A smart city traffic signal light control system

Abstract

The present invention discloses a smart city traffic signal light control system, which relates to the field of traffic signal control technology. The system includes the following components: a regional division module, a traffic flow detection sensor, a regional traffic flow analysis module, a signal light control strategy generation module, and an inter-regional signal light collaborative control module, as well as a variable information sign, an information processing and generation module. The present invention can monitor and analyze urban traffic flow conditions in real time and accurately by comprehensively utilizing advanced regional division algorithms, traffic flow detection technologies, and precise traffic flow status assessment models. Based on the analysis results, the system can intelligently generate signal light control strategies, including adopting a congestion relief dynamic timing algorithm in congested areas to reduce the number of signal light switching times, and adopting a flow balancing guidance timing algorithm in areas with less traffic. In addition, the system can also realize the collaborative control of inter-regional signal lights to ensure efficient connection and balanced distribution of traffic flows between regions.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control, and in particular to a smart city traffic signal light management and control system. Background Art

[0002] With the acceleration of urbanization, urban traffic problems have become increasingly prominent. Traffic congestion and frequent traffic accidents have seriously affected citizens' travel experience and the overall operation efficiency of the city. In order to solve these problems, the concept of smart city came into being. Among them, the smart city traffic signal control system, as a key link, is of great significance to improving the level of urban traffic management and alleviating traffic congestion.

[0003] There are shortcomings in traditional technologies. First, traditional systems are usually based on relatively simple traffic flow detection methods, such as a single induction coil or camera. These methods often cannot fully and accurately reflect the real-time changes in traffic flow, resulting in a lack of accurate basis for the formulation of traffic light control strategies. Second, traditional systems often use a fixed method for regional division, which lacks flexibility and cannot be dynamically adjusted according to the actual situation of urban traffic flow.

[0004] In summary, traditional technologies have many shortcomings in dealing with urban traffic congestion problems. Therefore, it is particularly important to develop a smart city traffic signal light control system. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a smart city traffic signal light control system, which can monitor and analyze the changes in urban traffic flow in real time and accurately by comprehensively using a variety of advanced traffic flow detection technologies and accurate traffic flow status assessment models. At the same time, the system should also have the ability to generate intelligent signal light control strategies and the ability to coordinate control of signal lights between regions to ensure efficient connection and balanced distribution of traffic flow between regions. Through the joint effect of these measures, the smoothness and efficiency of urban traffic can be significantly improved, the occurrence of traffic congestion can be reduced, and the travel experience of citizens can be enhanced.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart city traffic signal light control system, which includes the following components: a regional division module, a traffic flow detection sensor, a regional traffic flow analysis module, a signal light control strategy generation module and an inter-regional signal light coordinated control module, as well as a variable information sign and an information processing and generation module;

[0007] The regional division module divides the urban road network into multiple traffic areas. This division is based on a comprehensive assessment of multi-dimensional data, including but not limited to road infrastructure data, historical traffic flow data, geographic information data, and urban functional area distribution data. By constructing a regional division algorithm based on the combination of the analytic hierarchy process (AHP) and the fuzzy C-means clustering (FCM), the AHP is first used to determine the relative weights of each evaluation factor. The road infrastructure completeness weight w1 is determined based on expert scoring and statistical analysis of road width, road surface conditions, and traffic facility configuration factors. The historical traffic flow weight w2 is based on data analysis of the influence of traffic flow at different time periods and sections on regional division. The geographic information weight w3 takes into account the impact of topography and water system distribution on traffic flow. The urban functional area weight w4 is determined by analyzing the regional traffic characteristics of commercial areas, residential areas, and industrial areas. These weights are applied to the FCM algorithm. The formula is: Among them J m is the objective function, n is the number of data points, c is the number of cluster centers, u ij is the degree of membership of data point i to cluster j, m is the fuzzy index, x i is the eigenvector of data point i, v j is the center vector of cluster j, and J is optimized by continuous iteration. m , until the convergence condition is met and the optimal region division result is obtained;

[0008] The traffic flow detection sensor is installed in each traffic area to collect traffic flow data, including vehicle volume, speed, and vehicle type information. Traffic flow detection uses a fusion technology of high-precision induction coils and microwave radars. The induction coils are buried at a specific depth and position under the road surface and detect magnetic field changes caused by metal parts of the vehicle based on the principle of electromagnetic induction. The microwave radar transmits microwave signals and receives reflected waves, and calculates vehicle speed through the Doppler effect. The two work together to improve the accuracy of traffic flow detection. Vehicle type identification uses deep learning image recognition technology and a convolutional neural network to extract and classify vehicle images captured by the camera. The CNN network structure includes multiple convolutional layers, pooling layers, and fully connected layers. The convolution kernel size and number of the convolutional layers and the step size hyperparameters of the pooling layers are determined through training and optimization of a large number of vehicle image samples.

[0009] The regional traffic flow analysis module is connected to the traffic flow detection sensor and is used to analyze the traffic flow situation in each area. It uses an analysis algorithm based on the combination of traffic flow dynamics and data mining technology to build a traffic flow status assessment model. The formula is: Where S represents the traffic flow state value, Q is the traffic volume, C is the theoretical road capacity, δ is the traffic flow impact weight, V is the average speed, V f is the free flow speed, ∈ is the speed influence weight, Tmix is the equivalent travel time of mixed vehicle types, T t otal is the total observation time, and φ is the vehicle type influence weight. This model comprehensively evaluates the regional traffic flow status and provides an accurate basis for traffic light control strategies.

[0010] The signal light control strategy generation module is connected to the regional traffic flow analysis module and is used to generate a signal light control strategy based on the analysis results. In congested areas with large traffic flows, a congestion relief dynamic timing algorithm is used. The formula is: Among them, G1 is the green light duration after adjustment in the congested area, G0 is the basic green light duration, k is the adjustment coefficient, S is the current traffic flow state value, S t is the congestion threshold state value, T c The signal light cycle time is the same as the signal light switching time. The switching time adjustment formula is: N1=N0-λ×(SS t ), where N1 is the adjusted switching number, N0 is the basic switching number, and λ is the switching number adjustment coefficient. In areas with low traffic, the flow balance guidance timing algorithm is used, and the formula is: Where G2 is the green light duration after adjustment in the low traffic area, μ is the balance adjustment coefficient, S min is the minimum traffic flow state value in the area;

[0011] The inter-regional traffic light coordination control module is connected to the traffic light control strategy generation module and is used to coordinate the control of traffic lights within and between regions. An inter-regional traffic light coordination model is constructed based on graph theory and dynamic programming principles. Each traffic area is regarded as a node in the graph, and the connecting roads between regions are regarded as edges. The weight of the edge is determined by the road capacity, traffic flow and traffic light timing factors. The formula is: Where W is the weight of the connecting road between region i and region j, C is the road capacity, Q is the traffic flow, α is the impact weight of the capacity, T g T is the green light duration from area i to area j, c is the traffic light cycle length, and β is the traffic light timing influence weight. By solving the optimal path of the model, the coordinated switching strategy of traffic lights between regions is determined to achieve efficient connection and balanced distribution of traffic flow between regions.

[0012] The variable information sign is set at the intersection;

[0013] The information processing and generating module is connected to the traffic lights and traffic flow detection sensors, and is used to generate guidance information according to the changes in traffic light timing and real-time traffic conditions.

[0014] Furthermore, the induction coil in the traffic flow detection sensor adopts a double-winding structure, the inner winding adopts a highly sensitive enameled copper wire, which is used to capture the initial signal of the weak magnetic field change when a vehicle passes by, and the outer winding adopts a high-temperature resistant and corrosion-resistant alloy wire, which is used to enhance the magnetic field signal strength and stabilize the detection signal. The ratio of the number of turns of the inner winding to the number of turns of the outer winding is determined according to the road type and the expected traffic volume. On main roads with heavy traffic and fast speeds, the value is 1:3-1:5; on branches with less traffic, the value is 1:2-1:3. This double-winding structure and turn ratio design can effectively improve the accuracy and stability of traffic flow detection, reduce the impact of external electromagnetic interference, and ensure that traffic flow data can be accurately obtained in different traffic environments.

[0015] Furthermore, the calculation of the theoretical road capacity C in the traffic flow state assessment model in the regional traffic flow analysis module takes into account many factors. In addition to the basic parameters of the number of road lanes and width, the influence of road slope, curve curvature and surrounding interference factors is also included. By establishing a traffic capacity calculation model based on multiple linear regression: C = k1×L+k2×W+k3×G+k4×B+k5×P, where L is the number of lanes, W is the road width, G is the road slope, B is the curve curvature, P is the quantitative value of the surrounding interference factors, and k1-k5 are regression coefficients. These coefficients are obtained by analyzing a large number of The value of k1 is determined by collecting and analyzing field traffic data of different types of roads. The value of k1 is obtained by fitting the standard capacity of roads with different numbers of lanes and actual observation data, and is between 1000-1500 (vehicles / hour / lane). The value of k2 is determined by considering the impact of road width on vehicle driving space, and is between 50-100 (vehicles / hour / meter). The values ​​of k3, k4, and k5 are determined according to the degree of obstruction to traffic flow caused by road slope, curve curvature, and surrounding interference factors, and are between -100 and 100, respectively. This enables accurate calculation of the theoretical capacity of roads and improves the accuracy of traffic flow status assessment.

[0016] Furthermore, the congestion threshold state value S in the congestion relief dynamic timing algorithm in the signal light control strategy generation module t Adaptive learning method is used to determine the traffic flow state. The historical traffic flow data in a certain period are collected and cluster analysis is used to classify the traffic flow state into multiple levels: smooth, light congestion, moderate congestion, and severe congestion. Then the traffic flow state value range of each level is calculated and the lower limit of the moderate congestion level is taken as the initial S. t During the operation of the system, based on the feedback of actual traffic congestion, the incremental learning algorithm in machine learning is used to t Dynamic adjustment is performed. If a region appears multiple times in a specific period of time, the current S t If it is determined to be non-congested but the actual traffic is slow, the incremental learning algorithm will be used to appropriately improve St value to better adapt to the dynamic changes in urban traffic conditions and ensure the effectiveness and timeliness of congestion relief strategies.

[0017] Furthermore, the minimum traffic flow state value S in the area in the traffic balance guidance timing algorithm in the signal light control strategy generation module min The calculation adopts the sliding window statistical method, setting a time window T w , the value is 10-20 minutes, the traffic flow state value in each time window is counted, and the minimum value is taken as S in the window min As time goes by, the window keeps sliding and updating, and the latest S min At the same time, in order to avoid the influence of abnormal data, the median filtering technology is used to pre-process the traffic flow state values ​​obtained by statistics, remove data points that obviously deviate from the normal range, and improve S min The accuracy and reliability of the calculation provide a precise basis for flow balance guidance and timing, and promote the rational distribution of traffic flow between regions.

[0018] Furthermore, the signal light cycle length T in the inter-region traffic signal light coordination model in the inter-region signal light coordination control module is c The determination adopts a hierarchical optimization strategy, and determines the basic signal light cycle duration range according to the road grade and regional importance. The basic cycle duration of urban main roads is In 100-150 seconds, secondary roads In 60-100 seconds, considering the real-time changes of inter-regional traffic flow, the basic cycle duration is dynamically adjusted using the fuzzy logic control algorithm. The input of the fuzzy logic controller is the inter-regional traffic flow difference rate ΔQ and the intra-regional traffic flow saturation S. r , the output is the cycle length adjustment ΔT c , by defining the fuzzy rule table, when ΔQ is large and S r High ΔT c Take a larger positive value to increase the signal light cycle time to relieve traffic pressure, ΔQ is small and S r When low, ΔT c Take a smaller negative value to shorten the signal light cycle and improve traffic efficiency. After fuzzy reasoning and clarification processing, the final signal light cycle duration T is obtained. c =T c0 +ΔT c , realizing intelligent optimization and coordinated control of traffic light cycle duration between areas.

[0019] Furthermore, when the information processing and generation module generates the guidance information, the information generation for the road congestion ahead adopts a method based on the combination of traffic wave theory and data prediction model, and uses traffic wave theory to analyze the propagation characteristics of traffic congestion and determine the propagation speed V of the congestion wave. w and congestion density ρ w The relationship between them is: Where V f is the free flow speed, ρ j In order to estimate the congestion density, the real-time traffic flow data obtained by the traffic flow detection sensor is used, and the time series prediction model is used to predict the traffic flow changes in the future period, and then the propagation range and intensity of the congestion wave are deduced. This information is converted into intuitive graphics or text information and displayed on the variable information sign. Different colored line segments are used to represent different degrees of congestion. Red indicates heavy congestion, yellow indicates moderate congestion, and green indicates smooth traffic. This provides drivers with accurate and timely information on road congestion ahead, helping them plan their routes in advance and avoid getting stuck in congested areas.

[0020] Furthermore, the variable information sign display control module dynamically adjusts the layout of the display content of the variable information sign, determines the size and position of the display area according to the importance and urgency of the inductive information, adopts a full-screen display mode for urgent traffic control information, and highlights it with the largest font and bright color to ensure that the driver can obtain the information in the first time. For recommended driving route information, it is displayed in the main display area of ​​the variable information sign in the form of a combination of dynamic arrows and text. The direction of the arrow indicates the driving direction, and the text marks the road name and distance. For information on congestion conditions on the road ahead, it is scrolled in the form of a small window at the edge of the screen without affecting the display of the main information. At the same time, the display brightness is automatically adjusted according to the ambient light intensity, and a light sensor is used to detect the light intensity. When the light intensity is strong, the display brightness is increased to enhance visibility. When the light intensity is weak, the display brightness is reduced to reduce energy consumption and light pollution, thereby realizing intelligent layout of display content and adaptive brightness control, and improving the effectiveness and comfort of information transmission.

[0021] Furthermore, the system also includes a system fault diagnosis and self-repair module, which monitors the working status of each component of the system in real time. For traffic flow detection sensors, it determines whether they are working normally by sending detection signals of specific frequencies and receiving feedback signals. If the feedback signal is abnormal, the backup sensor is started, and the cause of the fault is analyzed using a fault diagnosis algorithm. The maintenance task is automatically dispatched according to the diagnosis result. For traffic light controllers, it monitors whether their signal output and control logic are normal. If a fault occurs, it switches to the backup controller and remotely resets and repairs the faulty controller. For variable information signs, it checks the integrity of the display content and the brightness uniformity index. If an abnormality is found, it automatically adjusts the display parameters or switches to the backup display module. Through this module, the system can achieve high-reliability operation, reduce the risk of traffic management interruption due to equipment failure, and improve the safety and stability of urban traffic.

[0022] Compared with the existing technology, this smart city traffic signal light control system has the following beneficial effects:

[0023] 1. This system can monitor and analyze urban traffic flow conditions in real time and accurately by comprehensively utilizing regional division algorithms, traffic flow detection technology, and precise traffic flow status assessment models. Based on the analysis results, the system can intelligently generate traffic light control strategies, including the use of a dynamic timing algorithm to alleviate congestion in congested areas to reduce the number of signal light switches, and the use of a flow balancing guidance timing algorithm in areas with less traffic. In addition, the system can also achieve coordinated control of traffic lights between regions to ensure efficient connection and balanced distribution of traffic flows between regions. These measures, working together, can significantly improve the smoothness and efficiency of urban traffic, reduce traffic congestion, and enhance citizens' travel experience.

[0024] 2. By adopting adaptive learning methods and incremental learning algorithms, this system can dynamically adjust the congestion threshold status value and key parameters of the signal light cycle duration based on feedback from actual traffic congestion conditions to better adapt to the dynamic changes in urban traffic conditions. At the same time, the system can also dynamically adjust the display content of variable information signs according to the importance and urgency of the inductive information, and automatically adjust the display brightness according to the ambient light intensity. These intelligent functions enable the system to provide more accurate, timely and humane traffic management services according to different scenarios and needs, thereby enhancing the overall efficiency of urban traffic management.

[0025] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0027] Figure 1 This is a process operation diagram of a smart city traffic signal light control system. DETAILED DESCRIPTION

[0028] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0029] Example 1

[0030] This embodiment describes a city center business district with narrow roads, numerous shops, and extremely large pedestrian and vehicle flows. Especially during the morning and evening rush hours, traffic congestion is severe and the traffic composition is complex, including a large number of private cars, taxis, and delivery vehicles of different types.

[0031] The method collects data on road infrastructure in commercial areas (road width, good road conditions, and complete traffic facilities), historical traffic flow data (extremely high vehicle and pedestrian traffic during peak hours), geographic information data (flat terrain, but with many parking lots and commercial building entrances in the surrounding area), and urban functional area distribution data (clearly commercial areas). The weights are determined using the hierarchical analysis method. The road infrastructure completeness weight w1 is determined based on expert scoring and statistical analysis, combined with the actual situation of commercial area roads. The historical traffic flow weight w2 is derived from an analysis of the influence of peak-hour traffic on regional division. The geographic information weight w3 takes into account the influence of surrounding parking lots and building entrances. The urban functional area weight w4 is determined based on the traffic characteristics of the commercial area. These weights are applied to the fuzzy C-means clustering algorithm. After iterative optimization, the commercial area road network is divided into multiple traffic areas, such as areas centered on large shopping malls and office buildings.

[0032] Traffic flow detection sensors are installed at key intersections and sections in each traffic area, using high-precision induction coil and microwave radar fusion technology. The inner winding of the induction coil on the main road uses high-sensitivity enameled copper wire, and the outer winding uses high-temperature and corrosion-resistant alloy wire. The ratio of the number of inner winding turns to the outer winding turns is 1:4 based on the characteristics of large traffic volume and high speed on the main road, and 1:2 on the branch road.

[0033] The induction coil detects the changes in the magnetic field caused by the metal parts of the vehicle based on the principle of electromagnetic induction. The microwave radar transmits microwave signals and receives reflected waves, and calculates the vehicle speed through the Doppler effect. The two work together to accurately collect traffic flow and speed information. At the same time, the camera captures vehicle images and uses convolutional neural networks to identify vehicle types. The hyperparameters of the convolutional layer and pooling layer are optimized through training with a large number of vehicle image samples to ensure accurate identification of different types of vehicles such as cars, buses, and taxis.

[0034] The regional traffic flow analysis module calculates the traffic flow state value S using the traffic flow state evaluation model based on the data collected by the traffic flow detection sensor. The calculation of the theoretical road capacity C takes into account the number of road lanes (mostly two-way four-lane or six-lane), width (wider), slope (smaller), curve curvature (smaller) and surrounding interference factors (such as parking lot entrances and exits, pedestrians crossing). By establishing a traffic capacity calculation model based on multiple linear regression, the traffic flow impact weight δ, speed impact weight ε and vehicle type impact weight are obtained. It is determined based on the traffic characteristics of the commercial area. For example, the impact weight of traffic flow is relatively high. It is calculated that the S value of each area is higher during peak hours, indicating that the traffic flow is large and the congestion level is high.

[0035] For areas with severe congestion, such as intersections around shopping malls, a congestion relief dynamic timing algorithm is used. The congestion threshold state value S is determined by the real-time calculated traffic flow state value S and the adaptive learning method. t (Initially take the lower limit of the moderate congestion level and adjust it dynamically according to the actual congestion feedback) Increase the green light duration and use the formula N1=N0-λ×(SS t ) Reduce the number of signal light switching times to ease congestion. For example, the basic green light duration G0 at a certain intersection is 30 seconds, and the signal light cycle duration T c is 120 seconds, the adjustment coefficient k is 0.5, and the switching times adjustment coefficient λ is 0.3. When S is higher than S t When the green light duration is appropriately increased, the number of switching times is reduced. For some areas with small traffic volume, the flow balance guidance timing algorithm is used, and the sliding window statistical method (time window T w Take 15 minutes) to calculate the minimum traffic flow state value S in the area min , and use median filtering technology to preprocess the data to avoid the influence of abnormal data, and then according to the formula Adjust the green light duration to balance traffic flow between areas. For example, the basic green light duration G0 of a branch road area is 20 seconds, and the balance adjustment coefficient μ is 0.4. When the traffic volume in this area is small, the green light duration is appropriately reduced to guide vehicles to divert to other areas.

[0036] Considering each traffic area in the commercial district as a node and the connecting roads between areas as edges, a coordinated model of traffic lights between areas is constructed. The weight of the edge is determined by the road capacity (calculated based on the number of lanes and width), traffic flow (real-time detection), and signal light timing factors. For example, a main road connects two important commercial areas. Its road capacity C is high, and the traffic flow Q is large during peak hours. According to the formula Calculate the weights, where the capacity impact weight α and the signal timing impact weight β are determined based on the importance of regional traffic.

[0037] By solving the optimal path of the collaborative model, the coordinated switching strategy of traffic lights between regions is determined. For example, during peak hours, in order to ensure smooth traffic between commercial areas, the traffic lights on main roads and branch roads are coordinated so that vehicles can flow from one commercial area to another in an orderly manner, avoiding information processing and generation and the display of variable information signs.

[0038] The information processing and generation module generates guidance information based on changes in traffic light timing and real-time traffic conditions. For road congestion ahead, it uses traffic wave theory to analyze the congestion propagation characteristics. Combined with real-time data obtained by traffic flow detection sensors, the time series prediction model is used to predict the propagation range and intensity of the congestion wave. For example, it predicts that moderate congestion will occur 500 meters ahead on a main road, and the congestion wave propagation speed will be 10 meters per minute.

[0039] Congestion information is converted into graphic or text information and displayed on variable information signs. Moderately congested sections are represented by yellow lines and scrolled at the edge of the screen. Recommended driving route information is displayed in the main display area using a combination of dynamic arrows and text, such as instructing vehicles to avoid congested sections by taking a branch road, and marking the branch road name and distance. At the same time, the display brightness is automatically adjusted according to the ambient light intensity, increasing the brightness when the sunlight is strong and reducing the brightness at night or in dim light, realizing intelligent layout of display content and adaptive brightness control, and preventing local congestion from causing traffic congestion between regions.

[0040] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A smart city traffic signal light control system, characterized in that: The system includes the following components: regional division module, traffic flow detection sensor, regional traffic flow analysis module, signal light control strategy generation module and inter-regional signal light coordinated control module as well as variable information sign, information processing and generation module; The regional division module divides the urban road network into multiple traffic zones. This division is based on a comprehensive assessment of multi-dimensional data, including road infrastructure data, historical traffic flow data, geographic information data, and urban functional area distribution data. By constructing a regional division algorithm based on the combination of the analytic hierarchy process (AHP) and the fuzzy C-means clustering (FCM), the AHP is first used to determine the relative weights of each evaluation factor. The road infrastructure completeness weight w1 is determined based on expert scoring and statistical analysis of road width, road surface conditions, and traffic facility configuration factors. The historical traffic flow weight w2 is based on data analysis of the influence of traffic flow at different time periods and sections on regional division. The geographic information weight w3 takes into account the impact of topography and water system distribution on traffic flow. The urban functional area weight w4 is determined by analyzing the regional traffic characteristics of commercial areas, residential areas, and industrial areas. These weights are applied to the FCM algorithm. The formula is: Among them I m is the objective function, n is the number of data points, c is the number of cluster centers, u ij is the degree of membership of data point i to cluster j, m is the fuzzy index, x i is the eigenvector of data point i, v j is the center vector of cluster j, and I is optimized through continuous iteration m , until the convergence condition is met and the optimal region division result is obtained; The traffic flow detection sensor is installed in each traffic area to collect traffic flow data, including vehicle volume, speed, and vehicle type information. Traffic flow detection uses a fusion technology of high-precision induction coils and microwave radars. The induction coils are buried at a specific depth and position under the road surface and detect magnetic field changes caused by metal parts of the vehicle based on the principle of electromagnetic induction. The microwave radar transmits microwave signals and receives reflected waves, and calculates vehicle speed through the Doppler effect. The two work together to improve the accuracy of traffic flow detection. Vehicle type identification uses deep learning image recognition technology and a convolutional neural network to extract and classify vehicle images captured by the camera. The CNN network structure includes multiple convolutional layers, pooling layers, and fully connected layers. The convolution kernel size and number of the convolutional layers and the step size hyperparameters of the pooling layers are determined through training and optimization of a large number of vehicle image samples. The regional traffic flow analysis module is connected to the traffic flow detection sensor and is used to analyze the traffic flow situation in each area. It uses an analysis algorithm based on the combination of traffic flow dynamics and data mining technology to build a traffic flow status assessment model. The formula is: Where S represents the traffic flow state value, Q is the traffic volume, C is the theoretical road capacity, δ is the traffic flow impact weight, V is the average speed, V f is the free flow speed, ∈ is the speed influence weight, T mix is the equivalent travel time of mixed vehicle types, is the total observation time, φ is the vehicle type influence weight, and the model is used to comprehensively evaluate the regional traffic flow status and provide an accurate basis for the signal light control strategy; The signal light control strategy generation module is connected to the regional traffic flow analysis module and is used to generate a signal light control strategy based on the analysis results. In congested areas with large traffic flows, a congestion relief dynamic timing algorithm is used. The formula is: Among them, G1 is the green light duration after adjustment in the congested area, G0 is the basic green light duration, k is the adjustment coefficient, S is the current traffic flow state value, S t is the congestion threshold state value, T c The signal light cycle time is the same as the signal light switching time. The switching time adjustment formula is: N1=N0-λ×(SS t ), where N1 is the adjusted switching number, N0 is the basic switching number, and λ is the switching number adjustment coefficient. In areas with low traffic, the flow balance guidance timing algorithm is used, and the formula is: Where G2 is the green light duration after adjustment in the low traffic area, μ is the balance adjustment coefficient, S min is the minimum traffic flow state value in the area; The inter-regional traffic light coordination control module is connected to the traffic light control strategy generation module and is used to coordinate the control of traffic lights within and between regions. An inter-regional traffic light coordination model is constructed based on graph theory and dynamic programming principles. Each traffic area is regarded as a node in the graph, and the connecting roads between regions are regarded as edges. The weight of the edge is determined by the road capacity, traffic flow and traffic light timing factors. The formula is: Where W is the weight of the connecting road between region i and region j, C is the road capacity, Q is the traffic flow, α is the impact weight of the capacity, T g T is the green light duration from area i to area j, c is the traffic light cycle length, and β is the traffic light timing influence weight. By solving the optimal path of the model, the coordinated switching strategy of traffic lights between regions is determined to achieve efficient connection and balanced distribution of traffic flow between regions. The variable information sign is set at the intersection; The information processing and generating module is connected to the traffic lights and traffic flow detection sensors, and is used to generate guidance information according to the changes in traffic light timing and real-time traffic conditions.

2. A smart city traffic signal light management and control system according to claim 1, characterized in that: The induction coil in the traffic flow detection sensor adopts a double-winding structure. The inner winding adopts a highly sensitive enameled copper wire to capture the initial signal of weak magnetic field changes when a vehicle passes by. The outer winding adopts a high-temperature and corrosion-resistant alloy wire to enhance the magnetic field signal strength and stabilize the detection signal. The ratio of the number of turns of the inner winding to the number of turns of the outer winding is determined according to the road type and the expected traffic volume. On main roads with heavy traffic and fast speeds, the ratio is 1:3-1:5; on branch roads with less traffic volume, the ratio is 1:2-1:

3.

3. A smart city traffic signal light management and control system according to claim 1, characterized in that: The calculation of the theoretical road capacity C in the traffic flow state assessment model in the regional traffic flow analysis module takes into account many factors. In addition to the basic parameters of the number of road lanes and width, the influence of road slope, curve curvature and surrounding interference factors is also incorporated. A capacity calculation model based on multivariate linear regression is established: C = k1×L+k2×W+k3×G+k4×B+k5×P, where L is the number of lanes, W is the road width, G is the road slope, B is the curve curvature, P is the quantitative value of the surrounding interference factors, and k1-k5 are regression coefficients.

4. A smart city traffic signal light management and control system according to claim 1, characterized in that: The congestion threshold state value S in the congestion relief dynamic timing algorithm in the signal light control strategy generation module t Adaptive learning method is used to determine the traffic flow state. The historical traffic flow data in a certain period are collected and cluster analysis is used to classify the traffic flow state into multiple levels: smooth, light congestion, moderate congestion, and severe congestion. Then the traffic flow state value range of each level is calculated and the lower limit of the moderate congestion level is taken as the initial S. t During the operation of the system, based on the feedback of actual traffic congestion, the incremental learning algorithm in machine learning is used to t Dynamic adjustment is performed. If a region appears multiple times in a specific period of time, the current S t If it is determined to be non-congested but the actual traffic is slow, the incremental learning algorithm will be used to appropriately improve S t The value of .

5. A smart city traffic signal light management and control system according to claim 1, characterized in that: The minimum traffic flow state value S in the area in the traffic balance guidance timing algorithm in the signal light control strategy generation module min The calculation adopts the sliding window statistical method, setting a time window T w , the value is 10-20 minutes, the traffic flow state value in each time window is counted, and the minimum value is taken as S in the window min As time goes by, the window keeps sliding and updating, and the latest S min At the same time, in order to avoid the influence of abnormal data, the median filtering technology is used to pre-process the traffic flow state values ​​obtained by statistics, remove data points that obviously deviate from the normal range, and improve S min The accuracy and reliability of the calculation provide a precise basis for flow balance guidance and timing, and promote the rational distribution of traffic flow between regions.

6. A smart city traffic signal light management and control system according to claim 1, characterized in that: The signal light cycle length T in the inter-region traffic signal light coordination model in the inter-region signal light coordination control module c The determination adopts a hierarchical optimization strategy, and determines the basic signal light cycle duration range according to the road grade and regional importance. The basic cycle duration of urban main roads is In 100-150 seconds, secondary roads In 60-100 seconds, considering the real-time changes of inter-regional traffic flow, the basic cycle duration is dynamically adjusted using the fuzzy logic control algorithm. The input of the fuzzy logic controller is the inter-regional traffic flow difference rate ΔQ and the intra-regional traffic flow saturation S. r , the output is the cycle length adjustment ΔT c , by defining the fuzzy rule table, when ΔQ is large and S r High ΔT c Take a larger positive value to increase the signal light cycle time to relieve traffic pressure, ΔQ is small and S r When low, ΔT c Take a smaller negative value to shorten the signal light cycle and improve traffic efficiency. After fuzzy reasoning and clarification processing, the final signal light cycle duration T is obtained. c =T c0 +ΔT c .

7. A smart city traffic signal light management and control system according to claim 1, characterized in that: When the information processing and generation module generates the induction information, the information generation of the road congestion ahead adopts a method based on the combination of traffic wave theory and data prediction model, and uses the traffic wave theory to analyze the propagation characteristics of traffic congestion and determine the propagation speed V of the congestion wave. w and congestion density ρ w The relationship between them is: Where V f is the free flow speed, ρ j In order to estimate the congestion density, the real-time traffic flow data obtained by the traffic flow detection sensor is used, and the time series prediction model is used to predict the traffic flow changes in the future period, and then the propagation range and intensity of the congestion wave are deduced. This information is converted into intuitive graphics or text information and displayed on the variable information sign. Different colored line segments are used to represent different degrees of congestion. Red indicates heavy congestion, yellow indicates moderate congestion, and green indicates smooth traffic. This provides drivers with accurate and timely information on road congestion ahead, helping them plan their routes in advance and avoid getting stuck in congested areas.

8. The smart city traffic signal light management and control system according to claim 1, characterized in that: The variable information sign display control module dynamically adjusts the layout of the display content of the variable information sign, determines the size and position of the display area according to the importance and urgency of the inductive information, adopts a full-screen display mode for urgent traffic control information, and highlights it with the largest font and bright color. For recommended driving route information, it is displayed in the main display area of ​​the variable information sign in a combination of dynamic arrows and text, with the arrow direction indicating the driving direction and the text marking the road name and distance. For information on congestion conditions on the road ahead, it is scrolled in a small window at the edge of the screen without affecting the display of the main information. At the same time, the display brightness is automatically adjusted according to the ambient light intensity, and a light-sensitive sensor is used to detect the light intensity. When the light intensity is strong, the display brightness is increased to enhance visibility. When the light intensity is weak, the display brightness is reduced to reduce energy consumption and light pollution.

9. A smart city traffic signal light management and control system according to claim 1, characterized in that: The system also includes a system fault diagnosis and self-repair module, which monitors the working status of each component of the system in real time. For traffic flow detection sensors, it determines whether they are working normally by sending detection signals of a specific frequency and receiving feedback signals. If the feedback signal is abnormal, the backup sensor is started, and the cause of the fault is analyzed using a fault diagnosis algorithm. A maintenance task is automatically dispatched based on the diagnosis result. For traffic light controllers, it monitors whether their signal output and control logic are normal. If a fault occurs, it switches to the backup controller and remotely resets and repairs the faulty controller. For variable information signs, it checks the integrity of the display content and the brightness uniformity index. If an abnormality is found, the display parameters are automatically adjusted or the backup display module is switched to.

Images