Intelligent optimization method of subgrade structure based on fusion of clustering analysis and particle swarm algorithm

Abstract

The application discloses a subgrade structure intelligent optimization method fusing clustering analysis and a particle swarm algorithm, relates to the technical field of subgrade structure optimization design, and comprises the following steps: based on an original subgrade structure model, dividing a subgrade structure cross section, and determining cross section characteristic data corresponding to the subgrade structure cross section; clustering the cross section characteristic data, and dividing the cross section characteristic data into corresponding data clusters; based on the cross section characteristic data in the data clusters, determining corresponding subgrade work point intervals; based on optimal cross section measures of the data clusters, determining measure attribute parameters and measure mileage direction information of the subgrade work point intervals corresponding to the data clusters; and based on the measure attribute parameters and the measure mileage direction information, constructing a new subgrade structure model. In the foregoing manner, the characteristic data of all subgrade structure cross sections are clustered, and then optimal cross section measures of each cluster of the subgrade structure are quickly and accurately searched, so that an optimized subgrade structure is obtained.

Description

Technical Field

[0001] This application relates to the field of roadbed structure optimization design technology, and in particular to an intelligent optimization method for roadbed structures that integrates cluster analysis and particle swarm optimization algorithm. Background Technology

[0002] Existing methods for optimizing roadbed structures primarily use the roadbed cross-section as the basic unit, employing component types and attributes from a specific cross-section design drawing to describe the design scheme of the roadbed structure within a certain range. This approach can only express a small portion of the characteristic parameters of the roadbed structural layers. Therefore, the accuracy of the roadbed structure design is determined by the cross-section spacing and the number of cross-sections; the denser the cross-section spacing, the higher the design accuracy. However, this process often consumes a significant amount of calculation time for designers, and due to the lack of strict cross-section division standards, the final design scheme is often not optimal.

[0003] Currently, structural optimization uses mathematical results and numerical computation methods to find the optimal choice. Modern optimization algorithms, such as genetic algorithms, simulated annealing, and their hybrid strategies, are frequently used in structural optimization design, characterized by strong algorithmic practicality and high computational efficiency. However, due to the strong correlation between roadbed structure and terrain data, its structural form exhibits significant irregularity. Directly applying modern optimization algorithms to roadbed structure optimization design requires constructing a large amount of cross-sectional data for numerical computation. Furthermore, the theoretically obtained optimal solutions still need to undergo manual processing before final adoption, consuming substantial computational and human resources.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide an intelligent optimization method for roadbed structures that integrates cluster analysis and particle swarm optimization, aiming to solve the technical problems of existing roadbed structure optimization design consuming a large amount of computational resources, having low data utilization, and low computational efficiency.

[0006] To achieve the above objectives, this application provides a method for intelligent optimization of roadbed structures that integrates cluster analysis and particle swarm optimization. The method includes:

[0007] Based on the original roadbed structure model, the roadbed structure cross sections are divided, and the cross section feature data corresponding to the roadbed structure cross sections are determined.

[0008] The cross-sectional feature data is clustered to divide the cross-sectional feature data into corresponding data clusters;

[0009] Based on the cross-sectional feature data in the data cluster, the corresponding roadbed construction point intervals are determined;

[0010] Based on the factors affecting the roadbed structure, the optimal cross-sectional measures for the data cluster are determined;

[0011] Based on the optimal cross-section measures of the data cluster, determine the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster;

[0012] Based on the attribute parameters of the measures and the mileage and orientation information of the measures, a new roadbed structure model is constructed to obtain an optimized roadbed structure.

[0013] In one embodiment, the step of clustering the cross-sectional feature data and dividing the cross-sectional feature data into corresponding data clusters includes:

[0014] Select a target clustering strategy from the preset clustering strategies. The preset clustering strategies include at least mean clustering strategy, hierarchical clustering strategy, and density clustering strategy.

[0015] Based on the target clustering strategy, the data clusters corresponding to the cross-sectional feature data are determined, and the cross-sectional feature data are divided into the corresponding data clusters. The cross-sectional feature data includes at least location data, linear feature data, and geological feature data. The linear feature data includes at least roadbed type, slope type, slope level, slope height, slope ratio, and platform width. The geological feature data includes at least environmentally sensitive areas, adverse geological conditions, stratigraphic lithology, and geological structures within the cross-section.

[0016] In one embodiment, the target clustering strategy is a mean clustering strategy, and the step of determining the data clusters corresponding to the cross-sectional feature data based on the target clustering strategy and dividing the cross-sectional feature data into the corresponding data clusters includes:

[0017] A preset number of initial cluster centers are randomly selected from the cross-sectional feature data, and the similarity between the cross-sectional feature data and the initial cluster centers is determined.

[0018] Based on the similarity between the cross-sectional feature data and the initial cluster center, the initial cluster center corresponding to the cross-sectional feature data is determined;

[0019] The cross-sectional feature data are divided into data clusters corresponding to the initial cluster centers;

[0020] Based on the cross-sectional feature data in the data cluster, the mean data of the data cluster is determined, and the mean data is used as the cluster center of the data cluster.

[0021] When the cluster center of the data cluster is the same as the initial cluster center, the clustering is considered complete, and a preset number of data clusters and the cluster centers of the data clusters are obtained.

[0022] When the cluster center of the data cluster is different from the initial cluster center, the initial cluster center of the data cluster is updated to the corresponding cluster center, and the process returns to the step of determining the similarity between the cross-sectional feature data and the initial cluster center.

[0023] In one embodiment, before the step of determining the corresponding roadbed construction point interval based on the cross-sectional feature data in the data cluster, the method further includes:

[0024] Evaluation data is selected from the cross-sectional feature data, and evaluation indicators for the evaluation data are determined.

[0025] When the evaluation index of the evaluation data is greater than or equal to the preset index threshold, it is determined that the quality and rationality of the clustering meet the preset requirements, and the step of determining the roadbed construction point interval corresponding to the data cluster is performed based on the cross-sectional feature data in the data cluster.

[0026] When the evaluation index of the evaluation data is less than the preset index threshold, it is determined that the clustering quality and clustering rationality do not meet the preset requirements. The target clustering strategy is optimized or a new target clustering strategy is selected from the preset clustering strategies. The process returns to the step of determining the data cluster corresponding to the cross-sectional feature data based on the target clustering strategy and dividing the cross-sectional feature data into the corresponding data cluster.

[0027] In one embodiment, the step of determining the corresponding roadbed construction point interval based on the cross-sectional feature data in the data cluster includes:

[0028] Based on the location data corresponding to the cross-sectional feature data in the data cluster, determine the starting mileage and ending mileage of the roadbed construction point interval;

[0029] Based on the cluster centers of the data clusters, the characteristic attribute information of the roadbed construction site intervals is determined. The characteristic attribute information includes at least roadbed information, slope information, and geological information.

[0030] In one embodiment, the number of roadbed construction site intervals is determined based on the division influencing factors, which include at least the roadbed length and topographic and geological conditions.

[0031] In one embodiment, the step of determining the optimal cross-sectional measures for the data cluster based on roadbed structure influencing factors includes:

[0032] Based on the particle swarm optimization strategy, under the conditions of roadbed structure influencing factors, measure objectives, and measure constraints, the optimal cross-sectional measures corresponding to the cross-sectional feature data in the data cluster are determined. The optimal cross-sectional measures include at least the optimal roadbed retaining measures, the optimal slope protection measures, and the optimal foundation reinforcement measures. The roadbed structure influencing factors include at least stability influencing factors and economic influencing factors.

[0033] In one embodiment, after the step of determining the optimal cross-section measure corresponding to the cross-section feature data in the data cluster based on the particle swarm strategy, under the conditions of roadbed structure influencing factors, measure objectives, and measure constraints, the method further includes:

[0034] The optimal cross-section measures are evaluated to determine whether their quality and rationality meet the preset requirements.

[0035] When the quality and rationality of the optimal cross-section measures meet the preset requirements, the optimal cross-section measures based on the data cluster are executed, and the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster are determined.

[0036] When the quality and rationality of the optimal cross-section measures do not meet the preset requirements, the key parameters of the particle swarm strategy are optimized, and the process returns to the step of determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster based on the particle swarm strategy, under the conditions of roadbed structure influencing factors, measure objectives and measure constraints. The key parameters include at least the number of particles, inertia weight and acceleration factor.

[0037] In one embodiment, the step of dividing the roadbed structure cross-section based on the original roadbed structure model and determining the cross-sectional feature data corresponding to the roadbed structure cross-section further includes:

[0038] Extract key foundational data from both network and local data;

[0039] Based on the aforementioned key basic data, the original roadbed structure model is constructed. The key basic data includes at least route data, terrain data, geological data, and roadbed construction site data.

[0040] In one embodiment, the step of dividing the roadbed structure cross-section based on the original roadbed structure model includes:

[0041] Based on the route data and the terrain data, determine the straight and gentle sections and the undulating sections in the original roadbed structure model;

[0042] Get the preset division interval;

[0043] Based on the pre-defined intervals after thinning, the cross-section of the roadbed structure in the straight and gentle section is determined;

[0044] Based on the encrypted preset division interval, the cross section of the roadbed structure in the undulating section of the curve is determined.

[0045] Furthermore, to achieve the above objectives, this application also proposes an intelligent optimization device for roadbed structures that integrates cluster analysis and particle swarm optimization algorithms. The intelligent optimization device for roadbed structures that integrates cluster analysis and particle swarm optimization algorithms includes:

[0046] The clustering analysis module is used to divide the roadbed structure cross sections based on the original roadbed structure model and determine the cross section feature data corresponding to the roadbed structure cross sections.

[0047] The clustering analysis module is also used to cluster the cross-sectional feature data and divide the cross-sectional feature data into corresponding data clusters;

[0048] The particle swarm optimization module is used to determine the corresponding roadbed construction point intervals based on the cross-sectional feature data in the data cluster.

[0049] The particle swarm optimization module is also used to determine the optimal cross-sectional measures for the data cluster based on the influencing factors of the roadbed structure.

[0050] The particle swarm optimization module is also used to determine the measure attribute parameters and measure mileage orientation information of the roadbed work point interval corresponding to the data cluster based on the optimal cross-section measures of the data cluster.

[0051] The structure optimization module is used to construct a new roadbed structure model based on the attribute parameters of the measures and the mileage and orientation information of the measures, so as to obtain an optimized roadbed structure.

[0052] Furthermore, to achieve the above objectives, this application also proposes a roadbed structure intelligent optimization device that integrates cluster analysis and particle swarm optimization algorithm. The roadbed structure intelligent optimization device that integrates cluster analysis and particle swarm optimization algorithm includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the roadbed structure intelligent optimization method that integrates cluster analysis and particle swarm optimization algorithm as described above.

[0053] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization as described above.

[0054] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization as described above.

[0055] This application provides an intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization. Based on the original roadbed structure model, the method divides the roadbed structure into cross-sections and determines the corresponding cross-sectional feature data. The cross-sectional feature data is then clustered into corresponding data clusters. Based on the cross-sectional feature data in the data clusters, the corresponding roadbed work point intervals are determined. Based on the roadbed structure influencing factors, the optimal cross-sectional measures for each data cluster are determined. Based on the optimal cross-sectional measures for each data cluster, the measure attribute parameters and measure mileage orientation information for the corresponding roadbed work point intervals are determined. Based on the measure attribute parameters and measure mileage orientation information, a new roadbed structure model is constructed to obtain the optimized roadbed structure. This application groups the data set of roadbed cross sections into multiple clusters according to certain correlations, and transforms the data instances in different clusters into corresponding component types and component attributes. This allows for the aggregation of complex data, standardization of complex structural data, and the concrete representation of multiple clusters. Each cluster can represent the cross-sectional characteristics within a certain continuous range. Simultaneously, considering factors such as the stability and economy of the roadbed structure, the optimal cross-sectional measures for each cluster of the roadbed structure are quickly and accurately searched based on the particle swarm optimization algorithm. The final result is assigned to the entire cluster, ultimately achieving the goal of structural optimization. This solves the technical problems of roadbed structure optimization design consuming large amounts of computational resources, low data utilization, and low computational efficiency, improving the computational efficiency of roadbed structure optimization design, increasing data utilization, and realizing intelligent optimization of roadbed structures. Attached Figure Description

[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0057] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart illustrating an embodiment of the intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization in this application.

[0059] Figure 2A schematic diagram of the clustering principle of the intelligent optimization method for roadbed structure that integrates clustering analysis and particle swarm optimization provided in Embodiment 1 of this application;

[0060] Figure 3 A schematic diagram of the clustering process of the intelligent optimization method for roadbed structure that integrates clustering analysis and particle swarm optimization provided in Embodiment 1 of this application;

[0061] Figure 4 A schematic diagram of the particle swarm optimization process for the intelligent optimization method of roadbed structure that integrates clustering analysis and particle swarm algorithm provided in Embodiment 1 of this application;

[0062] Figure 5 This is a schematic diagram of the module structure of the intelligent optimization device for roadbed structure that integrates cluster analysis and particle swarm optimization algorithm according to an embodiment of this application.

[0063] Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the intelligent optimization of roadbed structure that integrates cluster analysis and particle swarm optimization in the embodiments of this application.

[0064] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0065] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0066] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0067] The main solution of this application embodiment is as follows: Based on the original roadbed structure model, the roadbed structure cross sections are divided, and the cross section feature data corresponding to the roadbed structure cross sections are determined; the cross section feature data is clustered and divided into corresponding data clusters; based on the cross section feature data in the data clusters, the corresponding roadbed work point intervals are determined; based on the roadbed structure influencing factors, the optimal cross section measures for the data clusters are determined; based on the optimal cross section measures for the data clusters, the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point intervals of the data clusters are determined; based on the measure attribute parameters and measure mileage orientation information, a new roadbed structure model is constructed to obtain an optimized roadbed structure.

[0068] This application provides a solution that groups the data set of roadbed cross sections into multiple clusters according to certain correlations, and converts data instances in different clusters into corresponding component types and component attributes. This allows for the aggregation of complex data, standardization of complex structural data, and the representation of multiple clusters. Each cluster can represent the cross-sectional characteristics within a certain continuous range. Simultaneously, considering factors such as the stability and economy of the roadbed structure, the optimal cross-sectional measures for each cluster of the roadbed structure are quickly and accurately searched based on the particle swarm optimization algorithm. The final result is assigned to the entire cluster, ultimately achieving the goal of structural optimization. This solution solves the technical problems of roadbed structure optimization design consuming large amounts of computational resources, low data utilization, and low computational efficiency, improving the computational efficiency of roadbed structure optimization design, increasing data utilization, and realizing intelligent optimization of roadbed structures.

[0069] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone; or an electronic device capable of performing the above functions, or a roadbed structure intelligent optimization device integrating cluster analysis and particle swarm optimization algorithms, etc. This embodiment does not specifically limit it in this way. The following uses a roadbed structure intelligent optimization device integrating cluster analysis and particle swarm optimization algorithms as an example to describe this embodiment and the following embodiments.

[0070] This application provides an intelligent optimization method for roadbed structures that integrates cluster analysis and particle swarm optimization, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization in this application.

[0071] In this embodiment, the intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization includes steps S10 to S60:

[0072] Step S10: Based on the original roadbed structure model, divide the roadbed structure cross sections and determine the cross section feature data corresponding to the roadbed structure cross sections.

[0073] It should be noted that the original roadbed structure model refers to the preliminary roadbed structure model, which still needs further optimization. The roadbed structure cross section refers to a representative cross section selected from the original roadbed structure model.

[0074] Additionally, it should be noted that each roadbed structure cross-section has a large amount of relevant data. Cross-sectional characteristic data refers to the data within this data that can be used to describe the characteristics of the roadbed structure cross-section. Cross-sectional characteristic data includes at least location data, linear characteristic data, and geological characteristic data. Location data refers to the location of the roadbed structure cross-section. Linear characteristic data includes at least the roadbed form, slope type, slope grade, slope height, slope ratio, and platform width. Geological characteristic data includes at least the environmentally sensitive areas, adverse geological conditions, stratigraphic lithology, and geological structure within the cross-section area.

[0075] In one feasible implementation, steps S01 to S02 may be included before step S10:

[0076] Step S01: Obtain key basic data from network data and local data;

[0077] It should be noted that network data refers to relevant professional data that can be provided through network services, local data refers to relevant data stored locally, and key basic data refers to the key basic information that can be used to construct the roadbed structure model, including at least route data, terrain data, geological data, and roadbed construction site data.

[0078] It should be understood that geological data and roadbed construction site data can determine the cross-sectional characteristic data corresponding to the roadbed structure cross section, as shown in Table 1, and can be used as the data source for subsequent cluster analysis and particle swarm algorithm calculations.

[0079] Table 1

[0080]

[0081] Step S02: Based on the key basic data, construct the original roadbed structure model.

[0082] It is understandable that key basic data is obtained from network data and local data in order to construct the original roadbed structure model.

[0083] In one feasible implementation, the step of dividing the roadbed structure cross-section based on the original roadbed structure model may include steps S101 to S102:

[0084] Step S101: Based on the route data and the terrain data, determine the straight and gentle sections and the undulating sections in the original roadbed structure model;

[0085] It should be noted that "straight and flat sections" refers to sections where the route is straight and the terrain is relatively flat, while "curved and undulating sections" refers to sections where the route is curved and the terrain is more undulating. Based on the route data and terrain data, straight and flat sections and curved and undulating sections can be identified respectively.

[0086] Step S102: Obtain the preset division interval, determine the roadbed structure cross section in the straight and gentle section based on the thinned preset division interval, and determine the roadbed structure cross section in the curved and undulating section based on the densified preset division interval.

[0087] It should be noted that the preset division interval refers to the initial interval set for dividing the cross-section of the roadbed structure. It usually needs to be flexibly adjusted according to the route conditions and terrain conditions. In other words, the interval for dividing the roadbed cross-section can be determined based on the route data and terrain data.

[0088] Understandably, the intervals used to divide the roadbed cross sections in straight, flat sections and curved, undulating sections are usually different. For straight, flat sections, the intervals for dividing the roadbed cross sections can be appropriately reduced, while for curved, undulating sections, the intervals can be appropriately increased. In other words, it is usually necessary to use the reduced preset intervals to determine the roadbed cross sections in straight, flat sections and the increased preset intervals to determine the roadbed cross sections in curved, undulating sections. This allows for control of the number of roadbed cross sections while ensuring that the selection of roadbed cross sections is more representative.

[0089] In this embodiment, key basic data such as route data, terrain data, geological data, and roadbed construction site data are obtained through network data or local data. These data are then processed appropriately to generate an original roadbed structure model, determine the roadbed structure cross-section and related data for each cross-section, select appropriate feature data to describe the characteristics of the cross-section, and obtain the cross-sectional feature data of each roadbed structure cross-section.

[0090] Step S20: Cluster the cross-sectional feature data and divide the cross-sectional feature data into corresponding data clusters;

[0091] It should be noted that clustering of cross-sectional feature data involves dividing the data into several clusters based on the similarity between them, as shown in the reference. Figure 2 The principle of partitioning is to maximize intra-cluster similarity and minimize inter-cluster similarity. After the cross-sectional feature data is partitioned, the corresponding roadbed structure cross-sections can naturally be clustered.

[0092] In one feasible implementation, step S20 may include steps S201 to S202:

[0093] Step S201: Select a target clustering strategy from the preset clustering strategies. The preset clustering strategies include at least mean clustering strategy, hierarchical clustering strategy, and density clustering strategy.

[0094] It should be noted that the preset clustering strategy refers to the pre-set clustering algorithms that can be used, including at least mean clustering, hierarchical clustering, and density clustering. The mean clustering strategy can be k-means clustering, and the density clustering strategy can be DBSCAN. This embodiment does not impose specific limitations on this. The target clustering strategy is the clustering algorithm currently selected, which can be chosen from the preset clustering strategies.

[0095] Step S202: Based on the target clustering strategy, determine the data clusters corresponding to the cross-sectional feature data, and divide the cross-sectional feature data into the corresponding data clusters.

[0096] It should be noted that the selected clustering algorithm is used to perform clustering analysis on the cross-sectional feature data. The algorithm assigns the cross-sectional feature data to different clusters based on the similarity between them.

[0097] In one feasible implementation, if the target clustering strategy is a mean clustering strategy, then step S202 may include steps S2021 to S2025:

[0098] Step S2021: Randomly select a preset number of initial cluster centers from the cross-sectional feature data, and determine the similarity between the cross-sectional feature data and the initial cluster centers;

[0099] It should be noted that this embodiment uses the k-means clustering algorithm as an example. The preset number can be set according to actual needs. The initial cluster centers refer to the initially determined cluster centers, and the final cluster centers of each cluster need to be further determined later.

[0100] It is understandable that k samples are selected as the initial cluster centers μ from a cross-sectional feature data of quantity n. k Using variable r nk x represents the feature data of a single cross section n For cluster center μ k The similarity between the cross-sectional feature data and the initial cluster centers is calculated using the following formula:

[0101] E = argmin j ||x n -μ j || 2

[0102] In the formula, E represents the similarity, and x n Represents cross-sectional feature data, μ j Let j represent the j-th initial cluster center.

[0103] Step S2022: Based on the similarity between the cross-sectional feature data and the initial cluster center, determine the initial cluster center corresponding to the cross-sectional feature data;

[0104] Understandably, if the similarity calculation result meets the set threshold, then the cross-sectional feature data x will be... n Assigned to the initial cluster center with the highest similarity, r nk Assign a value of 1, otherwise r nk The value is assigned to 0.

[0105] Step S2023: Divide the cross-sectional feature data into data clusters corresponding to the initial cluster centers;

[0106] It is understandable that cross-sectional feature data should be assigned to the data cluster containing the initial cluster center with the highest similarity.

[0107] Step S2024: Based on the cross-sectional feature data in the data cluster, determine the mean data of the data cluster, and use the mean data as the cluster center of the data cluster;

[0108] It should be noted that after all the data has been partitioned, the cluster centers need to be redefined for each data cluster. Typically, the mean of all data points in the cluster is used as the cluster center, and the calculation formula is shown below:

[0109]

[0110] In the formula, μ k This represents the mean data, i.e., the calculated cluster centers, x. n Represents cross-sectional feature data, r nk x represents the feature data of a single cross section n For cluster center μ k Its ownership.

[0111] Step S2025: When the cluster center of the data cluster is the same as the initial cluster center, clustering is determined to be complete, and a preset number of data clusters and their cluster centers are obtained; when the cluster center of the data cluster is different from the initial cluster center, the initial cluster center of the data cluster is updated to the corresponding cluster center, and the process returns to the step of determining the similarity between the cross-sectional feature data and the initial cluster center.

[0112] It should be noted that if the latest calculated cluster center is the same as the initial cluster center, it means that the clustering is complete and the cross-sectional feature data in the data cluster has been divided, and the next step can be carried out; if the latest calculated cluster center is different from the initial cluster center, it means that the clustering is not complete. Substitute the latest calculated cluster center into the above-mentioned initial cluster center, return to step S2021, recalculate the similarity, and redivide the cross-sectional feature data.

[0113] In this embodiment, reference Figure 3 Given n cross-sectional feature data, randomly select k initial cluster centers, calculate the similarity between each cross-sectional feature data and the cluster centers, assign the cross-sectional feature data to the data cluster containing the cluster center with the highest similarity, use the mean of all data in each data cluster as the new cluster center, compare it with the previous cluster centers, if the cluster center changes, re-cluster based on the new cluster center, if the cluster center does not change, the cluster analysis is complete, and output the data clusters and their cluster centers.

[0114] In one feasible implementation, before step S30, the following steps may be included: selecting evaluation data from the cross-sectional feature data and determining the evaluation index of the evaluation data; when the evaluation index of the evaluation data is greater than or equal to a preset index threshold, determining that the quality and rationality of the clustering meet preset requirements, and executing the step of determining the roadbed construction point interval corresponding to the data cluster based on the cross-sectional feature data in the data cluster; when the evaluation index of the evaluation data is less than the preset index threshold, determining that the clustering quality and clustering rationality do not meet preset requirements, optimizing the target clustering strategy or reselecting the target clustering strategy from the preset clustering strategies, returning to the step of determining the data cluster corresponding to the cross-sectional feature data based on the target clustering strategy, and dividing the cross-sectional feature data into the corresponding data cluster.

[0115] It should be noted that after clustering is completed, it is also necessary to evaluate the quality and rationality of the clustering results, using internal or external evaluation metrics to assess the results.

[0116] Additionally, it should be noted that the evaluation data refers to the data selected for evaluation from the cross-sectional characteristic data, typically randomly chosen from a data cluster. The evaluation index refers to the calculated numerical value used for evaluation, which can be calculated using the following formula:

[0117]

[0118] In the formula, P represents the evaluation index, and c j Indicates the evaluation data, w iThe evaluation index represents the data cluster to which the evaluation data belongs. The evaluation index ranges from [0, 1], with a larger index indicating a better clustering effect. The preset requirement is the expected requirement. The preset index threshold is a pre-set threshold for the evaluation index. If the evaluation index is greater than or equal to the preset index threshold, the quality and rationality of the clustering can be considered to meet the expected requirements. If the evaluation index is less than the preset index threshold, the quality and rationality of the clustering can be considered to not meet the expected requirements.

[0119] Understandably, the clustering analysis results and evaluation indicators are used to determine whether the expected requirements are met. This involves examining characteristic data such as the roadbed type and geological attributes of the samples within the data clusters, and verifying whether the data cluster division and the data within each cluster conform to the design intent. If there are issues with the quality and rationality of the clustering results, adjustments can be made to the parameters of the selected clustering algorithm, the cross-sectional feature weights, improvements to the clustering analysis algorithm, or the selection of a new clustering algorithm to enhance the quality and rationality of the clustering analysis results. The process then returns to step S201 to re-perform the clustering until the clustering meets the expectations.

[0120] Step S30: Based on the cross-sectional feature data in the data cluster, determine the corresponding roadbed construction point interval;

[0121] In one feasible implementation, step S30 may include steps S301 to S302:

[0122] Step S301: Determine the starting mileage and ending mileage of the roadbed construction point interval based on the location data corresponding to the cross-sectional feature data in the data cluster.

[0123] It should be noted that cross-sectional feature data can be extracted from each data cluster and abstracted into a specific interval of roadbed work points, i.e., a roadbed work point interval. The starting mileage of the interval is the starting mileage of each roadbed work point interval, and the ending mileage of the interval is the ending mileage of each roadbed work point interval.

[0124] Understandably, based on the cluster analysis results, all cross-sectional feature data in the data cluster are extracted, and the location data in each cross-sectional feature data is traversed to abstract the data cluster into the corresponding roadbed construction point interval. At this time, the roadbed construction point interval contains information such as the starting mileage and ending mileage of the interval.

[0125] Step S302: Based on the cluster center of the data cluster, determine the characteristic attribute information of the roadbed construction site interval. The characteristic attribute information includes at least roadbed information, slope information, and geological information.

[0126] It should be noted that roadbed information refers to the cross-sectional form within the roadbed construction site section, such as the roadbed type; slope information refers to the geometric dimensions of the slope within the roadbed construction site section, such as the slope height; and geological information refers to the geological feature data within the roadbed construction site section.

[0127] It is understandable that the relevant data of the cluster center of the data cluster is assigned to the corresponding roadbed construction point interval. At this time, the roadbed construction point interval contains data such as cross-sectional form, slope geometry, and geological information. Thus, the roadbed construction point can be divided into multiple interval segments with different characteristic attributes. Table 2 shows an example of the relevant information contained in the roadbed construction point interval.

[0128] Table 2

[0129]

[0130] It should be understood that the number of roadbed work sections is determined based on the influencing factors, which include at least the roadbed length and topographic and geological conditions. The number of sections is jointly determined by factors such as roadbed length and topographic and geological conditions.

[0131] In this embodiment, cross-sectional feature data is extracted from each data cluster and abstracted into corresponding roadbed work point intervals. The roadbed work point intervals include attribute information such as starting mileage, ending mileage, cross-sectional form, and geometric dimensions.

[0132] Step S40: Based on the factors affecting the roadbed structure, determine the optimal cross-sectional measures for the data cluster.

[0133] In one feasible implementation, step S40 may include: based on the particle swarm strategy, under the conditions of roadbed structure influencing factors, measure objectives and measure constraints, determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster, wherein the optimal cross-section measures include at least the optimal roadbed retaining measures, the optimal slope protection measures and the optimal foundation reinforcement measures, and the roadbed structure influencing factors include at least stability influencing factors and economic influencing factors.

[0134] It should be noted that the particle swarm strategy refers to the particle swarm optimization algorithm. In this embodiment, the particle swarm optimization algorithm is used to determine the optimal cross-sectional measures for each data cluster. The optimal cross-sectional measures include at least the optimal roadbed retaining measures, the optimal slope protection measures, and the optimal foundation reinforcement measures. The applicability of all roadbed retaining measures, slope protection measures, and foundation reinforcement measures in the roadbed work area is calculated sequentially to determine the optimal roadbed retaining measures, slope protection measures, and foundation reinforcement measures.

[0135] Understandably, based on the particle swarm optimization algorithm, considering factors such as the stability and economy of the roadbed structure, the objective functions and constraints of roadbed support measures (gravity retaining walls, buttress retaining walls, cantilever retaining walls, pile-slab walls), slope protection measures (slope height, slope ratio, slope protection, platform), and foundation reinforcement measures (composite foundation, pile-slab structure) are defined. Based on the calculated optimal solution, the optimal cross-sectional measures for each data cluster are determined.

[0136] It should be understood that, for different orientations (left and right sides) of the roadbed cross section, the stability index K and economic index F of different measures are calculated. By comprehensively comparing the stability index and economic index, the applicable roadbed retaining measures and slope protection measures are obtained. Similarly, for foundation reinforcement measures, for the geological characteristics within the interval, the stability index K and economic index F of different foundation reinforcement measures are calculated. By comprehensively comparing the stability index K and economic index F, the applicable foundation reinforcement measures are obtained.

[0137] In this embodiment, reference Figure 4 Input relevant data (subgrade type, geological properties, and measure type), and based on constraints (design parameters and design criteria) and objective functions (stability calculation function and economic calculation function), use the particle swarm optimization algorithm to output the optimal cross-section measures, design parameters, stability indicators, and economic indicators after comprehensive comparison.

[0138] In one feasible implementation, step S40 may include: evaluating the optimal cross-section measures to determine whether the quality and rationality of the optimal cross-section measures meet preset requirements; when the quality and rationality of the optimal cross-section measures meet the preset requirements, executing the optimal cross-section measures based on the data cluster to determine the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster; when the quality and rationality of the optimal cross-section measures do not meet the preset requirements, optimizing the key parameters of the particle swarm strategy, and returning to execute the step of determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster based on the particle swarm strategy under the conditions of roadbed structure influencing factors, measure objectives, and measure constraints, wherein the key parameters include at least the number of particles, inertia weight, and acceleration factor.

[0139] Understandably, the calculation results (optimal cross-section measures) of the particle swarm optimization algorithm, which iterates through all data clusters, are evaluated for their rationality and accuracy through methods such as objective function values, convergence analysis, and multiple experimental runs. If the quality and rationality of the optimal cross-section measures do not meet the preset requirements, i.e., there are problems with the quality and rationality of the calculation results, it is necessary to test and optimize key parameters such as the number of particles, inertia weight, and acceleration factor to improve the performance of the algorithm and the accuracy of the results, thereby improving the quality and rationality of the calculation results. The optimized particle swarm optimization algorithm is then used to redetermine the optimal cross-section measures until the quality and rationality meet the preset requirements. If the quality and rationality of the optimal cross-section measures meet the preset requirements, then step S50 is continued.

[0140] Step S50: Based on the optimal cross-section measures of the data cluster, determine the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster.

[0141] It should be noted that the measure attribute parameters are the attribute parameters of each measure, and the measure mileage and orientation information are the mileage and orientation information of each measure.

[0142] Understandably, based on the optimal cross-sectional measures for each data cluster, the attribute parameters and mileage and orientation information of various roadbed retaining, slope protection, and foundation reinforcement measures used within the roadbed construction point section can be obtained.

[0143] Step S60: Based on the measure attribute parameters and measure mileage orientation information, construct a new roadbed structure model to obtain an optimized roadbed structure.

[0144] Table 3

[0145]

[0146] Understandably, the attribute parameters and mileage / orientation information of various roadbed support, slope protection, and foundation reinforcement measures adopted in the data cluster are summarized, as shown in Table 3. The summarized mileage / orientation information and attribute parameters of the measures are assigned to the original roadbed structure model, so that the roadbed work points can complete the modeling according to the optimized parameter data, resulting in a new roadbed structure model, and ultimately realizing intelligent optimization of the roadbed structure.

[0147] This embodiment provides an intelligent optimization method for roadbed structure that integrates cluster analysis and particle swarm optimization. Based on the original roadbed structure model, the method divides the roadbed structure into cross-sections and determines the cross-sectional feature data corresponding to each cross-section. The cross-sectional feature data is then clustered into corresponding data clusters. Based on the cross-sectional feature data in the data clusters, the corresponding roadbed work point intervals are determined. Based on the roadbed structure influencing factors, the optimal cross-sectional measures for each data cluster are determined. Based on the optimal cross-sectional measures for each data cluster, the measure attribute parameters and measure mileage orientation information for the corresponding roadbed work point intervals are determined. Based on the measure attribute parameters and measure mileage orientation information, a new roadbed structure model is constructed to obtain the optimized roadbed structure. The data set of roadbed cross sections is grouped into multiple clusters according to certain correlations. Data instances in different clusters are transformed into corresponding component types and component attributes. This allows for the aggregation of complex data, standardization of complex structural data, and the representation of multiple clusters. Each cluster can represent the cross-sectional characteristics within a certain continuous range. Simultaneously, considering factors such as the stability and economy of the roadbed structure, the optimal cross-sectional measures for each cluster of the roadbed structure are quickly and accurately searched based on the particle swarm optimization algorithm. The final result is assigned to the entire cluster, ultimately achieving the goal of structural optimization. This solves the technical problems of roadbed structure optimization design consuming large amounts of computational resources, low data utilization, and low computational efficiency, improving the computational efficiency of roadbed structure optimization design, increasing data utilization, and realizing intelligent optimization of roadbed structures.

[0148] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the intelligent optimization of roadbed structure that integrates cluster analysis and particle swarm optimization algorithm. Any simple transformations based on this technical concept are within the protection scope of this application.

[0149] This application also provides an intelligent optimization device for roadbed structures that integrates cluster analysis and particle swarm optimization. Please refer to [link / reference]. Figure 5 The intelligent optimization device for roadbed structure integrating cluster analysis and particle swarm optimization includes:

[0150] The clustering analysis module 10 is used to divide the roadbed structure cross sections based on the original roadbed structure model and determine the cross section feature data corresponding to the roadbed structure cross sections.

[0151] The clustering analysis module 10 is also used to cluster the cross-sectional feature data and divide the cross-sectional feature data into corresponding data clusters.

[0152] The particle swarm computing module 20 is used to determine the corresponding roadbed construction point intervals based on the cross-sectional feature data in the data cluster.

[0153] The particle swarm computing module 20 is also used to determine the optimal cross-sectional measures for the data cluster based on the influencing factors of the roadbed structure.

[0154] The particle swarm computing module 20 is also used to determine the measure attribute parameters and measure mileage orientation information of the roadbed work point interval corresponding to the data cluster based on the optimal cross-section measures of the data cluster.

[0155] The structure optimization module 30 is used to construct a new roadbed structure model based on the measure attribute parameters and the measure mileage orientation information to obtain an optimized roadbed structure.

[0156] In one embodiment, the clustering analysis module 10 is further configured to select a target clustering strategy from preset clustering strategies, wherein the preset clustering strategies include at least mean clustering strategy, hierarchical clustering strategy and density clustering strategy.

[0157] Based on the target clustering strategy, the data clusters corresponding to the cross-sectional feature data are determined, and the cross-sectional feature data are divided into the corresponding data clusters. The cross-sectional feature data includes at least location data, linear feature data, and geological feature data. The linear feature data includes at least roadbed type, slope type, slope level, slope height, slope ratio, and platform width. The geological feature data includes at least environmentally sensitive areas, adverse geological conditions, stratigraphic lithology, and geological structures within the cross-section.

[0158] In one embodiment, the clustering analysis module 10 is further configured to randomly select a preset number of initial cluster centers from the cross-sectional feature data and determine the similarity between the cross-sectional feature data and the initial cluster centers;

[0159] Based on the similarity between the cross-sectional feature data and the initial cluster center, the initial cluster center corresponding to the cross-sectional feature data is determined;

[0160] The cross-sectional feature data are divided into data clusters corresponding to the initial cluster centers;

[0161] Based on the cross-sectional feature data in the data cluster, the mean data of the data cluster is determined, and the mean data is used as the cluster center of the data cluster.

[0162] When the cluster center of the data cluster is the same as the initial cluster center, the clustering is considered complete, and a preset number of data clusters and the cluster centers of the data clusters are obtained.

[0163] When the cluster center of the data cluster is different from the initial cluster center, the initial cluster center of the data cluster is updated to the corresponding cluster center, and the process returns to the step of determining the similarity between the cross-sectional feature data and the initial cluster center.

[0164] In one embodiment, the particle swarm computing module 20 is further configured to determine that the quality and rationality of the clustering meet the preset requirements when the evaluation index of the evaluation data is greater than or equal to the preset index threshold, and to perform the step of determining the roadbed construction point interval corresponding to the data cluster based on the cross-sectional feature data in the data cluster;

[0165] When the evaluation index of the evaluation data is less than the preset index threshold, it is determined that the clustering quality and clustering rationality do not meet the preset requirements. The target clustering strategy is optimized or a new target clustering strategy is selected from the preset clustering strategies. The process returns to the step of determining the data cluster corresponding to the cross-sectional feature data based on the target clustering strategy and dividing the cross-sectional feature data into the corresponding data cluster.

[0166] In one embodiment, the particle swarm calculation module 20 is further configured to determine the starting mileage and ending mileage of the roadbed construction point interval based on the location data corresponding to the cross-sectional feature data in the data cluster.

[0167] Based on the cluster centers of the data clusters, the characteristic attribute information of the roadbed construction site intervals is determined. The characteristic attribute information includes at least roadbed information, slope information, and geological information.

[0168] In one embodiment, the number of roadbed construction site intervals is determined based on the division influencing factors, which include at least the roadbed length and topographic and geological conditions.

[0169] In one embodiment, the particle swarm computing module 20 is further configured to determine, based on the particle swarm strategy, the optimal cross-sectional measures corresponding to the cross-sectional feature data in the data cluster under the conditions of roadbed structure influencing factors, measure objectives, and measure constraints. The optimal cross-sectional measures include at least the optimal roadbed retaining measures, the optimal slope protection measures, and the optimal foundation reinforcement measures. The roadbed structure influencing factors include at least stability influencing factors and economic influencing factors.

[0170] In one embodiment, the particle swarm computing module 20 is further configured to evaluate the optimal cross-section measures and determine whether the quality and rationality of the optimal cross-section measures meet preset requirements;

[0171] When the quality and rationality of the optimal cross-section measures meet the preset requirements, the optimal cross-section measures based on the data cluster are executed, and the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster are determined.

[0172] When the quality and rationality of the optimal cross-section measures do not meet the preset requirements, the key parameters of the particle swarm strategy are optimized, and the process returns to the step of determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster based on the particle swarm strategy, under the conditions of roadbed structure influencing factors, measure objectives and measure constraints. The key parameters include at least the number of particles, inertia weight and acceleration factor.

[0173] In one embodiment, the clustering analysis module 10 is further configured to obtain key basic data from network data and local data;

[0174] Based on the aforementioned key basic data, the original roadbed structure model is constructed. The key basic data includes at least route data, terrain data, geological data, and roadbed construction site data.

[0175] In one embodiment, the clustering analysis module 10 is further configured to determine the straight and gentle sections and the undulating sections in the original roadbed structure model based on the route data and the terrain data.

[0176] Get the preset division interval;

[0177] Based on the pre-defined intervals after thinning, the cross-section of the roadbed structure in the straight and gentle section is determined;

[0178] Based on the encrypted preset division interval, the cross section of the roadbed structure in the undulating section of the curve is determined.

[0179] The intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm provided in this application, employing the intelligent roadbed structure optimization method integrating clustering analysis and particle swarm optimization algorithm as described in the above embodiments, can solve the technical problems of roadbed structure optimization design consuming large amounts of computational resources, low data utilization, and low computational efficiency. Compared with the prior art, the beneficial effects of the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm provided in this application are the same as those of the intelligent roadbed structure optimization method integrating clustering analysis and particle swarm optimization algorithm provided in the above embodiments, and other technical features in the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0180] This application provides a roadbed structure intelligent optimization device that integrates clustering analysis and particle swarm optimization algorithm. The roadbed structure intelligent optimization device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the roadbed structure intelligent optimization that integrates clustering analysis and particle swarm optimization algorithm as described in the first embodiment above.

[0181] The following is for reference. Figure 6 This document illustrates a structural schematic diagram of a roadbed structure intelligent optimization device suitable for implementing the embodiments of this application, which integrates clustering analysis and particle swarm optimization algorithms. The roadbed structure intelligent optimization device integrating clustering analysis and particle swarm optimization algorithms in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and vehicle-mounted terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 6 The intelligent optimization device for roadbed structure that integrates cluster analysis and particle swarm optimization algorithm shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0182] like Figure 6 As shown, the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithms may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in read-only memory (ROM) 1002 or the program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithms. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the roadbed structure intelligent optimization device integrating clustering analysis and particle swarm optimization algorithms to exchange data with other devices wirelessly or via wired communication. Although the figure shows a roadbed structure intelligent optimization device integrating clustering analysis and particle swarm optimization algorithms with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0183] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0184] The intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm provided in this application, employing the intelligent roadbed structure optimization method integrating clustering analysis and particle swarm optimization algorithm as described in the above embodiments, can solve the technical problems of roadbed structure optimization design consuming large amounts of computational resources, low data utilization, and low computational efficiency. Compared with the prior art, the beneficial effects of the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm provided in this application are the same as those of the intelligent roadbed structure optimization method integrating clustering analysis and particle swarm optimization algorithm provided in the above embodiments, and other technical features in this intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization algorithm are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0185] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0186] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0187] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to perform intelligent optimization of roadbed structure by fusing clustering analysis and particle swarm optimization algorithm in the above embodiments.

[0188] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0189] The aforementioned computer-readable storage medium may be included in the intelligent optimization device for roadbed structure that integrates cluster analysis and particle swarm optimization algorithm; or it may exist independently and not be assembled into the intelligent optimization device for roadbed structure that integrates cluster analysis and particle swarm optimization algorithm.

[0190] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the intelligent roadbed structure optimization device integrating clustering analysis and particle swarm optimization, the device performs the following: based on the original roadbed structure model, it divides the roadbed structure cross sections and determines the corresponding cross section feature data; it clusters the cross section feature data, assigning it to corresponding data clusters; based on the cross section feature data in the data clusters, it determines the corresponding roadbed work point intervals; based on the roadbed structure influencing factors, it determines the optimal cross section measures for the data clusters; based on the optimal cross section measures for the data clusters, it determines the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point intervals for the data clusters; based on the measure attribute parameters and measure mileage orientation information, it constructs a new roadbed structure model to obtain the optimized roadbed structure.

[0191] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0192] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0193] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0194] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for performing the intelligent optimization of roadbed structure using the fusion of clustering analysis and particle swarm optimization algorithm described above. This solves the technical problems of roadbed structure optimization design consuming large amounts of computational resources, having low data utilization, and low computational efficiency. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the intelligent optimization of roadbed structure using the fusion of clustering analysis and particle swarm optimization algorithm provided in the above embodiments, and will not be elaborated upon here.

[0195] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of intelligent optimization of roadbed structure by fusing cluster analysis and particle swarm optimization as described above.

[0196] The computer program product provided in this application can solve the technical problems of high computational resource consumption, low data utilization, and low computational efficiency in roadbed structure optimization design. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the intelligent optimization of roadbed structures by fusing clustering analysis and particle swarm optimization algorithms provided in the above embodiments, and will not be elaborated here.

[0197] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for intelligent optimization of roadbed structure integrating cluster analysis and particle swarm optimization, characterized in that, The method includes: Based on the original roadbed structure model, the roadbed structure cross sections are divided, and the cross section feature data corresponding to the roadbed structure cross sections are determined. The cross-sectional feature data is clustered to divide the cross-sectional feature data into corresponding data clusters; Based on the cross-sectional feature data in the data cluster, the corresponding roadbed construction point intervals are determined; Based on the factors affecting the roadbed structure, the optimal cross-sectional measures for the data cluster are determined, specifically including: based on the particle swarm strategy, under the conditions of factors affecting the roadbed structure, the objectives of the measures, and the constraints of the measures, the optimal cross-sectional measures corresponding to the cross-sectional feature data in the data cluster are determined. The optimal cross-sectional measures include at least the optimal roadbed retaining measures, the optimal slope protection measures, and the optimal foundation reinforcement measures. The factors affecting the roadbed structure include at least the stability factors and the economic factors. Based on the optimal cross-section measures of the data cluster, determine the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster; Based on the attribute parameters of the measures and the mileage and orientation information of the measures, a new roadbed structure model is constructed to obtain an optimized roadbed structure; Following the step of determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster based on the particle swarm optimization strategy, under the conditions of roadbed structure influencing factors, measure objectives, and measure constraints, the method further includes: The optimal cross-section measures are evaluated to determine whether their quality and rationality meet the preset requirements. When the quality and rationality of the optimal cross-section measures meet the preset requirements, the optimal cross-section measures based on the data cluster are executed, and the measure attribute parameters and measure mileage orientation information of the corresponding roadbed work point interval of the data cluster are determined. When the quality and rationality of the optimal cross-section measures do not meet the preset requirements, the key parameters of the particle swarm strategy are optimized, and the process returns to the step of determining the optimal cross-section measures corresponding to the cross-section feature data in the data cluster based on the particle swarm strategy, under the conditions of roadbed structure influencing factors, measure objectives and measure constraints. The key parameters include at least the number of particles, inertia weight and acceleration factor.

2. The method as described in claim 1, characterized in that, The step of clustering the cross-sectional feature data and dividing the cross-sectional feature data into corresponding data clusters includes: Select a target clustering strategy from the preset clustering strategies. The preset clustering strategies include at least mean clustering strategy, hierarchical clustering strategy, and density clustering strategy. Based on the target clustering strategy, the data clusters corresponding to the cross-sectional feature data are determined, and the cross-sectional feature data are divided into the corresponding data clusters. The cross-sectional feature data includes at least location data, linear feature data, and geological feature data. The linear feature data includes at least roadbed type, slope type, slope level, slope height, slope ratio, and platform width. The geological feature data includes at least environmentally sensitive areas, adverse geological conditions, stratigraphic lithology, and geological structures within the cross-section.

3. The method as described in claim 2, characterized in that, The target clustering strategy is the mean clustering strategy. The step of determining the data clusters corresponding to the cross-sectional feature data based on the target clustering strategy and dividing the cross-sectional feature data into the corresponding data clusters includes: A preset number of initial cluster centers are randomly selected from the cross-sectional feature data, and the similarity between the cross-sectional feature data and the initial cluster centers is determined. Based on the similarity between the cross-sectional feature data and the initial cluster center, the initial cluster center corresponding to the cross-sectional feature data is determined; The cross-sectional feature data are divided into data clusters corresponding to the initial cluster centers; Based on the cross-sectional feature data in the data cluster, the mean data of the data cluster is determined, and the mean data is used as the cluster center of the data cluster. When the cluster center of the data cluster is the same as the initial cluster center, the clustering is considered complete, and a preset number of data clusters and the cluster centers of the data clusters are obtained. When the cluster center of the data cluster is different from the initial cluster center, the initial cluster center of the data cluster is updated to the corresponding cluster center, and the process returns to the step of determining the similarity between the cross-sectional feature data and the initial cluster center.

4. The method as described in claim 2, characterized in that, Before the step of determining the corresponding roadbed construction point interval based on the cross-sectional feature data in the data cluster, the method further includes: Evaluation data is selected from the cross-sectional feature data, and evaluation indicators for the evaluation data are determined. When the evaluation index of the evaluation data is greater than or equal to the preset index threshold, it is determined that the quality and rationality of the clustering meet the preset requirements, and the step of determining the roadbed construction point interval corresponding to the data cluster is performed based on the cross-sectional feature data in the data cluster. When the evaluation index of the evaluation data is less than the preset index threshold, it is determined that the clustering quality and clustering rationality do not meet the preset requirements. The target clustering strategy is optimized or a new target clustering strategy is selected from the preset clustering strategies. The process returns to the step of determining the data cluster corresponding to the cross-sectional feature data based on the target clustering strategy and dividing the cross-sectional feature data into the corresponding data cluster.

5. The method as described in claim 1, characterized in that, The step of determining the corresponding roadbed construction point interval based on the cross-sectional feature data in the data cluster includes: Based on the location data corresponding to the cross-sectional feature data in the data cluster, determine the starting mileage and ending mileage of the roadbed construction point interval; Based on the cluster centers of the data clusters, the characteristic attribute information of the roadbed construction site intervals is determined. The characteristic attribute information includes at least roadbed information, slope information, and geological information.

6. The method as described in claim 5, characterized in that, The number of roadbed construction sites is determined based on the influencing factors, which include at least the roadbed length and topographic and geological conditions.

7. The method according to any one of claims 1 to 6, characterized in that, Before the step of dividing the roadbed structure cross-section based on the original roadbed structure model and determining the cross-sectional feature data corresponding to the roadbed structure cross-section, the following steps are also included: Extract key foundational data from both network and local data; Based on the aforementioned key basic data, the original roadbed structure model is constructed. The key basic data includes at least route data, terrain data, geological data, and roadbed construction site data.

8. The method as described in claim 7, characterized in that, The steps for dividing the roadbed structure cross-section based on the original roadbed structure model include: Based on the route data and the terrain data, determine the straight and gentle sections and the undulating sections in the original roadbed structure model; Get the preset division interval; Based on the pre-defined intervals after thinning, the cross-section of the roadbed structure in the straight and gentle section is determined; Based on the encrypted preset division interval, the cross section of the roadbed structure in the undulating section of the curve is determined.

Images