19 results about "Saturation flow rate" patented technology

The invention relates to a lane-level vehicle average delay calculation method considering supersaturation residual queuing, and relates to the technical field of intelligent traffic control. The method comprises the following steps: calculating the effective green light duration, the signal period, the average vehicle arrival rate and the saturation flow rate of a target lane i; calculating the number of vehicles queued at the initial green light stage and the number of vehicles queued at the initial red light stage of the lane i in the jth period; judging whether the current traffic state is a supersaturated state or not; when the traffic state is an unsaturated state, calculating lane-level vehicle average delay in the unsaturated state by using the single-cycle vehicle total delay, and ending the calculation; and when the traffic state is a supersaturated state, calculating to obtain the minimum signal cycle number required by the tail vehicle of the lane i to drive away from the intersection at the initial green light moment of the jth cycle, calculating the average delay of the lane-level vehicles, and ending the calculation. The method and the device have the effect of fully considering the condition of cycle-by-cycle accumulation or dissipation of the supersaturated residual queues.

The invention relates to the technical field of intelligent traffic, in particular to a traffic signal lamp control method based on vehicle path prediction under vehicle-road cooperation, and the method comprises the steps: collecting the driving path data of each vehicle within a set distance range in front of a designated intersection in real time; predicting the traffic flow of each signal phase of the specified intersection in a set future time period based on the acquired driving path data of the vehicle; the signal phase refers to a time period which is divided according to a passing direction and a passing mode and allows vehicles to pass in a signal period; calculating total vehicle delay time of each signal phase based on the predicted traffic flow, traffic capacity, queuing length and saturation flow rate of each signal phase; dynamically optimizing and adjusting the green light time of each signal phase based on the vehicle total delay time of each signal phase to obtain an optimized green light timing scheme; and issuing the optimized green light timing scheme to a signal controller at a specified intersection in real time so as to execute a corresponding signal timing control action.

The invention relates to the field of intelligent traffic, and discloses a road section traffic saturation flow prediction method based on deep ensemble learning, comprising the following steps: S1, data acquisition: acquiring traffic flow data and processing the acquired traffic flow data to obtain a test subset and a training subset; s2, a prediction model is constructed, an LSTM and BERT (LSBERT fusion model based on ensemble learning is constructed, the fusion model is trained and tested through the training subset obtained in the S1, the BERT module takes the preprocessed traffic flow data as input, the internal relation of the traffic flow data is deeply understood through the pre-training language model architecture and the bidirectional coding expression capacity of the BERT module, and the prediction model is obtained. And the LSTM module receives the output from the BERT model, and the long-term dependency relationship in the traffic flow data can be effectively captured by virtue of a unique gating mechanism and a memory unit of the LSTM module.

The application provides a traffic signal optimization method based on parameter calibration and improved Webster timing method, the method comprising: arranging detection coils in each lane in front of a stop line at an intersection, collecting vehicle passing information and storing locally; based on traffic flow theory analysis, calibrating saturated headway and calculating saturated flow of each lane according to the vehicle passing information, reducing the influence of oversaturated traffic flow on signal timing; for phase overlap and stage secondary release, the concept of phase residual flow ratio is proposed to solve the adaptation problem of Webster timing method under the signal timing requirements of the phase overlap and the stage secondary release; in the signal timing self-optimization link, if the signal timing meets the minimum green constraint relationship, the signal timing ends; if the signal timing does not meet the minimum green constraint relationship, the minimum green adjustment process is entered; when real-time optimization is performed, the updated signal timing is executed in the next cycle and the vehicle passing information is recorded again; when timing optimization is performed, adjustment is performed within a certain fixed time period based on historical data. The problems of unreasonable setting of basic parameters and limited use of traditional timing methods in actual application scenarios are solved, and a fast, accurate and stable traffic signal adaptive optimization system is established.

The invention discloses an intelligent traffic management and control system based on the Internet of Things, relates to the technical field of traffic management and control, and aims to optimize urban traffic flow through accurate monitoring and dynamic regulation and control. The system comprises a traffic data acquisition module which monitors the vehicle flow in real time by using a monitoring camera and calculates the average vehicle flow in combination with a sampling period; the traffic signal initial regulation module analyzes flow change in a monitoring period, draws a flow broken line and determines initial regulation green light time; the regulation and control signal control module monitors the current flow in real time and triggers a regulation and control mechanism when the current flow exceeds the saturated flow; the traffic advanced regulation and control module calculates a demand weight according to parameters such as current flow and saturation flow, dynamically adjusts green light duration and ensures smooth traffic; the system integrates real-time monitoring and data analysis, realizes fine management of traffic signals, improves urban road traffic efficiency, reduces congestion, and provides technical support for intelligent traffic construction.

The invention discloses a method for measuring and calculating the maximum signal period of a signal control intersection based on road traffic organization and traffic flow fusion research and judgment, and belongs to the field of urban road traffic signal control. Firstly, intersection static channelization and traffic organization data and dynamic traffic flow data are fused. Secondly, the effective saturation flow rate of each lane is calculated through the quantization correction coefficient; and finally, embedding the average correction factor reflecting the overall static condition level of the intersection into an innovative formula, and calculating to obtain a recommended maximum period. According to the method, the signal control parameters are accurately matched with the'congenital conditions' of the intersection, the traffic potential can be fully excavated, and the green light utilization rate and the overall operation efficiency are improved.

The present application relates to a lane-level average vehicle delay calculation method that considers oversaturated residual queues, and relates to the technical field of intelligent traffic control. The method comprises the following steps: calculating the effective green light duration, signal cycle, average vehicle arrival rate, and saturation flow rate of target lane i; calculating the number of vehicles in the initial green light queue and the initial red light queue of lane i in the jth cycle; determining whether the current traffic state is oversaturated; when the traffic state is unsaturated, calculating the lane-level average vehicle delay in the unsaturated state using the total vehicle delay in a single cycle, and then completing the calculation; when the traffic state is oversaturated, calculating the minimum number of signal cycles required for the rear vehicle in lane i to leave the intersection at the initial green light moment in the jth cycle, and calculating the lane-level average vehicle delay, and then completing the calculation. The present application has the effect of fully considering the accumulation or dissipation of oversaturated residual queues on a cycle-by-cycle basis.

The present invention discloses a method and device for designing the length of an early right turn based on a traffic trajectory diagram. The method collects relevant traffic data, converts the total traffic volume obtained into equivalent standard car traffic volume, and calculates the saturated flow of the right through lane of the intersection based on the maximum headway. A Greenshields linear relationship model is established to obtain the relationship between the speed before entering the intersection entrance and the green light speed of the intersection entrance. Based on the traffic trajectory diagram, the relationship between the gathering wave and the dissipation wave is obtained, thereby calculating the traffic dissipation time of the right through lane of the intersection. The maximum number of vehicles queuing in the right turn lane during the straight red light period is calculated, and finally the maximum queue length of the right turn lane of the intersection entrance is obtained, which is the distance from the stop line to the early right turn line. The present invention effectively alleviates the waste of resources caused by vehicle congestion at intersections, alleviates the problem of tight urban vehicle resources, and effectively improves travel efficiency.

The invention relates to a road network saturation flow detection method based on a microscopic simulation platform. The method comprises the following steps: S1, constructing a road network model in the microscopic simulation platform; s2, acquiring traffic density and traffic flow of each road section at different moments; s3, fitting to obtain a flow-density curve of each road section; s4, obtaining a flow distribution target of each road section; s5, generating an initial flow sequence of each road section; s6, the simulation flow of each road section is obtained, the difference value between the simulation flow of each road section and the flow distribution target is calculated to serve as the first fitness of each road section, and the sum of the first fitness of each road section serves as the total fitness value; s7, judging whether an iteration exit condition is met or not, if yes, executing the step S8, and otherwise, updating the flow sequence of each road section and returning to the step S6; and S8, generating the saturation flow of the road to be measured and the congestion degree of each road section. Compared with the prior art, the method has the advantages of efficiently and accurately solving the road network saturation flow demand under the condition of no complete historical data and the like.

The invention provides an AIS data-based busy water area macroscopic fundamental diagram acquisition method and system, an electronic device and a storage medium, and the method comprises the steps: constructing a water area macroscopic fundamental diagram with a water area ship cumulant as a state index and a water area boundary outflow as a performance index through mining ship automatic identification system data; forming a time sequence capable of reflecting the number of ships in the water area and the outflow efficiency; associating the two sequences to generate scatter data representing a macroscopic relationship; automatically dividing the scattered points into clusters corresponding to three typical states of free flow, saturation flow and congestion flow by using a clustering analysis technology; piecewise linear fitting is carried out on data in each state cluster, and a trapezoidal macroscopic fundamental diagram model with a clear ascending section, a stable section and a descending section is constructed; and a series of key characteristic parameters such as a critical inflection point of sign state transition, saturation flow representing the maximum traffic capacity and a slope reflecting the efficiency change rate are extracted, so that conversion from original data to a macroscopic cognitive model is completed.

The present disclosure provides a method and device for determining traffic control parameters, and a storage medium, relates to the field of artificial intelligence, specifically to the technical field of intelligent transportation, automatic driving and the like, and can be applied to the scene of road traffic capacity evaluation, traffic signal control and the like. The specific implementation scheme comprises: collecting a first traffic flow of a target flow direction corresponding to a target intersection in a preset time period; calibrating a first traffic saturation flow rate corresponding to the target flow direction according to the first traffic flow; obtaining a first traffic saturation degree corresponding to the target flow direction according to the first traffic saturation flow rate and the first traffic flow; and updating the first traffic saturation degree according to an oversaturation coefficient to obtain a second traffic saturation degree corresponding to the target flow direction when the first traffic saturation degree is less than a first threshold. The present disclosure can improve the accuracy of traffic saturation degree, and thus improve the effect of intelligent traffic signal control.

The application provides a method for calculating saturation of road intersection import direction, comprising: obtaining real-time vehicle quantity and vehicle speed of each import lane stop line position of road intersection; obtaining corresponding signal light color of each import lane of road intersection; establishing vehicle speed record list corresponding to current signal period, counting total vehicle quantity, and recording green light duration and yellow light duration; calculating average vehicle speed of import lane vehicle of road intersection, and comparing with maximum historical average vehicle speed; calculating import lane saturation flow of road intersection; calculating traffic flow of import lane of road intersection; and calculating saturation of road intersection import direction. The application can realize real-time, accurate and automatic calculation of import lane saturation value through vehicle detector, traffic signal control machine and other devices.

The application provides an AIS data-based busy water area macroscopic basic graph acquisition method and system, an electronic device and a storage medium. By mining ship automatic identification system data, a water area macroscopic basic graph is constructed with water area ship cumulative amount as a state index and water area boundary outflow as a performance index, and a time sequence sequence capable of reflecting the number of ships in the water area and the outflow efficiency is formed. The two sequences are associated to generate scatter data representing the macroscopic relationship. Then, clustering analysis technology is used to automatically divide the scatter points into clusters corresponding to three typical states of free flow, saturated flow and congested flow. The data in each state cluster is separately subjected to piecewise linear fitting to construct a trapezoidal macroscopic basic graph model with a clear rising section, a stable section and a falling section. A series of key characteristic parameters such as a critical inflection point indicating state transition, a saturated flow representing the maximum traffic capacity and a slope reflecting the efficiency change rate are extracted, thereby completing the transformation from the original data to the macroscopic cognitive model.

The application provides a kind of intersection traffic flow state identification method and traffic signal control equipment, it is related to intelligent transportation technical field.The application is according to each kind of traffic flow turning at target intersection, according to the maximum saturation flow rate of this kind of traffic flow turning and the actual signal control traffic data of this kind of traffic flow turning in current signal control period, the actual saturation of this kind of traffic flow turning in current signal control period is calculated, and the historical traffic flow state score of the last signal control period of this kind of traffic flow turning in current signal control period is combined, according to the target traffic flow state score rule adapted to the target intersection, the actual traffic flow state score of this kind of traffic flow turning in current signal control period is calculated to identify traffic flow state, so as to deeply consider the influence of traffic flow fluctuation in intersection traffic flow state identification process, ensure that the final traffic flow state identification result can accurately reflect the overall change trend of real intersection traffic flow state in time dimension level.

The present application relates to the technical field of intelligent traffic control, in particular to a kind of mixed environment under multi-lane single intersection space resource configuration method and system, storage medium, electronic equipment.The method comprises: determining the traffic flow of each flow direction of the intersection to be analyzed, the traffic flow of each flow direction of artificial vehicle, and the maximum and minimum permitted period length, the maximum and minimum permitted phase green time and green interval time of the intersection;Determine the saturation flow rate of the dedicated lane for the net-connected automatic vehicle and the dedicated lane for the artificial vehicle, and the conversion coefficient of the left, straight and right net-connected automatic vehicle flow and artificial vehicle flow;Determine the channelization scheme of the multi-lane intersection corresponding to the intersection to be analyzed under the mixed environment in combination with the layout of the connected road section of the intersection to be analyzed.

The invention discloses a phase and phase sequence configuration method and device of an intersection, equipment and a medium. The method comprises the following steps: matching lane channelization and / or lamp bank information with a preset judgment condition, and judging the traffic flow direction type of each entrance; determining a release sequence of each barrier unit based on the lane flow; based on the lane channelization and the lane flow, calculating the lane flow similarity between different turning lanes of each entrance; according to the lane channelization and the lane saturation flow, the minimum number of green passing vehicles of each lane is obtained; based on the lane channelization and the congestion delay index, the congestion state of the entrance is judged; when the traffic flow direction types of the opposite entrances in the barrier units are all left straight independent release, the phase sequence of the barrier units is set based on the lane flow similarity; otherwise, the phase sequence of the barrier unit is set according to the lane saturation flow, the minimum number of vehicles capable of passing through the green and the entrance congestion state; and combining the release sequence and the phase sequence of each barrier unit to obtain the phase sequence of the used intersection.

This invention discloses an algorithm-based method for evaluating the utilization efficiency of green lights in urban road traffic, comprising the following steps: obtaining a standardized dataset; performing lane matching for vehicles to obtain vehicle passage records for each lane; dividing the time interval and calculating the average flow rate of each lane within the target time period; calculating the saturation flow rate of each lane; obtaining the corrected saturation flow rate of each lane; using an improved Kuramoto model to output the total flow rate ratio of signal phases; obtaining low flow rate ratio scenarios and high flow rate ratio scenarios; using the Webster algorithm to calculate the signal cycle and the green light time of each signal phase, constructing an optimization model with the goal of minimizing the total delay at the intersection, and optimizing the solution for the signal cycle and the green light time of each signal phase; outputting signal timing parameters and corresponding traffic operation evaluation results to improve green light utilization efficiency, reduce traffic delay, and enhance the capacity and smoothness of the intersection.

The invention provides a water flow valve intelligent control method fusing a mechanism and a neural network, and relates to the technical field of industrial automation control. The method comprises the steps that flow and inlet pressure of a flow valve at different opening degrees in different system states are collected; based on the collected data, constructing and training a saturation opening degree prediction model, a saturation flow prediction model and an opening degree prediction model based on mixing of a mechanism and a neural network; when monitoring that the target flow is changed, judging whether the target flow is greater than saturated flow or not by using a saturated flow prediction model; if not, predicting a target opening degree by using an opening degree prediction model based on mixing of a mechanism and a neural network, and setting the opening degree of the flow valve as the predicted target opening degree; after the flow is stable, if the difference between the current flow and the target flow is smaller than or equal to a set threshold value, the PID control mode is directly used for fine adjustment so as to reach the target flow. In this way, rapid and high-precision control over the cooling water flow in the continuous casting process can be achieved.

The application discloses a real-time lane traffic capacity calculation method and system based on radar and video fusion. The method comprises the following steps: acquiring video image data and radar detection data; performing data fusion on the video image data and the radar detection data to obtain relative space-time information of each vehicle relative to a crossroad, and obtaining absolute space-time information of all vehicles at the crossroad according to the relative space-time information; acquiring traffic timing information and map information of the crossroad, and obtaining a saturation flow rate of a jth lane in a phase i and a stage green ratio of the jth lane in the phase i or a passable time proportion of the jth lane in the phase i according to the traffic timing information, the map information and the absolute space-time information; and obtaining a traffic capacity of the jth lane in the phase i according to the saturation flow rate of the jth lane in the phase i and the stage green ratio of the jth lane in the phase i.