Intelligent signal transmission system based on intelligent traffic

Abstract

The invention discloses an intelligent signal transmission system based on intelligent traffic, and the system comprises a data collection module which collects traffic flow parameters of each lane, and the traffic flow parameters comprise vehicle speed distribution, lane occupancy, time headway and vehicle position; the state coefficient acquisition module is used for constructing a # imgabs0 # model through the traffic flow parameters, introducing a dynamic congestion propagation factor into the # imgabs1 # model to obtain an improved # imgabs2 # model, inputting the traffic flow parameters into the improved # imgabs3 # model, and acquiring a state coefficient of driving out of each lane; the priority acquisition module is used for extracting a priority sequence based on the state coefficient, adjusting signal timing of different intersections according to the priority sequence and dynamically adjusting the signal timing based on the state coefficient and the priority sequence, can flexibly allocate green light duration according to the real-time traffic state of each lane, reduces the phenomena of green light idle running and vehicle backlog, and improves the traffic safety. The overall traffic efficiency of the intersection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control, and particularly to a signal intelligent transmission system based on intelligent transportation. Background Art

[0002] With the acceleration of the urbanization process, the number of motor vehicles has increased sharply, and urban traffic congestion has become a global problem. Traditional traffic signal control systems mostly rely on fixed timing plans or simple rules based on historical data, and cannot adapt to the dynamically changing traffic flow in real time, resulting in low intersection passing efficiency, and problems such as vehicle delays, energy waste, and environmental pollution becoming increasingly prominent.

[0003] Currently, traditional signal transmission systems mainly rely on manual intervention or simple priority rules to transmit signal control instructions, cannot perceive and adapt to the dynamic changes of traffic flow in real time, ignore the directional diffusion effect caused by the interaction of upstream and downstream road networks, resulting in a misjudgment rate of 15%-20% in traffic state assessment, often leading to unreasonable phenomena such as green lights being released in vain at some intersections while vehicles are congested at some intersections, reducing traffic operation efficiency and causing delays in the passage of priority vehicles. Moreover, in the event of special situations such as car accidents at intersections, the transmission of traffic signals will lack a dynamic priority sorting mechanism, and the response to the passing needs of priority vehicles such as ambulances and fire trucks will be lagged. Therefore, a signal intelligent transmission system based on intelligent transportation is proposed here. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention proposes the following technical solutions: A signal intelligent transmission system based on intelligent transportation, comprising: A data acquisition module: collecting traffic flow parameters of each lane, where the traffic flow parameters include vehicle speed distribution, lane occupancy, headway, and vehicle position; A state coefficient acquisition module: constructing a model, introducing a dynamic congestion propagation factor into the model to obtain an improved model, inputting the traffic flow parameters into the improved model to obtain the state coefficients of each lane exiting; A priority acquisition module: extracting the priority order based on the state coefficients and adjusting the signal timing of different intersections according to the priority order; The dynamic congestion propagation factor is obtained by directionally correcting the initial congestion propagation factor through an improved spatial autoregressive model ; The improved spatial autoregressive model is obtained by combining technology with the spatial autoregressive model; The vehicle speed distribution obtains the passing speed of a single vehicle based on a geomagnetic coil, and statistically calculates the average speed and speed standard deviation within the lane as the vehicle speed distribution, expressed as ; The lane occupancy rate is obtained by quantifying the proportion of the duration during which the coil is covered by vehicles within the monitoring unit time, and represents the degree to which the lane is actually occupied by vehicles, expressed as ; The time headway is obtained by measuring the time interval between the passing of the front and rear vehicles in the same lane through a radar monitoring point, expressed as ; The vehicle position is obtained by positioning the distance of the vehicle from the stop line at the intersection on the lane based on the time delay of electromagnetic wave reflection, expressed as ; The traffic flow parameters are expressed as .

[0005] The model construction process is as follows: Based on the traffic flow parameters construct a model; Obtain the vehicle dynamic characteristics through the vehicle speed distribution and the time headway ; ; Obtain the traffic flow density through the lane occupancy rate and the vehicle position ; ; The model is expressed as: ; Among them, represents the traffic flow density, represents the vehicle dynamic characteristics, represents the time variation, represents the spatial gradient variation, represents the traffic flow density variation.

[0006] The process of obtaining the initial congestion propagation factor is as follows: Extract real-time trajectory data from the devices of floating vehicles, including timestamps, longitude and latitude coordinates, and instantaneous speeds; Eliminate the abnormal points of instantaneous speed mutation and positioning drift points in the real-time trajectory data; Based on the real-time trajectory data, identify the boundaries of the congestion zone to obtain the length of the congestion zone; Calculate the change in the length of the congestion zone within adjacent time windows ; ; ; Obtain the initial congestion propagation factor through the formula: , represents the initial congestion propagation factor.

[0007] The process of obtaining the improved spatial autoregressive model based on technology is as follows: Through technology, the congestion indices of the upstream intersection and the downstream intersection are obtained in real time , ; Through technology, the lane-level traffic flow densities of the upstream intersection and the downstream intersection are obtained in real time , ; Based on the lane-level traffic flow densities , obtain the direction weights; Based on the obtained direction weights, construct the spatial weight matrix ; Through the spatial weight matrix constructed by the direction weights obtain the improved spatial autoregressive model , and the formula is expressed as: ; Among them, represents the initial congestion propagation factor of local observation, represents the spatial weight matrix, represents the error term; The process of direction correction for the initial congestion propagation factor by the improved spatial autoregressive model is expressed as: ; Among them, represents the sign function, represents the spatial autoregressive coefficient; If , , enhance the downstream propagation effect; If , , indicating that the congestion retraces upstream; The initial congestion propagation factor after direction correction is the dynamic congestion propagation factor.

[0008] The process of obtaining the direction weights is as follows: Define the propagation direction priority according to the density difference between upstream and downstream, and the formula is: ; Among them, is the block density; If , is positive, the congestion spreads downstream; If , is negative, the congestion develops upstream; This direction priority That is, the direction weight.

[0009] The process of obtaining the state coefficient is as follows: Add the dynamic congestion propagation factor to in the model to obtain an improved model, expressed as: ; Input the traffic flow parameters into the improved model, and output the state coefficients departing from each lane, where represents the road index.

[0010] The process of obtaining the priority order is as follows: Extract the historical traffic data of different roads; The historical traffic data includes traffic flow , traffic efficiency , and the proportion of congestion duration , where is the congestion duration, is the total operation duration; ; Among them, is the weight coefficient, , is the maximum number of vehicles corresponding to the lane, is the maximum passing speed corresponding to the lane; The process of calculating the priority order is: ; Among them, represents the priority coefficient of the th lane.

[0011] The process of adjusting the signal timing of different intersections according to the priority order is: Set the basic passing time reference duration for each intersection; Reserve a globally adjustable elastic duration pool for each intersection; Based on the time reference duration and the elastic duration pool Combined with the priority coefficient Perform dynamic allocation to obtain the signal timing of the i-th intersection ; Dynamic allocation formula: = , where is the signal timing of the i-th intersection, is the reference duration, is the elastic duration, is the total timing duration.

[0012] The present invention has the following beneficial effects: 1. By devices such as geomagnetic coils and microwave radars, traffic flow parameters such as vehicle speed distribution, lane occupancy, headway, and vehicle position are collected in real time, providing accurate data support for signal timing, enabling the system to perceive traffic state changes in real time. Combining with the improved CTM model, a dynamic congestion propagation factor β(t) is introduced, and information such as the change in the length of the congestion belt, the density difference between upstream and downstream traffic flows, and special accident scenario interventions is integrated, significantly improving the prediction accuracy of the direction and speed of congestion propagation, and making the analysis of traffic flow density changes more in line with the actual traffic scenario.

[0013] 2. Based on the state coefficient and priority order, the signal timing is dynamically adjusted, and the green light duration can be flexibly allocated according to the real-time traffic state of each lane (such as congestion degree, traffic efficiency), reducing the phenomenon of green light idling and vehicle backlog, and improving the overall traffic efficiency of the intersection.

[0014] 3. Based on V2X technology and the improved spatial autoregressive model, coordinated control between multiple intersections can be achieved, alleviating chain congestion. At the same time, when a traffic accident or the passage of an emergency vehicle occurs, the signal timing can be quickly adjusted by forcibly correcting the direction weight (forced ), ensuring that priority vehicles pass quickly and improving the emergency response ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is the system block diagram of a signal intelligent transmission system based on intelligent transportation proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment: As shown Figure 1 in the figure, a signal intelligent transmission system based on intelligent transportation proposed by the present invention includes: State coefficient acquisition module: Collect traffic flow parameters of each lane. The traffic flow parameters include vehicle speed distribution, lane occupancy, headway time, and vehicle position; Composition and acquisition method of traffic flow parameters: In the core traffic hub area of urban roads, including the entrance lanes of intersections (such as the approach lanes in all directions of crossroads and T-junctions) and the connecting sections between main roads and secondary roads (areas where traffic flow conversion is frequent and bottlenecks are easily formed), information collection devices are deployed. The information collection devices include induction loops and microwave radars; Composition of traffic flow parameters: Vehicle speed distribution, lane occupancy, headway time, and vehicle position; Specific acquisition method of traffic flow parameters: Vehicle speed distribution: Based on the time difference of vehicles passing through the induction loop within the lane, and combined with the distance between induction loops, the passing speed of a single vehicle is obtained. Based on the passing speed, the average speed and speed standard deviation within the lane are calculated. The average speed and speed standard deviation of the lane are statistically used as the vehicle speed distribution, expressed as ; Lane occupancy: Monitor the proportion of the duration of the loop covered by vehicles per unit time, and quantify the degree of actual occupancy of the lane by vehicles, expressed as ; Specifically, within 1 minute, if the time when the loop is covered by vehicles is 30 seconds, the lane occupancy is 50%. This parameter directly reflects the utilization efficiency of the lane; The microwave radar emits electromagnetic waves to the road area. After the electromagnetic waves encounter vehicles, they are reflected back to the radar receiver. The frequency difference and time difference between the transmitted wave and the reflected wave are analyzed to obtain headway time and vehicle position data; Headway time: Measure the time interval between the front and rear vehicles in the same lane passing through the radar monitoring point, which is used to evaluate the density of traffic flow. The headway time is expressed as .

[0018] For example, if the headway time is too small, it indicates that the vehicles are driving densely and there are potential safety hazards, and attention needs to be paid to the evacuation efficiency in signal timing; Vehicle position: Based on the time delay of electromagnetic wave reflection, the specific position of the vehicle on the lane is real-time located (such as the distance from the stop line of the intersection). The vehicle position is expressed as ; Specifically, the traffic flow parameters can be expressed as .

[0019] State coefficient acquisition module: Construct a model through traffic flow parameters. In An improvement is achieved by introducing a dynamic congestion propagation factor into the model For the model, traffic flow parameters are input for improvement In the model, the state coefficients of each lane exiting are obtained; The process of constructing the improved traffic flow model is as follows: In Based on the model, a dynamic congestion propagation factor is introduced Revise The vehicle conservation equation in the model; Based on traffic flow parameters Construct a Model; Specifically, The model includes; traffic flow density and vehicle dynamic characteristics, where: Traffic flow density: Reflects the degree of occupation of road space resources, through lane occupancy And vehicle position Comprehensively represented; Vehicle dynamic characteristics: Characterize the dynamic characteristics of traffic flow, through vehicle speed distribution And time headway Comprehensively represented; The model is expressed as: ; Wherein, Represents traffic flow density, Represents vehicle dynamic characteristics, Represents the change with time, Represents the spatial gradient change, Represents the change in traffic flow density; As a macroscopic traffic flow model, its core goal is to describe the overall evolution law of traffic flow (congestion propagation, bottleneck effect), rather than the individual behavior of microscopic vehicles. Traffic flow density and vehicle dynamic characteristics, as macroscopic state variables, can effectively represent the data in traffic flow parameters. For example: In A dynamic congestion propagation factor with direction correction for movement is added to the model ; Initial congestion propagation factor The acquisition process is as follows: Extract real-time trajectory data from the Devices of floating vehicles (taxis, online car-hailing services), including timestamps, longitude and latitude coordinates, and instantaneous speeds; Remove the abnormal points of instantaneous speed mutation (invalid data with vehicle speed dropping suddenly from To ) and positioning drift points (such as coordinates beyond the road boundary) in the real-time trajectory data; For low-frequency data (30 seconds per time), cubic spline interpolation is used to generate high-precision continuous (time resolution improved to 1 second) trajectory data; Based on the real-time trajectory data, the boundary of the congestion zone is identified to obtain the length of the congestion zone: Calculation of the change in the length of the congestion zone: Calculate the change in the length of the congestion zone (expansion / contraction amount) within adjacent time windows (5 minutes): : ; Among them, represents the length of the congestion zone at time , represents the length of the congestion zone after time has passed through the time window ; represents the end point of the congestion zone at time , represents the starting point of the congestion zone at time ; represents the time has passed through the time window and the end point of the congestion zone after that; represents the time has passed through the time window and the starting point of the congestion zone after that; Congestion determination: Mark the trajectory segments with vehicle speeds continuously lower than the threshold (20 KM / h), and record their start times and end times ; Spatial positioning: Map the GPS coordinates to the road network lanes through map matching to determine the starting point and end point of the congestion zone; The calculation process of the initial congestion propagation factor is as follows: , represents the initial congestion propagation factor; Based on technology (vehicle wireless communication technology), an improved spatial autoregressive model is obtained to correct the direction of the initial congestion propagation factor to obtain the dynamic congestion propagation factor The process is as follows: Real-time obtain the congestion indices of adjacent intersections (upstream intersection and downstream intersection ) through , , and the value range is , and the closer the value is to 1, the more serious the congestion; For example, at the upstream intersection = 0.6 (moderate congestion), and at the downstream intersection = 0.8 (severe congestion), which directly reflects the congestion status of adjacent intersections and provides a macroscopic indicator for propagation analysis; Through technology, the lane-level traffic flow density of the upstream intersection and the downstream intersection is obtained in real time. The traffic flow density characterizes the degree of vehicle concentration through the number of vehicles per kilometer 、 ; For example, = = indicating that the downstream is more congested; Based on the lane-level traffic flow density, the direction weight is obtained, and the propagation direction priority is defined according to the density difference between the upstream and downstream. The formula is: ; Among them, is the blocking density ( ), and the result is normalized to . If is positive, the congestion spreads downstream. If is negative, the congestion develops upstream; For example, is calculated, reflecting that the downstream congestion is more serious; This direction priority is the direction weight; If there is a traffic accident at the downstream, force , indicating that the congestion will surely spread downstream; Example: A rear-end collision occurred at a certain intersection, and was actually detected, ; Conventional calculation: ; Due to the existence of the accident, directly set , and the dynamic congestion propagation factor enables the model to immediately respond to congestion propagation; This is an intervention in special scenarios to ensure the accuracy of the model in extreme cases. When there is a downstream accident, even if the density difference calculation is not obvious, it is determined that the congestion spreads downstream; The purpose is to better fit the actual traffic scenario. Through ​​​​​​Integrate information such as the change in the length of the congestion belt, the difference in traffic flow density between upstream and downstream, and the intervention in special accident scenarios, so that the subsequent improved model can dynamically adapt to different traffic states. For example, when an accident occurs downstream, force to reflect the downstream propagation of congestion and make the model output closer to the real traffic flow evolution; Based on the obtained direction weights, construct a spatial weight matrix ; Through the direction weights constructed spatial weight matrix obtain an improved spatial autoregressive model , which is expressed by the formula: ; Among them, represents the initial congestion propagation factor of local observation, represents the spatial weight matrix, represents the error term, represents the spatial autoregressive coefficient; Through the improved spatial autoregressive model, perform direction correction on the initial congestion propagation factor , which is expressed by the formula: ; Among them, represents the sign function, represents the spatial autoregressive coefficient; If , , enhance the downstream propagation effect; If , , indicating that the congestion backtracks upstream; The initial congestion propagation factor after direction correction is the dynamic congestion propagation factor; Specifically, by integrating the congestion index of adjacent intersections obtained by communication and the traffic flow density monitored by geomagnetic coils and microwave radars , and through the direction weights combine with the congestion index to construct a spatial weight matrix to improve the traditional spatial autoregressive model, convert the spatial correlation unique to the traffic field (such as the reverse impact of downstream congestion on upstream) into matrix elements, and better combine with the spatial autoregressive model, providing a new practical scenario for the application of the spatial autoregressive model in traffic congestion analysis; Add the dynamic congestion propagation factor to the improved model. After adding, the model is expressed as: ; By introducing a dynamic congestion propagation factor, this model strengthens the description of the congestion propagation law in traffic flow, making the analysis of the change in traffic flow density more in line with the actual traffic scenario; By substituting the dynamic congestion propagation factor , the model implementation is improved: Enhanced dynamic adaptability: From statically describing traffic flow to dynamically responding to the characteristics of congestion propagation and adjusting the calculation of traffic flow density changes in real time; Enhanced scenario adaptability: Whether it is conventional congestion diffusion or special accident scenarios, the model can through correction, output results that are more in line with the actual traffic operation state; Specifically, the traditional model is a macroscopic traffic flow model. The core of the model is to divide the road into cells and describe the overall evolution law of traffic flow through macroscopic variables such as traffic flow density , vehicle speed v, etc., such as congestion propagation and traffic flow changes at bottlenecks; However, the traditional model inadequately depicts the dynamic characteristics of congestion propagation, does not fully consider the changes in congestion propagation speed and direction under different scenarios, and is difficult to accurately adapt to complex traffic environments. For example, the rapid spread of congestion caused by downstream accidents. The significance of substituting the dynamic congestion propagation factor is mainly reflected in substituting it into the improved model after direction correction. The core is to quantify the impact of congestion propagation on traffic flow density changes, integrate information such as the change in the length of the congestion belt, the difference in traffic flow density between upstream and downstream, and the intervention of special accident scenarios, enabling the model to dynamically adapt to different traffic states. For example, when congestion spreads downstream, increases, and the calculated change in traffic flow density is more in line with the actual scenario of congestion intensification.

[0020] The process of obtaining the state coefficient of each lane exiting is as follows: Calculate each item in the model; Traffic flow density is obtained based on the lane occupancy rate . Let the lane length be , and the number of vehicles be , then , where is obtained through the lane occupancy rate and the maximum number of vehicles that the lane can accommodate , that is ; Vehicle speed v is based on the lane speed distribution Obtaining the average speed; Change in traffic flow density Obtained from the difference in traffic flow density between adjacent time steps, i.e., ; Substitute the calculated parameters and traffic flow parameters into the improved traffic flow model, and the model outputs the state coefficients of each lane exiting , where i represents the road index; Specifically, the state coefficient S integrates the calculation terms of the improved CTM model and the original traffic flow parameter A. Its manifestation is a multi-dimensional vector, and each element corresponds to the state coefficient of a lane, which can not only reflect the current congestion intensity but also predict future change trends through the dynamic congestion propagation factor For example, in the congestion propagation scenario, by integrating factors such as the difference in traffic flow density between upstream and downstream lanes and accident intervention to correct , so that the state coefficient accurately reflects the deterioration of the upstream lane state caused by congestion propagation. Even if the original parameters are not significantly abnormal, it can also detect potential congestion risks, break through the limitations of traditional single-parameter characterization, and truly meet the analysis needs of complex traffic scenarios; For example: Priority vehicle handling: When a priority vehicle such as an ambulance is detected in the i-th lane, through communication to directly correct , improve the state coefficient of the corresponding lane ; Congestion propagation scenario: When congestion spreads upstream due to a downstream accident in the i-th lane, Integrate the difference in traffic flow density between upstream and downstream increase, accident intervention (forced ) and then increase, substitute into the improved CTM model for adjustment calculation, so that accurately reflects the deterioration of the upstream lane state caused by congestion propagation. Even if the original parameters are not significantly abnormal, it can also reflect potential congestion risks.

[0021] Signal transmission module: Extract the priority order based on the state coefficient, and adjust the signal timing of different intersections according to the priority order; Extract the historical traffic data of different roads, including: Traffic flow: Count the number of vehicles passing through the lane per unit time (vehicles / hour); Traffic efficiency: Calculate the average traffic speed of the lane ; Proportion of congestion duration: Count the daily congestion duration of the lane and the total operation duration ratio ; Calculate the initial function weights through a weighted formula: ; Among them, , is the maximum number of vehicles corresponding to the lane, is the maximum passing speed corresponding to the lane; Specifically, the weight coefficient is set according to the traffic management objective, and the process is as follows: When focusing on the traffic flow guidance objective: Emphasize the role of traffic flow , increase the weight so that the lanes with large traffic volume have higher priority in signal timing; Setting process: Determine , and the remaining ; Allocate (traffic efficiency), (congestion mitigation); Example: For the main road of a commercial street, where large traffic volume is the main management objective, using , when calculating the initial weight, the traffic flow has the greatest impact on ; When focusing on the traffic efficiency improvement objective: Highlight the importance of passing speed , increase the weight to ensure the rapid passage of vehicles; Setting process: Let , then ; Allocate (traffic volume), (congestion mitigation); Example: For an urban expressway, the goal is to maintain the high-speed passage of vehicles, , when calculating the initial weight, the passing speed has the dominant impact on the result ; When focusing on the congestion mitigation objective: Pay attention to the proportion of congestion duration , increase the weight to give priority to congestion mitigation; Setting process: Determine , then ; Allocate (traffic volume), (traffic efficiency).

[0022] Example: For a road near a school that is often congested, the management goal is to reduce congestion. , when calculating the initial weights, the proportion of congestion duration has the greatest impact on the result . The calculation process of the priority order is as follows: ; Among them, represents the priority coefficient of the i-th lane; Through obtain the lane priority coefficient, and combine the real-time status coefficient with the weight based on historical data , considering both the current lane status and integrating long-term traffic characteristics and management goals. Finally, determine the signal timing priority according to sorting from high to low, and perform signal timing for different intersections; The green light duration allocation of signal timing is; Benchmark duration: (guarantee the minimum passing time); Elastic duration pool: ; Set the basic passing time benchmark duration for each intersection to ensure the minimum passing demand; Reserve a globally adjustable elastic duration pool for responding to real-time traffic changes; Combine the priority coefficient and perform dynamic allocation: , among which, is the signal timing of the i-th intersection, is the total timing duration; Specifically, through the green light duration allocation mode of the benchmark duration and the elastic duration pool, the benchmark duration guarantees the minimum passing time, and the elastic duration pool combines the priority coefficient to dynamically allocate the duration , which can be flexibly adjusted according to the lane priority. Compared with fixed-cycle timing or simple proportional allocation, it can more accurately adapt to real-time traffic demands; Example: If the lane , the total , then: ; Specifically, in the example, it clearly shows the calculation process from the priority coefficient to the green light duration, making the signal timing result correspond to the lane priority.

[0023] In the application, several formulas involved are calculated by taking their numerical values after dimensionless treatment. The establishment of the formulas is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. Some coefficients or weights in the formulas are set by those skilled in the art according to the actual situation, so no more elaboration will be made here.

[0024] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution.

[0025] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A signal intelligent transmission system based on intelligent transportation, characterized in that, Including: Data acquisition module: It acquires traffic flow parameters of each lane. The traffic flow parameters include vehicle speed distribution, lane occupancy, headway time, and vehicle position; Status coefficient acquisition module: construct a model through traffic flow parameters, and introduce a dynamic congestion propagation factor into the model to obtain an improved model. Input the traffic flow parameters into the improved model to obtain the status coefficients of each lane exiting; Priority acquisition module: It extracts the priority order based on the state coefficient and adjusts the signal timing of different intersections according to the priority order; The dynamic congestion propagation factor is obtained by correcting the direction of the initial congestion propagation factor through an improved spatial autoregressive model; The improved spatial autoregressive model is obtained based on technology combined with the spatial autoregressive model.

2. The signal intelligent transmission system based on intelligent transportation according to claim 1, wherein The vehicle speed distribution obtains the passing speed of a single vehicle based on a geomagnetic coil, and statistically calculates the average speed and speed standard deviation within the lane as the vehicle speed distribution, expressed as ; The lane occupancy rate is obtained by monitoring the proportion of the duration during which the coil is covered by vehicles within a unit time and quantifying the degree to which the lane is actually occupied by vehicles, and is expressed as ; The time headway is obtained by measuring the time interval between the passing of the vehicle in front and behind in the same lane through the radar monitoring point, and is expressed as ; The vehicle position is based on the time delay of electromagnetic wave reflection, and the distance of the vehicle from the stop line at the intersection on the lane is obtained, expressed as ; The traffic flow parameters are expressed as .

3. An intelligent signal transmission system based on intelligent transportation according to claim 1, characterized in that, The said The model construction process is as follows: Based on traffic flow parameters Construct a model; Obtain vehicle dynamic characteristics through vehicle speed distribution and time headway ; ; Obtain traffic flow density through lane occupancy and vehicle position ; ; Based on vehicle dynamic characteristics and traffic flow density Build a model 4. The intelligent signal transmission system based on intelligent transportation according to claim 1, characterized in that, The initial congestion propagation factor is obtained as follows: Extract real-time trajectory data from the floating vehicle's device, including timestamp, longitude and latitude coordinates, and instantaneous speed; Eliminate the instantaneous speed mutation abnormal points and positioning drift points in the real-time trajectory data; Based on the real-time trajectory data, identify the boundary of the congestion zone to obtain the length of the congestion zone; Calculate the change in the length of the congestion belt within adjacent time windows within ; By the length change of the congestion belt within adjacent time windows the initial congestion propagation factor is obtained through .

5. A signal intelligent transmission system based on intelligent transportation according to claim 1, characterized in that, The process of obtaining an improved spatial autoregressive model based on the technology is as follows: Obtain the upstream intersection in real time through V2X technology and the downstream intersection congestion index , ; Real-time obtain upstream intersection through V2X technology and downstream intersection Lane-level traffic flow density , ; Based on lane-level traffic flow density , Obtain direction weights; Construct a spatial weight matrix based on the obtained directional weights ; Through directional weights Construct a spatial weight matrix Obtain an improved spatial autoregressive model ; The process of correcting the direction of the initial congestion propagation factor by improving the spatial autoregressive model is expressed as: ； Among them, represents the sign function, represents the spatial autoregressive coefficient; If , , enhance the downstream propagation effect; If , , it means that the congestion is backtracking upstream; Obtain the dynamic congestion propagation factor after direction correction .

6. An intelligent signal transmission system based on intelligent transportation according to claim 5, characterized in that, The process of obtaining the direction weight is as follows: Define the propagation direction priority according to the density difference between upstream and downstream ; If , is positive, congestion spreads downstream; If , is negative, congestion develops upstream; Direction priority That is, the direction weight.

7. An intelligent signal transmission system based on intelligent transportation according to claim 1, characterized in that The process of obtaining the state coefficient is as follows: Add the dynamic congestion propagation factor to the model to obtain an improved model; Input traffic flow parameters into the improved model, and output the state coefficients of each lane exiting , where represents the road index.

8. A signal intelligent transmission system based on intelligent transportation according to claim 1, characterized in that, The process of obtaining the priority order is as follows: Extract the historical traffic data of different roads; Historical traffic data includes traffic flow , traffic efficiency , and the proportion of congestion duration ; Obtain initial function weights based on historical traffic data ; Based on the initial function weights and the status coefficient Obtain the priority coefficient of the .

9. The intelligent signal transmission system based on intelligent transportation according to claim 1, wherein The process of adjusting the signal timing of different intersections according to the priority order is as follows: Set the baseline duration of the basic passing time ; Set a globally adjustable elastic duration pool ; Based on the time reference duration and the flexible duration pool combined with the priority coefficient to dynamically allocate and obtain the signal timing of the i-th intersection .

Images