Positive design method and system for municipal traffic engineering

Abstract

The application relates to the field of municipal traffic, and discloses a forward design method and system for municipal traffic engineering. The method comprises the following steps: acquiring climate data, traffic flow data, citizen demand indexes, cultural relic protection range restrictions and geological taboo area restrictions of a target city; calling climate influence parameters and traffic strategy adjustment parameters in an experience database; determining design parameter benchmark values of the municipal traffic engineering according to the climate data, the traffic flow data, the climate influence parameters and the traffic strategy adjustment parameters; optimizing the design parameter benchmark values by using a simulated annealing algorithm to generate an initial parameter set; processing the initial parameter set by using a genetic algorithm to generate a candidate scheme set; and calculating a sustainability quantitative score of the candidate scheme set by using a random forest algorithm to determine a final scheme. The scheme solves the problem that standardization and individualization cannot be considered in traditional design, and makes the municipal traffic engineering design scheme highly match the actual demand of the city.

Description

Technical Field

[0001] This application relates to the field of municipal transportation technology, and in particular to forward design methods and systems for municipal transportation engineering. Background Technology

[0002] Municipal transportation engineering, as a crucial component of urban construction, plays an irreplaceable role in ensuring urban operational efficiency and improving residents' quality of life. The research and practice of municipal transportation engineering directly relate to the smoothness of urban traffic, the safety of infrastructure, and the sustainability of urban development, making it an indispensable key link in the process of urban modernization.

[0003] In existing technologies, engineers first determine basic parameters based on standard manuals such as the "Code for Design of Urban Road Engineering," and then make local adjustments based on their personal experience. However, this standardized process has significant limitations: on the one hand, standardized design cannot fully reflect the characteristics of a city. Due to significant differences in topography, climate, and traffic demands across different regions, this fixed model often cannot flexibly adapt to actual changes, ultimately leading to a disconnect between the design scheme and actual needs. On the other hand, due to the limitations of engineers' personal experience, when faced with complex and ever-changing construction conditions, relying solely on manual judgment often makes it difficult to make comprehensive and accurate decisions, resulting in municipal transportation design schemes that cannot effectively adapt to local environmental characteristics.

[0004] In summary, existing technical solutions have the problem of poor matching with the actual needs of cities. Summary of the Invention

[0005] This application provides a forward design method and system for municipal transportation engineering to improve the matching degree between municipal transportation engineering and actual urban needs.

[0006] According to one aspect of this application, a forward design method for municipal traffic engineering is provided, comprising: Obtain climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions for the target city; Based on the climate data and the traffic flow data, retrieve the climate impact parameters and traffic strategy adjustment parameters from the empirical database; The baseline values ​​of the design parameters for the municipal transportation project are determined based on the climate data, the traffic flow data, the climate impact parameters, and the traffic strategy adjustment parameters. Based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas are used as constraints. The design parameter baseline values ​​are optimized using the simulated annealing algorithm to generate an initial parameter set. Using the maximization of fitness score as the objective function, a genetic algorithm is used to process the initial parameter set to generate a set of alternative solutions; Engineering efficiency evaluation parameters are extracted from the set of candidate solutions. Based on the engineering efficiency evaluation parameters, the sustainability quantification score of the set of candidate solutions is calculated by the random forest algorithm. A solution ranking list is generated, and the top-ranked solution is selected. Verify the compliance of the elements in the top row scheme to determine the final scheme.

[0007] Optionally, the climate data includes: temperature data, precipitation data, humidity data, and frequency of extreme weather events; the traffic flow data includes: vehicle traffic volume, peak traffic hours, average vehicle speed, and proportion of public transport vehicles; the climate impact parameters include: heat island effect adjustment coefficient and precipitation variation coefficient; the traffic strategy adjustment parameters include: signal timing optimization coefficient, lane number adjustment factor, speed limit adjustment factor, and public transport priority weight; the step of retrieving climate impact parameters and traffic strategy adjustment parameters from an empirical database based on the climate data and the traffic flow data includes: Based on the temperature data and the humidity data, the corresponding heat island effect adjustment coefficient is matched from the empirical database; Based on the precipitation data and the frequency of extreme weather events, the corresponding precipitation variation coefficient is matched from the empirical database; Based on the vehicle traffic volume and the peak traffic period, the corresponding traffic light timing optimization coefficients are matched from the experience database; The corresponding lane number adjustment factor is matched from the experience database based on the vehicle traffic volume. The corresponding vehicle speed limit adjustment factor is matched from the experience database based on the average vehicle speed. Based on the proportion of public transport vehicles, the corresponding public transport priority weights are matched from the experience database.

[0008] Optionally, the design parameter benchmark values ​​include: road foundation width benchmark value, lane number benchmark value, drainage system capacity benchmark value, pavement material weather resistance grade benchmark value, traffic signal cycle benchmark value, and bus lane proportion benchmark value; determining the design parameter benchmark values ​​of the municipal traffic engineering project based on the climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters includes: The road base width reference value is determined based on the vehicle traffic volume, the average vehicle speed, the speed limit adjustment factor, and the traffic light timing optimization coefficient. The baseline value for the number of lanes is determined based on the vehicle traffic volume and the lane number adjustment factor; The baseline value of the drainage system capacity is determined based on the precipitation data and the precipitation variation coefficient. The benchmark value for the weather resistance grade of the pavement material is determined based on the temperature data, the frequency of extreme weather events, the humidity data, and the heat island effect adjustment coefficient. The traffic signal cycle reference value is determined based on the vehicle traffic volume and the traffic light timing optimization coefficient. The benchmark value for the proportion of dedicated bus lanes is determined based on the proportion of public transport vehicles and the priority weight of public transport.

[0009] Optionally, the citizen demand indicators include: citizen travel frequency, public transportation utilization rate, and citizen congestion tolerance; based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas are used as constraints, and the design parameter baseline values ​​are optimized using a simulated annealing algorithm to generate an initial parameter set, including: The optimization objectives are set as maximizing the frequency of citizens' travel, maximizing the utilization rate of public transportation, and maximizing the satisfaction of citizens' congestion tolerance. The baseline values ​​of the design parameters are set as variables. A multi-objective optimization function is established based on the variables and the optimization objectives. Using the design parameter baseline value as the initial solution of the simulated annealing algorithm, verify whether the initial solution simultaneously meets the cultural relic protection scope restriction and the geological taboo zone restriction; If the initial solution simultaneously meets the restrictions of the cultural relic protection scope and the geological taboo zone, then the simulated annealing algorithm is used to optimize the initial solution to generate the initial parameter set that satisfies the multi-objective optimization function and meets the constraints.

[0010] Optionally, the step of optimizing the design parameter baseline values ​​using a simulated annealing algorithm based on the citizen demand indicators, taking the cultural relic protection scope restrictions and the geological taboo zone restrictions as constraints, to generate an initial parameter set further includes: If the initial solution does not meet the cultural relic protection scope limit, then obtain the geographical coordinates of the cultural relic protection scope, use a path planning algorithm to generate a cultural relic avoidance path, and update the initial solution based on the cultural relic avoidance path; And / or, if the initial solution does not meet the geological taboo zone restriction, then obtain the geographical coordinates of the geological taboo zone, use a path planning algorithm to generate an environmental avoidance path, and update the initial solution based on the environmental avoidance path.

[0011] Optionally, the adaptability score includes: environmental impact assessment score, economic benefit analysis score, regulatory compliance score, and technical feasibility score. The step of using a genetic algorithm to process the initial parameter set, with the objective function of maximizing the adaptability score, to generate a set of alternative solutions includes: Multiple initial candidate schemes are randomly generated based on the initial parameter set, and an initial candidate scheme set is formed based on the fitness score of each initial candidate scheme. Reorganize some parameters in the initial candidate solution set to generate a crossover solution; randomly change some parameters in the crossover solution to generate a mutation solution; Using the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas as constraints for the genetic algorithm, the mutation schemes are verified, and the mutation schemes that meet the constraints are retained as improvement candidate schemes. The improved candidate solution is used to update the initial candidate solution, and the iteration calculation continues until the termination condition is met, and the alternative solution set is output; wherein, the termination condition includes: reaching the maximum number of iterations, or the change value of the adaptive score is less than the preset score change threshold.

[0012] Optionally, forming an initial candidate solution set based on the fitness score of each initial candidate solution includes: Calculate the fitness score for each of the initial candidate solutions; For the initial candidate solutions that exceed the preset score threshold, the selection probability is allocated according to the corresponding fitness score ratio, and the roulette wheel selection method is used for screening to form the initial candidate solution set.

[0013] Optionally, the step of extracting engineering efficiency evaluation parameters from the set of candidate solutions, calculating the sustainability quantification score of the set of candidate solutions using a random forest algorithm based on the engineering efficiency evaluation parameters, generating a ranked list of solutions, and selecting the top-ranked solution includes: The engineering efficiency evaluation parameters are extracted from the set of alternative solutions; wherein, the engineering efficiency evaluation parameters include economic cost, construction time, construction quality score and environmental impact score, and the sustainability quantification score includes economic sustainability, time sustainability, quality sustainability and environmental sustainability; A set proportion of historical engineering efficiency evaluation parameters are taken from the experience database as sample features, and the historical sustainability quantitative scores corresponding to the historical engineering efficiency evaluation parameters are taken as label values ​​to train a random forest model. The economic cost, construction time, construction quality score, and environmental impact score are organized into a feature vector, which is then used as input to the random forest model to output a sustainability quantification score for the set of alternative solutions. The alternative solutions are sorted according to the sustainability quantification score to generate a sorted list of solutions, and the top-ranked solution with the highest score is selected.

[0014] Optionally, after verifying the element compliance of the top row scheme and determining the final scheme, the method further includes: When implementing the final solution, the climate data and traffic flow data are tracked in real time, and the final solution is dynamically adjusted accordingly.

[0015] According to another aspect of this application, a forward design system for municipal transportation engineering is provided, comprising: The data acquisition module is used to acquire climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions of the target city; and to retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database based on the climate data and traffic flow data. The benchmark determination module is used to determine the benchmark values ​​of the design parameters of the municipal transportation project based on the climate data, the traffic flow data, the climate impact parameters, and the traffic strategy adjustment parameters. The parameter optimization module is used to optimize the baseline values ​​of the design parameters using a simulated annealing algorithm, based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on the geological taboo areas, and to generate an initial parameter set. The scheme determination module is used to process the initial parameter set using a genetic algorithm with the objective function of maximizing the fitness score, generating a set of candidate schemes; then, it extracts engineering efficiency evaluation parameters from the set of candidate schemes, and calculates the sustainability quantification score of the set of candidate schemes using a random forest algorithm based on the engineering efficiency evaluation parameters, generates a scheme ranking list, and selects the top-ranked schemes; finally, it verifies the feature compliance of the top-ranked schemes and determines the final scheme.

[0016] The technical solution of this application, firstly, automatically generates benchmark values ​​for design parameters of municipal transportation engineering by matching climate data, traffic flow data, and experience databases, effectively overcoming the subjective limitations of human experience. Secondly, it uses a simulated annealing algorithm combined with constraints such as cultural relic protection scope limitations and geological taboo zone limitations to ensure that the generated initial parameter set schemes both meet regulatory requirements and take into account local characteristics. Then, with the goal of maximizing the fitness score, a genetic algorithm is used to globally optimize the initial parameter set, generating a set of alternative schemes that can balance multiple conflicts and meet the personalized needs of the target city. Finally, a random forest algorithm is used to quantitatively evaluate the life-cycle benefits of the schemes in the alternative scheme set, achieving scientific decision-making. The solution of this application, combined with computer-aided design, solves the problem in traditional design where it is difficult to balance construction standardization with the personalized characteristics of the city, making the municipal transportation engineering design scheme highly matched with the actual needs of the city.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0018] 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.

[0019] Figure 1 A flowchart illustrating the forward design method for municipal transportation engineering provided in this application embodiment; Figure 2 A flowchart illustrating another forward design method for municipal transportation engineering provided in this application embodiment; Figure 3 A flowchart illustrating another forward design method for municipal transportation engineering provided in this application embodiment; Figure 4 A schematic diagram of the forward design system for municipal transportation engineering provided in this application embodiment. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Figure 1This is a flowchart illustrating a forward design method for municipal transportation engineering provided in an embodiment of this application. This embodiment is applicable to planning urban traffic routes. The method can be executed by a forward design system for municipal transportation engineering, which can be implemented in hardware and / or software and can be configured on a large server. Figure 1 As shown, the method includes: S110: Obtain climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions for the target city.

[0023] Specifically, climate data refers to data reflecting the climate characteristics of the target city, including temperature, humidity, precipitation, and the frequency of extreme weather events, used to assess the potential impact of climate on transportation engineering. Traffic flow data refers to data recording urban traffic operations, including vehicle volume, peak traffic hours, average vehicle speed, and the proportion of public transportation vehicles, used to analyze traffic demand and current status. Citizen demand indicators refer to data indicators reflecting citizens' travel needs and behaviors, including travel frequency, utilization rate of public transportation, and tolerance for traffic congestion, used to ensure that the design scheme meets citizens' needs. Cultural relic protection scope restrictions refer to the regulations governing cultural relic protection areas that must be considered during the design and construction process. For example, the cultural relic protection scope restriction can be set as prohibiting any engineering construction work within a 500-meter radius of the location of the cultural relic. Geological taboo zone restrictions refer to specific geological areas that need to be avoided during design and construction. These areas may have unfavorable geological conditions, such as geological instability or high water levels, affecting the safety and feasibility of the project. For example, the geological taboo zone restriction can be set as requiring that the surface subsidence rate not exceed 2.5 millimeters per year.

[0024] In this application embodiment, collecting key data and indicators that affect the design of municipal transportation engineering in the target city can provide basic information for subsequent analysis and decision-making.

[0025] S120. Based on climate data and traffic flow data, retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database.

[0026] Specifically, the experience database refers to a historical database accumulated based on past experience, used to support design decisions and scheme optimization. Furthermore, the experience database is constructed based on publicly available cases of domestic municipal transportation engineering projects over the past 10 years, measured data from industry standards (such as the "Code for Design of Urban Road Engineering"), and project data accumulated by the applicant team. It covers engineering parameters for different climate zones, geological conditions, and city sizes. Climate impact parameters refer to quantitative or qualitative parameters describing the impact of climate on transportation engineering design, which may include heat island effect adjustment coefficients and precipitation variation coefficients. Traffic strategy adjustment parameters refer to parameters related to traffic flow management, such as signal timing optimization coefficients, lane number adjustment factors, speed limit adjustment factors, and public transportation priority weights, used to optimize traffic flow.

[0027] In this embodiment of the application, by referencing information from an experience database, and obtaining relevant climate impact parameters and traffic strategy adjustment parameters based on the actual climate and traffic flow data of the target city, it can be ensured that subsequent plans can be adjusted for specific climate and traffic flow.

[0028] S130. Determine the benchmark values ​​of design parameters for municipal transportation engineering based on climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters.

[0029] Specifically, the design parameter baseline values ​​refer to standardized design values ​​calculated based on experience using the aforementioned climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters. These values ​​may include road width, number of lanes, drainage system capacity, and traffic signal cycle, providing a basis for subsequent optimization.

[0030] In this embodiment, climate data and traffic flow data are actual values ​​reflecting the climate characteristics and traffic conditions of the target city; the climate impact parameters and traffic strategy adjustment parameters stored in the experience database are empirical values ​​extracted from historical engineering project data. This embodiment integrates real-time monitoring data with historical experience parameters to generate benchmark values ​​for design parameters of municipal transportation engineering, thereby ensuring that a prototype of a standardized design scheme that conforms to standards and reflects local characteristics can be constructed.

[0031] S140. Based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas are used as constraints. The design parameter benchmark values ​​are optimized using the simulated annealing algorithm to generate the initial parameter set.

[0032] Specifically, simulated annealing is a stochastic optimization algorithm that simulates the lattice recombination behavior of solid materials during annealing, providing efficient global search capabilities for municipal transportation engineering design. The core of the simulated annealing algorithm lies in its probabilistic acceptance mechanism: it allows for a certain degree of degradation at high temperatures to avoid getting trapped in local optima, and gradually converges to the globally optimal solution region as the "temperature parameter" decreases. The initial parameter set refers to the set of optimized design parameter baseline values, i.e., a set of potential design schemes generated under constraints of public demand indicators, cultural relic protection limits, and geologically restricted areas.

[0033] In this embodiment, the simulated annealing algorithm can accept suboptimal solutions with a certain probability, thereby avoiding getting trapped in local optima and enhancing global search capabilities. Optimizing the baseline design parameters using the simulated annealing algorithm can generate an initial parameter set containing multiple feasible solutions, offering the advantage of high diversity. Using the restrictions on the scope of cultural relic protection and geologically prohibited areas as constraints can filter out non-compliant solutions, reducing the complexity of subsequent calculations.

[0034] S150. Using the maximization of fitness score as the objective function, a genetic algorithm is used to process the initial parameter set and generate a set of alternative solutions.

[0035] Specifically, the fitness score refers to a score obtained by weighting various parameters; a higher score indicates a stronger adaptability of the solution to the actual environment. Maximizing the fitness score as the objective function helps improve the overall adaptability of the solution, meeting the requirements of various factors such as climate conditions, traffic demands, and public expectations. A genetic algorithm is an optimization algorithm based on the principles of biological evolution. Through selection, crossover, and mutation operations, it evolves better solutions from the population and is suitable for multi-objective optimization problems. The alternative solution set refers to a collection of different design solutions generated after processing by the genetic algorithm.

[0036] In this embodiment, the genetic algorithm can automatically and efficiently explore a massive parameter combination space, eliminating the reliance on manual parameter tuning in traditional methods. Specifically, the genetic algorithm fuses high-quality genes through crossover operations and introduces innovative solutions through mutation operations, effectively improving the diversity of municipal traffic engineering solutions. Combined with the high-quality initial solutions provided by the simulated annealing algorithm, this scheme can significantly improve global search capabilities.

[0037] S160. Extract engineering efficiency evaluation parameters from the set of alternative solutions. Based on the engineering efficiency evaluation parameters, calculate the sustainability quantification score of the set of alternative solutions using the random forest algorithm, generate a sorted list of solutions, and select the top-ranked solution.

[0038] Specifically, engineering efficiency evaluation parameters refer to parameters used to measure the performance of alternative solutions in terms of economy, construction time, quality, and environmental impact. The random forest algorithm is an ensemble learning method that improves the accuracy of classification and regression by constructing multiple decision trees and voting on the results, used to evaluate the sustainability quantification score of an alternative. The sustainability quantification score reflects a comprehensive score of each alternative across multiple dimensions, including environmental protection, economic benefits, and social impact, used to evaluate the feasibility of the alternative. The alternative ranking list refers to the list of alternatives ranked according to their sustainability quantification scores. The top-ranked alternative is the one ranked highest in the list and is usually considered the best choice.

[0039] In this embodiment, the sustainability of the scheme may involve dozens of indicators, including carbon emissions, green space occupation, and job creation, which exhibit complex nonlinear relationships. By employing the random forest algorithm and utilizing its multi-decision tree voting mechanism, the evaluation bias caused by a single model can be effectively avoided, and the risk of overfitting can be significantly reduced, thereby ensuring the accuracy and reliability of the sustainability quantitative score.

[0040] S170. Verify the compliance of the elements of the top row scheme and determine the final scheme.

[0041] Element compliance verification refers to checking whether the top row scheme meets all design requirements, industry standards and constraints to ensure that the scheme is feasible and compliant.

[0042] In this application embodiment, the top-ranking scheme can be verified through joint review by multiple departments to ensure that it is technically feasible, socially acceptable and compliant with legal regulations, and then the final scheme can be determined.

[0043] The technical solution of this application firstly automatically generates benchmark values ​​for design parameters of municipal transportation engineering by matching climate data, traffic flow data, and experience databases, effectively overcoming the subjective limitations of human experience. Secondly, it uses a simulated annealing algorithm combined with constraints such as cultural relic protection scope limitations and geological taboo zone limitations to ensure that the generated initial parameter set schemes both meet regulatory requirements and take into account local characteristics. Then, with the goal of maximizing the fitness score, a genetic algorithm is used to globally optimize the initial parameter set, generating a set of alternative schemes that can balance multiple conflicts and meet the personalized needs of the target city. Finally, a random forest algorithm is used to quantitatively evaluate the life-cycle benefits of the schemes in the alternative scheme set, achieving scientific decision-making. The forward design method for municipal transportation engineering provided by this application, combined with computer-aided design, solves the problem in traditional design where it is difficult to balance construction standardization with the personalized characteristics of the city, making the municipal transportation engineering design scheme highly matched with the actual needs of the city.

[0044] Based on the above embodiments, optionally, the climate data includes: temperature data, precipitation data, humidity data, and frequency of extreme weather events; traffic flow data includes: vehicle traffic volume, peak traffic hours, average vehicle speed, and proportion of public transport vehicles; climate impact parameters include: heat island effect adjustment coefficient and precipitation variation coefficient; traffic strategy adjustment parameters include signal timing optimization coefficient, lane number adjustment factor, speed limit adjustment factor, and public transport priority weight.

[0045] Based on climate and traffic flow data, climate impact parameters and traffic strategy adjustment parameters are retrieved from the empirical database, including: matching the corresponding heat island effect adjustment coefficient from the empirical database based on temperature and humidity data; matching the corresponding precipitation variation coefficient from the empirical database based on precipitation data and the frequency of extreme weather events; matching the corresponding traffic light timing optimization coefficient from the empirical database based on vehicle traffic volume and peak traffic hours; matching the corresponding lane number adjustment factor from the empirical database based on vehicle traffic volume; matching the corresponding speed limit adjustment factor from the empirical database based on average vehicle speed; and matching the corresponding public transport priority weight from the empirical database based on the proportion of public transport vehicles.

[0046] Specifically, the urban heat island effect adjustment coefficient quantifies the temperature rise in urban areas caused by human activities (such as construction and transportation). The heat island effect is typically influenced by air temperature and humidity; higher temperatures and humidity often exacerbate the urban heat island effect. The precipitation variation coefficient represents the degree of impact of precipitation changes on the transportation system. Changes in precipitation and the frequency of extreme weather events directly affect the design of traffic engineering, such as the demand for drainage systems. The traffic light timing optimization coefficient adjusts parameters for traffic light timing to optimize the efficiency of vehicle and pedestrian traffic. Vehicle traffic volume and peak traffic periods determine traffic flow; traffic light timing must be optimized based on these two data points to reduce congestion and improve traffic efficiency. The lane number adjustment factor determines and adjusts the number of lanes on a road. The number of lanes is directly proportional to vehicle traffic volume. The speed limit adjustment factor adjusts the maximum permissible speed on a road. The average vehicle speed reflects traffic flow to some extent; adjusting speed limits ensures traffic safety and efficiency. The public transport priority weight is a parameter used to evaluate the priority of public transport vehicles in traffic management. The proportion of public transportation affects the distribution of traffic flow, and the priority of public transportation determines its priority in traffic signals and road condition adjustments.

[0047] For example, the target city has an average annual temperature of 30°C and humidity of 70%. Based on the corresponding climate conditions found in the empirical database, the urban heat island effect adjustment coefficient is extracted to be 1.2. The target city has an annual precipitation of 1200 mm and an extreme weather event frequency (such as heavy rain) of 5 times per year. Based on the corresponding climate matching from the empirical database, the precipitation variation coefficient is 1.5. The target city has an average daily vehicle traffic volume of 2000 vehicles per hour, with peak hours from 8:00 AM to 9:00 AM. The traffic light timing optimization coefficient extracted from the empirical database is 0.75, and the lane number adjustment factor is 1.3. The target city's expected average vehicle speed is 40 km / h, and the speed limit adjustment factor obtained from the empirical database is 0.85. The target city's public transportation vehicle ratio is 20%, and the public transportation priority weight matched from the empirical database is 0.6.

[0048] Based on the above embodiments, optionally, the design parameter benchmark values ​​include: road foundation width benchmark value, lane number benchmark value, drainage system capacity benchmark value, pavement material weather resistance grade benchmark value, traffic signal cycle benchmark value, and bus lane proportion benchmark value. The design parameter benchmark values ​​for municipal traffic engineering are determined based on climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters, including: determining the road foundation width benchmark value based on vehicle traffic volume, average vehicle speed, speed limit adjustment factor, and traffic light timing optimization coefficient; determining the lane number benchmark value based on vehicle traffic volume and lane number adjustment factor; determining the drainage system capacity benchmark value based on precipitation data and precipitation variation coefficient; determining the pavement material weather resistance grade benchmark value based on temperature data, extreme weather event frequency, humidity data, and heat island effect adjustment coefficient; determining the traffic signal cycle benchmark value based on vehicle traffic volume and traffic light timing optimization coefficient; and determining the bus lane proportion benchmark value based on the proportion of public transport vehicles and public transport priority weight.

[0049] Specifically, the benchmark value for road foundation width refers to the standard width of the road foundation. The benchmark value for road foundation width can be calculated using the following formula:

[0050] Where W is the baseline value of road width, Q is the vehicle traffic volume, V is the average vehicle speed, Kv is the speed limit adjustment factor, Ks is the traffic light timing optimization coefficient, and α is the width conversion coefficient. The width conversion coefficient is determined by the proportion of different vehicle types; it is smaller when small vehicles predominate and larger when large vehicles predominate.

[0051] The baseline value for the number of lanes refers to the standard value for the number of lanes that should be provided on each road, determined during the design phase of municipal traffic engineering projects. The baseline value for the number of lanes can be calculated using the following formula:

[0052] Where N is the baseline value for the number of lanes, C is the single-lane capacity, and Kn is the lane number adjustment factor.

[0053] The baseline capacity value for a drainage system refers to the standard value of the flow rate that a road drainage system is required to handle during the design phase of municipal transportation engineering projects. The baseline capacity value for a drainage system can be calculated using the following formula:

[0054] Where M is the baseline value of drainage system capacity, p is the pavement runoff coefficient (for example, the pavement runoff coefficient of asphalt pavement is 0.9), q is the precipitation in mm / h, and F is the water accumulation area in km². 2 Kp is the precipitation variation coefficient.

[0055] The benchmark value for the weather resistance grade of pavement materials refers to the standard value of durability for different pavement materials under specific climatic conditions. The benchmark value for the weather resistance grade of pavement materials can be selected based on the weather resistance score, which can be calculated using the following formula:

[0056] Where S is the weather resistance score, Kt is the weight of temperature on weather resistance, T is the annual extreme temperature difference calculated from temperature data, and T0 is the reference extreme temperature difference; b is the weight of extreme weather frequency, E is the frequency of extreme weather events, c is the weight of humidity, H is the annual average relative humidity calculated from humidity data, H0 is the reference average humidity, d is the weight of heat island effect, and U is the heat island effect adjustment coefficient.

[0057] The traffic signal cycle reference value refers to the standard switching cycle time of traffic lights (such as red, green, and yellow lights). The traffic signal cycle reference value can be calculated using the following formula:

[0058] Where A is the traffic signal cycle reference value.

[0059] The benchmark value for the proportion of dedicated bus lanes refers to the standard proportion of dedicated bus lanes that must be set up on a road of a certain length. The benchmark value for the proportion of dedicated bus lanes can be calculated using the following formula:

[0060] Where B is the benchmark value for the proportion of bus lanes, Kr is the priority weight of public transportation, and R is the proportion of public transportation vehicles.

[0061] It should be noted that the values ​​of all coefficients set in the above formula, including but not limited to α, β, and p, should be determined based on the recommended range of GB 50220-2018 "Code for Design of Urban Road Engineering" and in conjunction with regression analysis of municipal transportation engineering cases in cities of different sizes.

[0062] Figure 2 A flowchart of another forward design method for municipal transportation engineering provided in this application embodiment, based on the above embodiments, such as... Figure 2 As shown, the method includes: S210: Obtain climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions for the target city.

[0063] S220. Based on climate data and traffic flow data, retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database.

[0064] S230. Determine the benchmark values ​​of design parameters for municipal transportation engineering based on climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters.

[0065] S240. Maximize the frequency of citizens' travel, maximize the utilization rate of public transportation, and maximize the satisfaction of citizens' congestion tolerance as optimization objectives. Set the baseline values ​​of design parameters as variables and establish a multi-objective optimization function based on the variables and optimization objectives.

[0066] Specifically, the indicators of citizen demand include: citizen travel frequency, public transportation utilization rate, and citizen congestion tolerance. For example, statistics show that the average daily travel frequency of citizens in the target city is 2 times, the public transportation utilization rate is 20%, and the citizen congestion tolerance is 15 minutes.

[0067] In the embodiments of this application, the multi-objective optimization function can simultaneously consider multiple conflicting objectives, thereby balancing the relationship between different indicators and improving the scientificity and rationality of decision-making.

[0068] S250. Using the design parameter baseline value as the initial solution of the simulated annealing algorithm, verify whether the initial solution simultaneously meets the restrictions of cultural relic protection scope and geological taboo area.

[0069] In this application embodiment, verifying in advance whether the initial solution complies with the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas can avoid invalid solution generation process and make the solution process simpler.

[0070] S260. If the initial solution simultaneously meets the restrictions of cultural relic protection scope and geological taboo area, then the simulated annealing algorithm is used to optimize the initial solution to generate an initial parameter set that satisfies the multi-objective optimization function and meets the constraints.

[0071] Specifically, the simulated annealing algorithm can simultaneously maximize multiple objectives, ensuring that the generated parameter set more comprehensively meets the needs of citizens and complies with the constraints of cultural relic protection and geological conditions, thus providing scientific support for urban traffic planning. For example, the simulated annealing algorithm sets the initial temperature to 100°C, the cooling rate to 0.95, the termination temperature to 1, and the number of iterations to 500. Optionally, if the initial solution does not meet the restrictions of the cultural relic protection area, the geographical coordinates of the cultural relic protection area are obtained, a path planning algorithm is used to generate a cultural relic avoidance path, and the initial solution is updated based on the cultural relic avoidance path.

[0072] Specifically, a path planning algorithm refers to a computer algorithm used to find the optimal or efficient path from a starting point to a destination in a given environment. For example, a path planning algorithm could be Dijkstra's algorithm.

[0073] In this embodiment of the application, planning the avoidance path for cultural relics can ensure that the scope of cultural relic protection is not violated in the design of municipal traffic engineering, and maintain the integrity of historical and cultural heritage.

[0074] Optionally, if the initial solution does not meet the geological taboo zone restriction, the geographical coordinates of the geological taboo zone are obtained, an environmental avoidance path is generated using a path planning algorithm, and the initial solution is updated based on the environmental avoidance path.

[0075] In this embodiment of the application, the planned environmental avoidance path can avoid geological environments that may affect construction quality, thus ensuring the quality and sustainability of municipal transportation projects.

[0076] S270. Using the maximization of fitness score as the objective function, a genetic algorithm is used to process the initial parameter set and generate a set of alternative solutions.

[0077] S280. Extract engineering efficiency evaluation parameters from the set of alternative solutions. Based on the engineering efficiency evaluation parameters, calculate the sustainability quantification score of the set of alternative solutions using the random forest algorithm, generate a sorted list of solutions, and select the top-ranked solution.

[0078] S290. Verify the compliance of the elements of the top row scheme and determine the final scheme.

[0079] The technical solution of this application, through simulated annealing algorithm to optimize the initial solution, can efficiently generate a set of parameters that satisfy multiple objectives and constraints. This technical solution not only generates higher-quality design schemes but also ensures the legal and environmental compliance of the municipal engineering project, providing scientific support for urban transportation planning.

[0080] Figure 3A flowchart of another forward design method for municipal transportation engineering provided in this application embodiment, based on the above embodiments, such as... Figure 3 As shown, the method includes: S310: Obtain climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions for the target city.

[0081] S320. Based on climate data and traffic flow data, retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database.

[0082] S330. Determine the benchmark values ​​of design parameters for municipal transportation engineering based on climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters.

[0083] S340. Based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas are used as constraints. The design parameter benchmark values ​​are optimized using the simulated annealing algorithm to generate the initial parameter set.

[0084] S350. Generate multiple initial candidate schemes randomly based on the initial parameter set, and form an initial candidate scheme set based on the fitness score of each initial candidate scheme.

[0085] Specifically, the adaptability score includes: environmental impact assessment score, economic benefit analysis score, regulatory compliance score, and technical feasibility score. The environmental impact assessment score can be quantified using the total pollutant emissions during construction; the economic benefit analysis score can be quantified using construction costs, operating costs, and maintenance costs; the regulatory compliance score can be quantified based on a compliance checklist; and the technical feasibility score can be quantified based on industry standards.

[0086] For example, the adaptability score = w1 × environmental impact assessment score + w2 × economic benefit analysis score + w3 × regulatory compliance score + w4 × technical feasibility score. Where w1, w2, w3, and w4 are the weights for environmental impact, economic benefits, regulatory compliance, and technical feasibility, respectively.

[0087] Optionally, an initial candidate solution set is formed based on the fitness score of each initial candidate solution, including: calculating the fitness score of each initial candidate solution; for initial candidate solutions that exceed a preset score threshold, allocating selection probabilities according to their corresponding fitness score proportions, and using a roulette wheel selection method to filter and form an initial candidate solution set.

[0088] Specifically, a preset score threshold is used to filter out candidate solutions with low fitness scores. The roulette wheel selection method refers to a selection mechanism that visualizes and converts the selection probabilities of candidate solutions into a roulette wheel model, randomly selecting a solution. The principle is as follows: First, a probability assignment is made for each initial candidate solution, ensuring that the selection probability of each solution is proportional to its fitness score; then, the selection probabilities of all candidate solutions are treated as the size of an area on a roulette wheel, with solutions having higher fitness scores occupying a larger area; finally, the roulette wheel selection method is used multiple times to generate the next generation of candidate solutions. In the roulette wheel algorithm, individuals with high fitness scores are more likely to be selected, thus driving the genetic algorithm towards a better solution. Simultaneously, due to the randomness of the roulette wheel selection, even candidate solutions with lower scores have a chance to be selected. This mechanism ensures solution diversity and prevents the algorithm from prematurely converging to a local optimum.

[0089] In this embodiment of the application, multiple initial candidate solutions are randomly generated using multiple initial parameters, which provides a rich candidate basis for subsequent optimization and increases the possibility of finding the optimal solution.

[0090] S360. Reorganize some parameters in the initial candidate solution set to generate a crossover solution; randomly change some parameters in the crossover solution to generate a variant solution.

[0091] Specifically, the recombination process is equivalent to simulating the natural selection mechanism, randomly combining the features of multiple excellent solutions to form new, potentially better design schemes, increasing the diversity of the structure. Then, random variations are introduced to increase the extensibility and exploratory nature of the solution space, enabling the algorithm to escape local optima and find better global solutions.

[0092] S370. Using the limitations of cultural relic protection scope and geological taboo areas as constraints for the genetic algorithm, the mutation schemes are verified, and the mutation schemes that meet the constraints are retained as improvement candidate schemes.

[0093] Specifically, since the mutation scheme includes newly generated schemes, it is necessary to re-verify whether they meet the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas, so as to eliminate unqualified schemes in a timely manner and reduce subsequent computing resources.

[0094] S380. Update the initial candidate solutions with improved candidate solutions, continue iterative calculation until the termination condition is met, and output the set of alternative solutions; wherein, the termination condition includes: reaching the maximum number of iterations, or the change value of the adaptive score is less than the preset score change threshold.

[0095] Specifically, the preset score change threshold can be set based on industry experience and best practices, and expert recommendations. Continuously iterating by replacing the initial candidate solution with newly generated improved candidate solutions can continuously optimize and improve the fitness score. Setting a maximum number of iterations and a preset score change threshold can prevent the genetic algorithm from looping infinitely and control the algorithm's runtime.

[0096] S390. Extract engineering efficiency evaluation parameters from the set of alternative solutions. Based on the engineering efficiency evaluation parameters, calculate the sustainability quantification score of the set of alternative solutions using the random forest algorithm, generate a sorted list of solutions, and select the top-ranked solution.

[0097] S300. Verify the compliance of the elements of the top row scheme and determine the final scheme.

[0098] The technical solution of this application utilizes a genetic algorithm to process the initial parameter set, thereby efficiently exploring and optimizing the solution space. Specifically, the crossover and mutation mechanisms in the genetic algorithm can generate new candidate solutions, driving the search for better solutions. Simultaneously, through multiple rounds of iterative calculations, the solution is continuously improved, ensuring that the final output set of candidate solutions has a higher fitness score.

[0099] Based on the above embodiments, optionally, engineering efficiency evaluation parameters are extracted from the candidate solution set. Based on these parameters, a sustainability quantification score for each candidate solution set is calculated using a random forest algorithm to generate a ranked solution list and select the top-ranked solution. This includes: extracting engineering efficiency evaluation parameters from the candidate solution set, wherein the engineering efficiency evaluation parameters include economic cost, construction time, construction quality score, and environmental impact score; and the sustainability quantification score includes economic sustainability, time sustainability, quality sustainability, and environmental sustainability. A set proportion of historical engineering efficiency evaluation parameters are taken from an experience database as sample features, and the corresponding historical sustainability quantification scores are taken as label values ​​to train a random forest model. The economic cost, construction time, construction quality score, and environmental impact score are organized into feature vectors, which are used as input to the random forest model. The sustainability quantification score of the candidate solution set is output. The candidate solutions are ranked according to the sustainability quantification score to generate a ranked solution list, and the top-ranked solution with the highest score is selected.

[0100] Specifically, engineering efficiency assessment parameters are used to evaluate municipal transportation projects, including economic cost, construction time, construction quality score, and environmental impact score, which correspond one-to-one with economic sustainability, time sustainability, quality sustainability, and environmental sustainability, respectively. For example, the weights for economic sustainability, time sustainability, quality sustainability, and environmental sustainability can be 0.3, 0.2, 0.25, and 0.25, respectively. Historical sustainability quantification scores are indicators stored in an experience database after historical engineering efficiency assessment parameters have been reviewed by experts or determined by industry sustainability evaluation standards.

[0101] For example, the set of alternative solutions output by the genetic algorithm is first standardized to map design parameters of different dimensions to the [0,1] interval, ensuring that the engineering efficiency evaluation parameters can be directly input into the random forest model; then the number of decision trees in the random forest model is set to 100, and the model accuracy is optimized by 5-fold cross-validation to avoid overfitting.

[0102] In this embodiment, a random forest model is first trained based on historical engineering efficiency evaluation parameters and their corresponding historical sustainability quantification scores. Then, the sustainability of the candidate solution set is evaluated using the random forest model to select the top-ranked solution. This achieves standardization and automation of the evaluation process, significantly improving the efficiency and accuracy of solution selection.

[0103] Based on the above embodiments, optionally, after verifying the compliance of the top row scheme with the elements and determining the final scheme, the method further includes: during the implementation of the final scheme, tracking climate data and traffic flow data in real time and making dynamic adjustments to the final scheme.

[0104] For example, when the tracked climate data or traffic flow data changes significantly, such as when the frequency of extreme weather events increases beyond a preset threshold, or when the traffic volume during peak hours exceeds 15% of the design threshold, the traffic strategy adjustment parameters in the final plan are dynamically adjusted to adapt to the gradually changing environmental requirements.

[0105] In this embodiment, dynamic adjustments are made based on real-time environmental changes during implementation, which enhances the flexibility and adaptability of municipal transportation engineering. Figure 4 This is a schematic diagram of the forward design system for municipal transportation engineering provided in an embodiment of this application. Figure 4 As shown, the forward design system for this municipal transportation project includes: The data acquisition module 410 is used to acquire climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions and geological taboo zone restrictions of the target city; and to retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database based on climate data and traffic flow data. The benchmark determination module 420 is used to determine the benchmark values ​​of design parameters for municipal transportation engineering based on climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters. The parameter optimization module 430 is used to optimize the baseline values ​​of design parameters based on the citizen demand indicators, taking the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas as constraints, and using the simulated annealing algorithm to generate an initial parameter set. The scheme determination module 440 is used to process the initial parameter set with the objective function of maximizing the fitness score, and generate a set of candidate schemes using a genetic algorithm. Then, engineering efficiency evaluation parameters are extracted from the set of candidate schemes. Based on the engineering efficiency evaluation parameters, the sustainability quantification score of the set of candidate schemes is calculated by the random forest algorithm to generate a scheme ranking list and select the top-ranked scheme. Finally, the feature compliance of the top-ranked scheme is verified to determine the final scheme.

[0106] The forward design system for municipal transportation engineering provided in this application can execute the forward design method for municipal transportation engineering provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects of the execution method.

[0107] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0108] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A forward design method for municipal transportation engineering, characterized in that, include: Obtain climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions for the target city; Based on the climate data and the traffic flow data, retrieve the climate impact parameters and traffic strategy adjustment parameters from the empirical database; The baseline values ​​of the design parameters for the municipal transportation project are determined based on the climate data, the traffic flow data, the climate impact parameters, and the traffic strategy adjustment parameters. Based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on geological taboo areas are used as constraints. The design parameter baseline values ​​are optimized using the simulated annealing algorithm to generate an initial parameter set. Using the maximization of fitness score as the objective function, a genetic algorithm is used to process the initial parameter set to generate a set of alternative solutions; Engineering efficiency evaluation parameters are extracted from the set of candidate solutions. Based on the engineering efficiency evaluation parameters, the sustainability quantification score of the set of candidate solutions is calculated by the random forest algorithm. A solution ranking list is generated, and the top-ranked solution is selected. Verify the compliance of the elements in the top row scheme to determine the final scheme.

2. The forward design method for municipal transportation engineering according to claim 1, characterized in that, The climate data includes: temperature data, precipitation data, humidity data, and frequency of extreme weather events; the traffic flow data includes: vehicle traffic volume, peak traffic hours, average vehicle speed, and proportion of public transport vehicles; the climate impact parameters include: heat island effect adjustment coefficient and precipitation variation coefficient; the traffic strategy adjustment parameters include: signal timing optimization coefficient, lane number adjustment factor, speed limit adjustment factor, and public transport priority weight; the step of retrieving climate impact parameters and traffic strategy adjustment parameters from an empirical database based on the climate data and the traffic flow data includes: Based on the temperature data and the humidity data, the corresponding heat island effect adjustment coefficient is matched from the empirical database; Based on the precipitation data and the frequency of extreme weather events, the corresponding precipitation variation coefficient is matched from the empirical database; Based on the vehicle traffic volume and the peak traffic period, the corresponding traffic light timing optimization coefficients are matched from the experience database; The corresponding lane number adjustment factor is matched from the experience database based on the vehicle traffic volume. The corresponding vehicle speed limit adjustment factor is matched from the experience database based on the average vehicle speed. Based on the proportion of public transport vehicles, the corresponding public transport priority weights are matched from the experience database.

3. The forward design method for municipal transportation engineering according to claim 2, characterized in that, The design parameter benchmark values ​​include: road foundation width benchmark value, lane number benchmark value, drainage system capacity benchmark value, pavement material weather resistance grade benchmark value, traffic signal cycle benchmark value, and bus lane proportion benchmark value; determining the design parameter benchmark values ​​of the municipal traffic engineering project based on the climate data, traffic flow data, climate impact parameters, and traffic strategy adjustment parameters includes: The road base width reference value is determined based on the vehicle traffic volume, the average vehicle speed, the speed limit adjustment factor, and the traffic light timing optimization coefficient. The baseline value for the number of lanes is determined based on the vehicle traffic volume and the lane number adjustment factor; The baseline value of the drainage system capacity is determined based on the precipitation data and the precipitation variation coefficient. The benchmark value for the weather resistance grade of the pavement material is determined based on the temperature data, the frequency of extreme weather events, the humidity data, and the heat island effect adjustment coefficient. The traffic signal cycle reference value is determined based on the vehicle traffic volume and the traffic light timing optimization coefficient. The benchmark value for the proportion of dedicated bus lanes is determined based on the proportion of public transport vehicles and the priority weight of public transport.

4. The forward design method for municipal transportation engineering according to claim 1, characterized in that, The citizen demand indicators include: citizen travel frequency, public transportation utilization rate, and citizen congestion tolerance. Based on these citizen demand indicators, and using the restrictions on the scope of cultural relic protection and the restrictions on geologically prohibited areas as constraints, a simulated annealing algorithm is employed to optimize the baseline values ​​of the design parameters, generating an initial parameter set, including: The optimization objectives are set as maximizing the frequency of citizens' travel, maximizing the utilization rate of public transportation, and maximizing the satisfaction of citizens' congestion tolerance. The baseline values ​​of the design parameters are set as variables. A multi-objective optimization function is established based on the variables and the optimization objectives. Using the design parameter baseline value as the initial solution of the simulated annealing algorithm, verify whether the initial solution simultaneously meets the cultural relic protection scope restriction and the geological taboo zone restriction; If the initial solution simultaneously meets the restrictions of the cultural relic protection scope and the geological taboo zone, then the simulated annealing algorithm is used to optimize the initial solution to generate the initial parameter set that satisfies the multi-objective optimization function and meets the constraints.

5. The forward design method for municipal transportation engineering according to claim 4, characterized in that, The step of optimizing the design parameter baseline values ​​using a simulated annealing algorithm, based on the citizen demand indicators, the restrictions on the scope of cultural relic protection, and the restrictions on geologically prohibited areas as constraints, to generate an initial parameter set, also includes: If the initial solution does not meet the cultural relic protection scope limit, then obtain the geographical coordinates of the cultural relic protection scope, use a path planning algorithm to generate a cultural relic avoidance path, and update the initial solution based on the cultural relic avoidance path; And / or, if the initial solution does not meet the geological taboo zone restriction, then obtain the geographical coordinates of the geological taboo zone, use a path planning algorithm to generate an environmental avoidance path, and update the initial solution based on the environmental avoidance path.

6. The forward design method for municipal transportation engineering according to claim 4, characterized in that, The adaptability score includes: environmental impact assessment score, economic benefit analysis score, regulatory compliance score, and technical feasibility score. The initial parameter set is processed using a genetic algorithm, with the objective function of maximizing the adaptability score, to generate a set of alternative solutions, including: Multiple initial candidate schemes are randomly generated based on the initial parameter set, and an initial candidate scheme set is formed based on the fitness score of each initial candidate scheme. Reorganize some parameters in the initial candidate solution set to generate a crossover solution; randomly change some parameters in the crossover solution to generate a mutation solution; Using the limitations of the cultural relic protection area and the limitations of the geological taboo area as constraints for the genetic algorithm, the mutation schemes are verified, and the mutation schemes that meet the constraints are retained as improvement candidate schemes. The improved candidate solution is used to update the initial candidate solution, and the iteration calculation continues until the termination condition is met, and the set of alternative solutions is output; wherein, the termination condition includes: reaching the maximum number of iterations, or the change value of the adaptive score is less than a preset score change threshold.

7. The forward design method for municipal transportation engineering according to claim 6, characterized in that, The step of forming an initial candidate solution set based on the fitness score of each initial candidate solution includes: Calculate the fitness score for each of the initial candidate solutions; For the initial candidate solutions that exceed the preset score threshold, the selection probability is allocated according to the corresponding fitness score ratio, and the roulette wheel selection method is used for screening to form the initial candidate solution set.

8. The forward design method for municipal transportation engineering according to claim 1, characterized in that, The process involves extracting engineering efficiency evaluation parameters from the set of candidate solutions, calculating the sustainability quantification score of the candidate solution set using a random forest algorithm based on these parameters, generating a ranked solution list, and selecting the top-ranked solution, including: The engineering efficiency evaluation parameters are extracted from the set of alternative solutions; wherein, the engineering efficiency evaluation parameters include economic cost, construction time, construction quality score and environmental impact score, and the sustainability quantification score includes economic sustainability, time sustainability, quality sustainability and environmental sustainability; A set proportion of historical engineering efficiency evaluation parameters are taken from the experience database as sample features, and the historical sustainability quantitative scores corresponding to the historical engineering efficiency evaluation parameters are taken as label values ​​to train a random forest model. The economic cost, construction time, construction quality score, and environmental impact score are organized into a feature vector, which is then used as input to the random forest model to output a sustainability quantification score for the set of alternative solutions. The alternative solutions are sorted according to the sustainability quantification score to generate a sorted list of solutions, and the top-ranked solution with the highest score is selected.

9. The forward design method for municipal transportation engineering according to claim 1, characterized in that, After verifying the element compliance of the top row scheme and determining the final scheme, the process further includes: When implementing the final solution, the climate data and traffic flow data are tracked in real time, and the final solution is dynamically adjusted accordingly.

10. A forward design system for municipal transportation engineering, characterized in that, include: The data acquisition module is used to acquire climate data, traffic flow data, citizen demand indicators, cultural relic protection scope restrictions, and geological taboo zone restrictions of the target city; and to retrieve climate impact parameters and traffic strategy adjustment parameters from the experience database based on the climate data and traffic flow data. The benchmark determination module is used to determine the benchmark values ​​of the design parameters of the municipal transportation project based on the climate data, the traffic flow data, the climate impact parameters, and the traffic strategy adjustment parameters. The parameter optimization module is used to optimize the baseline values ​​of the design parameters using a simulated annealing algorithm, based on the citizen demand indicators, the restrictions on the scope of cultural relic protection and the restrictions on the geological taboo areas, and to generate an initial parameter set. The scheme determination module is used to process the initial parameter set using a genetic algorithm with the objective function of maximizing the fitness score, generating a set of candidate schemes; then, it extracts engineering efficiency evaluation parameters from the set of candidate schemes, and calculates the sustainability quantification score of the set of candidate schemes using a random forest algorithm based on the engineering efficiency evaluation parameters, generates a scheme ranking list, and selects the top-ranked schemes; finally, it verifies the feature compliance of the top-ranked schemes and determines the final scheme.

Images