A passenger cableway line design method and system based on finite element analysis
By combining finite element analysis and machine learning, the problem of insufficient safety and economic evaluation in passenger ropeway route design was solved, and the optimal route design scheme was output, thereby improving the quality and efficiency of ropeway engineering.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- BEIJING ZHONGSUOGUOYOU ROPEWAY ENG TECH CO LTD
- Filing Date
- 2026-05-08
- Publication Date
- 2026-06-02
AI Technical Summary
Traditional passenger ropeway route design methods are insufficient for a comprehensive assessment of route safety and economy, resulting in inadequate analysis of the bearing capacity of complex geological structures, which increases construction risks and operational hazards.
Using a finite element analysis-based approach, the feasible region for cableway construction is delineated through geological testing, generating multiple route design schemes. Construction and operation efficiency and perceived risk analysis are conducted, and iterative optimization is performed by combining machine learning and genetic optimization algorithms to output the optimal route design scheme.
It has enabled a comprehensive and accurate assessment and systematic optimization of the safety and economy of passenger cableway lines under complex geological conditions, thereby improving the overall quality and investment benefits of cableway projects.
Smart Images
Figure CN122133413A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of finite element analysis technology, specifically to a passenger ropeway route design method and system based on finite element analysis. Background Technology
[0002] With the rapid development of tourism and mountain transportation, passenger cableways, as an efficient and convenient mode of transportation, have been widely used in scenic areas, mountainous regions, and other areas with complex terrain.
[0003] However, the design of passenger ropeway lines involves many factors such as geological conditions, topography, construction difficulty, and operational safety. Traditional design methods often rely on experience-based judgment and simplified models, making it difficult to comprehensively and accurately assess the safety and economy of the line.
[0004] Specifically, insufficient analysis of the bearing capacity of complex geological structures during route planning may lead to unreasonable selection of cableway support sites, increasing construction risks and operational hazards. Furthermore, traditional methods lack a systematic approach in the comparison and optimization of multiple options, making it difficult to quickly find the optimal route that balances efficiency and safety, thus affecting the overall quality and investment returns of the cableway project. Summary of the Invention
[0005] This application provides a passenger ropeway line design method and system based on finite element analysis, which solves the technical problem that existing passenger ropeway lines are difficult to comprehensively assess in terms of safety and economy, resulting in insufficient analysis of the bearing capacity of complex geological structures, increased construction risks and operational hazards.
[0006] The technical solution to the above-mentioned technical problems in this application is as follows: In a first aspect, this application provides a passenger ropeway route design method based on finite element analysis, the method comprising: The feasible construction zone for the cableway is obtained after geological testing within the target area. The target area is the region where the passenger cableway route is designed. The feasible construction zone for the cableway includes multiple layers of feasible zones, and each layer of feasible zone includes multiple feasible construction points. Multiple first route design schemes are randomly generated within the multi-layered feasible domain, and construction operation efficiency analysis is performed to obtain multiple first construction operation efficiency parameters. Each first route design scheme includes construction feasible points within the multi-layered feasible domain. Based on the geological testing data of multiple feasible construction points within each first route design scheme, a progressive finite element risk assessment analysis of each route segment is conducted to obtain multiple sets of first-perception risk parameters. Based on multiple primary construction and operation efficiency parameters, multiple sets of primary perceived risk parameters are fused and processed. The gene value of each construction feasible point is adjusted to obtain multiple sets of primary finite element gene values. Iterative optimization is then performed until the iterative optimization ends, and the optimal route design scheme is output.
[0007] Secondly, this application provides a passenger ropeway route design system based on finite element analysis, including: The construction area acquisition module is used to acquire the feasible construction area of the cableway within the target area after geological testing. The target area is the area where the passenger cableway route is designed. The feasible construction area includes multiple layers of feasible areas, and each layer of feasible areas includes multiple feasible construction points. The initial scheme generation module is used to randomly generate multiple first route design schemes within the multi-layered feasible domain, perform construction and operation efficiency analysis, and obtain multiple first construction and operation efficiency parameters. Each first route design scheme includes construction feasible points within the multi-layered feasible domain. The risk analysis module is used to perform finite element progressive risk analysis of each section of the line based on geological detection data of multiple construction feasibility points within each first line design scheme, and to obtain multiple sets of first-perceived risk parameters. The scheme optimization module is used to fuse multiple sets of first perceived risk parameters based on multiple first construction and operation efficiency parameters, adjust the gene value of each construction feasibility point, obtain multiple sets of first finite element gene values, and perform iterative optimization until the iterative optimization ends, outputting the optimal route design scheme.
[0008] This application provides one or more technical solutions, which have at least the following technical effects or advantages: This application provides a passenger cableway route design method and system based on finite element analysis. First, geological surveys are conducted on the target area, and the cableway construction feasibility zone is divided into layers according to altitude. Multi-layered feasibility zones and construction feasibility points that meet the support structure construction conditions are selected. Second, multiple first route design schemes are generated by randomly combining construction feasibility points within the multi-layered feasibility zones. Combining the geological survey data and route length of each scheme, the construction time is calculated using a cableway construction database, thereby obtaining first construction operation efficiency parameters and achieving a quantitative evaluation of the efficiency of different initial schemes. Then, based on the geological survey data of the construction feasibility points of each scheme, environmental data is extracted. Using a machine learning-based risk perception analysis agent, finite element risk perception analysis is performed segment by segment starting from the lowest altitude feasibility zone. The risk parameters of the next segment are corrected using a perception asymptotic coefficient, forming multiple sets of first perception risk parameters to capture the potential risks of each segment of the route. Finally, by integrating the first set of construction operation efficiency parameters and the first set of perceived risk parameters, the basic gene values of the feasible construction points are corrected to obtain the first set of finite element gene values. By calculating the line design fitness value, the probability of selecting feasible construction points is updated and iteratively optimized, and finally the optimal line design scheme with the largest design fitness value is converged and output.
[0009] Through the above technical solutions, this application combines finite element analysis, machine learning and gene optimization algorithms to achieve a comprehensive and accurate assessment and systematic optimization of the safety and economy of passenger cableway lines under complex geological conditions. It effectively solves the problems of traditional design methods relying on experience, one-sided evaluation and low optimization efficiency, and improves the overall quality and investment benefits of cableway projects. Attached Figure Description
[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a flowchart illustrating a passenger ropeway route design method based on finite element analysis provided in an embodiment of this application. Figure 2 This is a schematic diagram of a passenger ropeway line design system based on finite element analysis provided in an embodiment of this application.
[0012] The components represented by each number in the attached diagram are explained below: Construction area acquisition module 11, initial scheme generation module 12, risk analysis module 13, scheme optimization module 14. Detailed Implementation
[0013] This application provides a passenger ropeway route design method and system based on finite element analysis, which addresses the technical problem that existing passenger ropeway routes are difficult to comprehensively assess in terms of safety and economy, leading to insufficient analysis of the bearing capacity of complex geological structures, increased construction risks, and operational hazards.
[0014] Example 1, as Figure 1 As shown in the figure, this application provides a passenger ropeway route design method based on finite element analysis, including: S10: Obtain the feasible zone for cableway construction within the target area after geological testing. The target area is the area for designing passenger cableway routes. The feasible zone for cableway construction includes multiple layers of feasible zones, and each layer includes multiple feasible construction points. In this embodiment, geological surveys are conducted on the target area to obtain information such as topographic data, stratigraphic lithology distribution, geological structural characteristics, soil mechanical parameters, and hydrogeological conditions. Then, based on the geological survey data and the construction requirements for the passenger cableway support, such as foundation bearing capacity, slope stability, and groundwater level limitations, the target area is screened, and multiple feasible cableway construction zones are identified.
[0015] Furthermore, the feasible area is divided into layers according to altitude to form a multi-layer feasible area structure. Each layer contains several feasible construction points that meet the basic construction conditions. For example, areas with different altitudes and suitable geological conditions for support construction are divided into different layers, and multiple specific construction locations are identified as feasible construction points within each layer.
[0016] Specifically, step S10 in the method includes: The target area is divided into multiple layers according to altitude, resulting in multi-layered regions. Geological surveys were conducted on the multi-layered areas to screen out locations that met the requirements for cableway support construction, resulting in multiple sets of feasible construction points, which were used as multi-layered feasible regions. Among them, there was one feasible construction point within the feasible region with the highest altitude.
[0017] In this embodiment of the application, firstly, the altitude of the target area is divided into intervals, for example, the target area is divided into multiple regions from low to high according to an interval of 50 meters.
[0018] Secondly, for each layer, geological testing was conducted using methods such as ground-penetrating radar, drilling sampling, and soil mechanics tests to obtain key geological parameters such as foundation bearing capacity, rock integrity coefficient, soil shear strength, and groundwater depth.
[0019] Then, based on the design specifications and construction standards of the cableway support, the screening thresholds for feasible construction points are set, such as the foundation bearing capacity needing to be greater than 250 kPa, the rock integrity coefficient not less than 0.7, and the groundwater level burying depth needing to be 1.5 meters below the bottom surface of the support foundation. The locations that meet the threshold conditions are screened out to form a set of feasible construction points for each layer of the area, thus forming a multi-layer feasible domain.
[0020] In particular, to ensure that the starting or ending point of the cableway is set at a high position to meet the slope requirements, only one optimal construction feasible point, determined through rigorous geological assessment and comprehensive comparison, is retained as the critical endpoint of the line within the feasible area at the highest altitude.
[0021] S20: Randomly generate multiple first route design schemes within the multi-layered feasible domain, perform construction and operation efficiency analysis, and obtain multiple first construction and operation efficiency parameters, wherein each first route design scheme includes construction feasible points within the multi-layered feasible domain; In this embodiment of the application, within the multi-layered feasible domain, a construction feasible point is randomly selected from each feasible domain except for the highest altitude layer, and connected and combined with the fixed construction feasible point of the highest altitude layer to form multiple route paths containing different sequences of construction feasible points, thereby generating multiple first route design schemes.
[0022] Furthermore, for each first route design scheme, the construction time of the support structure within each scheme is analyzed based on geological data, the time for laying the cableway line is analyzed based on the line length, and the total construction time required for the scheme is calculated by matching and mapping the geological data and line length of the current scheme with the data in the database. The total construction time is used as an indicator to measure the construction operation efficiency, thus obtaining multiple first construction operation efficiency parameters.
[0023] Specifically, step S20 in the method includes: Multiple combinations of feasible construction points are selected within the multi-layered feasible domain to obtain multiple first-line design schemes; Geological testing data of multiple feasible construction points within each first route design scheme are obtained to generate multiple first geological testing datasets, and the first route length of each first route design scheme is obtained. Based on multiple primary geological monitoring datasets and multiple primary route lengths, construction operation efficiency analysis was conducted to obtain multiple primary construction operation efficiency parameters.
[0024] In this embodiment, firstly, multiple random samplings are performed within multiple feasible domains under computer program control, except for the highest altitude domain. One feasible construction point is selected from each feasible domain and sequentially connected with the fixed feasible construction point of the highest altitude domain to form a route path containing different combinations of feasible construction points, thereby obtaining multiple first route design schemes.
[0025] For example, if there are 5 feasible regions, with the highest layer having 1 fixed feasible construction point and the other 4 layers each having 10 feasible construction points, then 10×10×10×10=10000 different first route design schemes can be generated by random combination.
[0026] Secondly, for each generated first route design scheme, the geological test data of all construction feasible points included in it are extracted, including parameters such as foundation bearing capacity, rock integrity coefficient, soil shear strength, groundwater depth, and stratum dip angle. The extracted parameters are organized in the order of construction feasible points to form the first geological test dataset corresponding to each scheme.
[0027] Specifically, multiple parameters in the first geological monitoring dataset corresponding to each scheme are standardized for subsequent analysis and calculation. For example, parameters such as foundation bearing capacity, soil shear strength, groundwater depth, and stratum dip angle are converted into standardized values between 0 and 1. The rock integrity coefficient is dimensionless. For example, for positive indicators such as foundation bearing capacity, rock integrity coefficient, and soil shear strength, the standardized value = (actual parameter value - minimum parameter value) / (maximum parameter value - minimum parameter value); for negative indicators such as groundwater depth and stratum dip angle, the standardized value = (maximum parameter value - actual parameter value) / (maximum parameter value - minimum parameter value).
[0028] Meanwhile, using GIS map software or professional surveying tools, based on the coordinate information of each feasible construction point, the horizontal distance and vertical height difference between adjacent feasible construction points in each first route design scheme are calculated. Then, the actual length of each route segment is calculated using the Pythagorean theorem, and the total length of the first route of each scheme is obtained by summing them up.
[0029] Furthermore, based on multiple first geological detection datasets and multiple first route lengths, mapping is performed in the cableway construction database to obtain multiple first support construction time sets and multiple first route construction times for the first route design scheme. The total construction time for each first route design scheme is obtained by summing them up, and the first construction operation efficiency parameter is calculated. The shorter the total construction time, the higher the construction operation efficiency.
[0030] Furthermore, based on multiple primary geological monitoring datasets and multiple primary route lengths, a construction operation efficiency analysis was conducted, yielding multiple primary construction operation efficiency parameters, including: Obtain the cableway construction database, which includes sample geological detection datasets and sample support construction time sets mapped during support construction, as well as sample line length sets and sample line construction time sets mapped during line construction. The multiple first geological detection datasets and multiple first line lengths are respectively combined and input into the cableway construction database, and the multiple first support construction time sets and multiple first line construction times of multiple first line design schemes are mapped and output, and the construction times of multiple first lines are calculated. The first construction operation efficiency parameter was calculated based on the construction time of multiple first lines.
[0031] In this embodiment, since the transportation conditions for cableway construction are fixed, the configuration of construction machinery, material transportation routes, and personnel allocation patterns are pre-defined in the database as standardized procedures. When analyzing construction operation efficiency, a cableway construction database is first constructed. This database is built by collecting historical construction data from a large number of domestic and international passenger cableway projects. It includes sample geological testing datasets and corresponding sample support construction time sets for support structures under different geological conditions, as well as sample line length sets and sample line construction time sets for different line lengths. The sample geological testing datasets include parameters such as foundation bearing capacity and rock integrity coefficient. The database uses a structured storage method and standardizes the data, such as unifying the units and precision of geological parameters, to ensure data consistency and comparability.
[0032] Secondly, the first geological detection dataset and the first line length of each first line design scheme are used as inputs. The database's built-in mapping algorithm, such as the K-nearest neighbor algorithm, is used to find the sample data with the highest similarity to the current first geological detection dataset in the sample geological detection dataset. The corresponding sample support construction time set is obtained and used as the first support construction time set of the scheme. Similarly, the sample line construction time corresponding to the current first line length is obtained from the sample line length set and used as the first line construction time of the scheme.
[0033] Specifically, in the K-nearest neighbor algorithm, K is set to 5. The similarity between data points is measured by calculating Euclidean distance. The average construction time of the five nearest neighbor samples is selected as the first set of construction times for the current scheme. For example... , where x is the standardized parameter vector in the first geological detection dataset, y is the standardized parameter vector in the sample geological detection dataset, and n is the number of geological parameters. For matching the construction time of the line, the linear interpolation method is used to calculate the construction time of the first line based on the interval of the length of the first line within the sample line length set.
[0034] Finally, the construction times of the supports at each feasible point within the first support construction time set are summed to obtain the total support construction time. This total time is then added to the construction time of the first line to obtain the total construction time of each first line design scheme. The first construction operation efficiency parameter is then calculated. For example, the ratio of the average construction time of multiple first lines to the construction time of each first line can be used as the construction operation efficiency.
[0035] For example, a certain first route design includes 5 feasible construction points. After matching the first geological monitoring dataset, the support construction times for each point are 15 days, 12 days, 18 days, 14 days, and 10 days, respectively. The total support construction time is... The first line is 2000 meters long, and the construction time for the first line is 30 days. Therefore, the total construction time for this plan is... .
[0036] If the average total construction time for multiple first-line design schemes is 120 days, then the first construction and operation efficiency parameter of this scheme is: A value greater than 1 indicates that its construction and operation efficiency is higher than the average level.
[0037] S30: Based on the geological testing data of multiple feasible construction points within each first route design scheme, perform finite element-based progressive risk analysis of each route segment to obtain multiple sets of first-perception risk parameters; In this embodiment of the application, for each first route design scheme, starting from the feasible area with the lowest altitude, adjacent feasible construction points are selected in sequence to form route segments, and the perceived risk of each route segment is analyzed to characterize the degree of risk felt by tourists when riding the route.
[0038] Specifically, based on the environmental data of each feasible construction point, such as wind speed and cableway sway as perceived risk parameters, the entire line is analyzed and corrected in sequence to ultimately form a set of multiple first perceived risk parameters for each first line design scheme.
[0039] Specifically, step S30 in the method includes: Based on the geological testing data of multiple feasible construction points within each first route design scheme, environmental data at each feasible construction point is extracted to obtain multiple environmental data sets; Based on multiple first environmental data within the feasible domain with the lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters. Based on multiple second environmental data within the feasible domain with the second lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple second sensing risk parameters. The ratios of the plurality of second perceived risk parameters and the plurality of first perceived risk parameters are calculated respectively, and used as a plurality of perception asymptotic coefficients to correct the next perceived risk parameter and update the perception asymptotic coefficients. Continue to analyze and calculate multiple sets of first-perceived risk parameters from multiple environmental datasets.
[0040] In this embodiment of the application, firstly, parameters related to the cableway operating environment are extracted from the geological monitoring data of multiple feasible construction points included in each first route design scheme, such as the annual average wind speed, maximum instantaneous wind speed, and cableway swaying degree at each feasible construction point. These parameters are then organized in order of the altitude of the feasible construction points to form multiple environmental data sets corresponding to each scheme.
[0041] Secondly, from multiple environmental datasets, environmental data of the feasible construction point within the lowest altitude feasible region were selected as multiple first environmental datasets. For the first section of the route formed by the feasible construction point in the lowest altitude feasible region and the adjacent second lowest altitude feasible region, a finite element analysis model was established. In the model, the cableway steel rope was fixed at both ends and regarded as an elastic body. Its self-weight, rated load, and wind speed load in the first environmental dataset were considered. Dynamic analysis was performed using finite element software to calculate the lateral amplitude, longitudinal swing angle, and dynamic stress of the steel rope under different wind speed conditions for this section of the route. The physical quantities were converted into risk indicators that tourists could perceive. For example, the ratio of the lateral amplitude of this section of the route under a certain wind speed condition to the lateral amplitude under the previous wind speed condition was used as a perceived risk parameter.
[0042] Next, environmental data from feasible construction points within the second-lowest altitude feasible region are selected as multiple second environmental data, such as the probability of amplitude exceeding 0.5 meters and the proportion of duration of swing angle greater than 10 degrees, thereby obtaining multiple first perceived risk parameters.
[0043] Next, environmental data of construction feasible points in the second lowest altitude feasible domain are selected as multiple second environmental data. For the second section of the line, which is composed of construction feasible points in the second lowest altitude feasible domain and construction feasible points in adjacent higher altitude feasible domains, the same finite element modeling method and risk index conversion rules as the first section of the line are used to conduct finite element perception risk analysis and obtain multiple second perception risk parameters.
[0044] Then, the ratio of each second perceived risk parameter to its corresponding first perceived risk parameter is calculated, and these ratios are defined as multiple perception asymptotic coefficients. Since the line is continuous, the risk status of the preceding section will affect the perceived risk of the following section. Therefore, when analyzing the perceived risk parameters of the next section, i.e., the third section, the calculated perception asymptotic coefficients need to be used as correction factors to correct the original risk parameters directly output from the finite element analysis of that section. For example, if a certain perceived risk parameter in the second section is 1.2 times the corresponding parameter in the first section, then the perception asymptotic coefficient is 1.2. When calculating this perceived risk parameter in the third section, the original analysis result needs to be multiplied by 1.2 for correction.
[0045] After correcting the perceived risk parameters of the third segment, the ratio of the perceived risk parameters of the third segment to those of the second segment is calculated, and the asymptotic coefficients are updated to correct the perceived risk parameters of the fourth segment. Following this method, starting from the lowest altitude layer and working upwards layer by layer, finite element perceived risk analysis is performed on each segment, the asymptotic coefficients are calculated, the risk parameters of the next segment are corrected, and the coefficients are updated, until the analysis of all segmented segments is completed. Finally, all corrected perceived risk parameters of each segment are summarized to form multiple sets of first perceived risk parameters for each first-line design scheme.
[0046] Among them, based on multiple first environmental data within the feasible domain with the lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters, including: Based on the test data of the passenger ropeway, a sample environmental data set and a sample perceived risk parameter set are obtained. The sample environmental parameters include environmental interference parameters, and the sample perceived risk parameters include the sway amplitude of the tested ropeway. Based on machine learning, construct a perceptual risk analysis intelligent agent; Using the sample environment data set and the sample perceived risk parameter set, the perceived risk analysis agent is trained and tested under supervision. Training is completed after the test reaches the convergence requirement. Multiple first environmental data points within the feasible domain with the lowest altitude from the multiple environmental data sets are input into the perception risk analysis agent, and multiple first perception risk parameters are output.
[0047] In this embodiment of the application, firstly, by collecting actual operation test data of passenger ropeways under different environmental conditions, a sample environmental data set and a sample perceived risk parameter set are established. The sample environmental data set covers a variety of environmental interference parameters, such as the annual average wind speed, maximum instantaneous wind speed, and wind direction change frequency at different heights. The sample perceived risk parameters include the lateral sway amplitude and longitudinal swing angle of the ropeway steel cable, which can directly reflect the physical quantities of the passenger riding experience, obtained by actual measurement through devices such as acceleration sensors and displacement sensors. For example, the perceived risk parameters calculated above will be used as the input of the training samples.
[0048] Secondly, a perceptual risk analysis agent is constructed based on machine learning algorithms. Long Short-Term Memory (LSTM) network is selected as the core model because LSTM can effectively process sequential data and capture the dynamic characteristics of environmental parameters changing over time. It is used to simulate the continuous impact of environmental factors such as wind speed on cableway swaying. The input layer of the model is set as neurons corresponding to the dimensions of environmental disturbance parameters in the sample environmental data set. For example, the hidden layer contains 3 layers of LSTM units, with 64, 32 and 16 units in each layer, respectively. The output layer corresponds to parameters such as cableway swaying amplitude in the sample perceptual risk parameter set.
[0049] Furthermore, for example, the risk perception analysis agent is supervisedly trained and tested using the constructed sample environmental data set and sample perceived risk parameter set. 80% of the sample data is used as the training set, and 20% as the test set. During training, the root mean square error (RMSE) is used as the loss function, and the model parameters are iteratively updated using the Adam optimizer. The initial learning rate is set to 0.001 and dynamically adjusted according to the training progress. After every 100 training rounds, the model performance is evaluated using the test set. Training stops when the RMSE value is less than a preset convergence threshold (e.g., 0.05 meters) for 50 consecutive rounds. At this point, the model has a good ability to map environmental data to perceived risk parameters.
[0050] Finally, multiple first environmental data points within the feasible region with the lowest altitude from multiple environmental datasets—namely, the annual average wind speed, maximum instantaneous wind speed, and other specific environmental parameters at the feasible construction point within that region—are input into the trained perception risk analysis agent. The perception risk analysis agent then extracts features from the input environmental data and performs nonlinear mapping to output multiple first perception risk parameters corresponding to that section of the line, such as the predicted value of the cableway's lateral sway amplitude and the probability distribution of the swing angle under the current environmental conditions.
[0051] S40: Based on multiple first construction and operation efficiency parameters, multiple sets of first perceived risk parameters are fused and processed, the gene value of each construction feasible point is adjusted, multiple sets of first finite element gene values are obtained, and iterative optimization is performed until the iterative optimization ends, and the optimal route design scheme is output.
[0052] In this embodiment, the first construction and operation efficiency parameter of each first route design scheme is associated with the corresponding first perceived risk parameter set to adjust the gene value of each construction feasible point. The gene value of the construction feasible point represents the degree of merit of the point in cableway construction. The higher the gene value, the better the comprehensive performance of the point in terms of construction efficiency and risk control. Then, the multiple first finite element gene value sets are iteratively optimized to output the optimal route design scheme with the largest design fitness value.
[0053] Specifically, based on multiple first construction operation efficiency parameters, multiple sets of first perceived risk parameters are fused and processed to assign gene values to each construction feasibility point, resulting in multiple sets of first finite element gene values, including: Calculate the ratio of each first construction operation efficiency parameter to the mean of multiple first construction operation efficiency parameters to obtain multiple first efficiency gene adjustment coefficients; The ratio of the mean of multiple sets of first-perceived risk parameters to each first-perceived risk parameter is calculated to obtain multiple sets of first-risk gene adjustment coefficients; Obtain the number of feasible construction points in each feasible region, assign basic gene values to multiple feasible construction points in each feasible region, and obtain multiple sets of basic gene values; By using multiple sets of first-efficiency gene adjustment coefficients and multiple sets of first-risk gene adjustment coefficients, the basic gene values of each construction feasible point selected in one round of optimization are calculated and corrected to obtain multiple sets of first-finite element gene values.
[0054] In this embodiment of the application, firstly, the ratio of the first construction and operation efficiency parameter of each first line design scheme to the average value of the first construction and operation efficiency parameter of all first line design schemes is calculated, and it is defined as multiple first efficiency gene adjustment coefficients.
[0055] For example, if the first construction and operation efficiency parameter of a certain scheme is 1.21, and the average first construction and operation efficiency parameter of all schemes is 1.05, then the first efficiency gene adjustment coefficient of that scheme is... This coefficient reflects the degree of superiority or inferiority of the scheme in terms of construction and operation efficiency relative to the average level. A coefficient greater than 1 indicates that the efficiency is higher than average, and vice versa.
[0056] Secondly, for each first route design scheme, a set of multiple first perceived risk parameters is obtained. The mean of all perceived risk parameters in the set is calculated, and then this mean is divided by each first perceived risk parameter in the set to obtain a set of multiple first risk gene adjustment coefficients.
[0057] For example, the first perceived risk parameter set of a certain scheme includes five parameters, such as the probability of lateral sway amplitude and the proportion of sway angle duration, with a mean of 0.8. One parameter has a value of 1.0, and the adjustment coefficient of the first risk gene corresponding to that parameter is... This coefficient reflects the level of a single perceived risk parameter relative to the overall perceived risk level of the scheme. The larger the coefficient, the lower the risk level of the parameter and the greater its positive contribution to the gene value.
[0058] Next, obtain the number of feasible construction points in different altitude layers, i.e. different feasible domains, in each first route design scheme. According to the preset gene value allocation rules, assign basic gene values to multiple feasible construction points in each feasible domain. For example, if a feasible domain includes 10 feasible construction points, then the basic gene value set of that feasible domain includes 10 0.1 values, thus obtaining multiple basic gene value sets.
[0059] Finally, using the multiple first-efficiency gene adjustment coefficients and multiple first-risk gene adjustment coefficient sets obtained above, the basic gene values of each feasible construction point within each first route design scheme selected in the first round of optimization are calculated and corrected. The specific correction formula is as follows: .
[0060] For example, the first efficiency gene adjustment coefficient of a certain feasible construction point is 1.15, the first risk gene adjustment coefficient of the corresponding point is 0.8, and the basic gene value is 10. Then the first finite element gene value of the point is 10 × 1.15 × 0.8 = 9.2. By integrating the factors of construction efficiency and perceived risk into the gene value of each feasible construction point, a set of multiple first finite element gene values is obtained.
[0061] Further, iterative optimization is performed until the iteration ends, and the optimal route design scheme is output, including: Based on multiple sets of first-perception risk parameters, calculate multiple first-perception risk parameters for multiple first-perception design schemes; Multiple first construction and operation efficiency parameters and multiple first line perceived risk parameters are normalized, and multiple first design fitness values of multiple first line design schemes are calculated. Among them, the first design fitness value is positively correlated with the first construction and operation efficiency parameter and negatively correlated with the first line perceived risk parameter. Based on multiple sets of first finite element gene values, update the selection probability of construction feasible points within the multi-layer feasible domain; Continue generating route design schemes, iteratively optimizing them, and outputting the optimal route design scheme with the largest design fitness value after convergence.
[0062] In this embodiment of the application, firstly, the multiple sets of first perceived risk parameters for each first route design scheme are summarized. For example, by calculating the average value of the perceived risk parameters of each segment of the route, the overall first route perceived risk parameter of each scheme is obtained. This parameter comprehensively reflects the perceived risk level of the entire cableway route.
[0063] Secondly, the first construction operation efficiency parameters and the first line perceived risk parameters are normalized to eliminate the influence of dimensional differences on subsequent calculations. The first construction operation efficiency parameters are normalized to the [0,1] interval, with larger values indicating higher efficiency. Similarly, the first line perceived risk parameters are normalized to the [0,1] interval, with larger values indicating higher risk.
[0064] Specifically, the normalization method is min-max standardization, that is, for the construction and operation efficiency parameter, the normalized value = (original efficiency parameter - minimum efficiency parameter of all schemes) / (maximum efficiency parameter of all schemes - minimum efficiency parameter of all schemes); for the line perceived risk parameter, the normalized value = (original risk parameter - minimum risk parameter of all schemes) / (maximum risk parameter of all schemes - minimum risk parameter of all schemes).
[0065] Then, based on the normalized parameters, multiple first design fitness values for multiple first line design schemes are calculated. For example, the formula for calculating the design fitness value can be set as follows: .
[0066] For example, if the normalized construction and operation efficiency parameter of a certain scheme is 0.85 and the normalized line perceived risk parameter is 0.32, then its first design fitness value is... The higher the value, the better the solution performs in terms of overall balance between efficiency and risk.
[0067] Next, based on multiple sets of first finite element gene values, the selection probability of construction feasible points within the multi-layer feasible domain is updated. Specifically, for each feasible domain, the first finite element gene values of all construction feasible points within that layer are normalized. Next, based on multiple sets of first finite element gene values, the selection probability of feasible points within the multi-layered feasible domain is updated. Specifically, in each feasible domain, the selection probability of a feasible point is proportional to its first finite element gene value. Points with higher gene values are more likely to be selected in the generation of the next generation of solutions. For example, using a roulette wheel selection method, the gene values of each point are converted into selection probabilities. If the total gene value is 100, and the gene value of a point is 10, then its selection probability is 10%.
[0068] Finally, based on the updated probability of feasible construction points, the route design scheme is generated again, and the process from environmental data extraction, finite element risk analysis, gene value calculation to design fitness value evaluation is repeated for iterative optimization. After each iteration, the scheme with the higher design fitness value is retained. When the maximum value of the design fitness value no longer increases significantly in multiple consecutive iterations (e.g., the increase is less than a preset threshold of 0.01), or the preset maximum number of iterations of 100 is reached, the iteration is considered to have converged. At this time, the route design scheme with the highest design fitness value is output as the optimal route design scheme.
[0069] Specifically, based on multiple sets of first finite element gene values, the selection probability of construction feasible points within the multi-layer feasible domain is updated, including: Based on multiple sets of first finite element gene values and the basic gene values of construction feasible points that were not selected in a round of optimization, multiple sets of updated gene values of construction feasible points in multiple feasible domains are redistributed and calculated, wherein the sum of gene values in each feasible domain is 1. Multiple sets of updated gene values are treated as multiple sets of selection probabilities.
[0070] In this embodiment of the application, firstly, since there are some unselected feasible construction points in addition to the selected feasible construction points during a round of optimization, in order to ensure the diversity of the gene pool and provide potential optimization directions for subsequent iterations, the basic gene values of the unselected points are included in the calculation of the updated gene value set.
[0071] In practice, firstly, all feasible points within the multi-layered feasible domain are acquired, including both selected and unselected points. Then, based on multiple sets of first finite element gene values—namely, the gene values of selected points and the base gene values of unselected points—the gene values of all feasible points within each feasible domain are redistributed. For example, if a feasible domain has 20 feasible points, 10 of which are selected with a total first finite element gene value of 50, and the other 10 are unselected with a total base gene value of 10, assuming each unselected point has a base gene value of 1, then the total gene value of all points in this feasible domain is 60. Next, the gene value of each point is divided by the total gene value of this layer, 60, to obtain the updated gene value of each point, ensuring that the sum of the updated gene values of all feasible points within each feasible domain is 1.
[0072] For example, if the first finite element gene value of a selected point is 5, then its updated gene value is 5 / 60≈0.083; if the basic gene value of an unselected point is 1, then its updated gene value is 1 / 60≈0.017.
[0073] Then, the set of multiple updated gene values of construction feasible points in the multi-layer feasible domain obtained by the above method is directly used as the set of multiple selection probabilities of each construction feasible point when generating the next round of route design schemes. That is, the updated gene value of each construction feasible point is the probability of it being selected to participate in the construction of a new route design scheme in the corresponding feasible domain. For example, if the updated gene value of a certain construction feasible point is 0.083, then its selection probability in the feasible domain is 8.3%.
[0074] In summary, compared with existing technologies, this application constructs a route design framework based on finite element analysis and intelligent optimization algorithms by deeply coupling construction and operation efficiency with perceived environmental risks. On the one hand, it uses LSTM networks to model dynamic environmental disturbances, realizing a nonlinear mapping from complex environmental parameters to perceived risk parameters such as cableway sway amplitude. On the other hand, it incorporates construction efficiency and perceived risk quantification indicators into the same optimization dimension through a gene value fusion mechanism. It achieves dynamic optimization of the route design scheme through roulette wheel selection and gene value iterative updates. The final optimal route design scheme can ensure construction feasibility while simultaneously improving construction efficiency and reducing operational risks.
[0075] In summary, the embodiments of this application have at least the following technical effects: This application provides a passenger cableway route design method based on finite element analysis. First, geological surveys are conducted on the target area, and the cableway construction feasibility zone is divided into layers according to altitude. Multi-layered feasibility zones and feasible construction points that meet the support structure construction conditions are selected. Second, multiple first route design schemes are generated by randomly combining feasible construction points within the multi-layered feasibility zones. Combining the geological survey data and route length of each scheme, the construction time is calculated using a cableway construction database, thereby obtaining first construction operation efficiency parameters and achieving a quantitative evaluation of the efficiency of different initial schemes. Then, based on the geological survey data of the feasible construction points of each scheme, environmental data is extracted. A machine learning-based risk perception analysis agent is used to perform finite element risk perception analysis segment by segment, starting from the lowest altitude feasible zone. The risk parameters of the next segment are corrected using a perception asymptotic coefficient, forming multiple sets of first perception risk parameters to capture the potential risks of each segment of the route. Finally, by integrating the first set of construction operation efficiency parameters and the first set of perceived risk parameters, the basic gene values of the feasible construction points are corrected to obtain the first set of finite element gene values. By calculating the line design fitness value, the probability of selecting feasible construction points is updated and iteratively optimized, and finally the optimal line design scheme with the largest design fitness value is converged and output.
[0076] Through the above technical solutions, this application combines finite element analysis, machine learning and gene optimization algorithms to achieve a comprehensive and accurate assessment and systematic optimization of the safety and economy of passenger cableway lines under complex geological conditions. It effectively solves the problems of traditional design methods relying on experience, one-sided evaluation and low optimization efficiency, and improves the overall quality and investment benefits of cableway projects.
[0077] Example 2, as Figure 2 As shown, based on the same inventive concept as the finite element analysis-based passenger ropeway route design method provided in Embodiment 1, this application also provides a finite element analysis-based passenger ropeway route design system, including: The construction area acquisition module 11 is used to acquire the feasible area for cableway construction within the target area after geological testing. The target area is the area where passenger cableway line design is carried out. The feasible area for cableway construction includes multiple feasible areas, and each feasible area includes multiple feasible construction points. The initial scheme generation module 12 is used to randomly generate multiple first route design schemes within the multi-layer feasible domain, perform construction and operation efficiency analysis, and obtain multiple first construction and operation efficiency parameters. Each first route design scheme includes construction feasible points within the multi-layer feasible domain. Risk analysis module 13 is used to perform finite element progressive risk analysis of each section of the line based on geological detection data of multiple feasible construction points within each first line design scheme, and to obtain multiple sets of first perceived risk parameters. The scheme optimization module 14 is used to fuse multiple sets of first perceived risk parameters based on multiple first construction operation efficiency parameters, adjust the gene value of each construction feasible point, obtain multiple sets of first finite element gene values, and perform iterative optimization until the iterative optimization ends, and output the optimal route design scheme.
[0078] In one embodiment, the construction area acquisition module 11 is specifically used for: The target area is divided into multiple layers according to altitude, resulting in multi-layered regions. Geological surveys were conducted on the multi-layered areas to screen out locations that met the requirements for cableway support construction, resulting in multiple sets of feasible construction points, which were used as multi-layered feasible regions. Among them, there was one feasible construction point within the feasible region with the highest altitude.
[0079] In one embodiment, the initial scheme generation module 12 is specifically used for: Multiple combinations of feasible construction points are selected within the multi-layered feasible domain to obtain multiple first-line design schemes; Geological testing data of multiple feasible construction points within each first route design scheme are obtained to generate multiple first geological testing datasets, and the first route length of each first route design scheme is obtained. Based on multiple primary geological monitoring datasets and multiple primary route lengths, construction operation efficiency analysis was conducted to obtain multiple primary construction operation efficiency parameters.
[0080] Furthermore, based on multiple primary geological monitoring datasets and multiple primary route lengths, a construction operation efficiency analysis was conducted, yielding multiple primary construction operation efficiency parameters, including: Obtain the cableway construction database, which includes sample geological detection datasets and sample support construction time sets mapped during support construction, as well as sample line length sets and sample line construction time sets mapped during line construction. The multiple first geological detection datasets and multiple first line lengths are respectively combined and input into the cableway construction database, and the multiple first support construction time sets and multiple first line construction times of multiple first line design schemes are mapped and output, and the construction times of multiple first lines are calculated. The first construction operation efficiency parameter was calculated based on the construction time of multiple first lines.
[0081] In one embodiment of the application, the risk analysis module 13 is specifically used for: Based on the geological testing data of multiple feasible construction points within each first route design scheme, environmental data at each feasible construction point is extracted to obtain multiple environmental data sets; Based on multiple first environmental data within the feasible domain with the lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters. Based on multiple second environmental data within the feasible domain with the second lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple second sensing risk parameters. The ratios of the plurality of second perceived risk parameters and the plurality of first perceived risk parameters are calculated respectively, and used as a plurality of perception asymptotic coefficients to correct the next perceived risk parameter and update the perception asymptotic coefficients. Continue to analyze and calculate multiple sets of first-perceived risk parameters from multiple environmental datasets.
[0082] Furthermore, based on multiple first environmental data points within the feasible domain with the lowest altitude from multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters, including: Based on the test data of the passenger ropeway, a sample environmental data set and a sample perceived risk parameter set are obtained. The sample environmental parameters include environmental interference parameters, and the sample perceived risk parameters include the sway amplitude of the tested ropeway. Based on machine learning, construct a perceptual risk analysis intelligent agent; Using the sample environment data set and the sample perceived risk parameter set, the perceived risk analysis agent is trained and tested under supervision. Training is completed after the test reaches the convergence requirement. Multiple first environmental data points within the feasible domain with the lowest altitude from the multiple environmental data sets are input into the perception risk analysis agent, and multiple first perception risk parameters are output.
[0083] Furthermore, in one embodiment, based on multiple first construction operation efficiency parameters, multiple sets of first perceived risk parameters are fused, and gene values are assigned to each feasible construction point to obtain multiple sets of first finite element gene values, including: Calculate the ratio of each first construction operation efficiency parameter to the mean of multiple first construction operation efficiency parameters to obtain multiple first efficiency gene adjustment coefficients; The ratio of the mean of multiple sets of first-perceived risk parameters to each first-perceived risk parameter is calculated to obtain multiple sets of first-risk gene adjustment coefficients; Obtain the number of feasible construction points in each feasible region, assign basic gene values to multiple feasible construction points in each feasible region, and obtain multiple sets of basic gene values; By using multiple sets of first-efficiency gene adjustment coefficients and multiple sets of first-risk gene adjustment coefficients, the basic gene values of each construction feasible point selected in one round of optimization are calculated and corrected to obtain multiple sets of first-finite element gene values.
[0084] Further, iterative optimization is performed until the iteration ends, and the optimal route design scheme is output, including: Based on multiple sets of first-perception risk parameters, calculate multiple first-perception risk parameters for multiple first-perception design schemes; Multiple first construction and operation efficiency parameters and multiple first line perceived risk parameters are normalized, and multiple first design fitness values of multiple first line design schemes are calculated. Among them, the first design fitness value is positively correlated with the first construction and operation efficiency parameter and negatively correlated with the first line perceived risk parameter. Based on multiple sets of first finite element gene values, update the selection probability of construction feasible points within the multi-layer feasible domain; Continue generating route design schemes, iteratively optimizing them, and outputting the optimal route design scheme with the largest design fitness value after convergence.
[0085] Furthermore, based on multiple sets of first finite element gene values, the selection probability of construction feasible points within the multi-layer feasible domain is updated, including: Based on multiple sets of first finite element gene values and the basic gene values of construction feasible points that were not selected in a round of optimization, multiple sets of updated gene values of construction feasible points in the multi-layer feasible domain are redistributed and calculated, wherein the sum of gene values in each feasible domain is 1. Multiple sets of updated gene values are treated as multiple sets of selection probabilities.
Claims
1. A passenger ropeway route design method based on finite element analysis, characterized in that, The method includes: The feasible construction zone for the cableway is obtained after geological testing within the target area. The target area is the region where the passenger cableway route is designed. The feasible construction zone for the cableway includes multiple layers of feasible zones, and each layer of feasible zone includes multiple feasible construction points. Multiple first route design schemes are randomly generated within the multi-layered feasible domain, and construction operation efficiency analysis is performed to obtain multiple first construction operation efficiency parameters. Each first route design scheme includes construction feasible points within the multi-layered feasible domain. Based on the geological testing data of multiple feasible construction points within each first route design scheme, a progressive finite element risk assessment analysis of each route segment is conducted to obtain multiple sets of first-perception risk parameters. Based on multiple primary construction and operation efficiency parameters, multiple sets of primary perceived risk parameters are fused and processed. The gene value of each construction feasible point is adjusted to obtain multiple sets of primary finite element gene values. Iterative optimization is then performed until the iterative optimization ends, and the optimal route design scheme is output.
2. The passenger ropeway route design method based on finite element analysis according to claim 1, characterized in that, Obtain the feasible construction zone for the cableway within the target area, as delineated after geological testing, including: The target area is divided into multiple layers according to altitude, resulting in multi-layered regions. Geological surveys were conducted on the multi-layered areas to screen out locations that met the requirements for cableway support construction, resulting in multiple sets of feasible construction points, which were used as multi-layered feasible regions. Among them, there was one feasible construction point within the feasible region with the highest altitude.
3. The passenger ropeway route design method based on finite element analysis according to claim 1, characterized in that, Multiple first route design schemes are randomly generated within the multi-layered feasible domain, and construction and operation efficiency analysis is performed to obtain multiple first construction and operation efficiency parameters, including: Multiple combinations of feasible construction points are selected within the multi-layered feasible domain to obtain multiple first-line design schemes; Geological testing data of multiple feasible construction points within each first route design scheme are obtained to generate multiple first geological testing datasets, and the first route length of each first route design scheme is obtained. Based on multiple primary geological monitoring datasets and multiple primary route lengths, construction operation efficiency analysis was conducted to obtain multiple primary construction operation efficiency parameters.
4. The passenger ropeway route design method based on finite element analysis according to claim 3, characterized in that, Based on multiple primary geological monitoring datasets and multiple primary route lengths, a construction operation efficiency analysis was conducted, yielding multiple primary construction operation efficiency parameters, including: Obtain the cableway construction database, which includes sample geological detection datasets and sample support construction time sets mapped during support construction, as well as sample line length sets and sample line construction time sets mapped during line construction. The multiple first geological detection datasets and multiple first line lengths are respectively combined and input into the cableway construction database, and the multiple first support construction time sets and multiple first line construction times of multiple first line design schemes are mapped and output, and the construction times of multiple first lines are calculated. The first construction operation efficiency parameter was calculated based on the construction time of multiple first lines.
5. The passenger ropeway route design method based on finite element analysis according to claim 1, characterized in that, Based on geological testing data from multiple feasible construction points within each first route design scheme, a progressive finite element risk assessment analysis was conducted segment by segment along the route, resulting in multiple sets of first-perception risk parameters, including: Based on the geological testing data of multiple feasible construction points within each first route design scheme, environmental data at each feasible construction point is extracted to obtain multiple environmental data sets; Based on multiple first environmental data within the feasible domain with the lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters. Based on multiple second environmental data within the feasible domain with the second lowest altitude in multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple second sensing risk parameters. The ratios of the plurality of second perceived risk parameters and the plurality of first perceived risk parameters are calculated respectively, and used as a plurality of perception asymptotic coefficients to correct the next perceived risk parameter and update the perception asymptotic coefficients. Continue to analyze and calculate multiple sets of first-perceived risk parameters from multiple environmental datasets.
6. The passenger ropeway route design method based on finite element analysis according to claim 5, characterized in that, Based on multiple first environmental data points within the feasible region with the lowest altitude from multiple environmental datasets, finite element sensing risk analysis is performed to obtain multiple first sensing risk parameters, including: Based on the test data of the passenger ropeway, a sample environmental data set and a sample perceived risk parameter set are obtained. The sample environmental parameters include environmental interference parameters, and the sample perceived risk parameters include the sway amplitude of the tested ropeway. Based on machine learning, construct a perceptual risk analysis intelligent agent; Using the sample environment data set and the sample perceived risk parameter set, the perceived risk analysis agent is trained and tested under supervision. Training is completed after the test reaches the convergence requirement. Multiple first environmental data points within the feasible domain with the lowest altitude from the multiple environmental data sets are input into the perception risk analysis agent, and multiple first perception risk parameters are output.
7. The passenger ropeway route design method based on finite element analysis according to claim 1, characterized in that, Based on multiple primary construction and operation efficiency parameters, multiple sets of primary perceived risk parameters are fused and processed to assign gene values to each feasible construction point, resulting in multiple sets of primary finite element gene values, including: Calculate the ratio of each first construction operation efficiency parameter to the mean of multiple first construction operation efficiency parameters to obtain multiple first efficiency gene adjustment coefficients; The ratio of the mean of multiple sets of first-perceived risk parameters to each first-perceived risk parameter is calculated to obtain multiple sets of first-risk gene adjustment coefficients; Obtain the number of feasible construction points in each feasible region, assign basic gene values to multiple feasible construction points in each feasible region, and obtain multiple sets of basic gene values; By using multiple sets of first-efficiency gene adjustment coefficients and multiple sets of first-risk gene adjustment coefficients, the basic gene values of each construction feasible point selected in one round of optimization are calculated and corrected to obtain multiple sets of first-finite element gene values.
8. The passenger ropeway route design method based on finite element analysis according to claim 1, characterized in that, Perform iterative optimization until the iteration ends, and output the optimal route design scheme, including: Based on multiple sets of first-perception risk parameters, calculate multiple first-perception risk parameters for multiple first-perception design schemes; Multiple first construction and operation efficiency parameters and multiple first line perceived risk parameters are normalized, and multiple first design fitness values of multiple first line design schemes are calculated. Among them, the first design fitness value is positively correlated with the first construction and operation efficiency parameter and negatively correlated with the first line perceived risk parameter. Based on multiple sets of first finite element gene values, update the selection probability of construction feasible points within the multi-layer feasible domain; Continue generating route design schemes, iteratively optimizing them, and outputting the optimal route design scheme with the largest design fitness value after convergence.
9. The passenger ropeway route design method based on finite element analysis according to claim 8, characterized in that, Based on multiple sets of first finite element gene values, update the selection probability of construction feasible points within the multi-layer feasible domain, including: Based on multiple sets of first finite element gene values and the basic gene values of construction feasible points that were not selected in a round of optimization, multiple sets of updated gene values of construction feasible points in the multi-layer feasible domain are redistributed and calculated, wherein the sum of gene values in each feasible domain is 1. Multiple sets of updated gene values are treated as multiple sets of selection probabilities.
10. A passenger ropeway route design system based on finite element analysis, characterized in that, A method for designing a passenger ropeway route based on finite element analysis as described in any one of claims 1-9 includes: The construction area acquisition module is used to acquire the feasible construction area of the cableway within the target area after geological testing. The target area is the area where the passenger cableway route is designed. The feasible construction area includes multiple layers of feasible areas, and each layer of feasible areas includes multiple feasible construction points. The initial scheme generation module is used to randomly generate multiple first route design schemes within the multi-layered feasible domain, perform construction and operation efficiency analysis, and obtain multiple first construction and operation efficiency parameters. Each first route design scheme includes construction feasible points within the multi-layered feasible domain. The risk analysis module is used to perform finite element progressive risk analysis of each section of the line based on geological detection data of multiple construction feasibility points within each first line design scheme, and to obtain multiple sets of first-perceived risk parameters. The scheme optimization module is used to fuse multiple sets of first perceived risk parameters based on multiple first construction and operation efficiency parameters, adjust the gene value of each construction feasibility point, obtain multiple sets of first finite element gene values, and perform iterative optimization until the iterative optimization ends, outputting the optimal route design scheme.