A signal intelligent transmission system based on smart transportation

Abstract

The present invention discloses a signal intelligent transmission system based on smart transportation, comprising a data acquisition module for collecting traffic flow parameters of each lane, the traffic flow parameters including vehicle speed distribution, lane occupancy, headway and vehicle position; a state coefficient acquisition module for constructing an #imgabs0# model through 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 to obtain the state coefficient of each lane exit; a priority acquisition module for extracting a priority sequence based on the state coefficient, adjusting the 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. The system can flexibly allocate the green light duration according to the real-time traffic status of each lane, reduce the phenomenon of vacant green lights and vehicle backlogs, and improve the overall traffic efficiency of the intersection.

Description

Technical Field

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

[0002] With the acceleration of urbanization and the rapid growth of motor vehicle ownership, urban traffic congestion has become a global problem. Traditional traffic signal control systems mostly rely on fixed timing schemes or simple rules based on historical data, and are unable to adapt to dynamically changing traffic flows in real time, resulting in low traffic efficiency at intersections, and increasingly prominent problems such as vehicle delays, energy waste, and environmental pollution.

[0003] At present, traditional signal transmission systems mainly rely on manual intervention or simple priority rules to transmit signal control instructions. They are unable to perceive and adapt to the dynamic changes of traffic flow in real time, and ignore the directional diffusion effect caused by the interaction of upstream and downstream road networks, resulting in a 15%-20% misjudgment rate in traffic status assessment. This often leads to the unreasonable phenomenon of unused green lights at some intersections and vehicle backlogs at other intersections, reducing traffic operation efficiency and causing delays in the passage of priority vehicles. In addition, in special circumstances such as traffic accidents at intersections, the transmission of traffic signals lacks a dynamic priority sorting mechanism, resulting in a delayed response to the passage needs of priority vehicles such as ambulances and fire trucks. Therefore, a signal intelligent transmission system based on smart 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-mentioned objectives, the present invention proposes the following technical solutions:

[0005] A signal intelligent transmission system based on smart transportation, comprising:

[0006] Data acquisition module: collects traffic flow parameters of each lane, including vehicle speed distribution, lane occupancy, headway and vehicle position;

[0007] State coefficient acquisition module: constructed through traffic flow parameters Model, in Improvements are achieved by introducing dynamic congestion propagation factors into the model Model, traffic flow parameters are input to improve In the model, the state coefficient of each lane exit is obtained;

[0008] Priority acquisition module: extracts the priority order based on the state coefficient and adjusts the signal timing of different intersections according to the priority order;

[0009] The dynamic congestion propagation factor The initial congestion propagation factor is calculated by improving the spatial autoregressive model Perform direction correction and acquisition;

[0010] The improved spatial autoregressive model is based on The technology is combined with spatial autoregressive model to obtain;

[0011] The vehicle speed distribution is based on the geomagnetic coil to obtain the passing speed of a single vehicle, and the average speed and speed standard deviation in the lane are calculated as the vehicle speed distribution, which is expressed as ;

[0012] The lane occupancy rate is obtained by monitoring the proportion of the time the coil is covered by the vehicle in a unit time and quantifying the actual degree of lane occupancy by the vehicle, which is expressed as ;

[0013] The headway is obtained by measuring the time interval between the front and rear vehicles in the same lane passing the radar monitoring point, which is expressed as ;

[0014] The vehicle position is obtained based on the time delay of electromagnetic wave reflection and the distance between the vehicle and the stop line at the intersection on the lane, which is expressed as ;

[0015] The traffic flow parameters are expressed as .

[0016] described The model building process is:

[0017] Based on traffic flow parameters Build a Model;

[0018] Vehicle speed distribution Headway Obtaining vehicle dynamic characteristics ;

[0019] Pass lane occupancy and vehicle location Get traffic density ;

[0020] The model is represented as: ;

[0021] in, represents the traffic density, Represents the vehicle dynamic characteristics, Indicates time changes, represents the spatial gradient change, Indicates the change in traffic density.

[0022] The initial congestion propagation factor The acquisition process is:

[0023] From the floating car Extract real-time trajectory data from the device, including timestamp, longitude and latitude coordinates, and instantaneous speed;

[0024] Eliminate abnormal points of instantaneous speed mutation and positioning drift points in real-time trajectory data;

[0025] Based on real-time trajectory data, congestion zone boundary identification is performed to obtain the congestion zone length;

[0026] Calculate adjacent time windows Changes in the length of the congestion zone within ;

[0027] The initial congestion propagation factor is obtained by the formula: , represents the initial congestion propagation factor.

[0028] The based The process of obtaining an improved spatial autoregressive model is as follows:

[0029] pass Technology to obtain upstream intersections in real time and downstream intersection Congestion Index 、 ;

[0030] pass Technology to obtain upstream intersections in real time and downstream intersection Lane-level traffic density 、 ;

[0031] Based on lane-level traffic density 、 Get direction weight;

[0032] Based on the obtained directional weights, a spatial weight matrix is constructed ;

[0033] By direction weight Constructed spatial weight matrix Obtaining an improved spatial autoregressive model , the formula is:

[0034] ;

[0035] in, represents the initial congestion propagation factor of the local observation, represents the spatial weight matrix, represents the error term;

[0036] The initial congestion propagation factor is calculated by improving the spatial autoregressive model The process of direction correction is expressed as:

[0037] ;

[0038] in, represents the symbolic function, represents the spatial autoregressive coefficient;

[0039] like , , enhance the downstream propagation effect;

[0040] like , , indicating that the congestion is traced back upstream;

[0041] Initial congestion propagation factor after direction correction That is, the dynamic congestion propagation factor.

[0042] The direction weight acquisition process is as follows:

[0043] The propagation direction priority is defined based on the upstream and downstream density difference. The formula is: ;

[0044] in, is the blocking density;

[0045] like , is positive, congestion spreads downstream;

[0046] like , If it is negative, congestion develops upstream;

[0047] This direction priority That is, the direction weight.

[0048] The process of obtaining the state coefficient is as follows:

[0049] Dynamic Congestion Propagation Factor Add to Improvements in the model Model, expressed as: ;

[0050] Traffic flow parameters are input into the improved In the model, the state coefficients of each lane exit are output ,in, Indicates the road index.

[0051] The priority order acquisition process is:

[0052] Extract historical traffic data for different roads;

[0053] Historical traffic data including traffic flow , traffic efficiency and congestion duration ratio ,in , The congestion duration, is the total operating time;

[0054] Calculate the initial feature weights: ;

[0055] in, is the weight coefficient, , is the maximum number of vehicles corresponding to the lane, is the maximum speed corresponding to the lane;

[0056] The priority order calculation process is:

[0057] ;

[0058] in, Indicates the The priority coefficient of each lane.

[0059] The process of adjusting the signal timing of different intersections according to the priority order is as follows:

[0060] Set a basic travel time benchmark for each intersection ;

[0061] Reserve a globally adjustable flexible time pool for each intersection ;

[0062] Based on time base duration and flexible time pools Combined priority coefficient Perform dynamic allocation to obtain the signal timing of the i-th intersection ;

[0063] Dynamic allocation formula: = ,in, The signal timing for the i-th intersection, As the benchmark duration, For flexible duration, The total allocation duration.

[0064] The present invention has the following beneficial effects:

[0065] 1. Traffic flow parameters such as vehicle speed distribution, lane occupancy, headway, and vehicle position are collected in real time through equipment such as geomagnetic coils and microwave radars. This provides accurate data support for signal timing, enabling the system to perceive changes in traffic conditions in real time. Combined with the improved CTM model, the dynamic congestion propagation factor β(t) is introduced. This incorporates information such as changes in congestion strip length, upstream and downstream traffic density differences, and special accident scenario interventions. This significantly improves the accuracy of predicting congestion propagation direction and speed, making the analysis of traffic density changes more relevant to actual traffic scenarios.

[0066] 2. Dynamically adjust signal timing based on state coefficients and priority order, and flexibly allocate green light duration according to the real-time traffic status of each lane (such as congestion level and traffic efficiency), reducing the phenomenon of empty green lights and vehicle backlogs, and improving the overall traffic efficiency of the intersection.

[0067] 3. Based on V2X technology and improved spatial autoregressive model, it can realize coordinated control between multiple intersections to alleviate chain congestion. At the same time, when encountering traffic accidents or emergency vehicles, the direction weight can be forced to be corrected (forced ), quickly adjust signal timing to ensure that priority vehicles pass quickly and improve emergency response capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a system block diagram of a signal intelligent transmission system based on smart transportation proposed by the present invention. DETAILED DESCRIPTION

[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0070] Example:

[0071] like Figure 1 As shown, the present invention proposes a signal intelligent transmission system based on smart transportation, including:

[0072] State coefficient acquisition module: collects traffic flow parameters of each lane, including vehicle speed distribution, lane occupancy, headway and vehicle position;

[0073] Traffic flow parameter composition and acquisition method:

[0074] Deploy information collection equipment, including geomagnetic coils and microwave radar, in core traffic hubs on urban roads, including entrance lanes to intersections (such as entrance lanes in all directions at crossroads and T-junctions) and sections connecting main and secondary roads (areas with frequent traffic changes and prone to bottlenecks).

[0075] Traffic flow parameters consist of: vehicle speed distribution, lane occupancy, headway and vehicle position;

[0076] The specific method of obtaining traffic flow parameters is as follows:

[0077] Vehicle speed distribution: Based on the time difference between vehicles passing through the geomagnetic coils in the lane and the distance between the geomagnetic coils, the passing speed of a single vehicle is obtained. The average speed and speed standard deviation in the lane are calculated based on the passing speed. The average speed and speed standard deviation of the lane are used as the vehicle speed distribution, which is expressed as ;

[0078] Lane occupancy rate: monitors the proportion of time the coil is covered by vehicles per unit time and quantifies the degree to which the lane is actually occupied by vehicles, expressed as ;

[0079] Specifically, if the coil is covered by a vehicle for 30 seconds within 1 minute, the lane occupancy rate is 50%. This parameter directly reflects the lane utilization efficiency.

[0080] Microwave radar transmits electromagnetic waves to the road area. When the electromagnetic waves hit the vehicle, they are reflected back to the radar receiver. The radar receiver analyzes the frequency and time difference between the transmitted and reflected waves to obtain the headway and vehicle position data.

[0081] Headway: It measures the time interval between the front and rear vehicles in the same lane passing the radar monitoring point, and is used to evaluate the density of traffic flow. The headway is expressed as .

[0082] For example, if the headway is too short, it indicates that vehicles are traveling densely, which poses a safety hazard and requires attention to evacuation efficiency in signal timing.

[0083] Vehicle position: Based on the time delay of electromagnetic wave reflection, the specific position of the vehicle on the lane (such as the distance from the stop line at the intersection) is located in real time. The vehicle position is expressed as ;

[0084] Specifically, the traffic flow parameters can be expressed as .

[0085] State coefficient acquisition module: constructed through traffic flow parameters Model, in Improvements are achieved by introducing dynamic congestion propagation factors into the model Model, traffic flow parameters are input to improve In the model, the state coefficient of each lane exit is obtained;

[0086] The construction process of the improved traffic flow model is as follows:

[0087] exist Based on the model, a dynamic congestion propagation factor is introduced Correction Conservation equations for vehicles in the model;

[0088] Based on traffic flow parameters Build a Model;

[0089] Specifically, The model includes traffic density and vehicle dynamic characteristics, including:

[0090] Traffic density: reflects the degree of road space resource occupancy, through lane occupancy and vehicle location Comprehensive representation;

[0091] Vehicle dynamics: Characterize the dynamic characteristics of traffic flow through vehicle speed distribution Headway Comprehensive representation;

[0092] The model is represented as:

[0093] ;

[0094] in, represents the traffic density, Represents the vehicle dynamic characteristics, Indicates time changes, represents the spatial gradient change, Indicates the change of traffic density;

[0095] As a macroscopic traffic flow model, its core goal is to describe the overall evolution of traffic flow (congestion propagation, bottleneck effects), rather than the individual behavior of microscopic vehicles. Traffic density and vehicle dynamic characteristics, as macroscopic state variables, can effectively represent data in traffic flow parameters, such as:

[0096] exist Adding dynamic congestion propagation factor with direction correction in the model ;

[0097] Initial congestion propagation factor The acquisition process is:

[0098] From floating vehicles (taxis, online ride-hailing) Extract real-time trajectory data from the device, including timestamp, longitude and latitude coordinates, and instantaneous speed;

[0099] Eliminate abnormal points of instantaneous speed mutation in real-time trajectory data (vehicle speed changes from plummeted to invalid data) and positioning drift points (such as coordinates that exceed the road boundary);

[0100] For low frequency The data (30 seconds / time) is interpolated using cubic spline to generate high-precision continuous (time resolution improved to 1 second) trajectory data;

[0101] Based on real-time trajectory data, the congestion zone boundary is identified to obtain the congestion zone length:

[0102] Calculation of congestion belt length changes: Calculation of adjacent time windows Change in congestion zone length (expansion / contraction) within 5 minutes :

[0103] ;

[0104] in, Indicates time The length of the congestion zone when Indicates time Elapsed time window The length of the congestion zone after Indicates time The end of the congestion zone, Indicates time The starting point of the congestion zone, Indicates time Elapsed time window The end of the congestion zone, Indicates time Elapsed time window The starting point of the congestion zone after

[0105] Congestion determination: Mark the trajectory segments where the vehicle speed is continuously lower than the threshold (20KM / h) and record their starting time and end time ;

[0106] Spatial positioning: Map GPS coordinates to road network lanes through map matching to determine the starting point of the congestion zone and end point ;

[0107] The calculation process of the initial congestion propagation factor is: , represents the initial congestion propagation factor;

[0108] based on Technology (vehicle wireless communication technology) obtains improved spatial autoregressive model for initial congestion propagation factor Make direction corrections to obtain dynamic congestion propagation factors The process is:

[0109] pass Technology to obtain adjacent intersections (upstream intersections) in real time and downstream intersection ) congestion index 、 , value range , the closer the value is to 1, the more serious the congestion;

[0110] For example, the upstream intersection =0.6 (moderate congestion), downstream intersection =0.8 (severe congestion), directly reflecting the congestion status of adjacent intersections and providing a macro indicator for transmission analysis;

[0111] pass Technology to obtain upstream intersections in real time and downstream intersection Lane-level traffic density 、 , traffic density is the number of vehicles per kilometer Characterize vehicle density;

[0112] For example, = , = This indicates that congestion is greater downstream;

[0113] The direction weight is obtained based on the lane-level traffic density, and the propagation direction priority is defined according to the upstream and downstream density difference. The formula is: ;

[0114] in, is the blocking density ( ), the results were normalized to ,like , is positive, congestion spreads downstream. , If it is negative, congestion develops upstream;

[0115] For example, , , calculated , reflecting that congestion downstream is more serious;

[0116] This direction priority That is, the direction weight;

[0117] If there is a traffic accident downstream, , indicating that congestion will inevitably spread downstream;

[0118] For example:

[0119] A rear-end collision occurred at an intersection, and it was actually detected , ;

[0120] General calculations: ;

[0121] Due to the accident, set it directly ,The dynamic congestion propagation factor enables the model to respond immediately to congestion propagation;

[0122] This is an intervention for special scenarios to ensure the accuracy of the model in extreme cases. For example, in the case of a downstream accident, even if the density difference calculation is not obvious, the congestion is determined to propagate downstream;

[0123] The purpose is to better fit the actual traffic scene, through Integrating information such as changes in the length of the congestion belt, the difference in traffic density between upstream and downstream, and special accident scene interventions, the subsequent improved model can dynamically adapt to different traffic conditions. For example, when an accident occurs downstream, the vehicle is forced to Reflect the propagation of congestion downstream, making the model output closer to the actual traffic flow evolution;

[0124] Based on the obtained directional weights, a spatial weight matrix is constructed ;

[0125] By direction weight Constructed spatial weight matrix Obtaining an improved spatial autoregressive model , the formula is:

[0126] ;

[0127] in, represents the initial congestion propagation factor of the local observation, represents the spatial weight matrix, represents the error term, represents the spatial autoregressive coefficient;

[0128] The initial congestion propagation factor is calculated by improving the spatial autoregressive model To make direction correction, the formula is:

[0129] ;

[0130] in, represents the symbolic function, represents the spatial autoregressive coefficient;

[0131] like , , enhance the downstream propagation effect;

[0132] like , , indicating that the congestion is traced back upstream;

[0133] Initial congestion propagation factor after direction correction That is, the dynamic congestion propagation factor;

[0134] Specifically, through integration Congestion index of adjacent intersections obtained through communication Traffic density monitored by geomagnetic coils and microwave radar , and through the direction weight Combined with the congestion index to construct a spatial weight matrix It is used to improve the traditional spatial autoregressive model by converting the spatial correlation unique to the transportation field (such as the reverse impact of downstream congestion on upstream) into matrix elements, which can be better integrated with the spatial autoregressive model and provide a new practical scenario for the application of spatial autoregressive models in traffic congestion analysis.

[0135] Dynamic Congestion Propagation Factor , added to the improved After adding the model, the model is expressed as:

[0136] ;

[0137] The model introduces a dynamic congestion propagation factor , strengthen the description of the congestion propagation law in traffic flow, and make the analysis of traffic density changes more in line with actual traffic scenarios;

[0138] By substituting the dynamic congestion propagation factor ,improve Model implementation:

[0139] Improved dynamic adaptability: From static descriptions of traffic flow to dynamic responses to congestion propagation characteristics, real-time adjustments to calculations of traffic density changes;

[0140] Enhanced scenario adaptability: Whether it is conventional congestion diffusion or special accident scenarios, the model can Correction to output results that are more consistent with the actual traffic operation status;

[0141] Specific, traditional The model is a macro traffic flow model. The core of the model is to divide the road into cells and use the traffic density to calculate the traffic flow. , vehicle speed v and other macro variables to describe the overall evolution of traffic flow, such as congestion propagation and traffic flow changes at bottlenecks;

[0142] But tradition The model does not adequately describe the dynamic characteristics of congestion propagation and does not fully consider the changes in congestion propagation speed and direction in different scenarios. It is difficult to accurately adapt to complex traffic environments, such as the rapid spread of congestion caused by downstream accidents. The dynamic congestion propagation factor The significance of substitution is mainly reflected in the improvement after direction correction. Model The core is through Quantify the impact of congestion propagation on changes in traffic density, The model integrates information such as changes in the length of the congestion belt, the difference in traffic density between upstream and downstream, and intervention in special accident scenarios, so that it can dynamically adapt to different traffic conditions. For example, when congestion spreads downstream, As the value increases, the traffic density calculated by the model changes It is more in line with the actual scenario of increased congestion.

[0143] The process of obtaining the state coefficient of each lane exit is as follows:

[0144] Calculate the terms in the model;

[0145] Traffic density Based on lane occupancy Get, let the lane length be , the number of vehicles is ,but ,in, Pass lane occupancy and the maximum number of vehicles that can be accommodated by the lane Get, that is ;

[0146] The vehicle speed v is based on the lane speed distribution The average speed is obtained;

[0147] Traffic density change It is obtained by the difference of traffic density in adjacent time steps, that is, ;

[0148] Substitute the calculated parameters and traffic flow parameters into the improved traffic flow model, and the model outputs the state coefficient of each lane exit , where i represents the road index;

[0149] Specifically, the state coefficient S integrates the calculation items of the improved CTM model and the original traffic flow parameter A. It is expressed as a multidimensional vector, and each element corresponds to the state coefficient of a lane. It can not only reflect the current congestion intensity, but also the dynamic congestion propagation factor. Predict future trends. For example, in a congestion propagation scenario, factors such as upstream and downstream traffic density differences and accident intervention can be integrated to correct the trend. , so that the state coefficient Accurately reflects the deterioration of upstream lanes due to congestion propagation. Even if the original parameters are not obviously abnormal, it can also identify potential congestion risks. This breaks through the limitations of traditional single parameter representation and truly meets the analysis needs of complex traffic scenarios.

[0150] For example:

[0151] Priority vehicle handling: When an ambulance or other priority vehicle is detected in the i-th lane, communication direct correction , improve the state coefficient of the corresponding lane ;

[0152] Congested propagation scenario:

[0153] When the downstream accident of the i-th lane causes congestion to spread upstream, Integrate upstream and downstream traffic density differences Increase, accident intervention (mandatory ) and then increase, and substitute into the improved CTM model to adjust Calculate, make It accurately reflects the deterioration of the upstream lane due to congestion propagation, and can reflect the potential congestion risk even if the original parameters are not obviously abnormal.

[0154] Signal transmission module: extracts priority order based on state coefficients and adjusts signal timing at different intersections according to the priority order;

[0155] Extract historical traffic data for different roads, including:

[0156] Traffic flow: Count the number of vehicles passing through the lane in a unit of time (vehicles / hour);

[0157] Traffic efficiency: calculate the average lane speed ;

[0158] Congestion duration ratio: Statistics of lanes with daily congestion duration Total operating time Ratio ;

[0159] The initial function weight is calculated by the weighted formula: ;

[0160] in, , is the maximum number of vehicles corresponding to the lane, is the maximum speed corresponding to the lane;

[0161] Specifically, the weight coefficient According to the traffic management goal setting, the process is:

[0162] When focusing on traffic flow diversion goals:

[0163] Emphasis on traffic flow The effect of increasing Weights, giving lanes with heavy traffic a higher priority in signal timing;

[0164] Setting process: OK , the remaining ;

[0165] distribute (traffic efficiency), (congestion relief);

[0166] Example: For a main road in a commercial street, high traffic volume is the main management target. , when calculating the initial weight, the flow right The greatest impact;

[0167] When focusing on improving traffic efficiency:

[0168] Highlight traffic speed The importance of improving Weight, to ensure the rapid passage of vehicles;

[0169] Setting process: ,but ;

[0170] distribute (flow), (congestion relief);

[0171] Example: Urban expressways, the goal is to maintain high-speed traffic, , when calculating the initial weight, the speed Results Influence dominates;

[0172] When focusing on congestion relief goals:

[0173] Pay attention to the proportion of congestion time ,promote Weight, prioritize congestion relief;

[0174] Setting process: OK ,but ;

[0175] distribute (flow), (Traffic efficiency).

[0176] Example: The roads around a school are often congested, and the management goal is to reduce congestion. When calculating the initial weight, the congestion duration ratio has an impact on the result. The greatest impact;

[0177] The priority order calculation process is:

[0178] ;

[0179] in, represents the priority coefficient of the i-th lane;

[0180] pass Get the lane priority coefficient and set the real-time status coefficient With weights based on historical data Combined, it not only considers the current lane status, but also integrates the long-term traffic characteristics and management goals, and finally Sort the signal timing priorities from high to low and perform signal timing for different intersections;

[0181] The green light duration of signal timing is distributed as follows;

[0182] Benchmark duration: (guaranteeing minimum travel time);

[0183] Flexible time pool: ;

[0184] Set a basic travel time benchmark for each intersection , ensuring minimum traffic needs;

[0185] Reserve a globally configurable elastic time pool , used to respond to real-time traffic changes;

[0186] Combined priority coefficient , for dynamic allocation: ,in, The signal timing for the i-th intersection, is the total allocation duration;

[0187] Specifically, through the green light duration allocation mode of the benchmark duration and the flexible duration pool, the benchmark duration Guaranteed minimum travel time, flexible time pool Combined priority coefficient Dynamically allocate duration , can be flexibly adjusted according to lane priority, and more accurately adapt to real-time traffic needs than fixed-cycle timing or simple proportional allocation;

[0188] Example: If the lane ,total ,but:

[0189] ;

[0190] Specifically, the example clearly demonstrates the calculation process from priority coefficient to green light duration, so that the signal timing results correspond to the lane priority.

[0191] In the application, several formulas involved are calculated by taking their numerical values after removing the dimensions, and the formulas are established by collecting a large amount of data and performing software simulation to obtain a formula for the most recent real situation. Some coefficients or weights in the formulas are set by technical personnel in this field according to actual conditions, so they will not be elaborated here.

[0192] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0193] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A signal intelligent transmission system based on smart transportation, characterized in that: include: Data acquisition module: collects traffic flow parameters of each lane, including vehicle speed distribution, lane occupancy, headway and vehicle position; State coefficient acquisition module: constructed through traffic flow parameters Model, in Improvements are achieved by introducing dynamic congestion propagation factors into the model Model, traffic flow parameters are input to improve In the model, the state coefficient of each lane exit is obtained; Priority acquisition module: 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 The initial congestion propagation factor is calculated by improving the spatial autoregressive model Perform direction correction and acquisition; The improved spatial autoregressive model is based on The technology is combined with spatial autoregressive model to obtain; The based The process of obtaining an improved spatial autoregressive model is as follows: pass Technology to obtain upstream intersections in real time and downstream intersection Congestion Index 、 ; Real-time acquisition of upstream intersections through V2X technology and downstream intersection Lane-level traffic density 、 ; Based on lane-level traffic density 、 Get direction weight; Based on the obtained directional weights, a spatial weight matrix is constructed ; By direction weight Constructing a spatial weight matrix Obtaining an improved spatial autoregressive model ; The initial congestion propagation factor is calculated by improving the spatial autoregressive model The process of direction correction is expressed as: ； in, represents the symbolic function, represents the spatial autoregressive coefficient; like , , enhance the downstream propagation effect; like , , indicating that the congestion is traced back upstream; Dynamic congestion propagation factor obtained after direction correction .

2. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The vehicle speed distribution is based on the geomagnetic coil to obtain the passing speed of a single vehicle, and the average speed and speed standard deviation in the lane are calculated as the vehicle speed distribution, which is expressed as ; The lane occupancy rate is obtained by monitoring the proportion of the time the coil is covered by the vehicle in a unit time and quantifying the actual degree of lane occupancy by the vehicle, which is expressed as ; The headway is obtained by measuring the time interval between the front and rear vehicles in the same lane passing the radar monitoring point, which is expressed as ; The vehicle position is obtained based on the time delay of electromagnetic wave reflection and the distance between the vehicle and the stop line at the intersection on the lane, which is expressed as ; The traffic flow parameters are expressed as .

3. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: described The model building process is: Based on traffic flow parameters Build a Model; Vehicle speed distribution Headway Obtaining vehicle dynamic characteristics ; Pass lane occupancy and vehicle location Get traffic density ; Based on vehicle dynamic characteristics and traffic density Build Model.

4. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The initial congestion propagation factor The acquisition process is: From the floating car Extract real-time trajectory data from the device, including timestamp, longitude and latitude coordinates, and instantaneous speed; Eliminate abnormal points of instantaneous speed mutation and positioning drift points in real-time trajectory data; Based on real-time trajectory data, congestion zone boundary identification is performed to obtain the congestion zone length; Calculate adjacent time windows Changes in the length of the congestion zone within ; Through adjacent time windows Changes in the length of the congestion zone within Get the initial congestion propagation factor .

5. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The direction weight acquisition process is as follows: Define propagation direction priority based on upstream and downstream density differences ; like , is positive, congestion spreads downstream; like , If it is negative, congestion develops upstream; Direction priority That is, the direction weight.

6. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The process of obtaining the state coefficient is as follows: Dynamic Congestion Propagation Factor Add to Improvements in the model Model; Traffic flow parameters are input into the improved In the model, the state coefficients of each lane exit are output ,in, Indicates the road index.

7. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The priority order acquisition process is: Extract historical traffic data for different roads; Historical traffic data including traffic flow , traffic efficiency and congestion duration ratio ; Obtaining initial function weights based on historical traffic data ; Based on initial feature weights and state coefficient Get the Priority coefficient of each lane .

8. The intelligent signal transmission system based on smart transportation according to claim 1 is characterized in that: The process of adjusting the signal timing of different intersections according to the priority order is as follows: Set the basic travel time benchmark duration ; Set up a globally configurable flexible time pool ; Based on time base duration and flexible time pools Combined priority coefficient Perform dynamic allocation to obtain the signal timing of the i-th intersection .

Images