Intelligent traffic signal control system

Abstract

The invention relates to a traffic signal management technology, in particular to an intelligent traffic signal control system, which comprises a traffic data acquisition module for acquiring data of a traffic sensor in real time; the data processing module is used for analyzing the data collected by the sensor and generating an optimized signal switching strategy; the signal control module is used for controlling the state of the traffic signal lamp according to the instruction of the data processing module and automatically adjusting the signal time according to the change of the traffic flow; the cloud computing platform module is used for remotely monitoring and managing the plurality of signal control units; and the fault diagnosis and maintenance module automatically monitors the operation state of each component of the system. By acquiring the traffic flow and the pedestrian state in real time, the signal switching strategy can be intelligently analyzed and optimized, the vehicle waiting time is shortened, the traffic capacity of the intersection is improved, and the system can adjust the state of the signal lamp in time according to flow analysis and behavior pattern recognition, so that the traffic jam in the peak period is effectively relieved.

Description

Technical Field

[0001] The present invention relates to the field of traffic signal management, and in particular to an intelligent traffic signal control system. Background Art

[0002] With the acceleration of urbanization, traffic congestion is becoming increasingly serious, bringing huge challenges to urban traffic management. Traditional traffic signal control systems are usually based on fixed signal cycles and cannot dynamically respond to real-time traffic flow changes, which leads to inefficient use of traffic flow, long vehicle waiting times and increased environmental pollution. Therefore, it is particularly important to develop an intelligent traffic signal control system based on real-time data and intelligent algorithms.

[0003] Modern intelligent transportation systems integrate sensors, cloud computing and data analysis technologies to obtain traffic conditions in real time, analyze traffic flow, and automatically optimize signal switching strategies. This not only improves traffic efficiency, but also effectively improves driving safety and pedestrian crossing experience. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a

[0005] The technical solution of the present invention to solve the above technical problems is as follows: A smart traffic signal control system, comprising: Traffic data acquisition module: The traffic data acquisition module is used to acquire data from traffic sensors in real time and monitor traffic flow, vehicle speed and pedestrian status; Data processing module: The data processing module is electrically connected to the traffic data acquisition module, and the data processing module is used to analyze the data collected by the sensor and generate an optimized signal switching strategy; Signal control module: The signal control module is electrically connected to the data processing module, and is used to control the state of the traffic light according to the instructions of the data processing module, and automatically adjust the signal time according to the change of traffic flow; Cloud computing platform module: The cloud computing platform module is electrically connected to the signal control module, and the cloud computing platform module is used to remotely monitor and manage multiple signal control units, realize cross-regional traffic coordination, and generate traffic flow trend reports; Fault diagnosis and maintenance module: The fault diagnosis and maintenance module is electrically connected to the cloud computing platform module, and is used to automatically monitor the operating status of each component of the system.

[0006] Preferably, the traffic data acquisition module specifically includes: Data collection unit: The sensor captures information about traffic flow, vehicle speed, and pedestrian status in real time and transmits the data to the data collection unit; Data preprocessing unit: performs preliminary processing on the collected data, including denoising, data cleaning and format conversion; Data storage unit: storing the processed data into the cloud database; Data transmission unit: transmits the collected data to the data processing module through the network.

[0007] Preferably, the data processing module specifically includes: Traffic analysis unit: Based on the time series analysis method, it can identify the peak and valley periods of traffic flow; Behavior pattern recognition unit: Based on cluster analysis algorithm, it can identify the behavior patterns of vehicles and pedestrians and predict traffic conditions; Anomaly detection unit: Identify abnormal situations in traffic flow based on anomaly detection algorithms and adjust signal strategies in a timely manner; Signal strategy generation unit: Generates the optimal signal switching plan based on the particle swarm optimization algorithm.

[0008] Preferably, the traffic analysis unit specifically includes: Obtaining traffic flow data from the traffic data acquisition module in units of timestamps; Smooth the data, eliminate short-term fluctuations, and decompose the time series into three parts: trend, seasonality, and residual based on the seasonal decomposition method; Calculate the moving average of traffic data to determine the overall trend, set the traffic threshold based on historical data, and identify peaks and valleys. The moving average calculation formula for traffic data is:

[0009] In the formula, For in time The moving average of is the length of the period considered when calculating the moving average, For in time The observed value of For arrive The index of When the traffic value exceeds the peak threshold, it is marked as a peak period, and when the traffic value is lower than the trough threshold, it is marked as a trough period. The traffic data and its peak and trough periods are visualized to generate a report containing the peak and trough periods.

[0010] Preferably, the behavior pattern recognition unit specifically includes: Collect the motion data of vehicles and pedestrians, including location, speed, acceleration, and timestamp, select key features, and standardize the features; Based on the K-means clustering algorithm, cluster analysis is performed on the data, the number of clusters k is selected, k centroids are randomly initialized, each data point is assigned to the nearest centroid, and the centroid position is updated. The K-means clustering algorithm formula is:

[0011] In the formula, is the sum of the squares of the total distances between all data points and their cluster centers. is the number of clusters, is the number of data points in each cluster, For the data points, For the The centroid of the clusters, For the Data points With Cluster Centers The square of the Euclidean distance between them; Identify different behavior patterns based on clustering results and assign labels to each cluster based on the identified behavior patterns; Combined with historical data, based on the time series prediction model, future traffic conditions are predicted.

[0012] Preferably, the combining of historical data and predicting future traffic conditions based on a time series prediction model specifically includes: Visualize data, identify trends and seasonality, use unit root tests to check the stationarity of the time series, and if the data is not stationary, transform it into a stationary series through differencing; The autoregressive model is selected to establish a traffic condition prediction model, where the traffic condition prediction model expression is:

[0013] In the formula, For in time The observed value of is a constant term, Indicates the past The degree of influence of the value at a time point on the current value, is the autoregression coefficient, For in time The observed value of For in time Random disturbance of Use historical data to fit the autoregressive model, use the trained model to predict future traffic conditions, input data from previous time points, draw a comparison chart between the prediction results and historical data, and analyze the trend of future traffic conditions.

[0014] Preferably, the abnormality detection unit specifically includes: Important features are extracted from traffic data, including average flow, speed fluctuation and traffic density. Based on the Z-score algorithm, an abnormal data recognition model is established to detect whether the data is abnormal. The abnormal data recognition model expression is:

[0015] In the formula, represents the standard deviation distance of the data point from the mean, is the value of the current data point, is the mean of the data set, is the standard deviation of the data set; Use normal traffic data to train an abnormal data recognition model to identify normal patterns, and apply the trained model to real-time data to identify abnormal situations; Set an abnormal threshold based on the algorithm output, mark the data as abnormal when it exceeds the threshold, continuously monitor traffic flow data, identify and record abnormal situations, and trigger an alarm to notify traffic management personnel when an abnormality is detected.

[0016] Preferably, the signal strategy generating unit specifically includes: Define the objectives to be optimized, including maximizing traffic flow, minimizing delays, and minimizing queue lengths; Design particle representation, where each particle represents a signal switching scheme, including signal cycle and green light time, select the number of particles from tens to hundreds, and randomly initialize the speed and position of the particles in the defined search space; Use the objective function to evaluate the fitness of each particle. If the fitness of the current particle is better than the previous best fitness, update its individual optimal position, find the particle with the best fitness among all particles, and update the global optimal position. After the stop condition is reached, the optimal signal switching scheme is extracted from the global optimal particle, including the signal period and the green light time in each direction.

[0017] Preferably, the signal control module specifically includes: Data interface unit: establishes communication with the data processing module, receives control instructions, analyzes received instructions, and determines the state change of the signal light; Priority judgment unit: Based on real-time data and traffic flow trends, priority judgment is performed to determine which directions need priority passage; Signal time calculation unit: Based on fixed cycle control, the signal time is automatically adjusted according to the traffic analysis results, and the green, yellow and red light times in each direction are calculated; Control signal light unit: Based on the calculation results, the controller sends instructions to change the state of the signal light.

[0018] Preferably, the priority determination unit specifically includes: Set scoring criteria, set priority scores for each direction based on factors such as traffic volume, service level, and urgency, and assign weights to different priority indicators; The scores of each direction are combined to obtain the total priority score of each direction. The directions are sorted according to the priority scores to determine the direction that needs priority passage. Based on the calculation results, the direction requiring priority passage and the recommended signal time are output, and the decision result of priority passage is passed to the signal control system to adjust the status of the traffic light.

[0019] The beneficial effects of the present invention are as follows: by acquiring traffic flow and pedestrian status in real time, the system can intelligently analyze and optimize signal switching strategies, reduce vehicle waiting time, and improve the traffic capacity of intersections. The system can adjust the status of traffic lights in a timely manner based on traffic analysis and behavior pattern recognition, effectively alleviating traffic congestion during peak hours. By monitoring the status of pedestrians, the system can prioritize the adjustment of traffic lights when pedestrians cross the street, ensure pedestrian safety, and improve the overall safety of urban traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0022] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0024] Example 1 The sensors capture information about traffic flow, vehicle speed, and pedestrian status in real time and transmit the data to the data acquisition unit; Perform preliminary processing on the collected data, including denoising, data cleaning and format conversion; Store the processed data into a cloud database; Transmit the collected data to the data processing module through the network; Analyze the data collected by sensors and generate optimized signal switching strategies; Smooth the data, eliminate short-term fluctuations, and decompose the time series into three parts: trend, seasonality, and residual based on the seasonal decomposition method; Calculate the moving average of traffic data to determine the overall trend, set the traffic threshold based on historical data, and identify peaks and valleys. The moving average calculation formula for traffic data is:

[0025] In the formula, For in time The moving average of is the length of the period considered when calculating the moving average, For in time The observed value of For arrive The index of When the flow value exceeds the peak threshold, it is marked as a peak period, and when the flow value is lower than the trough threshold, it is marked as a trough period. The flow data and its peak and trough periods are visualized to generate a report containing the peak and trough periods. Collect the motion data of vehicles and pedestrians, including location, speed, acceleration, and timestamp, select key features, and standardize the features; Based on the K-means clustering algorithm, cluster analysis is performed on the data, the number of clusters k is selected, k centroids are randomly initialized, each data point is assigned to the nearest centroid, and the centroid position is updated. The K-means clustering algorithm formula is:

[0026] In the formula, is the sum of the squares of the total distances between all data points and their cluster centers. is the number of clusters, is the number of data points in each cluster, For the data points, For the The centroid of the clusters, For the Data points With Cluster Centers The square of the Euclidean distance between them; Identify different behavior patterns based on clustering results and assign labels to each cluster based on the identified behavior patterns; Combine historical data with time series prediction models to predict future traffic conditions; Visualize data, identify trends and seasonality, use unit root tests to check the stationarity of the time series, and if the data is not stationary, transform it into a stationary series through differencing; The autoregressive model is selected to establish a traffic condition prediction model, where the traffic condition prediction model expression is:

[0027] In the formula, For in time The observed value of is a constant term, Indicates the past The degree of influence of the value at a time point on the current value, is the autoregression coefficient, For in time The observed value of For in time Random disturbance of Use historical data to fit the autoregressive model, use the trained model to predict future traffic conditions, input previous time point data, draw a comparison chart between the prediction results and historical data, and analyze the trend of future traffic conditions; Important features are extracted from traffic data, including average flow, speed fluctuation and traffic density. Based on the Z-score algorithm, an abnormal data recognition model is established to detect whether the data is abnormal. The abnormal data recognition model expression is:

[0028] In the formula, represents the standard deviation distance of the data point from the mean, is the value of the current data point, is the mean of the data set, is the standard deviation of the data set; Use normal traffic data to train an abnormal data recognition model to identify normal patterns, and apply the trained model to real-time data to identify abnormal situations; Set anomaly thresholds based on algorithm outputs, mark data as abnormal when it exceeds the threshold, continuously monitor traffic flow data, identify and record abnormalities, and trigger an alarm to notify traffic management personnel when anomalies are detected; Define the objectives to be optimized, including maximizing traffic flow, minimizing delays, and minimizing queue lengths; Design particle representation, where each particle represents a signal switching scheme, including signal cycle and green light time, select the number of particles from tens to hundreds, and randomly initialize the speed and position of the particles in the defined search space; Use the objective function to evaluate the fitness of each particle. If the fitness of the current particle is better than the previous best fitness, update its individual optimal position, find the particle with the best fitness among all particles, and update the global optimal position. After reaching the stop condition, the optimal signal switching scheme is extracted from the global optimal particle, including the signal cycle and the green light time in each direction; Establish communication with the data processing module, receive control instructions, analyze the received instructions, and determine the state change of the signal light; Based on real-time data and traffic flow trends, priority is determined, and based on priority, which directions need priority passage? Based on fixed cycle control, the signal time is automatically adjusted according to the traffic analysis results, and the green, yellow and red light times in each direction are calculated; According to the calculation results, the controller sends instructions to change the state of the signal light; Set scoring criteria, set priority scores for each direction based on factors such as traffic volume, service level, and urgency, and assign weights to different priority indicators; The scores of each direction are combined to obtain the total priority score of each direction. The directions are sorted according to the priority scores to determine the direction that needs priority passage. Based on the calculation results, the direction requiring priority passage and the recommended signal time are output, and the decision result of priority passage is passed to the signal control system to adjust the status of the traffic light. According to the instructions of the data processing module, the state of the traffic lights is controlled, and the signal time is automatically adjusted according to the changes in traffic flow; Remotely monitor and manage multiple signal control units to achieve cross-regional traffic coordination and generate traffic flow trend reports; The cloud computing platform module remotely monitors and manages multiple signal control units, realizes cross-regional traffic coordination, and generates traffic flow trend reports; The fault diagnosis and maintenance module automatically monitors the operating status of each component of the system.

[0029] Example 2 Determine the functional requirements of the system, including flow monitoring, signal control and data analysis; Select appropriate traffic sensors to monitor traffic flow, vehicle speed and pedestrian status; Design traffic data acquisition module, data processing module, signal control module, cloud computing platform module and fault diagnosis module; Obtain traffic data in real time through sensors and transmit it to the data collection unit; In the data preprocessing unit, the raw data is denoised, cleaned and format converted; Store the processed data in the cloud database and transmit the collected data to the data processing module through the network; In the data processing module, time series analysis methods are used to identify peak and trough periods; Apply cluster analysis algorithms to identify the behavior patterns of vehicles and pedestrians and predict traffic conditions; Based on the Z-score algorithm, an abnormal data recognition model is established to monitor and mark abnormal traffic; Use particle swarm optimization algorithm to generate the optimal signal switching plan, considering flow maximization and delay minimization; According to the instructions of the data processing module, the state of the signal light is controlled through the data interface unit; Set a priority score for each direction based on real-time data and traffic flow trends; Calculate the green, yellow and red light times in each direction and automatically adjust the signal time based on traffic analysis results; Send instructions through the controller to change the status of the traffic lights to ensure smooth traffic flow; Carry out system monitoring and management on the cloud computing platform to achieve cross-regional traffic coordination; Automatically monitor the operating status of each component of the system, and promptly detect and record faults; Visualize traffic data and its peak and trough periods, and generate reports for decision-making; Regularly evaluate system performance, including the effectiveness of signal control and changes in traffic flow, and continuously optimize signal switching strategies and system functions based on evaluation results and user feedback.

[0030] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0031] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0032] Obviously, those skilled in the art can 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 of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart traffic signal control system, characterized in that: include: Traffic data acquisition module: The traffic data acquisition module is used to acquire data from traffic sensors in real time and monitor traffic flow, vehicle speed and pedestrian status; Data processing module: The data processing module is electrically connected to the traffic data acquisition module, and the data processing module is used to analyze the data collected by the sensor and generate an optimized signal switching strategy; Signal control module: The signal control module is electrically connected to the data processing module, and is used to control the state of the traffic light according to the instructions of the data processing module, and automatically adjust the signal time according to the change of traffic flow; Cloud computing platform module: The cloud computing platform module is electrically connected to the signal control module, and the cloud computing platform module is used to remotely monitor and manage multiple signal control units, realize cross-regional traffic coordination, and generate traffic flow trend reports; Fault diagnosis and maintenance module: The fault diagnosis and maintenance module is electrically connected to the cloud computing platform module, and is used to automatically monitor the operating status of each component of the system.

2. The intelligent traffic signal control system according to claim 1, characterized in that: The traffic data acquisition module specifically includes: Data collection unit: The sensor captures information about traffic flow, vehicle speed, and pedestrian status in real time and transmits the data to the data collection unit; Data preprocessing unit: performs preliminary processing on the collected data, including denoising, data cleaning and format conversion; Data storage unit: storing the processed data into the cloud database; Data transmission unit: transmits the collected data to the data processing module through the network.

3. The intelligent traffic signal control system according to claim 2 is characterized in that: The data processing module specifically includes: Traffic analysis unit: Based on the time series analysis method, it can identify the peak and valley periods of traffic flow; Behavior pattern recognition unit: Based on cluster analysis algorithm, it can identify the behavior patterns of vehicles and pedestrians and predict traffic conditions; Anomaly detection unit: Identify abnormal situations in traffic flow based on anomaly detection algorithms and adjust signal strategies in a timely manner; Signal strategy generation unit: Generates the optimal signal switching plan based on the particle swarm optimization algorithm.

4. The intelligent traffic signal control system according to claim 3 is characterized in that: The traffic analysis unit specifically includes: Obtaining traffic flow data from the traffic data acquisition module in units of timestamps; Smooth the data, eliminate short-term fluctuations, and decompose the time series into three parts: trend, seasonality, and residual based on the seasonal decomposition method; Calculate the moving average of traffic data to determine the overall trend, set the traffic threshold based on historical data, and identify peaks and valleys. The moving average calculation formula for traffic data is: In the formula, For in time The moving average of is the length of the period considered when calculating the moving average, For in time The observed value of For arrive The index of When the traffic value exceeds the peak threshold, it is marked as a peak period, and when the traffic value is lower than the trough threshold, it is marked as a trough period. The traffic data and its peak and trough periods are visualized to generate a report containing the peak and trough periods.

5. The intelligent traffic signal control system according to claim 4 is characterized in that: The behavior pattern recognition unit specifically includes: Collect the motion data of vehicles and pedestrians, including location, speed, acceleration, and timestamp, select key features, and standardize the features; Based on the K-means clustering algorithm, the data is clustered and analyzed. The number of clusters k is selected, k centroids are randomly initialized, each data point is assigned to the nearest centroid, and the centroid position is updated. The formula of the K-means clustering algorithm is: In the formula, is the sum of the squares of the total distances between all data points and their cluster centers. is the number of clusters, is the number of data points in each cluster, For the data points, For the The centroid of the clusters, For the Data points With Cluster Centers The square of the Euclidean distance between them; Identify different behavior patterns based on clustering results and assign labels to each cluster based on the identified behavior patterns; Combined with historical data, based on the time series prediction model, future traffic conditions are predicted.

6. The intelligent traffic signal control system according to claim 5, characterized in that: The combination of historical data and the prediction of future traffic conditions based on the time series prediction model specifically include: Visualize data, identify trends and seasonality, use unit root tests to check the stationarity of the time series, and if the data is not stationary, transform it into a stationary series through differencing; The autoregressive model is selected to establish a traffic condition prediction model, where the traffic condition prediction model expression is: In the formula, For in time The observed value of is a constant term, Indicates the past The degree of influence of the value at a time point on the current value, is the autoregression coefficient, For in time The observed value of For in time Random disturbance of Use historical data to fit the autoregressive model, use the trained model to predict future traffic conditions, input data from previous time points, draw a comparison chart between the prediction results and historical data, and analyze the trend of future traffic conditions.

7. The intelligent traffic signal control system according to claim 6, characterized in that: The abnormality detection unit specifically includes: Important features are extracted from traffic data, including average flow, speed fluctuation and traffic density. Based on the Z-score algorithm, an abnormal data recognition model is established to detect whether the data is abnormal. The abnormal data recognition model expression is: In the formula, represents the standard deviation distance of the data point from the mean, is the value of the current data point, is the mean of the data set, is the standard deviation of the data set; Use normal traffic data to train an abnormal data recognition model to identify normal patterns, and apply the trained model to real-time data to identify abnormal situations; Set an abnormal threshold based on the algorithm output, mark the data as abnormal when it exceeds the threshold, continuously monitor traffic flow data, identify and record abnormal situations, and trigger an alarm to notify traffic management personnel when an abnormality is detected.

8. The intelligent traffic signal control system according to claim 7, characterized in that: The signal strategy generating unit specifically includes: Define the objectives to be optimized, including maximizing traffic flow, minimizing delays, and minimizing queue lengths; Design particle representation, where each particle represents a signal switching scheme, including signal cycle and green light time, select the number of particles from tens to hundreds, and randomly initialize the speed and position of the particles in the defined search space; Use the objective function to evaluate the fitness of each particle. If the fitness of the current particle is better than the previous best fitness, update its individual optimal position, find the particle with the best fitness among all particles, and update the global optimal position. After the stop condition is reached, the optimal signal switching scheme is extracted from the global optimal particle, including the signal period and the green light time in each direction.

9. The intelligent traffic signal control system according to claim 8, characterized in that: The signal control module specifically includes: Data interface unit: establishes communication with the data processing module, receives control instructions, analyzes received instructions, and determines the state change of the signal light; Priority judgment unit: Based on real-time data and traffic flow trends, priority judgment is performed to determine which directions need priority passage; Signal time calculation unit: Based on fixed cycle control, the signal time is automatically adjusted according to the traffic analysis results, and the green, yellow and red light times in each direction are calculated; Control signal light unit: Based on the calculation results, the controller sends instructions to change the state of the signal light.

10. The intelligent traffic signal control system according to claim 9, characterized in that: The priority determination unit specifically includes: Set scoring criteria, set priority scores for each direction based on factors such as traffic volume, service level, and urgency, and assign weights to different priority indicators; The scores of each direction are combined to obtain the total priority score of each direction. The directions are sorted according to the priority scores to determine the direction that needs priority passage. Based on the calculation results, the direction requiring priority passage and the recommended signal time are output, and the decision result of priority passage is passed to the signal control system to adjust the status of the traffic light.

Images