A method for obtaining dynamic speed limit value of a section

Abstract

The present invention discloses a method for obtaining a dynamic speed limit value of a section, collects basic static data of a tunnel, processes and analyzes the collected static data, and outputs the speed limit value of each highway tunnel speed limit section, and the specific steps are as follows: S1: preliminarily judge the speed limit section division of the highway tunnel; S2: construct a highway tunnel simulation model; draw a vehicle driving trajectory diagram based on the constructed highway tunnel simulation model, identify the speed mutation points of different highway tunnel speed limit sections, integrate and re-divide the highway tunnel speed limit sections, and determine the highway tunnel speed limit sections according to the simulation results; S3: construct a calculation model for the speed limit value of each highway tunnel speed limit section; S4: optimize the calculation model according to the speed limit value of multiple highway tunnel speed limit sections; S5: solve the calculation model based on the intelligent optimization algorithm, and output the speed limit value of each highway tunnel limit section. The present invention can effectively improve the fluency of tunnel traffic and prevent traffic jams and congestion.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence tunnel control research, and in particular to a method for obtaining a dynamic speed limit value of a section. Background Art

[0002] Tunnels are an indispensable part of the modern transportation system, carrying a large amount of traffic flow and travel needs. Traffic management and safety issues in tunnels have attracted much attention. How to formulate a reasonable speed limit strategy based on multiple factors such as road conditions and traffic conditions while ensuring tunnel traffic efficiency and driving safety has become a key challenge in tunnel traffic management. With the continuous development of traffic engineering technology and the gradual popularization of intelligent transportation systems, the research and practice of speed limits in different areas of tunnels have also attracted widespread attention.

[0003] The speed limit setting in the tunnel is not only related to traffic efficiency and smoothness, but also to traffic safety and the stability of the operating environment. Through reasonable regional speed limit design, the probability of traffic accidents can be effectively reduced and the safety and stability of traffic operation can be improved. In addition, the regional speed limit in the tunnel can also be finely managed according to the characteristics of different sections and traffic needs, improve road utilization efficiency, optimize traffic resource allocation, and achieve sustainable development of the transportation system.

[0004] Domestic and foreign research on variable speed limits focuses on open-air roads such as highways and urban expressways, but there are few studies on tunnels. Existing studies have focused too much on a single factor and ignored the overall consideration of multi-dimensional factors, which means that the adaptability and stability of speed limit models in practical applications still need to be tested. As a key part of traffic organization, highway tunnels are particularly prone to traffic safety and efficiency issues. This patent focuses on highway tunnels, analyzes their road characteristics and traffic operation characteristics, explores the key factors that affect the speed of vehicles in tunnels, and proposes a method for obtaining speed limit values ​​in complex tunnels, providing scientific support for traffic management and control of complex highway tunnels. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by this patent application is how to provide a method for obtaining dynamic speed limit values ​​for different sections, by analyzing the road characteristics and traffic flow characteristics of the tunnel, classifying the tunnel into different areas, and calculating the speed limit for each area. By dynamically adjusting the tunnel speed limit, it can adapt to different traffic and environmental conditions to ensure a smooth and safe driving environment.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0007] A method for obtaining a dynamic speed limit value of a section, collecting basic static data of a tunnel, processing and analyzing the collected static data, and outputting the speed limit value of each speed limit section of a highway tunnel, the specific steps are as follows:

[0008] S1: Preliminary determination of the speed limit zones of highway tunnels based on the road characteristics and ramp settings of the tunnels;

[0009] S2: Based on the measured data calibration, a highway tunnel simulation model is constructed; based on the constructed highway tunnel simulation model, a vehicle driving trajectory diagram is drawn, the speed mutation points of different highway tunnel speed limit sections are identified, the highway tunnel speed limit sections are integrated and re-divided, and the highway tunnel speed limit sections are determined according to the simulation results;

[0010] S3: Construct a calculation model for the speed limit value of each highway tunnel speed limit section;

[0011] S4: Optimize the calculation model based on the speed limit values ​​of speed limit sections in multiple highway tunnels;

[0012] S5: Solve the calculation model based on the intelligent optimization algorithm and output the speed limit value of each highway tunnel limit section.

[0013] Specifically, in step S1, when preliminarily judging the speed limit section division of the highway tunnel, the speed limit section of the tunnel is preliminarily divided according to the tunnel road data, taking into account the linear conditions and the diverging and merging areas, and the speed limit section is divided into a straight basic section, a curved basic section, a diverging section, a merging section and other sections.

[0014] Specifically, the specific process of step S2 is as follows:

[0015] N1: Construct highway tunnel simulation model: calibrate parameters of simulation models of different types of road sections based on measured data, including expected speed and driving behavior;

[0016] N2: Conduct simulation tests on different types of road sections, draw vehicle driving trajectory maps based on the simulation model, and identify speed mutation points in different speed limit sections;

[0017] N3: Calculate the distance between the speed mutation point and the special road section, that is, the length of the special road section influence area using the following formula:

[0018] S=S a -S b

[0019] Where: S is the length of the affected area, S a is the position of the velocity mutation point, S b The starting position of the special section;

[0020] N4: Calculate the length of the entire speed limit section. The speed limit section length is calculated using the following formula:

[0021] L=L j +L j-1 +L j+1

[0022] Where: L is the length of the speed limit section, L j is the total length of the special section, L j+1 is the length of the upstream impact area of ​​the special road section, L j-1 is the length of the downstream impact area of ​​the special road section;

[0023] N5: The driving environment of the straight basic road section is better than that of the special road section. When the speed is limited, the speed limit section length of the straight basic road section is greater than that of the special road section.

[0024] Specifically, in step S3, when constructing a calculation model for the speed limit value of each speed limit section of a highway tunnel, the vehicle driving conditions in the highway tunnel under different influencing factors are simulated based on the simulation model, and the vehicle speed values ​​under different combinations are output. The data is fitted using a multivariate nonlinear regression equation to generate a calculation model for the speed limit value of the basic section, diversion section, and merging section.

[0025] Specifically, in step S4, when optimizing the calculation model, from the perspective of improving tunnel traffic efficiency, that is, the total number of vehicles passing through the tunnel is maximized in the shortest travel time, two indicators, total travel time and total number of passing vehicles, are selected, and the two indicators are weighted by normalization to construct a coordinated optimization calculation model for complex highway tunnel sections. The model is as follows:

[0026]

[0027]

[0028] Comprehensive objective function: Z = max(α·TQ'-β·TS')

[0029] stα+β=1

[0030]

[0031]

[0032]

[0033] j=0,1...m

[0034] Among them: TS is the total travel time, TQ is the total number of passing vehicles, is the speed limit value of speed limit zone j in time period t, is the calculated theoretical speed limit value of speed limit zone j in time period t.

[0035] Specifically, the specific process of step S5 is as follows:

[0036] Use the particle swarm algorithm to solve the optimal speed limit for the model:

[0037] First, 50 initial values ​​within the constraints are randomly generated;

[0038] Then, for each individual, determine its optimal position pbest; take the optimal individual as the center, update the position of the particle, that is, adjust the value of the variable; through the iterative process, find the optimal solution gbest of the group and the optimal position pbest of each individual; if a better solution is found, update gbest and pbest;

[0039] The loop is iterated until the optimal value is reached.

[0040] Specifically, the particle swarm algorithm solution steps are as follows:

[0041] P1: Initialize particle swarm: Generate a swarm of multiple particles; each particle represents a potential variable speed limit strategy, including multiple speed limit solutions; the position and speed of the particle are randomly initialized in the multidimensional search space, the position represents a possible solution, and the speed determines the search direction and step size;

[0042] P2: Evaluation objective function: For each particle, its performance on the two objective functions of maximum traffic flow and minimum travel time is evaluated according to the variable speed limit model; after the evaluation, each particle will obtain a fitness value on each objective according to its performance;

[0043] P3: Calculate particle fitness: Each particle will compare its current position with its historical optimal position, i.e., individual optimal position. For each particle, the fitness value, i.e., the value of the objective function, is calculated based on its current position.

[0044] P4: Update particle speed and position: Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update formula includes inertia factor, individual learning factor and social learning factor, which determine the way particles explore new solutions. The position update is to add the updated speed to the original position.

[0045] P5: Check termination conditions: Check whether the algorithm meets the termination conditions, such as reaching the maximum number of iterations, the quality of the solution exceeding the preset threshold, or the improvement of the solution falling below a certain critical value; if the termination conditions are met, the algorithm stops, otherwise it returns to the second step to continue iterating;

[0046] P6: Output the optimal solution: After the algorithm terminates, output the current global optimal solution.

[0047] In summary, this method of obtaining dynamic speed limit values ​​for different sections is a key measure to ensure driving safety inside tunnels. It can effectively prevent traffic accidents caused by excessive speed. Reasonable speed limit settings can help improve the smoothness of tunnel traffic and prevent traffic jams and congestion. In addition, speed limit measures can also reduce vehicle fuel consumption and exhaust emissions, reduce adverse impacts on the environment, and promote a virtuous cycle of tunnel traffic management and sustainable development of traffic. This application deeply analyzes factors such as curvature changes and ramp settings in tunnels, accurately identifies speed fluctuation points under different traffic conditions, scientifically divides speed limit sections, and calculates speed limit values ​​for each area, providing a scientific basis and practical methods for highway tunnel traffic management, and promoting the further development and improvement of highway traffic systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention provides a flow chart of a method for obtaining a dynamic speed limit value for a sub-section.

[0049] Figure 2 This is a schematic diagram of the speed limit section.

[0050] Figure 3 Provide a technical roadmap for particle swarm optimization solution. DETAILED DESCRIPTION

[0051] The present invention is further described in detail below in conjunction with the accompanying drawings. In the description of the present invention, it should be understood that the directions or positional relationships indicated by directional words such as "upper, lower" and "top, bottom" are usually based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description. Unless otherwise stated, these directional words do not indicate or imply that the devices or components referred to must have a specific direction or be constructed and operated in a specific direction, and therefore cannot be understood as limiting the scope of protection of the present invention; the directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0052] like Figure 1-3 As shown, a method for obtaining a dynamic speed limit value of a section is provided, wherein the basic static data of the tunnel is collected, and the collected static data is processed and analyzed, and the speed limit value of each speed limit section of the highway tunnel is output. The specific steps are as follows:

[0053] S1: Preliminary determination of the speed limit zones of highway tunnels based on the road characteristics and ramp settings of the tunnels;

[0054] S2: Based on the measured data calibration, a highway tunnel simulation model is constructed; based on the constructed highway tunnel simulation model, a vehicle driving trajectory diagram is drawn, the speed mutation points of different highway tunnel speed limit sections are identified, the highway tunnel speed limit sections are integrated and re-divided, and the highway tunnel speed limit sections are determined according to the simulation results;

[0055] S3: Construct a calculation model for the speed limit value of each highway tunnel speed limit section;

[0056] S4: Optimize the calculation model based on the speed limit values ​​of speed limit sections in multiple highway tunnels;

[0057] S5: Solve the calculation model based on the intelligent optimization algorithm and output the speed limit value of each highway tunnel limit section.

[0058] During the specific implementation, in step S1, when preliminarily judging the speed limit section division of the highway tunnel, the speed limit section of the tunnel is preliminarily divided according to the tunnel road data, taking into account the linear conditions and the diverging and merging areas, and the speed limit section is divided into a straight basic section, a curved basic section, a diverging section, a merging section and other sections.

[0059] Specifically, the specific process of step S2 is as follows:

[0060] N1: Construct highway tunnel simulation model: calibrate parameters of simulation models of different types of road sections based on measured data, including expected speed and driving behavior;

[0061] N2: Conduct simulation tests on different types of road sections, draw vehicle driving trajectory maps based on the simulation model, and identify speed mutation points in different speed limit sections;

[0062] N3: Calculate the distance between the speed mutation point and the special road section, that is, the length of the special road section influence area using the following formula:

[0063] S=S a -S b

[0064] Where: S is the length of the affected area, S a is the position of the velocity mutation point, S b The starting position of the special section;

[0065] Special road sections refer to road sections that, compared with general road sections, have lower horizontal and vertical alignment indicators, a combination of different structures, complex climatic conditions, etc., which are not conducive to driving safety.

[0066] N4: Calculate the length of the entire speed limit section. The speed limit section length is calculated using the following formula:

[0067] L=L j +L j-1 +L j+1

[0068] Where: L is the length of the speed limit section, L j is the total length of the special section, L j+1 is the length of the upstream impact area of ​​the special road section, L j-1 is the length of the downstream impact area of ​​the special road section;

[0069] N5: The driving environment of the basic straight road section is better than that of the special road section. When the speed is limited, the length of the speed limit section of the basic straight road section is longer than that of the special road section. The driving environment of the basic straight road section is better. When the speed is limited, the length of the speed limit section of the basic straight road section is longer; the length of the special road section is shorter. Speed ​​transition is required between speed limit sections, and the driver needs to drive steadily for a certain distance in a speed limit section.

[0070] During specific implementation, in step S3, when constructing a calculation model for the speed limit value of each highway tunnel speed limit section, the vehicle driving conditions in the highway tunnel under different influencing factors are simulated based on the simulation model, and the vehicle speed values ​​under different combinations are output. The multivariate nonlinear regression equation is used to fit the data to generate a calculation model for the speed limit value of the basic section, diversion section, and merging section.

[0071] In the specific implementation, in step S4, when optimizing the calculation model, from the perspective of improving the tunnel traffic efficiency, that is, the total number of vehicles passing through the tunnel is maximized in the shortest travel time, the total travel time and the total number of passing vehicles are selected as two indicators, and the two indicators are weighted by normalization to construct a coordinated optimization calculation model for complex highway tunnel sections. The model is as follows:

[0072]

[0073]

[0074] Comprehensive objective function: Z = max(α·TQ'-β·TS')

[0075] stα+β=1

[0076]

[0077]

[0078]

[0079] j=0,1...m

[0080] Among them: TS is the total travel time, TQ is the total number of passing vehicles, is the speed limit value of speed limit zone j in time period t, is the calculated theoretical speed limit value of speed limit zone j in time period t.

[0081] During specific implementation, the specific process of step S5 is as follows:

[0082] Use the particle swarm algorithm to solve the optimal speed limit for the model:

[0083] First, 50 initial values ​​within the constraints are randomly generated;

[0084] Then, for each individual, determine its optimal position pbest; take the optimal individual as the center, update the position of the particle, that is, adjust the value of the variable; through the iterative process, find the optimal solution gbest of the group and the optimal position pbest of each individual; if a better solution is found, update gbest and pbest;

[0085] The loop is iterated until the optimal value is reached.

[0086] In specific implementation, the particle swarm algorithm solution steps are as follows:

[0087] P1: Initialize particle swarm: Generate a swarm of multiple particles; each particle represents a potential variable speed limit strategy, including multiple speed limit solutions; the position and speed of the particle are randomly initialized in the multidimensional search space, the position represents a possible solution, and the speed determines the search direction and step size;

[0088] P2: Evaluation objective function: For each particle, its performance on the two objective functions of maximum traffic flow and minimum travel time is evaluated according to the variable speed limit model; after the evaluation, each particle will obtain a fitness value on each objective according to its performance;

[0089] P3: Calculate particle fitness: Each particle will compare its current position with its historical optimal position, i.e., individual optimal position. For each particle, the fitness value, i.e., the value of the objective function, is calculated based on its current position.

[0090] P4: Update particle speed and position: Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update formula includes inertia factor, individual learning factor and social learning factor, which determine the way particles explore new solutions. The position update is to add the updated speed to the original position.

[0091] P5: Check termination conditions: Check whether the algorithm meets the termination conditions, such as reaching the maximum number of iterations, the quality of the solution exceeding the preset threshold, or the improvement of the solution falling below a certain critical value; if the termination conditions are met, the algorithm stops, otherwise it returns to the second step to continue iterating;

[0092] P6: Output the optimal solution: After the algorithm terminates, output the current global optimal solution.

[0093] Tunnel speed limit is an important challenge in current tunnel traffic management. Tunnel speed limit is a key measure to ensure driving safety inside the tunnel. It can effectively prevent traffic accidents caused by excessive speed. Reasonable speed limit setting can help improve the smoothness of tunnel traffic and prevent traffic jams and congestion. In addition, speed limit measures can also reduce vehicle fuel consumption and exhaust emissions, reduce adverse impacts on the environment, and promote a virtuous cycle of tunnel traffic management and sustainable development of traffic. This technical solution aims to calculate the speed limit values ​​of each area of ​​the tunnel. A method for obtaining the speed limit value of a complex tunnel is proposed. By deeply analyzing factors such as curvature changes and ramp settings in the tunnel, the speed fluctuation points under different traffic conditions are accurately identified, the speed limit sections are scientifically divided, and the speed limit values ​​of each area are calculated. This method provides a scientific basis and practical methods for highway tunnel traffic management, and promotes the further development and improvement of the highway traffic system.

[0094] Finally, it should be noted that those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for obtaining a dynamic speed limit value of a partition section, It is characterized in that The basic static data of the tunnel is collected, and the collected static data is processed and analyzed to output the speed limit value of each highway tunnel speed limit section. The specific steps are as follows: S1: Preliminary determination of the speed limit zones of highway tunnels based on the road characteristics and ramp settings of the tunnels; S2: Based on the measured data calibration, a highway tunnel simulation model is constructed; based on the constructed highway tunnel simulation model, a vehicle driving trajectory diagram is drawn, the speed mutation points of different highway tunnel speed limit sections are identified, the highway tunnel speed limit sections are integrated and re-divided, and the highway tunnel speed limit sections are determined according to the simulation results; S3: Construct a calculation model for the speed limit value of each highway tunnel speed limit section; S4: Optimize the calculation model based on the speed limit values ​​of speed limit sections in multiple highway tunnels; S5: Solve the calculation model based on the intelligent optimization algorithm and output the speed limit value of each highway tunnel limit section; In step S1, when preliminarily determining the speed limit section division of the highway tunnel, the speed limit section of the tunnel is preliminarily divided into a straight basic section, a curved basic section, a diverging section, a merging section and other sections according to the tunnel road data, taking into account the linear conditions and the diverging and merging areas; The specific process of step S2 is as follows: N1: Construct highway tunnel simulation model: calibrate parameters of simulation models of different types of road sections based on measured data, including expected speed and driving behavior; N2: Conduct simulation tests on different types of road sections, draw vehicle driving trajectory maps based on the simulation model, and identify speed mutation points in different speed limit sections; N3: Calculate the distance between the speed mutation point and the special road section, that is, the length of the special road section influence area using the following formula: S=S a -S b Where: S is the length of the affected area, S a is the position of the velocity mutation point, S b The starting position of the special section; N4: Calculate the length of the entire speed limit section. The speed limit section length is calculated using the following formula: L=L j +L j-1 +L j+1 Where: L is the length of the speed limit section, L j is the total length of the special section, L j+1 is the length of the upstream impact area of ​​the special road section, L j-1 is the length of the downstream impact area of ​​the special road section; N5: The driving environment of the straight basic road section is better than that of the special road section. When the speed is limited, the speed limit section length of the straight basic road section is greater than that of the special road section.

2. A method for obtaining a dynamic speed limit value of a section according to claim 1, It is characterized in that In step S3, when constructing a calculation model for the speed limit value of each highway tunnel speed limit section, the vehicle driving conditions in the highway tunnel under different influencing factors are simulated based on the simulation model, the vehicle speed values ​​under different combinations are output, and the multivariate nonlinear regression equation is used to fit the data to generate a calculation model for the speed limit value of the basic section, diversion section, and merging section.

3. A method for obtaining a dynamic speed limit value of a section according to claim 1, It is characterized in that In step S4, when optimizing the calculation model, from the perspective of improving tunnel traffic efficiency, that is, the total number of vehicles passing through the tunnel is maximized in the shortest travel time, two indicators, total travel time and total number of passing vehicles, are selected, and the two indicators are weighted by normalization to construct a coordinated optimization calculation model for complex highway tunnel sections. The model is as follows: Comprehensive objective function: Z = max(α·TQ'-β·TS') stα+β=1 j=0,1...m Among them: TS is the total travel time, TQ is the total number of passing vehicles, is the speed limit value of speed limit zone j in time period t, is the calculated theoretical speed limit value of speed limit zone j in time period t.

4. A method for obtaining a dynamic speed limit value of a section according to claim 3, It is characterized in that The specific process of step S5 is as follows: Use the particle swarm algorithm to solve the optimal speed limit for the model: First, 50 initial values ​​within the constraints are randomly generated; Then, for each individual, determine its optimal position pbest; take the optimal individual as the center, update the position of the particle, that is, adjust the value of the variable; through the iterative process, find the optimal solution gbest of the group and the optimal position pbest of each individual; if a better solution is found, update gbest and pbest; The loop is iterated until the optimal value is reached.

5. A method for obtaining a dynamic speed limit value of a section according to claim 4, It is characterized in that The particle swarm algorithm solution steps are as follows: P1: Initialize particle swarm: Generate a swarm of multiple particles; each particle represents a potential variable speed limit strategy, including multiple speed limit solutions; the position and speed of the particle are randomly initialized in the multidimensional search space, the position represents a possible solution, and the speed determines the search direction and step size; P2: Evaluation objective function: For each particle, its performance on the two objective functions of maximum traffic flow and minimum travel time is evaluated according to the variable speed limit model; after the evaluation, each particle will obtain a fitness value on each objective according to its performance; P3: Calculate particle fitness: Each particle will compare its current position with its historical optimal position, i.e., individual optimal position. For each particle, the fitness value, i.e., the value of the objective function, is calculated based on its current position. P4: Update particle speed and position: Update the speed and position of each particle according to the individual optimum and the global optimum. The speed update formula includes inertia factor, individual learning factor and social learning factor, which determine the way particles explore new solutions. The position update is to add the updated speed to the original position. P5: Check termination conditions: Check whether the algorithm meets the termination conditions, such as reaching the maximum number of iterations, the quality of the solution exceeding the preset threshold, or the improvement of the solution falling below a certain critical value; if the termination conditions are met, the algorithm stops, otherwise it returns to the second step to continue iterating; P6: Output the optimal solution: After the algorithm terminates, output the current global optimal solution.

Images