Traffic signal lamp intelligent regulation and control system based on big data

Abstract

The invention provides a traffic signal lamp intelligent regulation and control system based on big data, and relates to the technical field of traffic signal lamp regulation and control systems, and the system comprises a multi-channel data collection module which is responsible for collecting traffic data of a plurality of channels, guaranteeing the comprehensiveness and accuracy of the data, and transmitting the traffic data to a cloud server; a geomagnetic sensor, a radar sensor and a camera device on a road are used for collecting the flow, speed and occupancy information of vehicles in real time, the change of the traffic flow can be sensed timely and accurately through multi-source data collection and real-time analysis, and a signal lamp timing scheme is adjusted rapidly according to the change condition, so that the traffic light timing efficiency is improved. Regulation and control of signal lamps are more in line with actual traffic demands, vehicle waiting time is effectively reduced, road passing efficiency is improved, and through green wave band control and trunk line coordination control means, overall traffic operation efficiency of a region is improved, road network traffic flow is balanced, congestion diffusion of local road sections is avoided, and overall operation stability of urban traffic is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control systems, and in particular to an intelligent traffic signal control system based on big data. Background Art

[0002] With the continuous growth of the urban motor vehicle ownership, the problem of traffic congestion has become increasingly serious. As an important means of regulating traffic flow, traffic signals directly affect the road traffic efficiency. Traditional traffic signals adopt a fixed-time control method, switching the signal states according to a pre-set time plan, and cannot be dynamically adjusted according to the changes in real-time traffic flow. During the morning and evening rush hours, the traffic flow in the inbound or outbound direction of the urban arterial roads will increase significantly, while the traffic flow on the intersecting secondary roads is relatively small. However, the fixed-time controlled signals cannot timely sense this traffic flow difference and still operate according to the fixed time allocation plan, resulting in an increasing queue length of vehicles on the arterial roads, slow traffic speed, and a large amount of idle time on the secondary roads.

[0003] To solve these problems, induction traffic signals are adopted in cities, which detect the presence and arrival of vehicles through sensors such as inductive loops and radars, and dynamically adjust the signal duration according to the detection results. However, such systems have the disadvantages of limited detection range, being easily interfered by environmental factors, and can only respond to local traffic conditions, lacking the overall analysis and coordinated control capabilities of regional traffic flow.

[0004] The rapid development of big data technology has provided a new solution for the intelligent control of traffic signals. By collecting, analyzing, and mining massive traffic data, the spatio-temporal variation law of traffic flow can be grasped more accurately to achieve precise and intelligent control of signals. However, the existing traffic signal control systems based on big data still have some deficiencies, such as incomplete data collection, inefficient analysis algorithms, and lack of flexibility in control strategies, making it difficult to fully utilize the advantages of big data technology to effectively solve the complex and changeable urban traffic congestion problems. Summary of the Invention

[0005] To achieve the above object, the present invention proposes an intelligent traffic signal control system based on big data, including

[0006] Multi-channel data collection module: The multi-channel data collection module is responsible for collecting traffic data from multiple channels to ensure the comprehensiveness and accuracy of the data. By using geomagnetic sensors, radar sensors, and camera devices on the road, it can collect the traffic flow, speed, and occupancy information of vehicles in real time, and access the urban bus system and taxi operation system to obtain the operation information of public transportation vehicles;

[0007] Data Processing and Analysis Module: The data processing and analysis module cleans, preprocesses, and deeply analyzes the collected data, establishes a traffic flow prediction model, and combines historical traffic data and real-time collected data to predict the traffic flow change trends of each road section in the future for a period of time.

[0008] Intelligent Regulation and Decision-making Module: Based on the results of the data processing and analysis module, the intelligent regulation and decision-making module formulates a scientific and reasonable traffic signal regulation strategy, uses optimization algorithms, and aims at maximizing the road traffic efficiency and minimizing the average vehicle delay time to optimize the signal timing plan.

[0009] Regional Cooperative Control Module: The regional cooperative control module enables the cooperative operation of traffic signals within the region, improves the overall traffic operation efficiency, constructs a regional traffic network model, regards each intersection within the region as a node, and the road as an edge connecting the nodes, and comprehensively considers the traffic correlation relationship, traffic flow transfer law, and signal cycle coordination and matching factors among intersections.

[0010] Information Publishing and Interaction Module: The information publishing and interaction module is responsible for conveying traffic signal regulation information and real-time road condition information to traffic participants, and at the same time receiving feedback information from traffic participants.

[0011] In one example, the geomagnetic sensor can accurately detect the geomagnetic changes generated when a vehicle passes by, count the traffic flow, the radar sensor measures the driving speed of the vehicle, and the camera uses image recognition technology to obtain the vehicle type, position, queue length, arrival time, departure frequency, and driving route of bus vehicles, the occupancy situation and driving trajectory of taxis, and integrates the real-time road condition data of the map navigation software.

[0012] In one example, the data processing and analysis module uses data cleaning algorithms to remove noise data, outliers, and duplicate data, the obvious error data generated by sensors due to faults or external interference, sets reasonable data range thresholds for screening and correction, and the duplicate recorded data, and uses data deduplication algorithms to eliminate them, and adopts data mining and machine learning technologies to analyze the processed traffic data.

[0013] In one example, the data processing and analysis module establishes a traffic flow prediction model, based on the long short-term memory network model of deep learning, combines historical traffic data and real-time collected data to predict the traffic flow change trends of each road section in the future time, and uses clustering analysis algorithms to classify the traffic flow characteristics in different regions and different time periods, find similar traffic patterns, and provide a basis for formulating targeted regulation strategies.

[0014] In one example, the intelligent regulation decision-making module considers the traffic flow prediction results, real-time traffic conditions, and the characteristics of different traffic flow patterns. It predicts that the traffic flow on a certain road section will increase significantly in the next period of time, and adjusts the green light duration of the traffic lights at this road section and related intersections in advance to increase the traffic capacity in this direction. For road sections with relatively low traffic flow, the green light time is appropriately shortened to avoid waste of resources.

[0015] In one example, the intelligent regulation decision-making module has a real-time feedback adjustment mechanism, which dynamically corrects the regulation strategy according to the actual traffic operation situation. When it detects a large deviation between the actual traffic flow and the predicted value, it recalculates and adjusts the signal timing plan in a timely manner.

[0016] In one example, the regional cooperative control module uses a distributed cooperative control algorithm to achieve the functions of green wave band control and arterial coordination control. On the main urban roads, the phase difference and green light time of the traffic lights at each intersection are reasonably set. When vehicles drive within a certain speed range, they can continuously pass through multiple intersections. The regional cooperative control module dynamically adjusts the traffic flow distribution according to the traffic congestion conditions of different road sections in the region, guides vehicles to avoid congested road sections, and balances the traffic flow of the road network.

[0017] In one example, the information release and interaction module real-time releases the signal timing adjustment information, road congestion conditions, and traffic control measures to drivers and pedestrians through traffic guidance screens, map navigation software, and traffic radio channels. Drivers plan their travel routes in advance based on this information and choose relatively unobstructed roads to drive on.

[0018] In one example, the information release and interaction module provides a user feedback interface. Traffic participants can feedback abnormal situations on the road, such as traffic accidents and road construction, to the system through a mobile application. After receiving the feedback information, it is incorporated into the data processing and analysis module for comprehensive analysis, and the signal light regulation strategy is adjusted in a timely manner, and the processing result is feedback to the user to form an information interaction closed loop, improving the refinement level of traffic management.

[0019] The intelligent traffic signal regulation system based on big data proposed by the present invention can bring the following beneficial effects:

[0020] 1. Through multi-source data collection and real-time analysis, the present invention can timely and accurately sense the changes in traffic flow, and quickly adjust the signal timing plan according to the changes, making the regulation of signal lights more in line with the actual traffic demand, effectively reducing the waiting time of vehicles, improving the road traffic efficiency. Through green wave band control and arterial coordination control means, the overall traffic operation efficiency of the region is improved, the traffic flow of the road network is balanced, the congestion spread of local road sections is avoided, and the overall operation stability of urban traffic is enhanced.

[0021] 2. By applying big data processing, machine learning, and optimization algorithm technologies, the present invention realizes the intelligent decision-making and dynamic optimization of traffic signal control strategies, can cope with complex and changeable traffic conditions, improves the scientific and intelligent level of traffic management. The information release and interaction module provides timely and accurate traffic information for traffic participants, helping them reasonably plan travel routes. At the same time, the user feedback mechanism also enables the traffic management department to better understand the public's needs, further optimize traffic management measures, and enhance the travel experience and satisfaction of traffic participants. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0023] Figure 1 It is a schematic diagram of the architecture of an intelligent traffic signal control system based on big data according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to more clearly and completely illustrate the technical solution of the present invention, the present invention will be further described below with reference to the drawings.

[0025] Please refer to Figure 1 , the present invention proposes an intelligent traffic signal control system based on big data, including a multi-channel data acquisition module, a data processing and analysis module, an intelligent control decision module, a regional collaborative control module, and an information release and interaction module;

[0026] Multi-channel data acquisition module: The multi-channel data acquisition module is responsible for collecting traffic data from multiple channels to ensure the comprehensiveness and accuracy of the data. By using geomagnetic sensors, radar sensors, and camera devices on the road, it can collect information such as vehicle flow, speed, and occupancy in real time, and access the urban bus system and taxi operation system to obtain the operation information of public transportation vehicles;

[0027] Data processing and analysis module: The data processing and analysis module cleans, preprocesses, and deeply analyzes the collected data, establishes a traffic flow prediction model, and combines historical traffic data and real-time collected data to predict the traffic flow change trend of each road section in the future for a period of time;

[0028] Intelligent control decision module: Based on the results of the data processing and analysis module, the intelligent control decision module formulates scientific and reasonable traffic signal control strategies, and uses optimization algorithms to optimize the signal timing plan with the goal of maximizing the road traffic efficiency and minimizing the average vehicle delay time;

[0029] Regional Cooperative Control Module: The regional cooperative control module enables the coordinated operation of traffic lights within a region, improves the overall traffic operation efficiency, constructs a regional traffic network model, regards each intersection within the region as a node, and the roads as edges connecting the nodes, comprehensively considering the traffic correlation relationships between intersections, the traffic flow transfer rules, and the coordinated matching factors of signal cycles;

[0030] Information Publishing and Interaction Module: The information publishing and interaction module is responsible for conveying traffic light regulation information and real-time traffic conditions information to traffic participants, and at the same time receiving feedback information from traffic participants.

[0031] Multi-channel data collection. In a busy traffic area of a certain city, a large number of advanced sensor devices are deployed, including geomagnetic sensors, radar sensors, and high-definition cameras. These sensors are distributed on main roads and intersections to collect traffic data in real time. The geomagnetic sensors collect vehicle passing information every 10 seconds and accurately count the traffic flow through built-in algorithms. These sensors can detect the geomagnetic changes generated when vehicles pass by, thereby accurately calculating the number of passing vehicles. The radar sensors measure the driving speed of vehicles at a frequency of 5 times per second. Through the principle of radar wave reflection, the instantaneous speed of vehicles can be obtained in real time, providing important data for traffic flow analysis. The high-definition cameras take real-time pictures of the roads and analyze the vehicle type, position, and queue length once per second using advanced image recognition technology. The cameras can not only identify the license plate information of vehicles but also determine the vehicle type and calculate the length of the queuing vehicles.

[0032] The data of the urban bus system and the taxi operation system are also accessed in this region. The arrival time, departure frequency of bus vehicles, and the occupancy status and driving trajectories of taxis are updated every 30 seconds. At the same time, in cooperation with mainstream map navigation software, the real-time traffic conditions data of this region are obtained every 5 minutes. Through this multi-source data collection method, the system comprehensively and accurately obtains the traffic information of this region, providing rich data support for subsequent analysis and regulation.

[0033] Data Processing and Analysis: The collected raw data is first transmitted to the data processing and analysis module. The main tasks of this module are to clean, preprocess, and deeply analyze the data. Data cleaning: Use data cleaning algorithms to remove noise data, outliers, and duplicate data. By setting the vehicle speed range from 0 to 120 km / h, some abnormal vehicle speed data caused by sensor failures is excluded. For duplicate recorded data, use the data deduplication algorithm to eliminate it, ensuring the accuracy and integrity of the data. Traffic flow prediction: Use the long short-term memory network model based on deep learning to analyze the processed data and predict the traffic flow of each road section within the next 30 minutes. When training the model, historical traffic data of the past month is used. After multiple iterations and optimizations, the prediction accuracy reaches more than 90%. Cluster analysis: Use the cluster analysis algorithm to classify the traffic flow characteristics at different times, and a total of 8 different traffic flow patterns are divided, including morning and evening rush hours on weekdays, off-peak hours on weekdays, weekend rush hours, and weekend off-peak hours. Through this classification, the system can provide a strong basis for formulating targeted regulation strategies.

[0034] Intelligent Regulation Decision-making: During the morning rush hour, the intelligent regulation decision-making module, based on the results of the data processing and analysis module, predicts that the traffic flow in the inbound direction of a main road will increase significantly within the next 15 minutes. At this time, the system uses the genetic algorithm to optimize the signal timing plan of this main road and related intersections, with the goal of maximizing the traffic efficiency in this direction. After multiple calculations and optimizations, the system extends the green light duration in the inbound direction from the original 30 seconds to 45 seconds, while correspondingly shortening the green light time in other directions. During the actual operation process, the system monitors the traffic flow changes in real-time. When it is found that there is a deviation between the actual traffic flow and the predicted value, it recalculates and adjusts the signal timing plan in a timely manner. At a certain moment, it is found that the queue length of vehicles in the inbound direction exceeds the expectation. By optimizing the timing plan again, the green light duration is further extended to 50 seconds, effectively alleviating traffic congestion and reducing the average delay time of vehicles in this direction by about 30%.

[0035] Regional Cooperative Control: In an urban area containing 10 intersections, the regional cooperative control module constructs a regional traffic network model. Through the distributed cooperative control algorithm, it realizes the green wave belt control of the signal lights within this area. According to the distance between intersections and the average driving speed of vehicles, the system reasonably sets the phase difference and green light time of the signal lights. On a main trunk road in this area, when vehicles are driving at a speed of 40 - 50 km / h, they can continuously pass through 5 intersections without having to stop and wait, and the trunk road traffic capacity is increased by about 40%. At the same time, when traffic congestion occurs at a certain intersection within the area, the regional cooperative control module dynamically adjusts the signal timing of other intersections to guide vehicles to avoid the congested intersection and balance the traffic flow of the road network, effectively preventing the spread of congestion.

[0036] Information release and interaction: On the traffic guidance screens in the city, the system real-time displays the timing adjustment information of traffic lights at each intersection and the road congestion situation. Meanwhile, through the map navigation software, it pushes the real-time traffic conditions and the optimal travel routes to drivers. Drivers plan their trips in advance based on this information and choose relatively unobstructed roads to drive on. Traffic participants feedback abnormal situations on the road through the mobile application. A driver found a traffic accident on a certain section during the driving process and uploaded the accident location and on-site photos through the mobile application. After receiving the feedback information, the system immediately incorporated it into the data processing and analysis module for comprehensive analysis, timely adjusted the control strategies of traffic lights at the surrounding intersections, and released the accident information and detour suggestions to other traffic participants through the traffic guidance screens and the map navigation software, improving the timeliness and refinement level of traffic management.

[0037] Certainly, the present invention can also have many other implementation manners. Based on this implementation manner, other implementation manners obtained by ordinary technicians in this field without any creative labor belong to the scope protected by the present invention.

Claims

1. An intelligent traffic signal control system based on big data, characterized in that, including Multi-channel data acquisition module: The multi-channel data acquisition module is responsible for collecting traffic data from multiple channels. By using geomagnetic sensors, radar sensors, and camera devices on the road, it can collect vehicle information in real time, access the urban bus system and taxi operation system, and obtain the operation information of public transportation vehicles. Data processing and analysis module: The data processing and analysis module cleans, preprocesses, and deeply analyzes the collected data, and establishes a traffic flow prediction model. Intelligent regulation and decision-making module: Based on the results of the data processing and analysis module, the intelligent regulation and decision-making module formulates traffic signal regulation strategies, and uses optimization algorithms to optimize the signal timing plan. Regional coordinated control module: The regional coordinated control module realizes the coordinated operation of traffic signals within the region, improves the overall traffic operation efficiency, and constructs a regional traffic network model. Information release and interaction module: The information release and interaction module is responsible for conveying traffic signal regulation information and real-time traffic conditions to traffic participants, and at the same time receiving feedback information from traffic participants.

2. The intelligent traffic signal control system based on big data according to claim 1, wherein The geomagnetic sensor can accurately detect the geomagnetic changes generated when a vehicle passes by, and count the traffic flow. The radar sensor measures the driving speed of the vehicle. The camera uses image recognition technology to obtain the vehicle type, location, queue length, arrival time, departure frequency, and driving route of bus vehicles, as well as the passenger-carrying situation and driving trajectory of taxis, and integrates the real-time traffic condition data of map navigation software.

3. An intelligent traffic signal control system based on big data according to claim 1, characterized in that, The data processing and analysis module uses data cleaning algorithms to remove noise data, outliers, and duplicate data, as well as obvious error data generated by sensors due to faults or external interference. It sets reasonable data range thresholds for screening and correction, and uses data deduplication algorithms to eliminate duplicate recorded data. It also uses data mining and machine learning technologies to analyze the processed traffic data.

4. An intelligent traffic signal control system based on big data according to claim 1, characterized in that The data processing and analysis module establishes a traffic flow prediction model. Based on the long short-term memory network model of deep learning, combined with historical traffic data and real-time collected data, it predicts the traffic flow change trend of each road section in the future. It uses clustering analysis algorithms to classify the traffic flow characteristics in different regions and different time periods, and find similar traffic patterns, providing a basis for formulating targeted regulation strategies.

5. The intelligent traffic signal control system based on big data according to claim 1, characterized in that, The intelligent regulation and decision-making module considers the traffic flow prediction results, real-time traffic conditions, and the characteristics of different traffic flow patterns. If it predicts that the traffic flow on a certain road section will increase significantly in the future, it will adjust the green light duration of the traffic signals at that road section and related intersections in advance. Using optimization algorithms, with the goal of maximizing road traffic efficiency and minimizing the average vehicle delay time, it optimizes the signal timing plan to increase the traffic capacity in that direction. For road sections with relatively small traffic flow, it appropriately shortens the green light time to avoid wasting resources.

6. An intelligent traffic signal control system based on big data according to claim 1, characterized in that, The intelligent regulation and decision-making module has a real-time feedback adjustment mechanism, which dynamically corrects the regulation strategy according to the actual traffic operation situation. When it detects a large deviation between the actual traffic flow and the predicted value, it will recalculate and adjust the signal timing plan in a timely manner.

7. An intelligent traffic signal control system based on big data according to claim 1, characterized in that, The regional collaborative control module uses a distributed collaborative control algorithm to achieve the functions of green wave band control and arterial coordination control. On the urban arterial roads, the phase difference and green light time of the signal lights at each intersection are reasonably set. Each intersection in the region is regarded as a node, and the road is regarded as the edge connecting the nodes. Considering the traffic correlation relationship between intersections, the traffic flow transfer law, and the coordination and matching factors of the signal cycle, vehicles can continuously pass through multiple intersections when driving within a certain speed range. The regional collaborative control module dynamically adjusts the traffic flow distribution according to the traffic congestion conditions of different sections in the region, guides vehicles to avoid congested sections, and balances the traffic flow of the road network.

8. An intelligent traffic signal control system based on big data according to claim 1, characterized in that, The information release and interaction module real-time releases the signal light timing adjustment information, road congestion conditions, and traffic control measures to drivers and pedestrians through traffic guidance screens, map navigation software, and traffic radio channels. Drivers can plan their travel routes in advance based on this information and choose a relatively unobstructed road to drive on.

9. An intelligent traffic signal control system based on big data according to claim 1, characterized in that, The information release and interaction module provides a user feedback interface. Traffic participants can feedback abnormal situations on the road, such as traffic accidents and road construction, to the system through the mobile application program. After receiving the feedback information, it is incorporated into the data processing and analysis module for comprehensive analysis, and the signal light control strategy is adjusted in a timely manner. The processing results are feedback to users to form an information interaction closed-loop, improving the refined level of traffic management.

Images