A drainage facility layout optimization method for a widened highway

Abstract

This invention discloses a method for optimizing the layout of drainage facilities for wide-width pavements of reconstructed and expanded highways, belonging to the field of road drainage technology. The method includes the following steps: digital modeling of road features; modeling of rainfall conditions and surface runoff; prediction of water film thickness based on the coupling characteristics of water flow on wide pavements; parametric modeling of drainage structural capacity; adaptive multi-segment road zoning and multi-objective optimization; global layout optimization based on an improved genetic algorithm; and scheme output. This invention constructs a complete technology chain from digital modeling of road features, rainfall runoff analysis, and water film thickness prediction to adaptive zoning, intelligent optimization, and scheme output. It transforms the traditional trial-and-error model relying on manual experience into a data-driven automated design process, effectively improving design efficiency and thus significantly reducing labor costs and design cycle time.

Description

Technical Field

[0001] This invention relates to the field of road drainage technology, and in particular to a method for optimizing the layout of drainage facilities for wide road surfaces of highways undergoing reconstruction and expansion. Background Technology

[0002] As a core component of the transportation system, the safety and durability of highways directly depend on the rationality of their pavement drainage system design. Traditional highway drainage design mainly relies on the deployment of infrastructure such as cross slopes, longitudinal slopes, drainage ditches, and drainage holes to achieve rapid drainage of water film on the pavement under rainfall conditions, thereby ensuring driving safety. However, with the continuous growth of traffic demand, modern highways are gradually exhibiting significant characteristics such as wider width (6-10 lanes), higher speed (design speed of 120 km / h and above), and greater complexity (including special geometric structures such as superelevated transition sections, low-lying vertical curves, extra-wide merging and diverging sections, and bridge deck transition sections). Traditional drainage design methods based on human experience are no longer sufficient to meet the actual engineering needs.

[0003] The core problems of existing technologies are mainly reflected in the following aspects: The road segmentation method is fixed and rigid, often based on pre-defined logic such as 50m before and after superelevation sections and 50m before and after low-lying points, without adaptive adjustment according to the actual changes in road geometry parameters, resulting in insufficient targeted design for complex sections; Furthermore, the drainage facilities are of a single type and have a fixed layout, mostly using regular layouts of transverse or longitudinal drainage ditches, lacking flexibility in location and spacing, and unable to adapt to the drainage needs of special areas such as low-lying points, superelevation points, interchange noses, and bridge transition sections, resulting in a persistently high risk of water accumulation in some areas; At the same time, the accuracy of water film thickness prediction is insufficient. Many existing models are based on average slope estimation and do not consider local cross slope reversal, longitudinal slope changes, catchment area changes, and water flow coupling effects between multiple lanes, making it difficult to accurately identify high-risk areas for hidden water accumulation. Furthermore, existing technologies have not established a synergistic model for multiple types of drainage facilities, and the drainage capacity of combined measures such as transverse drainage ditches, longitudinal culverts, and permeable pavements has not been quantitatively coupled, resulting in poor overall drainage system efficiency. Finally, existing technologies lack intelligent optimization algorithms, and the design process relies on manual calculations, making it impossible to achieve global optimization of the type, location, and quantity of drainage facilities, and also making it difficult to balance multiple objectives such as water film control, project cost, and maintenance accessibility.

[0004] Based on the existing technical problems, there is a lack of road zoning algorithms suitable for wide-span highways, making it difficult to accurately classify road segment characteristics; there is a lack of high-precision water film prediction models that can map the water flow characteristics of different road segments, making it impossible to accurately capture the water accumulation mechanism under complex geometric conditions; there is a lack of a unified parameterized mathematical model for drainage structures, making it difficult to incorporate various facilities into the collaborative optimization framework; and there is a lack of intelligent algorithm systems that support multi-objective automatic optimization, making it impossible to automate and improve the efficiency of the design process. Therefore, it is particularly important to develop a wide-span highway drainage layout optimization method with adaptive capabilities, high-precision prediction, and intelligent optimization characteristics. Summary of the Invention

[0005] The purpose of this invention is to solve the problems mentioned in the background art by proposing an optimization method for the layout of drainage facilities for wide road surfaces of highways that have been reconstructed and expanded.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: A method for optimizing the layout of drainage facilities for wide-width road surfaces in highway reconstruction and expansion includes the following steps: S1. Digital Modeling of Road Features: Collecting the geometric and material parameters of the target highway, and discretizing the continuous road into... Each of the tiny computing units records the road width. , Hengpo Longitudinal slope curve radius and the permeability coefficient of road surface materials Total length of road ,in For the first The length of each computational unit; S2. Rainfall Condition and Surface Runoff Modeling: Determine rainfall intensity based on the design standards of the project location. Calculate the rainfall inflow per unit area ; Determining the first based on cross slope and longitudinal slope Water flow direction vector of each computing unit ; and by using the confluence analysis method, the flow through the first Original unit width flow rate of each computing unit ; in To merge into the first The set of upstream units of each computing unit. Contribute indicator factors to traffic flow; S3. Water film thickness prediction based on the coupling characteristics of water flow on wide road surfaces: introducing a lane confluence correction factor. The original unit width flow rate was corrected to obtain , in , For empirical coupling coefficients, To merge into the lane The upstream adjacent lane set, For the upstream adjacent lane In unit The cross slope at that location, It is a very small positive value. For lane The width; Substitute the corrected flow rate into the equation for calculating water film thickness. ; in The roughness coefficient of the road surface is Manning's roughness coefficient. To take into account the slope, the water film thickness distribution along the confluence path was calculated iteratively to obtain the total water film thickness distribution along the entire road section. S4. Parametric Modeling of Drainage Structure Capacity: Parametric models of drainage capacity are established for transverse drainage ditches, longitudinal drainage facilities, and permeable pavements, and the drainage capacity of each type of drainage facility is quantified as a function of its key design parameters. S5. Adaptive Multi-Segment Road Zoning and Multi-Objective Optimization: Constructing a Multi-Dimensional Feature Vector for Each Computational Unit ; in For geometric parameters, For meteorological parameters, For road surface material parameters, As a sensitivity indicator for drainage structure, As a risk indicator for predicting water film thickness; Clustering algorithms or threshold detection based on the rate of change are used to analyze the feature vector set and automatically divide the road into zones. Within each zone, a multi-objective optimization problem is constructed, with the objective function being: ; in This represents the maximum water film thickness within the zone. The total construction cost, To maintain the quantifiable burden indicators, the constraints are as follows: and , The safe threshold for water film thickness. For the total drainage capacity of the facility, Total inflow; S6. Global layout optimization based on improved genetic algorithm: Chromosome encoding is used to represent the drainage layout scheme, and chromosomes... ; Each gene , For the location of the facility, For lateral position or lane number, Code the facility type. For a specific parameter vector; Genetic iteration is performed using a segmented preservation crossover operator and a risk-oriented adaptive mutation operator, with mutation probability... , Based on the probability of mutation, The adjustment coefficient is used to comprehensively evaluate the performance of the scheme through the fitness function, and constraints and penalties are applied. S7. Solution Output: The output includes the type, quantity, location and spacing of drainage facilities in each zone, the predicted maximum water film thickness and safety margin assessment, the total project cost estimate and the optimization report of construction recommendations for key parts.

[0007] Preferably, the geometric and material parameters mentioned in step S1 include longitudinal slope, cross slope, curve radius, pavement width, and pavement material permeability coefficient, and the length of the calculation unit. The value of allows the discretized model to reflect the continuous changes in road geometric parameters.

[0008] Furthermore, the confluence analysis method described in step S2 is based on the principle of digital elevation model, and the flow contribution indicator factor... Automatically determined by the confluence direction vector, when the upstream unit Water inlet unit hour, The value is 1 if it is not 1, otherwise the value is 0.

[0009] Furthermore, the empirical coupling coefficient in step S3 The value ranges from 0.05 to 0.2, and is calibrated using historical hydrological data or computational fluid dynamics simulations; the minimum positive value... An example value is 1e-5, used to prevent division by zero.

[0010] Preferably, the solution process for the water film thickness calculation equation in step S3 is to iterate sequentially from upstream to downstream of the road along the confluence path until the water film thickness distribution across the entire road surface tends to stabilize.

[0011] Furthermore, the parameterized model for drainage structural capacity described in step S4 is specifically as follows: Horizontal drainage ditch: ,in For flow coefficient, For effective water inlet length, The water depth or threshold height is calculated from the entrance. Longitudinal drainage facilities: ,in The roughness coefficient is Manning's coefficient. The cross-sectional area of ​​the water passage. The hydraulic radius is calculated using the following formula: , For wet period, To create a slope; Permeable pavement: , To ensure the stable infiltration rate of road surface materials, It represents the surface area of ​​the permeable pavement.

[0012] Furthermore, the clustering algorithm described in step S5 is the K-means algorithm, and the dynamic partitioning algorithm forms road partitions by identifying computational units with similar properties.

[0013] Furthermore, the weighting coefficients mentioned in step S5 Adjustments based on project priority requirements to meet [the needs of the project]. .

[0014] Furthermore, the segmented preservation type crossover operator described in step S6 identifies the road partition boundaries during crossover and swaps the gene segments corresponding to the complete partitions in the parent generation as a whole. In risk-oriented adaptive mutation, location mutation moves step by step towards the upstream of the affected area or adjacent units with greater water film thickness. Type mutation refers to the preset facility and scenario adaptation rule library, specifically including: low concave vertical curve segments are preferentially mutated into longitudinal underground ditches, and ultra-high gradient segments are preferentially mutated into transverse drainage ditches.

[0015] Furthermore, in step S6, deterministic rules are used to avoid illegal solutions during the initial population generation, excluding bridge approach slabs and no-layout zones; the fitness function comprehensively evaluates drainage performance, cost, and construction risks, and imposes penalties on individuals that violate spacing constraints and no-layout zone constraints.

[0016] Compared with the prior art, the present invention provides a method for optimizing the layout of drainage facilities for wide road surfaces in highway reconstruction and expansion, which has the following beneficial effects: 1. This invention constructs a complete technology chain from digital modeling of road features, rainfall runoff analysis, water film thickness prediction, to adaptive zoning, intelligent optimization, and scheme output. It transforms the traditional trial calculation mode that relies on human experience into a data-driven automated design process, which effectively improves design efficiency and thus effectively reduces labor costs and design cycle.

[0017] 2. This invention quantifies the water flow coupling effect between multiple lanes by introducing a lane confluence correction factor. Combined with a confluence analysis method based on the principle of digital elevation model, it constructs a high-precision water film thickness prediction model suitable for wide road surfaces. It can accurately capture the influence of factors such as local cross slope reversal, longitudinal slope change, and water catchment area change on water film thickness, and successfully identify hidden high-risk areas of water accumulation that are difficult to detect by traditional models, providing a reliable basis for subsequent optimization design.

[0018] 3. This invention constructs a multi-dimensional feature vector containing geometric parameters, meteorological parameters, pavement material parameters, drainage structure sensitivity indicators, and water film risk indicators. It uses K-means clustering algorithm or threshold detection method based on rate of change to achieve adaptive road zoning, ensuring that the design strategy of each section is accurately matched with its own characteristics. For different types of sections such as superelevation transition sections, low-concave vertical curve sections, straight super-wide sections, and bridge deck transition sections, it formulates differentiated optimization schemes for different types of sections, such as transverse drainage ditches as the main type, transverse and longitudinal combined drainage, longitudinal underground ditches as the main type, and densified drainage holes, which effectively solves the problem that traditional fixed layouts cannot adapt to complex road sections.

[0019] 4. This invention establishes a parameterized capability model for multiple types of drainage facilities, quantifying the drainage capacity of facilities such as transverse drainage ditches, longitudinal culverts, and permeable pavements into functions of design parameters. Combined with an improved genetic algorithm, it achieves multi-objective global optimization. Under the premise of meeting the safety threshold of water film thickness ≤ 3.5mm and the total drainage capacity of the facilities ≥ total inflow, it takes into account drainage performance, engineering cost, and maintenance burden, effectively solving the risk of water accumulation in complex sections. At the same time, the total number of drainage facilities is significantly reduced, achieving synergistic optimization of safety and economy. Attached Figure Description

[0020] Figure 1 This is a flowchart of a method for optimizing the layout of drainage facilities for wide-width road surfaces in highway reconstruction and expansion, as proposed in this invention. Figure 2 This is a diagram illustrating the effect of a water film thickness prediction model in a drainage facility layout optimization method for wide-width road surfaces of highways proposed in this invention. Figure 3 This is a parameterized model diagram of drainage facilities in a drainage facility layout optimization method for wide-width road surfaces of highways proposed in this invention. Figure 4 This is a schematic diagram of the drainage facility layout coding in a drainage facility layout optimization method for wide road surfaces of highways proposed in this invention. Detailed Implementation

[0021] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] Example 1: In the specific implementation, a 1.2km long wide section of a certain expressway was selected as the target section. This section has typical characteristics of wide width, high speed, and complexity: eight lanes in both directions, a design speed of 120km / h, and includes four types of complex geometric sections: superelevation transition sections, low-concave vertical curve sections, straight super-wide sections, and bridge deck transition sections. The design rainfall intensity at the project site is [not specified]. =120mm / h, the required maximum safe water film thickness on the road surface ≤3.5mm.

[0023] Reference Figures 1-4 A method for optimizing the layout of drainage facilities for wide-width road surfaces in highway reconstruction and expansion, comprising the following steps: Step S1: Digital modeling of road features: Collect the geometric and material parameters of this road section, specifically including the cross slope of each section. Longitudinal slope curve radius Road width and the permeability coefficient of road surface materials Using a uniform discretization method, the 1.2km continuous road was discretized into N=1210 tiny computational units, each with a length of... ≈1m, total road length Each calculation unit independently records parameter data. For example, the parameters of a certain unit in the ultra-high gradient section are: =34.5m =2.5%, =0.8%, =2500m =80mm / h.

[0024] Step S2, Rainfall Condition and Surface Runoff Modeling: Rainfall inflow calculation: Based on the design rainfall intensity of i=120mm / h at the project site, according to the formula... The rainfall inflow per unit area was calculated. =120×10 - ³ / 3600≈3.33×10 -5 m³ / (s m²); Confluence direction determination: based on the cross slope of each computational unit and longitudinal slope Determine the direction vector of water flow. For example, a certain unit of a low-concave vertical curve segment ; Raw unit width flow rate calculation: Based on the principle of digital elevation model, a runoff analysis method is used to calculate the raw unit width flow rate of each calculation unit. ;in For the set of upstream units that merge into the k-th unit, Automatically determined by the confluence direction vector, upstream unit When the water flows in =1, otherwise 0; Calculation shows that the core unit of the low-concave vertical curve segment... ≈0.0012m³ / (s m).

[0025] Step S3: Prediction of water film thickness based on the coupling characteristics of water flow on wide road surfaces: Inter-lane merging correction: Empirical coupling coefficient The value was calibrated to 0.12 based on historical hydrological data, representing a very small positive value. Take the example value 1e-5; for a certain unit in the 5th lane of the straight extra-wide section, This corresponds to the unit for lane 4. =1.0%, =1.0%, =4.25m =4.25m, calculated =1 + 0.12 × [1.0% / (1.0% + 1e-5) × 4.25 / 4.25] ≈ 1.12, Corrected unit width flow rate = ×1.12≈0.0011m³ / (s m); Water film thickness calculation: Manning roughness coefficient of road surface n = 0.016s / m, comprehensive slope Substitute into the equation for calculating water film thickness The water film thickness distribution along the confluence path determined by the DEM principle was calculated iteratively from upstream to downstream, and the final result was the water film thickness distribution of the entire road section. The original maximum water film thickness of the low-concave vertical curve section reached 4.72 mm, which exceeded the safety threshold.

[0026] Step S4: Parametric modeling of drainage structure capacity: Parametric models were established for the three types of drainage facilities: Horizontal drainage ditch: Flow coefficient =0.65, effective inlet length =3.0m, water depth from the inlet =0.002m, drainage capacity ,when When = 4.72mm, ≈0.018m³ / s; Longitudinal dark trench: Manning roughness coefficient =0.013s / m, cross-sectional area of ​​water passage =0.196m², wetted perimeter =1.57m, hydraulic radius =0.125m, paving slope =1.2%, drainage capacity ≈0.32m³ / s; Permeable pavement: stable infiltration rate =5×10 -4 m / s, surface area =17.0m², drainage capacity ≈0.0085m³ / s.

[0027] Step S5: Adaptive multi-segment road zoning and multi-objective optimization: Dynamic partitioning: Constructing multidimensional feature vectors for each computational unit: Quantity, of which Including longitudinal slope, cross slope, and curve radius. With a rainfall intensity of 120 mm / h, With a permeability coefficient of 80 mm / h, As a sensitivity indicator for drainage structure, The water film thickness is used as a risk indicator for prediction. K-means clustering algorithm is used to analyze the feature vector set, automatically dividing the entire road section into four zones: S1 superelevation gradient section (0-300m), S2 low-concave vertical curve section (300-600m), S3 straight super-wide section (600-900m), and S4 bridge deck transition section (900-1200m). The specific partitions are shown in Table 1 below:

[0028] Table 1 Multi-objective optimization: Weighting coefficients are set according to project priority. =0.5、 =0.3、 =0.2, satisfying ω1+ω2+ω3=1; constraint condition is ≤3.5mm and Solving the optimization problem for each partition: Super-high gradient section: The optimization goal is to quickly drain the water flow caused by the change in cross slope, and to determine the layout of transverse drainage ditches; Low-lying vertical curve sections: It is necessary to take into account both longitudinal diversion and lateral collection, and determine the combination strategy of lateral drainage ditches and longitudinal underground ditches. For straight, extra-wide sections: reduce redundant facilities and prioritize longitudinal underground drainage. Bridge deck transition section: Water needs to be drained from the bridge deck quickly, and additional drainage holes need to be installed.

[0029] Step S6: Global layout optimization based on improved genetic algorithm: Chromosome Encoding and Initialization: Chromosomes Each ; The coding rules are: 1-transverse drainage ditch, 2-longitudinal culvert, 3-permeable pavement section, 4-drainage hole; When initializing the population, avoid restricted areas such as bridge approach slabs. For example, the restricted area for bridge deck transition sections is within 0.5m on both sides of the expansion joint. Improved crossover operator: Employs segmented, preservative crossover, identifies four partition boundaries, randomly selects complete partitions, swaps corresponding gene segments from the parent generation, and inherits superior local layouts; Improved mutation operator: basic mutation probability =0.08, adjustment coefficient =0.15, when the location changes, the facility in the high water film thickness area moves upstream step by step; the type change refers to the facility-scene adaptation rule library, the S2 low concave vertical curve segment gene preferentially changes to the longitudinal dark ditch, and the S1 ultra-high gradient segment preferentially changes to the transverse drainage ditch. Fitness evaluation: The drainage performance, cost and construction risk are comprehensively evaluated. Penalties are imposed on transverse drainage ditches with a spacing of less than 5m. Finally, the optimal layout scheme is obtained through iterative convergence.

[0030] Step S7, Solution Output: Output an adaptive multi-segment drainage layout optimization report, the contents of which are as follows: Zoning facility layout: Super-high transition section: 4 transverse drainage ditches, adaptive spacing 20m. The m lengths are 50m, 70m, 90m, and 110m respectively. =2-7 lanes =1, = =3.0m; Low-recessed vertical curve section: 2 transverse drainage ditches ( =380m, 430m) + 1 longitudinal culvert ( =300-600m, =3 / 4 lanes, =2, =Pipe diameter 500mm); Straight-line extra-wide section: 1 longitudinal underground culvert ( =600-900m, =4 / 5 lanes, =2, =Pipe diameter 400mm); Bridge deck transition section: 30 drainage holes, spaced 2m apart (optimized from the standard spacing of 3m). =902-1198m, =Bridge edge, =4, =Aperture 100mm; Performance and cost assessment: After optimization, the maximum water film thickness of the entire road section was reduced to 3.01mm, meeting the safety threshold; the total number of drainage facilities was reduced by 23% compared to the traditional design, and the estimated engineering cost was reduced by 18%.

[0031] Implementation results: Drainage safety: After optimization, the maximum water film thickness of the target road section was reduced from 4.72mm to 3.01mm, a reduction of 36.2%, completely eliminating the risk of water accumulation in complex sections; Economic benefits: The total number of drainage facilities is reduced by 23%, and the project cost is reduced by 18%, achieving the optimal balance between performance and economy; Design efficiency: Traditional manual calculations take 3-5 days to complete, while the automated design of this invention only takes 4 hours, and the output can be directly used for construction drawing design, improving design efficiency by 5-10 times.

[0032] The verification results show that the present invention effectively improves the accuracy and reliability of groundwater level simulation by integrating the hysteresis response characteristics of multi-aquifer systems with a multi-head self-attention mechanism, and can be effectively applied to groundwater resource regulation and management.

[0033] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for optimizing the layout of drainage facilities for wide-width road surfaces in the reconstruction and expansion of expressways, characterized in that, Includes the following steps: S1. Digital Modeling of Road Features: Collecting the geometric and material parameters of the target highway, and discretizing the continuous road into... Each of the tiny computing units records the road width. , Hengpo Longitudinal slope curve radius and the permeability coefficient of road surface materials Total length of road ,in For the first The length of each computational unit; S2. Rainfall Condition and Surface Runoff Modeling: Determine rainfall intensity based on the design standards of the project location. Calculate the rainfall inflow per unit area ; Determining the first based on cross slope and longitudinal slope Water flow direction vector of each computing unit ; and by using the confluence analysis method, the flow through the first Original unit width flow rate of each computing unit ; in To merge into the first The set of upstream units of each computing unit. Contribute indicator factors to traffic flow; S3. Water film thickness prediction based on the coupling characteristics of water flow on wide road surfaces: introducing a lane confluence correction factor. The original unit width flow rate was corrected to obtain , in , For empirical coupling coefficients, To merge into the lane The upstream adjacent lane set, For the upstream adjacent lane In unit The cross slope at that location, It is a very small positive value. For lane The width; Substitute the corrected flow rate into the equation for calculating water film thickness. ; in The roughness coefficient of the road surface is Manning's roughness coefficient. To take into account the slope, the water film thickness distribution along the confluence path was calculated iteratively to obtain the total water film thickness distribution along the entire road section. S4. Parametric Modeling of Drainage Structure Capacity: Parametric models of drainage capacity are established for transverse drainage ditches, longitudinal drainage facilities, and permeable pavements, and the drainage capacity of each type of drainage facility is quantified as a function of its key design parameters. S5. Adaptive Multi-Segment Road Zoning and Multi-Objective Optimization: Constructing a Multi-Dimensional Feature Vector for Each Computational Unit ; in For geometric parameters, For meteorological parameters, For road surface material parameters, As a sensitivity indicator for drainage structure, As a risk indicator for predicting water film thickness; Clustering algorithms or threshold detection based on the rate of change are used to analyze the feature vector set and automatically divide the road into zones. Within each zone, a multi-objective optimization problem is constructed, with the objective function being: ; in This represents the maximum water film thickness within the zone. The total construction cost, To maintain the quantifiable burden indicators, the constraints are as follows: and , The safe threshold for water film thickness. For the total drainage capacity of the facility, Total inflow; S6. Global layout optimization based on improved genetic algorithm: Chromosome encoding is used to represent the drainage layout scheme, and chromosomes... ; Each gene , For the location of the facility, For lateral position or lane number, Code the facility type. For a specific parameter vector; Genetic iteration is performed using a segmented preservation crossover operator and a risk-oriented adaptive mutation operator, with mutation probability... , Based on the probability of mutation, The adjustment coefficient is used to comprehensively evaluate the performance of the scheme through the fitness function, and constraints and penalties are applied. S7. Solution Output: The output includes the type, quantity, location and spacing of drainage facilities in each zone, the predicted maximum water film thickness and safety margin assessment, the total project cost estimate and the optimization report of construction recommendations for key parts.

2. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded highways according to claim 1, characterized in that, The geometric and material parameters mentioned in step S1 include longitudinal slope, cross slope, curve radius, pavement width, and pavement material permeability coefficient, as well as the length of the calculation unit. The value of allows the discretized model to reflect the continuous changes in road geometric parameters.

3. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded highways according to claim 1, characterized in that, The confluence analysis method described in step S2 is based on the principle of digital elevation model and the flow contribution indicator factor. Automatically determined by the confluence direction vector, when the upstream unit Water inlet unit hour, The value is 1 if it is not 1, otherwise the value is 0.

4. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded highways according to claim 1, characterized in that, Empirical coupling coefficient in step S3 The value ranges from 0.05 to 0.2, and is calibrated using historical hydrological data or computational fluid dynamics simulations; the minimum positive value... An example value is 1e-5, used to prevent division by zero.

5. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded highways according to claim 1, characterized in that, The solution process for the water film thickness calculation equation in step S3 is to iterate sequentially from upstream to downstream along the confluence path until the water film thickness distribution across the entire road surface tends to stabilize.

6. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded highways according to claim 1, characterized in that, The parameterized model for drainage structure capacity mentioned in step S4 is specifically as follows: Horizontal drainage ditch: ,in For flow coefficient, For effective water inlet length, The water depth or threshold height is calculated from the entrance. Longitudinal drainage facilities: ,in The roughness coefficient is Manning's coefficient. The cross-sectional area of ​​the water passage. The hydraulic radius is calculated using the following formula: , For wet period, To create a slope; Permeable pavement: , To ensure the stable infiltration rate of road surface materials, It represents the surface area of ​​the permeable pavement.

7. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded expressways according to claim 1, characterized in that, The clustering algorithm mentioned in step S5 is the K-means algorithm, and the dynamic partitioning algorithm forms road partitions by identifying computational units with similar properties.

8. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded expressways according to claim 1, characterized in that, The weighting coefficients mentioned in step S5 Adjustments based on project priority requirements to meet [the needs of the project]. .

9. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded expressways according to claim 1, characterized in that, The segmented preservation type crossover operator described in step S6 identifies the road partition boundaries during crossover and swaps the gene segments corresponding to the complete partitions in the parent generation as a whole. In risk-oriented adaptive mutation, location mutation moves step by step towards the upstream of the affected area or adjacent units with greater water film thickness. Type mutation refers to the preset facility and scenario adaptation rule library, specifically including: low concave vertical curve segments are preferentially mutated into longitudinal underground ditches, and ultra-high gradient segments are preferentially mutated into transverse drainage ditches.

10. The method for optimizing the layout of drainage facilities for wide-width road surfaces of reconstructed and expanded expressways according to claim 1, characterized in that... In step S6, deterministic rules are used to avoid illegal solutions during the initial population generation, excluding bridge approach slabs and no-layout zones; the fitness function comprehensively evaluates drainage performance, cost, and construction risk, and imposes penalties on individuals that violate spacing constraints and no-layout zone constraints.

Images