A method and system for dynamically setting speed limit of road in urban waterlogging

Abstract

A method and system for dynamically setting road speed limit in urban waterlogging are disclosed. First, a two-dimensional water accumulation grid and a spatial mapping relationship with a road section are established to realize the integration of a water dynamics model of urban waterlogging and a city road traffic simulation model to construct a waterlogging and traffic coupling model. Then, the road parameters of the road to be set and the waterlogging parameters of the current or predicted time period are obtained according to the waterlogging and traffic coupling model. Then, the speed limit information of the road to be set is obtained by applying a speed limit setting model. The speed limit information of the corresponding road to be set is released. By applying the constructed waterlogging and traffic coupling model to simulate and predict the changes of water accumulation and traffic capacity of each road section under the urban waterlogging scenario, and applying the water accumulation and speed limit curve to obtain the speed limit information of the road to be set, the function of dynamically setting the road speed limit information under the urban waterlogging scenario is realized, the vehicles are guided to drive quickly and safely under the premise of complying with the traffic rules, and the urban traffic emergency control ability is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent road traffic management technology, specifically to a method and system for dynamically setting road speed limits for urban flooding. Background Technology

[0002] With the continuous improvement of the intelligence level of urban road traffic, traffic management has gradually transformed from traditional fixed speed limit control to a closed-loop dynamic management system encompassing "perception, analysis, control, and service." Dynamic speed limit technology, as one of the core applications, plays a crucial role in coping with severe weather and sudden road conditions. Urban flooding, as a sudden disaster during heavy rainfall, easily leads to road surface water accumulation, a sharp drop in friction coefficient, and insufficient visibility, resulting in traffic accidents such as vehicle stalling, skidding, and rear-end collisions, seriously threatening urban traffic order and safety. Currently, most cities have deployed multi-source sensing devices, edge computing, 5G communication, and urban brain platforms on core road sections for flood monitoring and traffic control. Monitoring coverage of flood-prone areas in typical cities has exceeded half, and the response time for flood monitoring and speed limits has been significantly shortened. However, in practical applications, dynamic speed limits in flood scenarios still face many technical bottlenecks. For example, it is difficult to achieve accurate speed limits for different types of road sections and different levels of flooding, and it cannot fully adapt to the risk characteristics of dynamic changes in flooding. Therefore, it is urgent to optimize dynamic speed limit technology in flood scenarios, solve the defects of existing technologies, and improve the accuracy and safety of traffic control. This is also the core research and development background and practical need of this application. Summary of the Invention

[0003] The main technical problem solved by this invention is how to dynamically set road speed limits in urban flooding scenarios.

[0004] According to the first aspect, one embodiment provides a method for dynamically setting road speed limits for urban flooding, comprising:

[0005] A coupled model of urban flooding and traffic is constructed; the coupled model integrates the urban flooding hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments.

[0006] Based on the waterlogging and traffic coupling model, obtain the road parameters of the road to be set, as well as the waterlogging parameters for the current or predicted time period;

[0007] The waterlogging parameters and road parameters are input into a preset speed limit setting model, and the speed limit information corresponding to the road to be set is obtained from the speed limit setting model. The speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve. The water accumulation and speed limit curve is used to identify the correspondence between the speed limit value and water depth of the road to be set. The water accumulation and speed limit curve is a curve corresponding to the water accumulation and dynamic speed limit value generated by applying a water accumulation and speed limit function based on the water depth of the road section, the road design speed, and the road category. The water accumulation and speed limit function is a Logistic curve shape function.

[0008] Publish speed limit information corresponding to the road to be set; wherein, the speed limit information includes the current speed limit value of the road to be set.

[0009] In one embodiment, constructing the waterlogging and traffic coupling model includes:

[0010] Collect multi-source data within the target city area and normalize the data according to the spatial accuracy of the road segment; wherein, the multi-source data includes at least rainfall process data, topographic data, drainage system data, road network data, historical no-rain vehicle speed data, and thermal data and / or OD data characterizing the intensity of traffic activity, and pre-set a unique identifier for each road segment;

[0011] Construct an urban waterlogging hydrodynamic model; using drainage pipe network, inspection wells, rainwater inlets, and two-dimensional surface water catchment grids as basic units, output the grid water accumulation depth and water accumulation range at different simulation times;

[0012] Construct a simulation model of urban road traffic; generate a simulateable road network structure based on road grade, number of lanes, design speed, traffic direction and signal control information; set time-sharing traffic demand based on the average thermal intensity of the study area on rainless days, and generate the number of vehicles per lane corresponding to different road categories;

[0013] A spatial mapping relationship between a two-dimensional water accumulation grid and road segments is established. Within each simulation step, the water accumulation results of the grid within the road surface area are transformed into a time series of water accumulation depth in the road segment through identification and calculation methods.

[0014] In one embodiment, the construction of the waterlogging and traffic coupling model further includes:

[0015] A hydrodynamic-traffic simulation model converter is established through an interface to convert the grid water depth values ​​of the road surface range output by the urban waterlogging hydrodynamic model into the water accumulation time sequence of road sections, and dynamically adjust the road speed limit value according to the water accumulation and speed limit function to realize the encapsulation of control logic and automated operation.

[0016] The waterlogging and traffic coupling model is used to respond to the user's road navigation request command and plan at least one driving route for the user according to preset priority conditions; the priority conditions include shortest time priority, shortest route priority and / or priority to avoid congested road sections.

[0017] The waterlogging and traffic coupling model is used to respond to the traffic reduction control strategy. When planning routes for users, it avoids road sections that meet preset avoidance conditions. The preset avoidance conditions include road sections that are determined to be congested, road sections that are determined to be flooded or whose flooding situation is unknown, and road sections that are confirmed to be under construction.

[0018] In one embodiment, the construction of the waterlogging and traffic coupling model further includes:

[0019] Speed ​​limit information and traffic cost information for each road segment are dynamically written through an interface and integrated into the waterlogging and traffic coupling model, providing a simulation platform for simulating and comparing different traffic control strategies. The traffic cost information serves as a quantitative evaluation parameter for the comprehensive traffic cost of each road segment when a vehicle is about to pass through it. This traffic cost information is related to the distance travel cost, time travel cost, and additional water wading cost associated with that road segment. The distance travel cost is determined by the segment length and road type. The time travel cost is related to the speed limit information, traffic density, traffic light control duration, and speed reduction caused by waterlogging. The additional water wading cost is related to waterlogging parameters.

[0020] In one embodiment, publishing the speed limit information corresponding to the road to be set includes:

[0021] The speed limit information for each road segment is displayed in the waterlogging and traffic coupling model.

[0022] And / or, dynamically change the speed limit information on road signs within the target city area.

[0023] In one embodiment, the road speed limit dynamic setting method further includes:

[0024] The road parameters of the road to be set include the road type, which includes expressways, arterial roads, secondary arterial roads, local roads and / or special road sections; wherein, the water accumulation and speed limit curves corresponding to different road types are different.

[0025] In one embodiment, the road speed limit dynamic setting method further includes:

[0026] Obtain vehicle type information uploaded by users; the vehicle type information includes small passenger cars, freight cars, passenger cars and special-purpose vehicles, wherein the special-purpose vehicles include police cars, fire trucks, ambulances and / or engineering rescue vehicles;

[0027] The vehicle type information, waterlogging parameters, and road parameters are input into the speed limit setting model, and the speed limit information corresponding to the road to be set is obtained from the speed limit setting model; wherein, the speed limit setting model obtains the speed limit information based on the water accumulation and speed limit curves of different road types and vehicle types.

[0028] The system publishes speed limit information corresponding to the user's vehicle type and the route to be traveled, which is used as a suggested speed for the user's vehicle.

[0029] According to a second aspect, one embodiment provides a dynamic road speed limit setting system for urban flooding, used to apply the dynamic road speed limit setting method as described in the first aspect, the dynamic road speed limit setting system comprising:

[0030] The model building module is used to construct a coupled model of urban flooding and traffic. The coupled model of urban flooding and traffic integrates the urban flooding hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments.

[0031] The parameter acquisition module obtains the road parameters of the road to be set, as well as the flooding parameters for the current or predicted time period, based on the waterlogging and traffic coupling model.

[0032] The speed limit information acquisition module is used to input the waterlogging parameters and the road parameters into a preset speed limit setting model, and to acquire the speed limit information corresponding to the road to be set, output by the speed limit setting model; wherein, the speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve, the water accumulation and speed limit curve is used to identify the correspondence between the speed limit value and the water accumulation depth of the road to be set; the water accumulation and speed limit curve is a curve corresponding to the water accumulation and dynamic speed limit value generated by applying the water accumulation and speed limit function based on the water accumulation depth of the road section, the road design speed, and the road category, and the water accumulation and speed limit function is a Logistic curve shape function;

[0033] The information publishing module is used to publish speed limit information corresponding to the road to be set; wherein, the speed limit information includes the current speed limit value of the road to be set.

[0034] According to a third aspect, one embodiment provides a computer-readable storage medium including a program that can be executed by a processor to implement the road speed limit dynamic setting method as described in any of the embodiments herein.

[0035] According to a fourth aspect, one embodiment of a computer program product includes a program that can be executed by a processor to implement a road speed limit dynamic setting method as described in any of the embodiments herein.

[0036] The road speed limit dynamic setting method, system, and computer-readable storage medium according to the above embodiments, by using a constructed waterlogging and traffic coupling model to simulate and predict the actual working conditions of each road section in the scenario of urban waterlogging, and by using water accumulation and speed limit curves to obtain the speed limit information of the road to be set, can realize the dynamic setting of road speed limit information in the scenario of urban waterlogging, guide vehicles to drive fast and safely while complying with traffic rules, and improve the city's traffic emergency management capabilities. Attached Figure Description

[0037] Figure 1 A schematic diagram of quadratic function curves showing water accumulation and speed limits for different road types;

[0038] Figure 2 This is a flowchart illustrating a method for dynamically setting road speed limits in one embodiment;

[0039] Figure 3 This is a schematic diagram of the framework of a model for the coupling of urban flooding and traffic in one embodiment;

[0040] Figure 4 This is a schematic diagram illustrating the construction process of a model coupling urban flooding and traffic in one embodiment.

[0041] Figure 5 This is a schematic diagram of the Logistic morphological function curve in one embodiment;

[0042] Figure 6 This is a schematic diagram showing the corresponding curves of different types of road flooding and speed limits in one embodiment;

[0043] Figure 7 This is a schematic diagram of the framework of a road speed limit dynamic setting system in one embodiment. Detailed Implementation

[0044] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0045] Furthermore, the features, operations, or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can be rearranged or adjusted in a manner obvious to those skilled in the art. Therefore, the various orders in the specification and drawings are only for the clear description of a particular embodiment and do not imply a necessary order, unless otherwise stated that a particular order must be followed.

[0046] The serial numbers assigned to components in this document, such as "first" and "second," are used only to distinguish the described objects and have no sequential or technical meaning. The terms "connection" and "linkage" used in this invention, unless otherwise specified, include both direct and indirect connections (linkages).

[0047] Currently, dynamic speed limit technology for urban flooding scenarios primarily relies on core parameters such as water depth, road surface friction coefficient, and visibility, combined with differences in road type, to set and issue speed limits through threshold triggering, model calculation, or a combination of manual and intelligent methods. Existing technologies for setting speed limits mainly fall into three categories: water depth and speed reduction formulas, hard safety rules, and differentiated standards based on road type. Specifically, these include:

[0048] 1) The reduction of vehicle speed based on water depth is based on a general empirical formula.

[0049] Please refer to Figure 1 This is a schematic diagram showing the water accumulation and speed limit curves for different road types. The expression for the water accumulation and speed limit curves is as follows:

[0050] v(w) = a×w² - b×w + v d ;

[0051] Where w is the water depth in mm; v is the speed limit in km / h; v d a and b are preset constants.

[0052] Based on engineering practice experience, speed reduction standards are determined for different water depths. For example, when the water depth h=15cm, the speed is reduced by 30%, and when h=30cm, driving is prohibited. At the same time, considering the height of the passenger car's exhaust pipe, the safe water depth for passenger cars is limited to ≤25cm.

[0053] 2) Hard safety rules.

[0054] Forced trigger thresholds are set for visibility, road surface friction coefficient, and water flow velocity in urban flooding scenarios. Specifically: when visibility is <100m, the speed limit is ≤40km / h; when visibility is <50m, the speed limit is ≤20km / h or the road is closed; when the road surface friction coefficient μ<0.3, the speed limit is ≤40km / h to prevent vehicles from skidding or hydroplaning; when the water flow velocity is >0.5m / s, the speed limit is 20km / h; when the water flow velocity is >1.0m / s, traffic restrictions are implemented to prevent vehicles from being washed away by floods.

[0055] 3) Differentiated standards for road types.

[0056] Based on the characteristics of urban arterial roads (elevated / expressways), secondary arterial roads / local roads, and underpasses / low-lying areas, different speed limits are set for water accumulation. For example, on arterial roads, the speed limit is 60 km / h when the water accumulation is 5-10 cm, 40 km / h when it is 10-15 cm, and the road is closed when the water accumulation is >15 cm. On secondary arterial roads / local roads, the speed limit is 40 km / h when the water accumulation is 5 cm, 20 km / h when it is 10 cm, and the road is closed when the water accumulation is >15 cm. A zero-tolerance policy is adopted for underpasses / low-lying areas, issuing a warning when the water accumulation is >5 cm and closing the road when it is >10 cm to avoid the risk of vehicles stalling.

[0057] Although the above three speed limit settings have enabled the initial application of dynamic speed limiting in flood-prone scenarios, the methods for setting road speed limits remain relatively simplistic. They cannot dynamically adjust based on changes in actual environmental factors, only addressing the "existence" issue. However, in practical applications, deficiencies in perception accuracy, model adaptability, collaborative linkage capabilities, and standard specifications result in speed limit control's accuracy, reliability, and efficiency failing to meet actual needs. Furthermore, in addition to adhering to traffic sign speed limits, drivers also need to reasonably anticipate their own deceleration behavior based on the actual conditions of their vehicles, thus driving quickly while still complying with traffic rules.

[0058] In this embodiment, a simulation of waterlogging and traffic coupling is constructed. A digital simulation model is applied to fit the speed limit curves of different types of roads. Based on the speed limit curves, the road speed limit information of different types of roads is dynamically set when urban waterlogging occurs. This enables the dynamic setting of road speed limit information in urban waterlogging scenarios, guiding vehicles to drive quickly and safely while complying with traffic rules, thereby improving the city's traffic emergency management capabilities.

[0059] Example 1:

[0060] Please refer to Figure 2 This is a flowchart illustrating a method for dynamically setting road speed limits in one embodiment. The method includes:

[0061] Step 101: Construct the coupling model.

[0062] Please refer to Figure 3 This is a schematic diagram of the framework of a waterlogging and traffic coupling model in one embodiment. The construction of this model involves the selection and design of an urban waterlogging hydrodynamic model, a traffic simulation model, and the interface between the waterlogging and traffic coupling. In one embodiment, the waterlogging and traffic coupling model integrates the urban waterlogging hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments. Specifically, this includes:

[0063] 1) Selection of urban waterlogging hydrodynamic model.

[0064] In one embodiment of this application, for urban flooding-traffic coupling simulation, the selected urban flooding model must not only provide sufficient water depth, water range, and process accuracy at the spatial scale required for determining road segment passability, but also be able to output dynamic water accumulation information that can directly drive the traffic model, and support calibration and batch simulation under multiple rainfall scenarios. The model must reflect key mechanisms such as rainfall input, surface runoff, pipe network drainage, and surface-to-subsurface exchange to ensure the credibility of water accumulation rise, peak, and receding processes; the model must also simultaneously output time-series results of a two-dimensional grid and a one-dimensional drainage system, so as to map grid water accumulation to road cross-sections and trigger speed limit, closure, and recovery decisions; it also needs to have a calibrable parameter system, such as Horton infiltration-related parameters (initial infiltration rate f0, stable infiltration rate f...). c Attenuation factor k, drying time T d and initial loss I a Adjustable variables are included to support model performance analysis under different rainfall scenarios and underlying surface conditions.

[0065] Within the aforementioned framework, commonly used urban flooding models such as MIKE and InfoWorks ICM are all viable candidates because they typically cover the basic chain of "rainfall-runoff generation-drainage-inundation," possess a certain degree of 1D-2D coupling, and can output temporal data on water depth and spatial inundation processes, thus meeting the most basic information requirements for coupling with traffic models. Considering the coupling capability, consistency between output and calibration, engineering stability of multi-scenario batch calculations, and the flexibility of secondary development interfaces, Autodesk InfoWorks ICM was ultimately selected as the urban flooding simulation platform in one embodiment of this application. InfoWorks ICM is an integrated watershed modeling platform that emphasizes rapid and reliable hydrological and hydraulic simulation and collaborative workflows. It can express the response process of urban stormwater systems by coupling river hydraulics with urban drainage networks. Its advantage lies in its ability to more fully characterize the interaction between surface runoff and underground drainage networks, thereby improving the consistency of the dynamic description of urban flooding. In typical applications, InfoWorks ICM usually includes core components such as rainfall-runoff generation, pipe network hydraulics, river channel calculations, and two-dimensional inundation, which highly aligns with the objective of outputting the pipe network hydraulic response and two-dimensional waterlogging evolution. Furthermore, existing studies have used InfoWorks' 1D–2D flooding models to reconstruct the inundation dynamics of the study area and assess the impact on travel, demonstrating the platform's strong adaptability and transferability in the "flooding simulation—traffic impact analysis" chain. Based on these reasons, this application adopts InfoWorks ICM to ensure that the flooding process simulation meets the needs of coupled research in terms of spatiotemporal resolution, stability, and achievable qualitative analysis.

[0066] 2) Selection of traffic simulation model.

[0067] One embodiment of this application focuses on the spatiotemporal variations of road operational efficiency and resilience under different rainfall and control measures. Therefore, the traffic model must stably output road segment-scale vehicle speeds and, when needed, expand to operational status indicators such as traffic flow, density, and travel time to support speed assessment and comparative analysis under different scenarios. Simultaneously, the traffic model must also possess the ability to realistically represent urban road networks and traffic control elements, including the ability to set geometric and regular attributes such as road design speed, number of lanes and traffic direction, intersections and traffic lights, as well as behavioral mechanisms such as following and lane changing, thereby ensuring the interpretability and credibility of the characterization of operational status in dense urban road networks. Furthermore, this research framework requires the traffic model to be able to conduct minute-level information interaction with the urban flooding model and support the writing of scenario-based control strategies. Therefore, the model needs to have adjustable demand inputs (such as time-segmented departure volumes, OD or route generation rules) and be able to dynamically apply changes in road speed limits, closures, or toll costs, thereby triggering adaptive adjustments to vehicle route selection and road network traffic load. In addition, an API interface will significantly improve the automation and reproducibility of coupled computation and batch testing.

[0068] A variety of traffic simulation platforms meet the above requirements. Commonly used commercial or open-source models include the microscopic traffic simulation PTV Vissim, which emphasizes multi-modal traffic participant interaction and scenario assessment capabilities; TransModeler, covering multi-level simulations from micro to meso / macro, which can conduct road and regional road network assessments; and the open-source, agent-based MATSim, which focuses on large-scale individual travel and road network interaction simulation. Considering the requirements for coupling controllability, reproducibility, and large-scale scenario batch computation, SUMO (Simulation of Urban Mobility) is selected as the traffic simulation platform in one embodiment of this application. As an open-source, cross-platform traffic simulation system, SUMO supports continuous-time simulation and can be scaled to large-scale road networks, while providing relatively complete scenario construction tools. Furthermore, SUMO can effectively characterize the path selection adjustment process when road conditions are disturbed, making it suitable for analyzing traffic dynamics and the effectiveness of management strategies under disaster disturbances such as floods. In SUMO, road network and travel demand are two core inputs. In one embodiment, the road network of the study area is derived from OpenStreetMap and includes key attributes of each road segment, such as length, number of lanes, direction of travel, and speed limit. For travel demand, the spatial distribution of activity heatmap values ​​is used as an initial reference for activity intensity; however, the final demand is determined through model calibration to match the simulated vehicle speeds under no-rain baseline and two typical heavy rainfall disaster scenarios with historically observed vehicle speeds.

[0069] 3) Design of the interface between waterlogging and traffic.

[0070] Taking the traffic simulation software SUMO as an example, two modes are used to fit the impact of urban flooding on road traffic: one setting road sections to be interrupted due to parking, and the other setting roads to have speed limits changed due to varying depths of flooding. The latter is more event-driven. The focus is on exploring ways to change road capacity (speed limits) by inputting external conditions (flooding process lines covering various catchment areas of the road section, or real-time flooding conditions). In one embodiment of this application, SUMO's Traffic Control Interface (TraCI) tool is used as a secondary development interface to integrate spatiotemporal dynamic control methods into the model. TraCI reads vehicle and road section status in real time during simulation and provides an interface for online modification of vehicle behavior and road operation parameters, thereby achieving minute-level dynamic scenario control and intervention evaluation. Control logic is encapsulated and automated by calling TraCI via Python. The coupling framework reads spatiotemporally changing flooding data at each simulation step, identifies flooded road sections, and synchronously updates the road speed limit input, ensuring that the flooding impact mechanism is integrated throughout the entire traffic simulation process. The road section remains open to traffic when the water depth does not exceed the threshold, and the implementation of the response is ensured through an update mechanism that updates step by step in the simulation.

[0071] The coupling interface, within the model set, provides a simulation platform for simulating and comparing different traffic control strategies. The first dimension involves implementing control measures by monitoring traffic density. A flood-traffic coupling model is used to simultaneously read road segment water depth, speed limit status, and traffic density within a fixed step size. When a road segment reaches a congestion threshold, the edge weight of that segment is dynamically increased or it becomes nearly closed via TraCI, triggering vehicle path recalculation. For slow-moving but not completely congested road segments, a lower penalty coefficient is used to adjust the path selection probability, creating a tiered detour scenario. To suppress the oscillations caused by frequent detours, this study sets a detour cooling-off time, triggering detours only for vehicles expected to enter congested road segments in the future, making path replanning more targeted. Different penalty intensities, trigger thresholds, and detour cooling-off times are used as parameter combinations for scenarios, compared with a baseline scenario without control, to analyze the maximum relative loss of vehicle speed and the degree of improvement in recovery time. The second dimension focuses on reducing traffic volume to implement control measures. The departure times of vehicles and their destinations in the traffic volume file are identified by time period, and the number of departures within the corresponding time window is reduced according to a set ratio. The inflection point of diminishing marginal returns is analyzed, and the reduction ratio of this inflection point is applied to various rainfall recurrence periods for further analysis. Furthermore, a combined control scheme integrating route replanning and travel intention guidance can be constructed to test the synergistic effect of traffic diversion and peak shaving. Within a multi-dimensional spatiotemporal control framework, traffic diversion and peak shaving are simulated and quantified: the former reduces the new entry rate of high-risk road sections through dynamic detours; the latter weakens the impact of peak rainfall and flooding periods on traffic by reducing departure demand in different rainfall scenarios.

[0072] Please refer to Figure 4 This is a flowchart illustrating the process of constructing a coupled model of urban flooding and traffic in one embodiment, specifically including:

[0073] Step 201: Obtain multi-source data.

[0074] For the road network within the target urban area, multi-source data is collected, divided into road segments. The multi-source data includes at least rainfall process data, topographic data, drainage system data, road network data, historical dry-time vehicle speed data, and thermal data and / or OD data characterizing traffic activity intensity, with each road segment assigned a unique identifier.

[0075] Step 202: Construct a hydrodynamic model.

[0076] A hydrodynamic model of urban flooding is constructed, using drainage pipe network, inspection well, rainwater inlet, and two-dimensional surface water catchment grid as basic units, and outputting the grid water depth and water accumulation range at different simulation times.

[0077] Step 203: Construct a traffic simulation model.

[0078] A simulation model of urban road traffic is constructed, generating a simulateable road network structure based on road grade, number of lanes, design speed, traffic direction, and signal control information. Time-specific traffic demand is set according to the thermal intensity at different times on rainless days, generating the vehicle departure volume per lane corresponding to different road categories.

[0079] Step 204: Establish spatial mapping relationship.

[0080] A spatial mapping relationship is established between a two-dimensional water accumulation grid and road segments. Within each simulation step, the numerical results of the grid water accumulation depth within the road surface area are transformed into a time series of road segment water accumulation depths through identification and calculation methods. One specific approach is as follows: First, the InfoWorks ICM model outputs the two-dimensional grid water depth at a fixed result step size. Second, it is determined whether the continuous water accumulation grid on the cross-section can cover the road width. Third, for multi-lane roads, this study uses the minimum water depth of the passable grid on the cross-section as the road segment water depth to approximate the behavior of vehicles changing lanes into shallow water lanes. Fourth, the water depth is input into a water accumulation-speed limit function to generate a dynamic speed limit value executable by SUMO; if the water depth exceeds the closure threshold, it is set to an extremely high passage cost.

[0081] Step 205: Integrate coupling and control functions.

[0082] The TraCI tool is used to write progressively increasing speed limits into the side file attributes of the SUMO model. At the end of each simulation step, road segment speeds, vehicle density, queue lengths, and replanning states are read, providing a simulation platform for simulating and comparing different traffic control strategies. The first step identifies flooded road segments and synchronously updates the road speed limit inputs, ensuring the impact of water accumulation is integrated throughout the traffic simulation. The second step implements control measures by monitoring traffic density. When a road segment reaches a congestion threshold, the TraCI tool dynamically increases the edge weight of that segment or makes it nearly closed, triggering a mechanism to recalculate the path to the destination. For slow-moving but not completely congested road segments, a lower penalty coefficient is used to adjust the path selection probability, creating a tiered detour scenario. The third step implements control strategies such as reducing traffic volume. The departure times of vehicles and destinations in the traffic volume file are identified by time period, and the number of departures within the corresponding time window is reduced according to a set ratio. The fourth step constructs a combined control scheme that integrates path replanning and travel intention guidance, testing the synergistic effect of traffic diversion and peak shaving.

[0083] In one embodiment, constructing the waterlogging-traffic coupling model further includes:

[0084] Speed ​​limit and toll cost information for each road segment is dynamically written via an interface and integrated into a flooding-traffic coupling model. This provides a simulation platform for simulating and comparing different traffic control strategies, primarily targeting vehicle users with Level 2 or higher assisted driving functions enabled. Toll cost information serves as a quantitative evaluation parameter for the overall toll cost of a road segment when a vehicle is about to traverse it. Toll cost information is related to the distance traveled, the time traveled, and the additional cost of wading through water. The distance traveled is determined by the segment length and road type; the time traveled is related to the speed limit, traffic density, traffic light duration, and speed reduction due to flooding; and the additional cost of wading is related to flooding parameters.

[0085] In one embodiment, when the flooding and traffic coupling model is used as a traffic control strategy simulation platform, it responds to users' road navigation requests and plans at least one travel route for the user according to preset priority conditions. These priority conditions include shortest time priority, shortest route priority, and / or priority to avoid congested road sections. In another embodiment, the flooding and traffic coupling model also responds to traffic reduction control strategies, avoiding road sections that meet preset avoidance conditions when planning travel routes for users. These preset avoidance conditions include road sections identified as congested, road sections identified as experiencing flooding or with unknown flooding conditions, and road sections identified as under construction.

[0086] In the default settings of urban road traffic simulation models regarding simulated traffic flow, routes are typically planned by assigning starting and ending points and then calculating the shortest path distance. In one embodiment of this application, considering the speed limits on road sections caused by flooding, route replanning is guided by defining traffic cost information. In one embodiment, the traffic cost information includes a traffic cost coefficient, which is calculated by dividing the road's design speed by the speed limit caused by flooding. Furthermore, the actual length of the flooded road section is multiplied by the traffic cost coefficient to obtain the weighted length of the flooded road section. This weighted length is then applied to the shortest path calculation, thereby providing model users with an optimization strategy that more closely aligns with the goal of shortening travel time. For example, when planning routes, model users can try to avoid congested road sections; in this case, traffic cost information can be used as a reference standard for dynamically evaluating each road section, gradually alleviating congestion.

[0087] The waterlogging and traffic coupling model disclosed in this application is constructed by collecting multi-source data from the target urban area, including at least rainfall processes, topography, drainage systems, road networks, historical no-rain vehicle speeds, traffic activity thermal data, and / or OD data. The data is normalized according to road segment spatial accuracy and a unique identifier is preset for each road segment. Urban waterlogging hydrodynamic models are then constructed, using drainage pipe networks, manholes, storm drains, and two-dimensional surface catchment grids as basic units, outputting the water depth and range of the grid at different simulation times. Furthermore, a simulateable road network structure is generated based on road grade, number of lanes, design speed, traffic direction, and signal control information, and based on no-rain data... A city road traffic simulation model is generated by setting time-of-day traffic demand based on the daily average thermal intensity and generating corresponding vehicle departure volumes per unit lane. A spatial mapping relationship between a two-dimensional water accumulation grid and road segments is established. Within each simulation step, the grid water accumulation results within the road surface area are converted into a time series of road segment water accumulation depths. A hydrodynamic-traffic simulation model converter is built through an interface to aggregate the grid water accumulation depths output by the hydrodynamic model to the road cross-section and generate a time series of road segment water accumulations. Based on this, the road speed limit value is dynamically adjusted according to the water accumulation and speed limit function to achieve control logic encapsulation and automated operation. Furthermore, the speed limit information and toll cost information of each road segment are dynamically written and integrated through an interface. The toll cost information is a quantitative assessment parameter of the comprehensive toll cost of each road segment when a vehicle is about to pass through it. The distance consumption cost (i.e., the cost of traveling the actual mileage of a road segment) is directly related to the vehicle's fuel / electricity consumption. The time consumption cost is calculated comprehensively based on the real-time speed limit of the road segment, traffic density, signal control duration, and the speed reduction effect caused by water accumulation. It accurately reflects the actual time taken for a vehicle to pass through the road segment. The additional cost of wading is quantified by combining parameters such as water depth and water flow rate. It covers the failure risk cost, power loss cost, and additional safety risk cost of driving through water. This passage cost information serves as a core evaluation reference for different path selections when planning vehicle travel routes. It provides scientific and accurate quantitative support for the model to carry out path optimization and traffic control strategy comparison, ensuring that path planning and traffic control strategies are in line with the actual passage needs under water accumulation scenarios.

[0088] In one embodiment, the method for dynamically setting road speed limits further includes:

[0089] Step 102: Obtain waterlogging parameters.

[0090] The road parameters for the road to be configured, as well as the flooding parameters for the current or predicted time period, are obtained based on a coupled flooding and traffic model. In one embodiment, the road parameters include road grade, road type, reference speed, number of lanes, lane width, lane longitudinal and cross slopes, and road curvature. Road types include expressways, arterial roads, secondary arterial roads, local roads, and / or special road sections. Special road sections refer to maintenance and repair sections, underpasses, ramps, and / or low-lying sections. In one embodiment, flooding parameters include steady-state water depth, water level rise rate, water level receding rate, surface flow velocity of water, surface flow direction of water, road surface water film thickness, and visibility.

[0091] In one embodiment, the method for obtaining the water accumulation and speed limit curve is to generate a dynamic speed limit value for the corresponding road segment based on the water accumulation depth, road design speed, and road category using a water accumulation and speed limit function. In another embodiment, the water accumulation and speed limit function is a Logistic curve shape function.

[0092] Please refer to Figure 5 This is a schematic diagram of the Logistic morphological function curve in one embodiment. The standard expression of the Logistic morphological function (S-curve) is:

[0093] f(x) = L ÷ {1 + e^[-k(x-x0)]};

[0094] The curve parameters include the upper limit parameter L, the slope parameter k, and the midpoint parameter x0.

[0095] The upper limit parameter L (asymptote parameter) is the upper asymptote value of the curve, representing the maximum limit value that the variable f(x) can reach. It reflects the saturation state or maximum carrying capacity of the system and will not exceed this value as the independent variable x increases.

[0096] The slope parameter k (growth rate parameter) determines the steepness of the curve and reflects the rate at which the variable f(x) approaches the limit value L.

[0097] The larger the absolute value of k, the steeper the curve rises (k>0) or falls (k<0), and the faster the rate.

[0098] When k=0, the curve is a horizontal straight line, and the speed remains unchanged.

[0099] The midpoint parameter x0 (center parameter) is the abscissa of the midpoint of the curve, corresponding to the inflection point of the curve (the point where the concavity and convexity of the curve change). At this point, f(x0) = L / 2, which is the position where the curve has the fastest growth rate, and also the dividing point where the variable transitions from rapid growth to slow growth.

[0100] Please refer to Figure 6This is a schematic diagram showing the corresponding curves of water accumulation and speed limits for different types of roads in one embodiment. From top to bottom, the curves correspond to road types: expressway, arterial road, secondary arterial road, and local road. The Logistic function is used for setting; after parameter adjustment, the parameter k of the Logistic function curve is 0.01, and the main inflection point w... c With a water depth of 480mm and a sensitivity coefficient α of 0.01, the system completely cuts off the road when the water depth reaches 600mm. For special road sections, more flexible speed limits and interruption thresholds can be set after further weighing functionality and risks.

[0101] Step 103: Obtain speed limit information.

[0102] Input the waterlogging parameters and road parameters into a preset speed limit setting model, and obtain the speed limit information of the corresponding road to be set from the speed limit setting model. The speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve, which is used to identify the correspondence between the speed limit value and the water depth of the road to be set.

[0103] Step 104: Publish speed limit information.

[0104] Publish the speed limit information for the road to be set, including the current speed limit value for the road to be set.

[0105] In one embodiment, the speed limit information for each road segment is displayed in the urban flooding hydrodynamic model. In another embodiment, the speed limit information is dynamically changed on road signs within the target urban area.

[0106] In one embodiment, the road parameters of the road to be set include the road type, which includes expressways, arterial roads, secondary arterial roads, local roads and / or special road sections. Different road types correspond to different water accumulation and speed limit curves.

[0107] In one embodiment, the method for dynamically setting road speed limits further includes:

[0108] First, the system obtains vehicle type information uploaded by the user. Vehicle type information includes passenger cars, trucks, buses, and special-purpose vehicles, with special-purpose vehicles including police cars, fire trucks, ambulances, and / or engineering rescue vehicles. Then, the system inputs the vehicle type information, flooding parameters, and road parameters into the speed limit setting model and obtains the corresponding speed limit information for the road to be set, output by the model. The speed limit setting model obtains the speed limit information based on the water accumulation and speed limit curves for different road types and vehicle types. Finally, the system publishes the corresponding vehicle type and speed limit information for the user's intended driving route to the user as a suggested driving speed.

[0109] Please refer to Figure 7This is a schematic diagram of the framework of a dynamic road speed limit setting system in one embodiment. In another embodiment of this application, a dynamic road speed limit setting system is also disclosed, used to apply the dynamic road speed limit setting method described above. The system includes a model building module 10, a speed limit information acquisition module 20, a speed limit information acquisition module 30, and an information publishing module 40. The model building module 10 is used to construct a waterlogging and traffic coupling model. This model integrates the urban waterlogging hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments. The parameter acquisition module 20 acquires the road parameters of the road to be set, as well as the waterlogging parameters for the current or predicted time period, based on the waterlogging and traffic coupling model. The speed limit information acquisition module 30 is used to input waterlogging parameters and road parameters into a preset speed limit setting model, and to acquire the speed limit information of the corresponding road to be set, output by the speed limit setting model. The speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve. The water accumulation and speed limit curve is used to identify the correspondence between the speed limit value and water depth of the road to be set. The water accumulation and speed limit curve is generated by applying a water accumulation and speed limit function based on the water depth of the road segment, the road design speed, and the road category. The water accumulation and speed limit function is a curve logistic function. The information publishing module 40 is used to publish the speed limit information of the corresponding road to be set, including the current vehicle speed limit value of the road to be set.

[0110] To facilitate understanding of the Logistic curve shape function used for water accumulation and speed limit functions in this application embodiment, the principle is briefly described below, including:

[0111] In road flooding impact assessment and driving safety studies, the "depth-velocity" perturbation function is often used to characterize the inhibitory effect of water depth on driving speed. The first type is based on quadratic function attenuation, as shown in the following equation:

[0112] ;

[0113] in, Let t be the depth of the water accumulation at time t (mm). The depth of the accumulated water is The road speed limit (km / h) is given. This formula reflects well the monotonically decreasing trend of vehicle speed with increasing water depth from no water to 300mm of water, and within the experimental verification range, it can approximately match the speed reduction characteristics of passenger cars. In this embodiment, the constant term is scaled to the version of the actual road design speed, as shown in the following formula:

[0114] v(w) = a×w² - b×w + v d ;

[0115] Where w is the water depth in mm; v(w) is the road speed limit when the water depth is w in km / h.

[0116] However, when actual roads have fixed speed limits (e.g., 60 km / h or 40 km / h), directly using this formula may result in situations with no water depth (w=0), or even in shallow water, where the speed limit exceeds the road's design speed, which is inconsistent with actual operating conditions. To make this speed limit function better suit road management needs and safety requirements, it is necessary to perform function transformations for various road types. The quadratic function coefficients obtained for different road categories are shown in the table below:

[0117]

[0118] Use appropriate normalization or recalibration to simultaneously satisfy all three conditions:

[0119] 1) It adopts the characteristic of a quadratic function decaying rapidly at first and then slowly, and has monotonicity within the range of water depths under discussion;

[0120] 2) When w = 300 mm, v(w) = v min (Approximately 2 km / h), considered the strictest speed limit on the road;

[0121] 3) When w=0, v(w)=v d .

[0122] The quadratic function pattern typically shows a rapid initial decrease in speed as water depth increases linearly. In contrast, the Logistic function offers greater morphological flexibility across its entire domain: it exhibits a slow-fast-slow decay process overall; however, considering only the initial or subsequent phases, it can approximate a slow-then-fast or fast-then-slow deceleration characteristic, respectively. Therefore, it is more suitable as a universal expression for different road conditions and driving behaviors. Furthermore, the 300mm water depth speed limit mechanism is relatively strict and applies to earlier vehicle models. In recent years, with improvements in vehicle performance and design, for example, the speed limit mode for four-wheel drive vehicles only considers the road interrupted at a water depth of 60cm.

[0123] v(w)=v d ×[s(w)-s(600)]÷[s(0)-s(600)];

[0124] s(w)=1÷;1+exp[α×(ww) c )]};

[0125] Where v(w) is the speed limit (km / h) when the water depth is w, s(w) represents the Logistic decay function, used to characterize the nonlinear decline in vehicle operating capability as the water depth increases, w cThe characteristic water depth corresponding to the most sensitive interval of vehicle speed decay is defined, and a kurtosis parameter α is introduced to control the rate and shape of the vehicle speed descent. Thus, the original Logistic function can be scaled to the [0,1] interval using a normalized decay factor, ensuring that when w is 0, the decay factor is 1 and v(w0) is v d When w is 600mm, the attenuation factor is 0, and v(600) is 0.

[0126] Through the above transformations, the theoretical speed under no-water conditions can be matched with the road speed limit, while maintaining a reasonable minimum driving speed at the maximum water depth. Simultaneously, it ensures that the speed curve monotonically decreases within the intermediate water depth range, preventing abnormal rebound phenomena. In application, it is necessary to further integrate with on-site traffic management strategies. For example, if road management departments implement closures or diversions after water accumulation exceeds a certain threshold, the speed can be cut off to 0 at the corresponding water depth. Specifically, a, b, and v... d w c The constant terms, such as α, need to be selected and verified through model calibration based on historical road speed data. From a strategic perspective, the aforementioned method of localizing the formula can provide speed predictions and decision-making references that are more aligned with actual road conditions for urban flooding early warning and traffic control.

[0127] This application discloses a method for dynamically setting road speed limits in urban flooding scenarios. First, it establishes a spatial mapping relationship between a two-dimensional water accumulation grid and road segments, integrating an urban flooding hydrodynamic model and an urban road traffic simulation model to construct a flooding-traffic coupling model. Then, based on this model, it obtains the road parameters for the road to be set, as well as the flooding parameters for the current or predicted time period. Next, it applies the speed limit setting model to obtain the speed limit information for the road to be set and publishes the corresponding speed limit information. By applying the constructed flooding-traffic coupling model to simulate and predict changes in water accumulation and traffic capacity on various road segments under urban flooding scenarios, and using water accumulation and speed limit curves to obtain the speed limit information for the road to be set, it achieves the function of dynamically setting road speed limits under urban flooding scenarios, guiding vehicles to drive quickly and safely while adhering to traffic rules, thereby improving the city's traffic emergency management capabilities.

[0128] In the above embodiments, implementation can be achieved, in whole or in part, by software, hardware, firmware, or any combination thereof. Furthermore, as those skilled in the art will understand, the principles herein can be reflected in a computer program product on a computer-readable storage medium pre-loaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disks, floppy disks, etc.), optical storage devices (CDs, DVDs, Blu-ray discs, etc.), flash memory, and / or the like. These computer program instructions can be loaded onto a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to form a machine, such that instructions executing on the computer or other programmable data processing apparatus can generate means for performing a specified function. These computer program instructions can also be stored in a computer-readable storage medium that can instruct the computer or other programmable data processing apparatus to operate in a particular manner, such that instructions stored in the computer-readable storage medium can form an article of manufacture, including means for implementing the specified function. The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to perform a series of operational steps on the computer or other programmable apparatus to produce a computer-implemented process, such that instructions executing on the computer or other programmable apparatus can provide steps for implementing the specified function.

[0129] This document describes various exemplary embodiments with reference to them. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope of this document. For example, various operational steps and components for performing operational steps can be implemented in different ways depending on the specific application or considering any number of cost functions associated with the operation of the system (e.g., one or more steps can be deleted, modified, or combined with other steps).

[0130] While the principles herein have been illustrated in various embodiments, numerous modifications to the structures, arrangements, proportions, elements, materials, and components, particularly suited to specific environments and operational requirements, may be used without departing from the principles and scope of this disclosure. These modifications and other alterations or alterations will be included within the scope of this document. Those skilled in the art will recognize that many changes can be made to the details of the above embodiments without departing from the fundamental principles of the invention.

Claims

1. A method for dynamically setting road speed limits for urban flooding, characterized in that, include: A coupled model of urban flooding and traffic is constructed; the coupled model integrates the urban flooding hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments. Based on the waterlogging and traffic coupling model, obtain the road parameters of the road to be set, as well as the waterlogging parameters for the current or predicted time period; The waterlogging parameters and road parameters are input into a preset speed limit setting model, and the speed limit information corresponding to the road to be set is obtained from the speed limit setting model. The speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve. The water accumulation and speed limit curve is used to identify the correspondence between the speed limit value and water depth of the road to be set. The water accumulation and speed limit curve is a curve corresponding to the water accumulation and dynamic speed limit value generated by applying a water accumulation and speed limit function based on the water depth of the road section, the road design speed, and the road category. The water accumulation and speed limit function is a Logistic curve shape function. Publish speed limit information corresponding to the road to be set; wherein, the speed limit information includes the current speed limit value of the road to be set.

2. The method as described in claim 1, characterized in that, The construction of the waterlogging and traffic coupling model includes: Collect multi-source data within the target city area and normalize the data according to the spatial accuracy of the road segment; wherein, the multi-source data includes at least rainfall process data, topographic data, drainage system data, road network data, historical no-rain vehicle speed data, and thermal data and / or OD data characterizing the intensity of traffic activity, and pre-set a unique identifier for each road segment; Construct an urban waterlogging hydrodynamic model; using drainage pipe network, inspection wells, rainwater inlets, and two-dimensional surface water catchment grids as basic units, output the grid water accumulation depth and water accumulation range at different simulation times; Construct a simulation model of urban road traffic; generate a simulateable road network structure based on road grade, number of lanes, design speed, traffic direction and signal control information; set time-sharing traffic demand based on the average thermal intensity of the study area on rainless days, and generate the number of vehicles per lane corresponding to different road categories; A spatial mapping relationship between a two-dimensional water accumulation grid and road segments is established. Within each simulation step, the water accumulation results of the grid within the road surface area are transformed into a time series of water accumulation depth in the road segment through identification and calculation methods.

3. The method as described in claim 2, characterized in that, The construction of the waterlogging and traffic coupling model also includes: A hydrodynamic-traffic simulation model converter is established through an interface to convert the grid water depth values ​​of the road surface range output by the urban waterlogging hydrodynamic model into the water accumulation time sequence of road sections, and dynamically adjust the road speed limit value according to the water accumulation and speed limit function to realize the encapsulation of control logic and automated operation. The waterlogging and traffic coupling model is used to respond to the user's road navigation request command and plan at least one driving route for the user according to preset priority conditions; the priority conditions include shortest time priority, shortest route priority and / or priority to avoid congested road sections. The waterlogging and traffic coupling model is used to respond to the traffic reduction control strategy. When planning routes for users, it avoids road sections that meet preset avoidance conditions. The preset avoidance conditions include road sections that are determined to be congested, road sections that are determined to be flooded or whose flooding situation is unknown, and road sections that are confirmed to be under construction.

4. The method as described in claim 3, characterized in that, The construction of the waterlogging and traffic coupling model also includes: Speed ​​limit information and traffic cost information for each road segment are dynamically written through an interface and integrated into the waterlogging and traffic coupling model, providing a simulation platform for simulating and comparing different traffic control strategies. The traffic cost information serves as a quantitative evaluation parameter for the comprehensive traffic cost of each road segment when a vehicle is about to pass through it. This traffic cost information is related to the distance travel cost, time travel cost, and additional water wading cost associated with that road segment. The distance travel cost is determined by the segment length and road type. The time travel cost is related to the speed limit information, traffic density, traffic light control duration, and speed reduction caused by waterlogging. The additional water wading cost is related to waterlogging parameters.

5. The method as described in claim 3, characterized in that, The process of publishing the speed limit information corresponding to the road to be set includes: The speed limit information for each road segment is displayed in the waterlogging and traffic coupling model. And / or, dynamically change the speed limit information on road signs within the target city area.

6. The method as described in claim 3, characterized in that, Also includes: The road parameters of the road to be set include the road type, which includes expressways, arterial roads, secondary arterial roads, local roads and / or special road sections; wherein, the water accumulation and speed limit curves corresponding to different road types are different.

7. The method as described in claim 3, characterized in that, Also includes: Obtain vehicle type information uploaded by users; the vehicle type information includes small passenger cars, freight cars, passenger cars and special-purpose vehicles, wherein the special-purpose vehicles include police cars, fire trucks, ambulances and / or engineering rescue vehicles; The vehicle type information, waterlogging parameters, and road parameters are input into the speed limit setting model, and the speed limit information corresponding to the road to be set is obtained from the speed limit setting model; wherein, the speed limit setting model obtains the speed limit information based on the water accumulation and speed limit curves of different road types and vehicle types. The system publishes speed limit information corresponding to the user's vehicle type and the route to be traveled, which is used as a suggested speed for the user's vehicle.

8. A dynamic speed limit setting system for urban flooding, characterized in that, For applying the road speed limit dynamic setting method as described in any one of claims 1 to 7, the road speed limit dynamic setting system comprises: The model building module is used to construct a coupled model of urban flooding and traffic. The coupled model of urban flooding and traffic integrates the urban flooding hydrodynamic model and the urban road traffic simulation model by establishing a spatial mapping relationship between a two-dimensional water accumulation grid and road segments. The parameter acquisition module obtains the road parameters of the road to be set, as well as the flooding parameters for the current or predicted time period, based on the waterlogging and traffic coupling model. The speed limit information acquisition module is used to input the waterlogging parameters and the road parameters into a preset speed limit setting model, and to acquire the speed limit information corresponding to the road to be set, output by the speed limit setting model; wherein, the speed limit setting model outputs speed limit information based on the water accumulation and speed limit curve, the water accumulation and speed limit curve is used to identify the correspondence between the speed limit value and the water accumulation depth of the road to be set; the water accumulation and speed limit curve is a curve corresponding to the water accumulation and dynamic speed limit value generated by applying the water accumulation and speed limit function based on the water accumulation depth of the road section, the road design speed, and the road category, and the water accumulation and speed limit function is a Logistic curve shape function; The information publishing module is used to publish speed limit information corresponding to the road to be set; wherein, the speed limit information includes the current speed limit value of the road to be set.

9. A computer program product, characterized in that, Includes a program that can be executed by a processor to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Includes a program that can be executed by a processor to implement the method as described in any one of claims 1 to 7.

Images