A method, device and medium for optimizing underground assembly structure

Abstract

The present application relates to an underground assembly structure optimization method, equipment and medium, and relates to underground space structure optimization; the method includes: obtaining data related to urban stratum properties; based on the data related to urban stratum properties and the use requirements of underground assemblies, on the basis of meeting preset design conditions and constraints, traversing the structural system, component type and layout within the pre-stored range, and constructing a variety of underground prefabricated structure design schemes; determining the comprehensive seismic capacity values ​​of different underground prefabricated structure design schemes; based on a variety of underground assembly structure design schemes and multi-objective optimization models, using a preset multi-objective optimization algorithm to determine the optimal underground assembly structure design scheme. The present application can comprehensively consider the influence of stratum properties, use requirements and dynamic loads, accurately evaluate the reliability performance of the design scheme through systematic reliability analysis, reduce safety risks, and improve the disaster resistance of underground assemblies in natural disasters such as earthquakes.

Description

Technical Field

[0001] The present invention relates to the field of underground space structure optimization, and in particular to an underground assembly structure optimization method, equipment and medium. Background Art

[0002] With the acceleration of urbanization, the development and utilization of underground space has become an effective way to ease the shortage of ground space and improve the comprehensive carrying capacity of cities. Underground assembly structures, especially prefabricated underground stations, are widely used in modern urban construction due to their fast construction speed, small environmental impact, and excellent quality control. However, the design of underground assembly structures faces many challenges, especially in complex and changeable geological conditions, such as soft soil layers and liquefiable soil layers in cities. How to ensure structural safety, economic feasibility, and convenient construction while reducing the impact on the surrounding environment has become an urgent problem to be solved.

[0003] Traditional underground structure design methods often focus on the optimization of a single performance indicator, such as structural safety or cost control, ignoring the multi-dimensional needs of structural design. In cities, underground assembly structures must not only deal with the settlement problem caused by soft strata, but also consider the stability of liquefiable soil layers under earthquakes, as well as the additional impact of superstructures on underground structures. In addition, the opening of joints between underground assembly structures is also a key factor affecting the overall structural safety and waterproof performance. Therefore, how to optimize construction costs, shorten construction periods, and reduce interference with the environment while ensuring structural safety has become an urgent need in the current design of underground assembly structures. Summary of the invention

[0004] In order to design a safer and more economical underground assembly structure, the present application provides an underground assembly structure optimization method, equipment and medium.

[0005] In a first aspect, the present application provides a method for optimizing the structure of an underground assembly, which adopts the following technical solution:

[0006] Acquire data related to urban stratum properties; wherein the data related to urban stratum properties include: data related to soil mechanical properties, data related to liquefiable strata, and data on superstructure layout parameters;

[0007] According to the relevant data of urban stratum properties and the use requirements of underground assemblies, on the basis of meeting the preset design conditions and constraints, the structural system, component type and layout within the pre-stored range are traversed to construct a variety of underground prefabricated structure design schemes; the use requirements of underground assemblies include: the use function, space requirements and bearing capacity of underground assemblies;

[0008] Conduct earthquake response simulations on a variety of underground prefabricated structure design schemes to obtain earthquake-related index data of different underground prefabricated structure design schemes under earthquake conditions, and determine the comprehensive earthquake-resistant capacity values ​​of different underground prefabricated structure design schemes based on the corresponding relationship between the data ranges of different earthquake-resistant index data and the earthquake-resistant capacity values ​​and the weight ratios of different earthquake-resistant index data;

[0009] According to a variety of underground assembly structure design schemes and multi-objective optimization models, a preset multi-objective optimization algorithm is used to determine the optimal underground assembly structure design scheme.

[0010] By adopting the above technical solutions, through the precise collection and analysis of urban stratum data, combined with the specific needs of underground assemblies, many underground prefabricated structure design solutions have been cleverly conceived. It uses advanced seismic response simulation technology to scientifically evaluate the performance of each design solution in an earthquake to ensure that each solution has excellent seismic performance. Through multi-objective optimization models and algorithms, this method can accurately screen out the optimal design, which not only meets the functional, spatial and load-bearing requirements, but also achieves excellent stability and safety in structure.

[0011] Optionally, the method further comprises: determining the optimal underground assembly structure design scheme by using a preset multi-objective optimization algorithm according to the multiple underground assembly structure design schemes and the multi-objective optimization model; and then:

[0012] Obtain historical earthquake data;

[0013] Construct a geomechanical model of the geological environment where the underground assembly is located based on the geological survey data and geological structural characteristics of the target area;

[0014] The optimal underground assembly structure design scheme is used to establish a refined model of the underground assembly structure using nonlinear finite element analysis software, and then imported into the geomechanics model to form a complete nonlinear dynamic analysis model;

[0015] According to the preset representative seismic wave selection conditions, representative seismic waves are selected from historical seismic data, and the seismic waves are adjusted according to different seismic intensities. The adjusted seismic waves are input into the nonlinear dynamic analysis model to perform seismic response simulation and obtain seismic response simulation results;

[0016] According to the seismic response simulation results, the key response index data of the optimal underground assembly structure design scheme under seismic action are extracted, and the mean and standard deviation of the key response index data are calculated;

[0017] Calculate the limit state function value according to the mean and standard deviation of the key response indicator data and the preset limit state function of the key response indicator data;

[0018] According to the limit state function value, combined with the mean and standard deviation of the key response indicator data, the reliability index is determined according to the preset reliability index calculation formula;

[0019] Determine whether the reliability index exceeds the preset target reliability index;

[0020] If yes, the current optimal underground assembly structure design scheme is used as the optimal underground assembly structure design scheme for this time;

[0021] If not, the current optimal underground assembly structure design scheme is excluded, and the process jumps to the step of determining the optimal underground assembly structure design scheme according to a plurality of underground assembly structure design schemes and a multi-objective optimization model using a preset multi-objective optimization algorithm, and the optimal underground assembly structure design scheme is re-formed, and it is determined whether the reliability index exceeds the preset target reliability index;

[0022] Repeat the above steps until the reliability index of the re-formed optimal underground assembly structure design scheme exceeds the preset target reliability index, and determine the corresponding optimal underground assembly structure design scheme as the optimal underground assembly structure design scheme this time.

[0023] By adopting the above technical solutions and comprehensively considering historical earthquake data and geological characteristics, the design scheme is more in line with the actual situation. Through multiple rounds of optimization and screening, the reliability of the final scheme is ensured to meet the standards. It can accurately extract key response indicators, scientifically calculate reliable indicators, and effectively eliminate substandard schemes. Repeated iterations until the requirements are met improve the safety and stability of the design scheme.

[0024] Optionally, according to a plurality of underground assembly structure design schemes and a multi-objective optimization model, a preset multi-objective optimization algorithm is used to determine the optimal underground assembly structure design scheme, specifically including:

[0025] Obtain the data involved in the preset multi-objective optimization algorithm;

[0026] Input the constructed safety performance objective function, economic index objective function and construction period objective function into the preset multi-objective optimization algorithm;

[0027] A multi-objective optimization algorithm is used to search in the solution space of various underground assembly structure design schemes to generate a series of design solution solutions. For each solution, the corresponding safety performance objective function, economic index objective function and construction period objective function are calculated.

[0028] Filter out non-dominated solutions from all solutions;

[0029] According to the weight ratio of the preset safety performance objective function, economic index objective function and construction period objective function, the comprehensive score of each non-dominated solution is calculated, and the solution with the highest score is selected as the optimal underground assembly structure design solution.

[0030] By adopting the above technical solutions and integrating multi-objective optimization algorithms, the optimal design solution for underground assemblies can be efficiently determined. By comprehensively considering key factors such as safety, economy, and construction period, the solution is fully optimized. The intelligent search and screening mechanism is used to ensure that the final solution is optimal in all aspects, significantly improving design efficiency and quality.

[0031] Optionally, the process of determining the weight ratio of the preset safety performance objective function, economic index objective function and construction period objective function specifically includes:

[0032] Obtain weather condition information for the planned underground assembly structure construction time range;

[0033] According to the corresponding relationship between the corresponding key parameter data range within which the key parameter data contained in the weather condition information falls and the weight distribution ratio of the three objective functions, the weight ratio of the preset safety performance objective function, economic indicator objective function and construction period objective function is determined.

[0034] By adopting the above technical solution, weather conditions are taken into account in the weight distribution of the objective function, and dynamic adjustment of the weight is achieved. By analyzing weather data, the weights of the three objectives of safety, economy and construction period can be more reasonably allocated, making the design of underground assembly structures more practical and flexible. This method not only optimizes the design scheme, but also improves the feasibility and efficiency of construction, demonstrating the unique advantages of intelligent decision-making in underground structure design.

[0035] Optionally, the method further includes steps after extracting the key response index data of the optimal underground assembly structure design solution under earthquake action according to the earthquake response simulation results and before calculating the mean and standard deviation of the key response index data, which are specifically as follows:

[0036] The amount of sample data for obtaining reliable indicators for analysis; the amount of sample data includes the amount of data related to the mechanical properties of the underground assembly structure, the amount of data on material properties, the amount of data on the loads on the structure, and the amount of geometrical dimension measurements or design data of the underground assembly structure;

[0037] If the sample data volume of the reliability index exceeds the preset sample quantity threshold, the key random variables affecting the reliability of the underground assembly structure are used, and the probability distribution function is specified for each random variable;

[0038] Using a random number generator, a large number of random sample combinations are generated according to the probability distribution of random variables;

[0039] Substitute each random sample combination into the established nonlinear dynamic analysis model, re-simulate the earthquake response, and calculate new earthquake response simulation results;

[0040] According to the pre-set structural performance requirements, determine whether each calculated earthquake response simulation result meets the requirements;

[0041] Collect statistics on all earthquake response simulation results and record the number of samples that meet the performance requirements;

[0042] The ratio of the number of samples that meet the performance requirements to the total number of samples is taken as the reliability, and the reliability index is determined based on the mapping relationship between the reliability and the reliability index;

[0043] If the sample data volume of the reliability indicator is less than or equal to the preset sample quantity threshold, the original setting is maintained.

[0044] By adopting the above technical solutions, the reliability of underground assembly structures is effectively evaluated through refined data analysis, combined with random simulation and seismic response testing. It not only considers a variety of key data, but also more comprehensively simulates the structural response under actual earthquake scenarios by generating a large number of random samples. This method can accurately determine whether the structure meets the performance requirements, thereby ensuring the safety and stability of the underground assembly.

[0045] Optionally, the method further includes steps after extracting the key response index data of the optimal underground assembly structure design solution under earthquake action according to the earthquake response simulation results and before calculating the mean and standard deviation of the key response index data, which are specifically as follows:

[0046] Obtain the sample data volume for analyzing reliable indicators and weather condition information within the planned construction time range of the underground assembly structure; the sample data volume includes the data volume related to the mechanical properties of the underground assembly structure, the data volume on material properties, the data volume on the loads borne by the structure, and the quantity of geometric dimension measurements or design data of the underground assembly structure;

[0047] If the amount of sample data of the reliability index exceeds the preset sample quantity threshold and / or the data of the key parameters contained in the future weather condition information falls within the limit range of the preset parameters, then according to the key random variables affecting the reliability of the underground assembly structure, a probability distribution function is specified for each random variable;

[0048] Using a random number generator, a large number of random sample combinations are generated according to the probability distribution of random variables;

[0049] Substitute each random sample combination into the established nonlinear dynamic analysis model, re-simulate the earthquake response, and calculate new earthquake response simulation results;

[0050] According to the pre-set structural performance requirements, determine whether each calculated earthquake response simulation result meets the requirements;

[0051] Collect statistics on all earthquake response simulation results and record the number of samples that meet the performance requirements;

[0052] Calculate the ratio of the number of samples that meet the performance requirements to the total number of samples as the reliability, and determine the reliability index based on the mapping relationship between the reliability and the reliability index;

[0053] Otherwise, the original settings are maintained.

[0054] By adopting the above technical solution, when a specific condition is triggered, random samples are generated by specifying the probability distribution, the structural response is re-simulated, and the reliability is statistically analyzed to determine the reliability index, which enhances the accuracy and comprehensiveness of the reliability assessment. It can cope with a large number of samples and extreme weather conditions, and improve the adaptability of the assessment.

[0055] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the underground assembly structure optimization method.

[0056] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the underground assembly structure optimization method when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the overall process of an underground assembly structure optimization method according to an embodiment of the present application.

[0058] Figure 2 It is a flowchart diagram of the steps after determining the optimal underground assembly structure design scheme in another embodiment of the present application.

[0059] Figure 3 It is a flowchart of another embodiment of the present application that determines the optimal underground assembly structure design scheme based on a plurality of underground assembly structure design schemes and a multi-objective optimization model using a preset multi-objective optimization algorithm.

[0060] Figure 4 It is a schematic diagram of the process of obtaining the weight ratios of the three objective functions preset in another embodiment of the present application. DETAILED DESCRIPTION

[0061] The present application is further described in detail below in conjunction with the accompanying drawings.

[0062] Reference Figure 1 , is a method for optimizing underground assembly structure disclosed in the present application, comprising:

[0063] Step S100, obtaining data related to urban stratum properties.

[0064] Among them, the data related to urban stratum properties include data related to soil mechanical properties, data related to liquefiable strata, and data on superstructure layout parameters.

[0065] Specifically, the data related to the mechanical properties of the soil layer include soil type, density, compression modulus, shear strength and other data; the data related to the liquefiable stratum include the burial depth, thickness and distribution range of the liquefiable soil layer and other data; the superstructure layout parameters include building distribution, load conditions, foundation form and other data. These data will provide a reference for the design of the underground assembly structure to ensure its coordination and stability with the superstructure.

[0066] The acquisition of data related to the properties of urban strata is mainly achieved through geological surveys and equipment monitoring. Specifically, geological surveys mainly obtain detailed physical and mechanical properties of soil layers, as well as the distribution and characteristics of liquefiable strata through means such as drilling sampling and geological radar detection; equipment monitoring mainly uses professional monitoring equipment, such as sedimentation meters and inclinometers, to monitor the real-time status of soil layers and superstructures, and collect relevant data to guide the design and optimization of underground assembly structures.

[0067] Step S200, based on the relevant data of urban stratum properties and the use requirements of underground assemblies, on the basis of meeting the preset design conditions and constraints, traverse the structural systems, component types and layouts within the pre-stored range, and then construct a variety of underground prefabricated structure design solutions.

[0068] The use requirements of underground assemblies include the use functions, space requirements, and load-bearing capacity of underground assemblies. Different use functions, such as parking, commercial or public facilities, will directly affect the design of the structure. If the underground assembly is planned to be used as a parking lot, its space requirements may be 100 meters long, 50 meters wide, and 4 meters high, and the load-bearing capacity requirement is 2.5 tons per square meter.

[0069] The preset design conditions and constraints include size restrictions, material usage restrictions, safety regulations, etc. Data example: The design conditions may stipulate that the maximum height of the structure shall not exceed 10 meters, the main material used must be reinforced concrete, and the earthquake resistance level must reach 8.

[0070] On the basis of meeting the above conditions, multiple design solutions are constructed by traversing different structural systems (such as frame, arch, box, etc.), component types (such as beams, columns, plates, etc.), and different layout methods. For example, if three structural systems, four component types and five layout methods are considered, theoretically 3x4x5=60 different design solutions can be generated.

[0071] Step S300, conduct seismic response simulation on the various underground prefabricated structure design schemes constructed, obtain seismic resistance related index data of different underground prefabricated structure design schemes under seismic conditions, and determine the comprehensive seismic resistance capacity values ​​of different underground prefabricated structure design schemes according to the correspondence between the data ranges of different seismic resistance related index data and the seismic resistance capacity values ​​and the weight ratios of different seismic resistance related index data.

[0072] Earthquake response simulation is to evaluate the response of the structure when an earthquake occurs, so as to determine the seismic performance of the structure. By simulating the impact of earthquake waves of different intensities on the structure, key data such as deformation and displacement of the structure during an earthquake can be obtained.

[0073] Seismic-related index data include maximum displacement, maximum acceleration, inter-story displacement angle, etc. These are important parameters for evaluating the seismic performance of structures.

[0074] The comprehensive seismic capacity values ​​of different underground prefabricated structure design schemes are determined as follows: First, a corresponding seismic capacity value is assigned according to the data range in which each indicator data falls. For example, for the maximum displacement indicator, different displacement ranges can be set to correspond to different seismic capacity values. A smaller displacement indicates that the structure is more stable in an earthquake, so a higher seismic capacity value will be assigned; otherwise, a lower value will be assigned.

[0075] At the same time, the weight of different earthquake-related index data also needs to be considered. Some indicators may be more important for evaluating the overall seismic performance of the structure, so they will be given a greater weight. For example, if the maximum displacement is considered to be a key indicator for evaluating the seismic performance of the structure, then it may have a greater weight in the calculation of the comprehensive seismic capacity value.

[0076] Finally, the seismic capacity values ​​of each scheme are weighted averaged according to their weights to obtain the comprehensive seismic capacity value of each scheme.

[0077] For example: suppose there are three underground assembly structure design schemes A, B, and C. Through earthquake response simulation, their maximum displacement, acceleration response spectrum, and structural damage index data are obtained. Based on these data and the predetermined index weights, the comprehensive seismic capacity value of each scheme can be calculated. For example, the comprehensive seismic capacity value of scheme A is 80 points, scheme B is 85 points, and scheme C is 90 points (out of 100 points).

[0078] Step S400, based on a plurality of underground assembly structure design schemes and a multi-objective optimization model, a preset multi-objective optimization algorithm is used to determine an optimal underground assembly structure design scheme.

[0079] Specifically, the various design schemes, earthquake response simulation results, and comprehensive seismic capacity values ​​obtained in the previous steps are input into the multi-objective optimization model. This model can comprehensively evaluate the schemes based on multiple optimization goals (such as cost, safety, stability, etc.). Through the preset multi-objective optimization algorithm, various schemes can be automatically compared and screened.

[0080] The optimization algorithm considers the trade-offs and priorities between multiple objectives, such as minimizing costs while ensuring safety, or improving stability while ensuring that the structure's functionality is not affected. In this way, a design solution that achieves the best balance between multiple objectives can be found.

[0081] Let's take an example to illustrate this process: suppose there are three candidate underground assembly structure design solutions A, B and C. In step S400, these solutions are input into the multi-objective optimization model, and the optimization goals are set as the lowest cost, the highest safety and the best stability. The optimization algorithm will evaluate each solution based on these goals. For example, Solution A has low cost but average safety, Solution B has good safety but high cost, and Solution C achieves a good balance between cost and safety. In the end, the optimization algorithm will select Solution C as the optimal design solution because it achieves the best trade-off between multiple goals.

[0082] Reference Figure 2 , a method for optimizing underground assembly structure further includes steps after determining the optimal underground assembly structure design scheme, specifically as follows:

[0083] Step S500, obtaining historical earthquake data.

[0084] Specifically, historical earthquake data includes key information such as the time, location, magnitude, and focal depth of an earthquake. Historical earthquake data can be obtained by querying from a preset database that stores historical earthquake data.

[0085] Step S600: constructing a geomechanical model of the geological environment in which the underground assembly is located based on the geological survey data and geological structural characteristics of the target area.

[0086] First, collect detailed geological survey data of the target area. This data should include information such as geological structure, rock layer distribution, soil characteristics, groundwater level, etc. This data can be obtained through geological survey teams, geological data storage institutions or public geological information platforms.

[0087] Geological structural characteristics can identify the main geological structural characteristics of the target area based on the geological data obtained, such as faults, folds, lithology changes, etc.

[0088] The geomechanical model is mainly constructed based on the geological structure characteristics obtained through analysis, using the principles of geomechanics and numerical simulation technology.

[0089] Assuming that the target area is an area with frequent earthquakes, the underground assembly needs to withstand potential earthquake impacts. In step S600, it is first necessary to collect earthquake history records, geological structure maps, rock layer distribution data, etc. of the area. Through analysis, it is found that there are multiple active faults in the area and the rock layer types are varied, which poses a challenge to the stability of the underground assembly.

[0090] Next, geomechanical software and numerical simulation techniques are used to construct a geomechanical model that incorporates these fault and rock formation properties. In the model, the effects of different seismic waves on the underground assembly and the response of the rock formation under earthquake action can be simulated.

[0091] Step S700, the optimal design solution determined by multi-objective optimization is used to establish a refined model of the underground assembly structure using nonlinear finite element analysis software, and is imported into the geomechanics model to form a complete nonlinear dynamic analysis model.

[0092] The optimal design solution is obtained as follows: First, through the multi-objective optimization method, the strength, stiffness, stability and economy of the structure are comprehensively considered to obtain the optimal design solution.

[0093] The refined model of the underground assembly structure is mainly established using professional nonlinear finite element analysis software, such as ANSYS or ABAQUS. This step ensures that the model can reflect every detail and characteristic of the underground assembly in detail.

[0094] The formation of a complete nonlinear dynamic analysis model is as follows: After the refined model is established, it is imported into the previously created geomechanical model. Through precise coordinate matching and model adjustment, it is ensured that the two models can be perfectly integrated to form a complete and accurate nonlinear dynamic analysis model.

[0095] Suppose that an underground tunnel assembly is being designed, and it is necessary to ensure that it can withstand the impact of various natural forces such as earthquakes. In step S700, a tunnel design scheme that is both economical and safe is first obtained through multi-objective optimization. Then, nonlinear finite element analysis software is used to simulate every corner and detail of the tunnel structure in detail, including support structures, wall thickness, material properties, etc. Next, this refined tunnel model is imported into the previously constructed geomechanical model. This geomechanical model has reflected in detail the geological structure and characteristics of the tunnel location, including rock layer distribution, soil properties, etc. By integrating the two models together, a complete nonlinear dynamic analysis model that can simulate the tunnel response under a real earthquake environment is obtained.

[0096] Step S800, according to the preset representative seismic wave selection conditions, select representative seismic waves from historical seismic data, adjust the seismic waves according to different seismic intensities, input the adjusted seismic waves into the nonlinear dynamic analysis model, perform seismic response simulation, and obtain seismic response simulation results.

[0097] The preset representative seismic wave selection conditions include the magnitude, epicenter distance, spectrum characteristics, etc. For example, seismic waves with a magnitude of more than 6, an epicenter distance of less than 100 kilometers, and a spectrum similar to the earthquake characteristics in the target area are selected.

[0098] Selecting representative seismic waves is to screen out seismic wave records that meet preset conditions from historical seismic data. For example, a seismic wave with a magnitude of 7 and an epicenter distance of 80 kilometers is selected from a large amount of historical data.

[0099] Adjusting seismic waves according to different seismic intensities mainly involves adjusting the amplitude and frequency of the selected seismic waves according to the set seismic intensity (such as 7 degrees, 8 degrees, etc.). Assuming that the peak acceleration of the original seismic wave is 0.2g, it needs to be adjusted to 0.4g corresponding to the 8-degree intensity.

[0100] Inputting the adjusted seismic waves into the nonlinear dynamic analysis model is to use professional software to load the adjusted seismic waves onto the constructed nonlinear dynamic analysis model.

[0101] Assume that the structure optimization is being performed for an underground parking lot located in an earthquake-prone area. In step S800, firstly, several seismic waves that can represent the seismic characteristics of the area are selected from a large amount of historical seismic data, and these seismic waves include different energy and frequency components.

[0102] Then, these seismic waves were adjusted according to the intensity of earthquakes that might occur in the area, such as enhancing the amplitude of certain frequency bands to simulate stronger earthquake impacts.

[0103] Then, these adjusted seismic waves were input into the established nonlinear dynamic analysis model, which simulated every structural and material property of the underground parking lot in detail. Through the simulation, the structural response of the underground parking lot under the action of different seismic waves was observed, including structural deformation, stress distribution, etc.

[0104] Step S900: extract key response index data of the underground assembly structure under earthquake action according to the earthquake response simulation result, and calculate the mean and standard deviation of the key response index data.

[0105] Among them, the earthquake response simulation results include various data such as displacement, stress distribution, deformation, etc. of underground assemblies under the action of different seismic waves.

[0106] The key response index data extraction mainly involves identifying and extracting the key response index data that have the most significant impact on the safety performance of underground assembly structures under earthquake action from the simulation results. These key indicators may include maximum displacement, maximum stress value, deformation of specific parts, etc.

[0107] The mean and standard deviation of the key response indicator data are mainly calculated by statistical calculation of the extracted key response indicator data, including the calculation of the mean and standard deviation of each indicator. The mean reflects the average level of the indicator, while the standard deviation reflects the degree of dispersion of the indicator, that is, the volatility of the data.

[0108] Assume that a seismic response simulation of an underground pipeline assembly is performed. In step S900, the simulation results are first analyzed, and it is found that the maximum displacement of the pipeline under the action of the earthquake and the stress distribution of the connection part are key response indicators.

[0109] Next, the data of these two indicators in multiple simulations were extracted and statistically calculated. By calculating the mean, the maximum displacement and stress level of the pipeline under average conditions were obtained. At the same time, by calculating the standard deviation, the variation range of these indicators under different seismic waves was obtained, thereby evaluating the stability and seismic resistance of the pipeline assembly.

[0110] Step SA00, calculating the limit state function value according to the mean value and standard deviation of the key response indicator data and the preset limit state function of the key response indicator.

[0111] The limit state function is a mathematical expression used to determine whether a structure has reached a certain limit state (such as damage or failure). If the key response indicators are the maximum stress of the structure (represented by S) and the yield stress of the material (represented by R), then a simple limit state function can be expressed as: g=RS. When g>0, the structure is in a reliable state (i.e., the stress has not reached yield), g=0 is the critical limit state, and g<0 is the failure state. If the displacement response (D) and the maximum allowable displacement (Dmax) of the structure under earthquake action are considered, the limit state function can be: g=Dmax-D, etc.

[0112] Step SB00, according to the value of the limit state function, combined with the mean and standard deviation of the key response indicator data, and according to the preset reliability indicator calculation formula, the reliability indicator is determined.

[0113] Among them, the reliability index calculation formula is the first-order second moment method. In the first-order second moment method, the reliability index β can be calculated by the following formula: β=(μ_g-g(μ_X)) / σ_g, where μ_g is the mean of the limit state function g, g(μ_X) is the value of the limit state function at the mean of the random variable, and σ_g is the standard deviation of the limit state function g.

[0114] Specifically, the calculation process is as follows:

[0115] First, determine the expression of the limit state function g and calculate its value g(μ_X) at the mean value of the key response index.

[0116] Then, the mean μ_g and standard deviation σ_g of the limit state function g are calculated. This may need to be obtained through analysis of a large number of simulation results or statistical data.

[0117] Finally, the value obtained by the above calculation is substituted into the reliability index calculation formula to obtain the reliability index β.

[0118] For example, suppose the limit state function is g(X)=RS, where R is the resistance of the structure and S is the response of the structure under earthquake. The mean value of the key response index S is μ_S=100, the standard deviation is σ_S=20, and the mean value of the resistance R is μ_R=150. First, calculate the value of the limit state function at the mean value: g(μ_S)=μ_R-μ_S=150-100=50; assuming that the standard deviation of the limit state function g obtained through analysis is 30, the reliability index is as follows:

[0119] β=(μ_g-g(μ_S)) / σ_g=(μ_R-μ_S-(μ_R-μ_S)) / σ_g=(150-100-50) / 30=0.

[0120] When β = 0, it means that the structure is at the boundary of the limit state and the reliability is at a critical level.

[0121] Step SC00, judging whether the determined reliability index exceeds the preset target reliability index. If yes, executing step SD00; if no, executing step SE00.

[0122] Step SD00, taking the optimal underground assembly structure design scheme formed by the multi-objective optimization algorithm as the current optimal underground assembly structure design scheme.

[0123] Step SE00, excludes the optimal underground assembly structure design scheme currently formed by the multi-objective optimization algorithm, and jumps to the step of using the preset multi-objective optimization algorithm to determine the optimal underground assembly structure design scheme, re-forms the optimal underground assembly structure design scheme, and determines whether the determined reliability index exceeds the preset target reliability index.

[0124] Specifically, when it is determined in step SC00 that the determined reliability index does not reach the preset target reliability index, it means that the optimal underground assembly structure design scheme currently formed by the multi-objective optimization algorithm is insufficient, so it is necessary to exclude this scheme first. After excluding the current scheme, it is necessary to jump back to the preset multi-objective optimization algorithm, which will comprehensively consider multiple design goals (such as cost, structural strength, service life, etc.) and optimize the design scheme again. The multi-objective optimization algorithm re-forms a series of new underground assembly structure design schemes and selects the best design scheme under the current conditions.

[0125] Step SF00, repeat the above steps until the reliability index of the re-formed optimal underground assembly structure design scheme exceeds the preset target reliability index, and determine the corresponding optimal underground assembly structure design scheme as the current optimal underground assembly structure design scheme.

[0126] Reference Figure 3 , according to a variety of underground assembly structure design schemes and multi-objective optimization models, the preset multi-objective optimization algorithm is used to determine the optimal underground assembly structure design scheme, including:

[0127] Step S410, obtaining data involved in a preset multi-objective optimization algorithm.

[0128] First, it is necessary to clarify the data types required for the multi-objective optimization algorithm, which usually includes but is not limited to geological survey data, material performance data, design specification requirements, historical engineering case data, etc.

[0129] Step S420, input the constructed safety performance objective function, economic index objective function and construction period objective function into a preset multi-objective optimization algorithm.

[0130] Among them, the safety performance objective function as follows:

[0131] = ;

[0132] This function comprehensively considers the three indicators related to safety performance: station vault settlement, floating displacement and joint opening. By assigning corresponding weights to each indicator ( , , ), and multiply by the corresponding measured value (A i , b i 、c i ), and then sum them up to quantify the safety performance. The size of the weight reflects the relative importance of each indicator in evaluating safety performance.

[0133] Economic indicator objective function as follows:

[0134] = ;

[0135] This function takes into account the total cost of different construction stages. For M construction stages, the total construction cost of each stage is , and assign corresponding weight coefficients to each total cost . Through weighted summation, the economic indicators of the entire project are comprehensively evaluated.

[0136] Construction period objective function as follows:

[0137] = ;

[0138] This function focuses on the construction period. For M construction stages, the total construction period of each stage is p i , and assign corresponding weight coefficient q i . Through weighted summation, the overall construction period target value is obtained.

[0139] Once these objective functions are input into the multi-objective optimization algorithm, the algorithm searches through multiple design alternatives to find the best design that optimizes these objectives simultaneously.

[0140] In step S430, the multi-objective optimization algorithm searches in the solution space of various underground assembly structure design solutions to generate a series of possible design solution solutions, and for each solution, calculates the corresponding three objective function values.

[0141] The solution space is the combination of all possible design solutions. This space is defined according to the design requirements and constraints, including the possible value ranges of various parameters and variables.

[0142] Searching for design solutions: Next, the algorithm will perform an efficient search in the solution space. It may use genetic algorithms, particle swarm optimization, or other advanced optimization methods to quickly locate possible high-quality design solutions in the vast design space.

[0143] For each possible design solution found during the search process, the algorithm will calculate the corresponding safety performance objective function, economic index objective function and construction period objective function. These values ​​will serve as an important basis for evaluating the pros and cons of the design solution.

[0144] Step S440, screening out non-dominated solutions from all solutions, that is, solutions for which no other solution is superior in all objectives.

[0145] In step S440, the algorithm will filter out non-dominated solutions from all possible design solutions generated in step S430. The so-called "non-dominated solution" refers to a solution in the solution set that is not "dominated" or "better" than any other solution in all objective functions (safety performance, economic indicators and construction period in this example). In other words, no other solution can perform better than this solution in all objective functions.

[0146] This screening process is done by comparing the performance of all solutions on various objective functions. If a solution performs no worse than any other solution on a certain objective and is better than at least one other solution on at least one objective, then the solution is considered a non-dominated solution.

[0147] Assume that there is a set of underground assembly structure design solutions generated by a multi-objective optimization algorithm, and each solution has a corresponding score value in terms of safety, economy and construction period.

[0148] Solution A: Safety 80, Economy 70, Construction period 60;

[0149] Solution B: Safety 75, Economy 85, Construction period 75;

[0150] Solution C: Safety 85, Economy 65, Construction period 70;

[0151] In this example, you can find:

[0152] Solution A is better than Solution B in terms of safety, but inferior to Solution B in terms of economy and construction period.

[0153] Solution B is better than Solution A in terms of economy and construction period, but inferior to Solution A in terms of safety.

[0154] Solution C is better than Solution B in terms of safety, but inferior to Solution B in terms of economy and construction period.

[0155] From the above comparison, we can see that in this simplified example, no solution is better than other solutions in all objectives. Therefore, solutions A, B and C are all non-dominated solutions.

[0156] Step S450, calculating the comprehensive score of each non-dominated solution according to the preset weight ratios of the three objective functions, and selecting the solution with the highest score as the determined optimal underground assembly structure design solution.

[0157] In practical applications, different design objectives (such as safety, economy, and construction period) often have different importance. Therefore, at the beginning of step S450, the weight ratios of the three objective functions need to be preset. These ratios reflect the decision maker's preference and importance for each objective.

[0158] The comprehensive score of each non-dominated solution is calculated as follows: A comprehensive score is calculated for each non-dominated solution according to the preset weight ratio. This score is obtained by multiplying the performance value of the solution on each objective function with its corresponding weight and then adding these products. The comprehensive score reflects the overall performance of the solution in meeting each design goal.

[0159] Among all non-dominated solutions, the solution with the highest comprehensive score is selected as the optimal underground assembly structure design solution. This solution is considered to be the optimal solution that best meets the design requirements after considering the trade-offs and compromises between multiple design objectives.

[0160] Assume that after step S440, three non-dominated solutions are screened out: A, B and C. These three solutions have different performances in terms of safety performance, economic indicators and construction period.

[0161] In order to determine the optimal design solution, we first need to set the weight ratio of the objective function. For example, suppose safety performance is the most important (weight is set to 0.5), followed by economic indicators (weight is set to 0.3), and finally construction period (weight is set to 0.2).

[0162] Next, calculate the composite score for each non-dominated solution:

[0163] The comprehensive score of solution A = safety performance value × 0.5 + economic index value × 0.3 + construction period value × 0.2.

[0164] The comprehensive score of solution B = safety performance value × 0.5 + economic index value × 0.3 + construction period value × 0.2.

[0165] The comprehensive score of solution C = safety performance value × 0.5 + economic index value × 0.3 + construction period value × 0.2.

[0166] By comparing the comprehensive scores of the three solutions, the solution with the highest score (assumed to be solution B) is selected as the optimal underground assembly structure design solution.

[0167] Reference Figure 4 , the acquisition of the preset weight ratios of the three objective functions includes:

[0168] Step S451, obtaining weather condition information within the planned construction time range of the underground assembly structure.

[0169] In order to obtain accurate weather information, it can be collected through a variety of channels, including but not limited to official forecasts from the Meteorological Bureau, historical weather data analysis, field visits, and the use of professional meteorological service software or API interfaces. The weather information collected should include but not be limited to key parameter data of temperature, humidity, rainfall, wind speed, wind direction, and special weather phenomena (such as haze, sandstorms, etc.).

[0170] Step S452, determining the weight distribution ratios of the three objective functions according to the corresponding relationship between the corresponding key parameter data ranges into which the data of the key parameters contained in the weather condition information fall and the weight distribution ratios of the three objective functions.

[0171] The key parameters of weather condition information include rainfall, temperature, wind speed, humidity, etc.

[0172] The weight distribution ratios of the three objective functions are determined as follows: taking the corresponding key parameter data range within which the data of the key parameters contained in the weather condition information falls as the query object, querying and obtaining the weight distribution ratios of the three objective functions from a preset database that stores the corresponding key parameter data range within which the data of the key parameters contained in the weather condition information falls and the corresponding relationship between the weight distribution ratios of the three objective functions.

[0173] For example, rainfall can be divided into light rain (0-10mm / day), moderate rain (10-25mm / day), heavy rain (25-50mm / day) and rainstorm (greater than 50mm / day). For light rain, the safety performance weight may be set at 30%, the economic index weight at 40%, and the construction period weight at 30%; in moderate rain, the safety performance weight is increased to 40%, the economic index weight at 30%, and the construction period weight at 30%; in heavy rain, the safety performance weight is further increased to 50%, the economic index weight at 25%, and the construction period weight at 25%; in rainstorm, the safety performance weight may reach 60%, the economic index weight at 20%, and the construction period weight at 20%.

[0174] A method for optimizing underground assembly structures further includes steps after extracting key response index data of the underground assembly structure under earthquake action and before calculating the mean and standard deviation of the key response index data, which are specifically as follows:

[0175] Step Sa00, obtaining the sample data volume for analyzing the reliability index.

[0176] The sample data volume includes the data volume related to the mechanical properties of the underground assembly structure, the data volume about the material characteristics, the data volume of the load on the structure, and the quantity of geometric dimension measurement or design data of the underground assembly structure.

[0177] The data related to the mechanical properties of underground assembly structures include the measured or calculated data of mechanical properties such as strength, stiffness, stability, etc. For example, the compressive strength value of components obtained through experiments, the overall bending stiffness of the structure, etc.

[0178] The amount of data about material properties, such as the material's elastic modulus, Poisson's ratio, yield strength, etc. This data is usually obtained through material testing or information provided by the supplier.

[0179] The amount of data on the loads acting on the structure includes relevant data on static loads (such as the dead weight of the structure, the weight of fixed equipment, etc.), live loads (loads generated by personnel activities, temporarily stacked goods, etc.) and dynamic loads (such as wind loads, earthquake effects, etc.).

[0180] The number of geometric measurements or design data of underground assembly structures, such as the length, width, height of components, size and location of holes, etc.

[0181] Suppose in an underground assembly structure project, for mechanical properties, 50 sets of component strength test data were collected; for material properties, there were performance data of 30 different batches of materials; for loads, the load distribution data under 20 different working conditions were statistically analyzed; for geometric dimensions, the dimensional data of 100 key parts were measured. Then, summarizing the number of these data, we can get the sample data volume for analyzing the reliability index.

[0182] Step Sb00, if the sample data volume of the reliability index exceeds the preset sample quantity threshold, then according to the key random variables affecting the reliability of the underground assembly structure, a probability distribution function is specified for each random variable.

[0183] Key random variables include uncertainty in material strength (such as the compressive strength of concrete and the yield strength of steel), changes in loads (such as the magnitude and direction of seismic loads and the intensity of wind loads), deviations in geometric dimensions (the difference between the actual dimensions of a component and its designed dimensions), etc.

[0184] According to the characteristics of random variables, historical data, engineering experience, etc., select a suitable probability distribution function for each random variable. Common probability distribution functions include normal distribution (applicable to many variables such as material strength and load), uniform distribution (applicable to some variables with a certain range but relatively uniform distribution), lognormal distribution (applicable to some positively skewed data, such as the durability index of some materials), etc.

[0185] Assume that for the random variable of concrete compressive strength, based on a large amount of test data and engineering experience, it is considered to conform to normal distribution. Its mean is determined to be 30MPa and its standard deviation is 5MPa. For the magnitude of earthquake load, it may be considered to conform to log-normal distribution based on the earthquake history and geological conditions of the area.

[0186] Step Sc00, using a random number generator to generate a large number of random sample combinations according to the probability distribution of random variables.

[0187] In this step, a random number generator is used to generate a large number of random sample combinations according to the probability distribution previously specified for the key random variables.

[0188] A random number generator is a tool or algorithm that can generate random numbers that conform to a specific probability distribution. Through it, corresponding random values ​​can be generated according to the probability distribution function of each key random variable, and then these random values ​​are combined together to form a complete random sample combination.

[0189] For example, if there are two key random variables, one is material strength (assumed to follow a normal distribution) and the other is load magnitude (assumed to follow a log-normal distribution). The random number generator will generate a random value for material strength and a random value for load magnitude based on these two distribution functions, and these two values ​​will form a simple random sample combination.

[0190] This process is repeated to generate a large number of such random sample combinations to fully cover all possible situations.

[0191] For example: Assume that the mean of the normal distribution of material strength is 50MPa, the standard deviation is 5MPa, and the mean of the logarithmic normal distribution of load size is 10kN, and the standard deviation is 2kN. The random number generator may generate a set of random sample combinations, such as material strength of 52MPa and load size of 11kN; another set may be material strength of 48MPa, load size of 9kN, etc. By generating enough such combinations, a rich data foundation is provided for subsequent simulation analysis.

[0192] Step Sd00, substitute each random sample combination into the established nonlinear dynamic analysis model, re-perform the earthquake response simulation, and calculate and obtain a new earthquake response simulation result.

[0193] First, the established nonlinear dynamic analysis model is a mathematical or numerical model constructed based on actual design parameters and physical properties, which can reflect the mechanical behavior of the structure under earthquake action.

[0194] The random variable values ​​(such as material properties, load magnitude, etc.) in each random sample combination are then input into the model to simulate the response of the structure when subjected to an earthquake under these specific conditions.

[0195] Through simulation calculation, new structural response data such as structural displacement, stress, strain, etc. can be obtained.

[0196] Assume that a finite element model of an underground assembly structure has been established. A random sample combination is generated with a specific value for material strength and another specific value for seismic load. After entering these values ​​into the model and performing a simulation, the displacement of the structure vertex is calculated to be 20 cm, the stress of some key components reaches 150 MPa, etc. These are the new structural responses.

[0197] Step Se00, judging whether each calculated structural response meets the requirement according to the preset structural performance requirement standard.

[0198] The pre-set structural performance requirement standards are based on relevant building codes, design criteria and specific project needs. These standards may include the maximum allowable displacement of the structure, the maximum stress or strain limit, the bearing capacity requirements of the components, etc. During the judgment process, the calculated structural response (such as displacement, stress, strain, etc.) is compared with the corresponding performance requirement standards.

[0199] Assume that the pre-set structural performance requirement standard stipulates that under the action of an earthquake, the vertex displacement of the underground assembly structure shall not exceed 30 cm, and the stress of a key component shall not exceed its yield stress. For a calculated structural response, if the vertex displacement is 25 cm and the stress of the key component does not reach the yield stress, then the structural response is judged to meet the requirements; if the vertex displacement is 35 cm or the stress of the key component exceeds the yield stress, then the structural response is judged to not meet the requirements.

[0200] Step Sf00, statistics are collected on all simulation results, and the number of samples that meet the performance requirements is recorded.

[0201] In this step, all simulation results need to be comprehensively statistically processed.

[0202] First, check one by one the judgment results of whether each structural response meets the requirements in step Se00.

[0203] Then, record the number of samples that meet the performance requirements. This recording process needs to be accurate to ensure that no sample judgment result is missed. When doing statistics, spreadsheet software or specialized statistical analysis tools may be used to assist in order to improve efficiency and accuracy.

[0204] Assume that there are 1,000 earthquake response simulation results, and after judgment, 850 of them meet the pre-set structural performance requirements. Then the number of samples that meet the performance requirements is recorded as 850.

[0205] Step Sg00, calculating the ratio of the number of samples that meet the performance requirements to the total number of samples as the reliability, and determining the reliability index according to the mapping relationship between the reliability and the reliability index.

[0206] In this step, the ratio of the number of samples that meet the performance requirements to the total number of samples is first calculated, and this ratio is defined as reliability.

[0207] Reliability reflects the proportion of all simulated situations in which the structure can meet the performance requirements. For example, if there are a total of 1000 samples and 800 of them meet the performance requirements, then the reliability is 800 / 1000=0.8.

[0208] Then, the reliability index is determined based on the mapping relationship between the reliability and the reliability index determined in advance. This mapping relationship is usually established based on the theory of probability statistics and a large amount of engineering practice experience.

[0209] For example, assuming that the reliability index corresponding to the reliability value of 0.8 is 2.0, the corresponding reliability index is searched in the mapping relationship table or function according to the calculated reliability value.

[0210] The reliability index is a quantitative value used to measure the reliability of underground assembly structures under given conditions. The higher the reliability index, the more reliable the structure is.

[0211] Step Sh00: If the sample data volume of the reliability indicator is less than or equal to the preset sample quantity threshold, the original setting is maintained.

[0212] A method for optimizing underground assembly structures further includes steps after extracting key response index data of the underground assembly structure under earthquake action and before calculating the mean and standard deviation of the key response index data, which are specifically as follows:

[0213] Obtain sample data volume for analyzing reliable indicators and weather condition information within the planned construction time range of the underground assembly structure, wherein the sample data volume includes data volume related to the mechanical properties of the underground assembly structure, data volume on material properties, data volume on the load borne by the structure, and the amount of geometric dimension measurement or design data of the underground assembly structure.

[0214] If the amount of sample data of the reliability index exceeds the preset sample quantity threshold and / or the data of the key parameters contained in the future weather condition information falls into the extreme range of the preset parameters, then the key random variables affecting the reliability of the underground assembly structure are determined and their probability distribution functions are specified for each random variable.

[0215] The preset sample quantity threshold is a value set in advance based on experience, engineering requirements or statistical analysis methods. When the amount of sample data obtained for analyzing reliability indicators (including data related to the mechanical properties, material properties, loads on the structure, geometric dimensions, etc. of the underground assembly structure) is greater than this threshold, it means that there is enough data to conduct a more accurate and complex reliability analysis.

[0216] For example, if the preset sample quantity threshold is set to 500, and the actual amount of sample data obtained is 800, then the condition that "the amount of sample data of the reliability indicator exceeds the preset sample quantity threshold" is met.

[0217] Key parameters of future weather conditions may include rainfall, temperature, wind speed, etc. The extreme range of preset parameters is a range set in advance based on factors such as the nature of the project, the geographical environment and the characteristics of the structure.

[0218] For example, for a key parameter such as rainfall, the preset extreme range may be a single-day rainfall of more than 100 mm. If the future weather forecast shows that a single-day rainfall of 150 mm is likely during a certain construction period, it will fall within the extreme range of the preset parameter.

[0219] For example, for the temperature parameter, the preset extreme low temperature range may be below -10°C. If the weather forecast indicates that the temperature may drop to -15°C during construction, it also falls within the extreme range of the preset parameter.

[0220] When at least one of the above two conditions is met, a series of subsequent operations such as specifying probability distribution functions based on key random variables will be performed to more accurately evaluate the reliability of the underground assembly structure.

[0221] Using a random number generator, a large number of random sample combinations are generated according to the probability distribution of random variables.

[0222] Each random sample combination is substituted into the established nonlinear dynamic analysis model, the seismic response simulation is re-performed, and new seismic response simulation results are calculated.

[0223] According to the preset structural performance requirement standards, it is judged whether each calculated structural response meets the requirements.

[0224] Statistics are collected for all earthquake response simulation results, and the number of samples that meet the performance requirements is recorded.

[0225] The ratio of the number of samples that meet the performance requirements to the total number of samples is calculated as the reliability, and the reliability index is determined based on the mapping relationship between the reliability and the reliability index.

[0226] Otherwise, the original settings are maintained.

[0227] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0228] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store video tag processing data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an underground assembly structure optimization method is implemented.

[0229] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing underground assembly structure, characterized in that: include: Acquire data related to urban stratum properties; wherein the data related to urban stratum properties include: data related to soil mechanical properties, data related to liquefiable strata, and data on superstructure layout parameters; According to the relevant data of urban stratum properties and the use requirements of underground assemblies, on the basis of meeting the preset design conditions and constraints, the structural system, component type and layout within the pre-stored range are traversed to construct a variety of underground prefabricated structure design schemes; the use requirements of underground assemblies include: the use function, space requirements and bearing capacity of underground assemblies; Conduct earthquake response simulations on a variety of underground prefabricated structure design schemes to obtain earthquake-related index data of different underground prefabricated structure design schemes under earthquake conditions, and determine the comprehensive earthquake-resistant capacity values ​​of different underground prefabricated structure design schemes based on the corresponding relationship between the data ranges of different earthquake-resistant index data and the earthquake-resistant capacity values ​​and the weight ratios of different earthquake-resistant index data; According to various underground assembly structure design schemes and multi-objective optimization models, the preset multi-objective optimization algorithm is used to determine the optimal underground assembly structure design scheme; According to various underground assembly structure design schemes and multi-objective optimization models, the preset multi-objective optimization algorithm is used to determine the optimal underground assembly structure design scheme, including: Obtain the data involved in the preset multi-objective optimization algorithm; Input the constructed safety performance objective function, economic index objective function and construction period objective function into the preset multi-objective optimization algorithm; A multi-objective optimization algorithm is used to search in the solution space of various underground assembly structure design schemes to generate a series of design solution solutions. For each solution, the corresponding safety performance objective function, economic index objective function and construction period objective function are calculated. Filter out non-dominated solutions from all solutions; According to the weight ratio of the preset safety performance objective function, economic index objective function and construction period objective function, the comprehensive score of each non-dominated solution is calculated, and the solution with the highest score is selected as the optimal underground assembly structure design solution; The process of determining the weight ratio of the preset safety performance objective function, economic index objective function and construction period objective function specifically includes: Obtain weather condition information for the planned underground assembly structure construction time range; According to the corresponding relationship between the corresponding key parameter data range within which the key parameter data contained in the weather condition information falls and the weight distribution ratio of the three objective functions, the weight ratio of the preset safety performance objective function, economic indicator objective function and construction period objective function is determined.

2. The underground assembly structure optimization method according to claim 1, characterized in that: The method further comprises: determining the optimal underground assembly structure design scheme based on a plurality of underground assembly structure design schemes and a multi-objective optimization model by using a preset multi-objective optimization algorithm; and then further comprising: Obtain historical earthquake data; Construct a geomechanical model of the geological environment where the underground assembly is located based on the geological survey data and geological structural characteristics of the target area; The optimal underground assembly structure design scheme is used to establish a refined model of the underground assembly structure using nonlinear finite element analysis software, and then imported into the geomechanics model to form a complete nonlinear dynamic analysis model; According to the preset representative seismic wave selection conditions, representative seismic waves are selected from historical seismic data, and the seismic waves are adjusted according to different seismic intensities. The adjusted seismic waves are input into the nonlinear dynamic analysis model to perform seismic response simulation and obtain seismic response simulation results; According to the seismic response simulation results, the key response index data of the optimal underground assembly structure design scheme under seismic action are extracted, and the mean and standard deviation of the key response index data are calculated; Calculate the limit state function value according to the mean and standard deviation of the key response indicator data and the preset limit state function of the key response indicator data; According to the limit state function value, combined with the mean and standard deviation of the key response indicator data, the reliability index is determined according to the preset reliability index calculation formula; Determine whether the reliability index exceeds the preset target reliability index; If yes, the current optimal underground assembly structure design scheme is used as the optimal underground assembly structure design scheme for this time; If not, the current optimal underground assembly structure design scheme is excluded, and the process jumps to the step of determining the optimal underground assembly structure design scheme according to a plurality of underground assembly structure design schemes and a multi-objective optimization model using a preset multi-objective optimization algorithm, and the optimal underground assembly structure design scheme is re-formed, and it is determined whether the reliability index exceeds the preset target reliability index; Repeat the above steps until the reliability index of the re-formed optimal underground assembly structure design scheme exceeds the preset target reliability index, and determine the corresponding optimal underground assembly structure design scheme as the optimal underground assembly structure design scheme this time.

3. The underground assembly structure optimization method according to claim 2, characterized in that: The method also includes steps after extracting the key response index data of the optimal underground assembly structure design scheme under the earthquake action according to the earthquake response simulation results and before calculating the mean and standard deviation of the key response index data, which are as follows: The amount of sample data for obtaining reliable indicators for analysis; the amount of sample data includes the amount of data related to the mechanical properties of the underground assembly structure, the amount of data on material properties, the amount of data on the loads on the structure, and the amount of geometrical dimension measurements or design data of the underground assembly structure; If the sample data volume of the reliability index exceeds the preset sample quantity threshold, the key random variables affecting the reliability of the underground assembly structure are used, and the probability distribution function is specified for each random variable; Using a random number generator, a large number of random sample combinations are generated according to the probability distribution of random variables; Substitute each random sample combination into the established nonlinear dynamic analysis model, re-simulate the earthquake response, and calculate new earthquake response simulation results; According to the pre-set structural performance requirements, determine whether each calculated earthquake response simulation result meets the requirements; Collect statistics on all earthquake response simulation results and record the number of samples that meet the performance requirements; The ratio of the number of samples that meet the performance requirements to the total number of samples is taken as the reliability, and the reliability index is determined based on the mapping relationship between the reliability and the reliability index; If the sample data volume of the reliability indicator is less than or equal to the preset sample quantity threshold, the original setting is maintained.

4. The underground assembly structure optimization method according to claim 1, characterized in that: The method also includes steps after extracting the key response index data of the optimal underground assembly structure design scheme under the earthquake action according to the earthquake response simulation results and before calculating the mean and standard deviation of the key response index data, which are as follows: Obtain the sample data volume for analyzing reliable indicators and weather condition information within the planned construction time range of the underground assembly structure; the sample data volume includes the data volume related to the mechanical properties of the underground assembly structure, the data volume on material properties, the data volume on the loads borne by the structure, and the quantity of geometric dimension measurements or design data of the underground assembly structure; If the amount of sample data of the reliability index exceeds the preset sample quantity threshold and / or the data of the key parameters contained in the future weather condition information falls within the limit range of the preset parameters, then according to the key random variables affecting the reliability of the underground assembly structure, a probability distribution function is specified for each random variable; Using a random number generator, a large number of random sample combinations are generated according to the probability distribution of random variables; Substitute each random sample combination into the established nonlinear dynamic analysis model, re-simulate the earthquake response, and calculate new earthquake response simulation results; According to the pre-set structural performance requirements, determine whether each calculated earthquake response simulation result meets the requirements; Collect statistics on all earthquake response simulation results and record the number of samples that meet the performance requirements; Calculate the ratio of the number of samples that meet the performance requirements to the total number of samples as the reliability, and determine the reliability index based on the mapping relationship between the reliability and the reliability index; If the earthquake response simulation results do not meet the performance requirements, the original settings are maintained.

5. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the underground assembly structure optimization method according to any one of claims 1 to 4.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the underground assembly structure optimization method described in any one of claims 1 to 4 is implemented.

Images