ'=μ×(1+λ), η'=η×(1+λ), ζ'=ζ×(1+λ), ξ'=ξ×(1+λ), where λ is the ratio of temporary support cost to the original retaining wall cost (λ=total cost of temporary support / volume of retaining wall×unit price of materials); if the temporary load of a certain construction stage exceeds the bearing capacity of conventional construction (such as construction machinery load causing the base stress to approach the allowable bearing capacity of the foundation) or the temporary stability is seriously insufficient (K<1.0), then the corresponding penalty weight will be doubled (μ'=2μ, η'=2η, ζ'=2ζ, ξ'=2ξ) to strengthen the penalty for this type of construction risk. After the weights are updated, the fitness function value is recalculated according to the updated penalty weights. The new fitness function expression is: F'=V+μ'∑|min(0,Kci-[Kci])|+η'∑|min(0,K0i-[K0i])|+ζ'∑|min(0,[Pmaxi]-Pmaxi)|+ξ'∑|min(0,P min0i )|+ξ'∑|min(-100,P min1i )| where F' is the updated fitness function value, μ', η', ζ', ξ' are the updated penalty weights, and the meanings of the other parameters are the same as those of the original fitness function.

[0065] like Figure 3 As shown in the figure, an embodiment of the present invention provides a retaining wall shape optimization device 300 based on atomic search, comprising: Module 310 is used to construct an objective function based on the standard proportions of the retaining walls and the key shape parameters of multiple pre-determined retaining walls, in order to minimize the volume of the retaining wall per unit width. The generation module 320 is used to randomly generate multiple sets of key body shape parameters under the same working conditions to obtain initial body shape parameters, calculate the corresponding mechanical index based on each set of initial body shape parameters and corresponding load, obtain preset constraints according to design specifications, and generate fitness function values ​​according to the mechanical index, the preset constraints and the objective function. The iteration module 330 is used to iteratively optimize the fitness function value using an atomic search optimization algorithm to obtain the optimized body shape parameters.

[0066] like Figure 4 As shown, an electronic device 400 provided in this embodiment of the invention includes a memory 410 and a processor 420; the memory 410 is used to store a computer program; the processor 420 is used to implement the retaining wall shape optimization method based on atomic search as described above when the computer program is executed.

[0067] Alternatively, an electronic device 400 includes a memory 410 and a processor 420 coupled to the memory 410; the memory 410 is configured to store a computer program; and the processor 420 is configured to perform the following operations when the computer program is executed: Based on the predetermined key shape parameters of multiple retaining walls, an objective function is constructed to minimize the volume of the retaining wall per unit width, according to the standard proportion of the retaining walls. Multiple sets of key body shape parameters under the same working conditions are randomly generated to obtain initial body shape parameters. Based on each set of initial body shape parameters and the corresponding load, the corresponding mechanical index is calculated, and the preset constraints are obtained according to the design specifications. The fitness function value is generated according to the mechanical index, the preset constraints and the objective function. An atomic search optimization algorithm is used to iteratively optimize the fitness function value to obtain the optimized body shape parameters.

[0068] This invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the retaining wall shape optimization method based on atomic search as described above.

[0069] Alternatively, a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following operations: Based on the predetermined key shape parameters of multiple retaining walls, an objective function is constructed to minimize the volume of the retaining wall per unit width, according to the standard proportion of the retaining walls. Multiple sets of key body shape parameters under the same working conditions are randomly generated to obtain initial body shape parameters. Based on each set of initial body shape parameters and the corresponding load, the corresponding mechanical index is calculated, and the preset constraints are obtained according to the design specifications. The fitness function value is generated according to the mechanical index, the preset constraints and the objective function. An atomic search optimization algorithm is used to iteratively optimize the fitness function value to obtain the optimized body shape parameters.

[0070] The present invention will now be described an electronic device 400 that can serve as a server or client of the present invention, which is an example of a hardware device that can be applied to various aspects of the present invention. Electronic device 400 is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 400 can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0071] Electronic device 400 includes a computing unit that can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) or a computer program loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The computing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0072] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc. In this application, the units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention according to actual needs. Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units can be implemented in hardware or as software functional units.

[0073] While the present invention has been disclosed above, its scope of protection is not limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, and all such changes and modifications will fall within the scope of protection of the present invention.

Claims

1. A method for optimizing the shape of a retaining wall based on an atomic search optimization algorithm, characterized in that, include: Based on the key shape parameters of multiple pre-determined retaining walls, an objective function is constructed to minimize the volume of the retaining wall per unit width, according to the standard proportion of the retaining walls. Multiple sets of key body shape parameters under the same working conditions are randomly generated to obtain initial body shape parameters. Based on each set of initial body shape parameters and the corresponding load, the corresponding mechanical index is calculated, and the preset constraints are obtained according to the design specifications. The fitness function value is generated according to the mechanical index, the preset constraints and the objective function. An atomic search optimization algorithm is used to iteratively optimize the fitness function value to obtain the optimized body shape parameters.

2. The retaining wall shape optimization method based on atomic search optimization algorithm according to claim 1, characterized in that, The process involves constructing an objective function based on predetermined key shape parameters of multiple retaining walls, taking into account the standard proportions of the retaining walls, and minimizing the volume of the retaining wall per unit width. This includes: Using the bottom point of the retaining wall as the origin of the coordinate system, the coordinates of multiple vertices of the retaining wall are determined based on the influence relationship of the key shape parameters and the standard proportion. The cross-sectional area of ​​the retaining wall is calculated based on the vertex coordinates, and the cross-sectional area is used to characterize the volume of the retaining wall per unit width. An objective function is then constructed to minimize the volume of the retaining wall per unit width.

3. The retaining wall shape optimization method based on atomic search optimization algorithm according to claim 1, characterized in that, The process of calculating the corresponding mechanical indices based on each set of initial body shape parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values ​​based on the mechanical indices, the preset constraints, and the objective function includes: Based on the working conditions and the corresponding load combination rules, select the corresponding load, and calculate the corresponding mechanical index according to each set of initial body parameters and the load; According to the design specifications, retrieve the limit values ​​of the mechanical indicators corresponding to the working conditions, and generate the preset constraints based on the limit values. The external penalty function method is adopted, and the volume of the retaining wall is used as the basic term of the functional degree function. A penalty term is applied according to the comparison result of the preset constraints and the mechanical index to obtain a fitness function that includes the objective function and the constraint penalty, wherein the constraint penalty is obtained according to the preset constraints and the corresponding penalty term.

4. The retaining wall shape optimization method based on atomic search according to claim 3, characterized in that, The penalty term includes penalty weight and standard weight; the external penalty function method uses the retaining wall volume as the basis term of the usability function, and applies a penalty term based on the comparison results of the preset constraints and the mechanical indicators to obtain a fitness function that includes the objective function and the constraint penalties, including: The penalty weight and the standard weight are set for each mechanical index based on the preset design specifications; Determine whether the mechanical index meets the preset constraint. If not, match the corresponding penalty weight for the corresponding mechanical index. If yes, match the corresponding standard weight for the corresponding mechanical index. Based on the mechanical index, the preset constraints, and the corresponding penalty weights or standard weights, the constraint penalty is obtained using the external penalty function method. The fitness function value is obtained by summing the objective function and the constraint penalty.

5. The retaining wall shape optimization method based on atomic search optimization algorithm according to claim 1, characterized in that, The atomic search optimization algorithm is used to iteratively optimize the fitness function value to obtain optimized body shape parameters, including: The initial velocity of each set of initial body size parameters is initialized, and the initial value of the global optimal fitness function is set to infinity; Compare the fitness function value corresponding to the current parameter group with the global optimal fitness function value. If the fitness function value of the current parameter group is less than the global optimal fitness function value, then update the global optimal fitness function value and the optimal parameters corresponding to the global optimal fitness function value according to the current parameter group and the fitness function value of the current parameter group. The quality of the corresponding parameter group is calculated based on the fitness function value corresponding to each parameter group, wherein the smaller the fitness function value, the higher the quality of the corresponding parameter group; Calculate the K value based on the quality and number of iterations of the parameter set, and update the parameter set consisting of the top K initial body shape parameters with the best fitness function values; Calculate the interaction force between each set of initial body shape parameters in the parameter set, and the geometric constraint force of the optimal parameters on the parameter set; and solve for the acceleration of the parameter set based on the interaction force and the geometric constraint force. The velocity and parameter values ​​corresponding to the parameter group are updated according to the acceleration, and the corresponding fitness function value is calculated according to the body shape parameters of the updated parameter group. The updated parameter group is used as the current parameter group. The step of comparing the fitness function value corresponding to the current parameter group with the global optimal fitness function value is returned and iterated repeatedly until the preset maximum number of iterations is reached. The global optimal parameter corresponding to the global optimal fitness function value is output as the optimized body shape parameter.

6. The retaining wall shape optimization method based on atomic search optimization algorithm according to claim 1, characterized in that, The mechanical properties include the anti-slip stability safety factor, the anti-overturning stability safety factor, the maximum base stress, and the minimum base stress; The preset constraints include: Under each working condition, the anti-sliding stability safety factor shall not be less than the anti-sliding stability safety limit of the corresponding specification, the calculated value of the anti-overturning stability safety factor shall not be less than the corresponding anti-overturning safety limit, the maximum base stress shall not be greater than the allowable bearing capacity of the foundation, and no tensile stress shall occur under non-earthquake working conditions, and the minimum base stress under non-construction and earthquake working conditions shall not be the tensile stress. If the minimum base stress under construction working conditions and earthquake working conditions is the tensile stress, then the absolute value of the minimum base stress shall not be greater than the stress limit.

7. The retaining wall shape optimization method based on atomic search optimization algorithm according to claim 4, characterized in that, It also includes the following steps: After obtaining the optimized body shape parameters, construction strategy parameters are set, including preset typical construction sequence, maximum allowable single excavation depth, and layer height range for layered pouring. Simulate each stage of construction according to the construction strategy parameters and the optimized body shape parameters, and calculate the temporary load and temporary stability of each stage; The penalty weights are updated based on the temporary loads and the temporary stability, and the fitness function value is updated according to the updated penalty weights. Based on the updated fitness function value, iterative optimization is performed again to obtain the final body shape parameters.

8. A retaining wall shape optimization device based on an atomic search optimization algorithm, characterized in that, include: The module is used to construct an objective function based on the standard proportions of the retaining walls and the key shape parameters of multiple pre-determined retaining walls, in order to minimize the volume of the retaining wall per unit width. The generation module is used to randomly generate multiple sets of key body shape parameters under the same working conditions to obtain initial body shape parameters, calculate the corresponding mechanical index based on each set of initial body shape parameters and corresponding load, obtain preset constraints according to design specifications, and generate fitness function values ​​according to the mechanical index, the preset constraints and the objective function. The iterative module is used to iteratively optimize the fitness function value using an atomic search optimization algorithm to obtain the optimized body shape parameters.

9. An electronic device, characterized in that, Including memory and processor; The memory is used to store computer programs; The processor is configured to, when executing the computer program, implement the retaining wall shape optimization method based on the atomic search optimization algorithm as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the retaining wall shape optimization method based on the atomic search optimization algorithm as described in any one of claims 1 to 7.

Images