CN117275260A - Emergency control method for urban road intersection entrance road traffic accident - Google Patents
Emergency control method for urban road intersection entrance road traffic accident Download PDFInfo
- Publication number
- CN117275260A CN117275260A CN202311548753.1A CN202311548753A CN117275260A CN 117275260 A CN117275260 A CN 117275260A CN 202311548753 A CN202311548753 A CN 202311548753A CN 117275260 A CN117275260 A CN 117275260A
- Authority
- CN
- China
- Prior art keywords
- intersection
- traffic accident
- traffic
- road
- entrance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 172
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000005457 optimization Methods 0.000 claims abstract description 53
- 238000011217 control strategy Methods 0.000 claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000002068 genetic effect Effects 0.000 claims abstract description 11
- 238000011144 upstream manufacturing Methods 0.000 claims description 50
- 230000006698 induction Effects 0.000 claims description 25
- 230000035772 mutation Effects 0.000 claims description 18
- 210000004027 cell Anatomy 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 210000000349 chromosome Anatomy 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 229920006395 saturated elastomer Polymers 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 8
- 230000000903 blocking effect Effects 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
- G08G1/082—Controlling the time between beginning of the same phase of a cycle at adjacent intersections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
- G08G1/083—Controlling the allocation of time between phases of a cycle
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of traffic safety strategies, and particularly relates to an urban road intersection entrance road traffic accident emergency management and control method, which comprises the following steps: acquiring traffic flow data of each lane of a road intersection by an electronic police, and calculating traffic flow standard deviation of an entrance lane; determining the traffic accident level by using a self-coding-based entrance road traffic accident identification method; establishing constraint conditions of a signal timing optimization model; establishing a corresponding emergency management and control strategy containing a signal timing optimization model according to the constraint condition in the S3 and the traffic accident level; and solving a signal timing optimization model in the emergency management and control strategy through a genetic algorithm. According to the invention, through the formulated multilevel emergency management and control strategy, the traffic running efficiency of the intersection is improved, the traffic jam caused by traffic accidents of the entrance road of the urban road intersection can be effectively relieved, and the smoothness and traffic safety of the road are ensured.
Description
Technical Field
The invention belongs to the technical field of traffic safety strategies, and particularly relates to an urban road intersection entrance road traffic accident emergency management and control method.
Background
At present, in urban road intersections, various traffic flows cross and run, so that various traffic accidents are very easy to occur in a plurality of conflict areas, and traffic jams are caused.
With the increasing development of cities, vehicles are more and more, traffic pressure is increased, and traffic accidents at intersections of the urban roads are more and more. Traffic accidents occurring at the entrance road of the urban road intersection and the like are extremely easy to cause traffic jam, and the running efficiency of the urban road intersection is seriously affected.
At present, after a traffic accident occurs at an urban road intersection, no scientific emergency treatment measures exist at present, and the problems are usually solved by the self negotiation of an owner or the treatment of traffic police, but the blocking time is uncontrollable, and long-time congestion can be caused.
Therefore, in order to reduce the blocking time of the urban road after the traffic accident, and quickly restore the operation efficiency of the intersection, an emergency management and control strategy is needed to relieve the traffic jam of the entrance road of the urban road due to the traffic accident.
Disclosure of Invention
According to the defects in the prior art, the invention provides the emergency management and control method for the traffic accidents at the entrance of the urban road intersection, which improves the traffic running efficiency of the intersection, can effectively relieve the traffic jam of the entrance of the urban road intersection caused by the traffic accidents, and ensures the smoothness and the traffic safety of the road.
In order to achieve the above purpose, the invention provides an urban road intersection entrance road traffic accident emergency control method, which comprises the following steps:
s1, acquiring traffic flow data of each lane of a road intersection through an electronic police, and calculating traffic flow standard deviation of an entrance lane;
s2, determining a traffic accident level by using a self-coding-based entrance road traffic accident identification method, wherein the self-coding-based entrance road traffic accident identification method comprises the following steps:
s21, extracting an inlet lane traffic flow standard deviation feature vector in the S1 through an encoder;
s22, reconstructing the feature vector of the S21 by using a decoder;
s23, calculating the mean square error of the reconstruction data and the input current period data, and calculating the mean square error of all periods;
s24, determining a threshold value, and identifying the traffic accident level of the entrance road according to the threshold value;
s3, establishing constraint conditions of a signal timing optimization model;
s4, establishing a corresponding emergency management and control strategy containing a signal timing optimization model according to the constraint condition in the S3 and the traffic accident level;
and S5, solving a signal timing optimization model in the emergency management and control strategy through a genetic algorithm.
In the step S1, the method for calculating the traffic flow standard deviation of the entrance lane comprises the following steps:
taking 5min as a period, counting traffic flow data of each lane by an electronic police, calculating a traffic flow average value according to traffic flow of each lane within 5min, and further calculating an inlet lane flow standard deviation, wherein the calculation formula is as follows:
；
wherein: sigma (sigma) j The standard deviation of traffic flow of the entrance lane is n, the number of the entrance lanes is i, i is the ith entrance lane, j is the jth period, Q ij The traffic flow of the ith entrance lane of the jth period, Q j Is the average value of traffic flow of the inlet lane in the j-th period.
According to the basic principle of statistics, the traffic accident judgment threshold is determined according to the three sigma criterion.
In the step S24, the specific method for identifying the traffic accident level of the entrance road according to the threshold value is that the mean square error of the reconstructed data and the input current period data is calculated and compared with the mean square error of all the periods:
a. normal, no traffic accident: less than 90% quantiles of the mean square error for all time periods;
b. first-level traffic accident: 90% quantiles of the mean square error of all time periods are more than or equal to, and less than 95% quantiles of the mean square error of all time periods;
c. secondary traffic accident: 95% quantiles of the mean square error of all time periods are larger than or equal to, and 99% quantiles of the mean square error of all time periods are smaller than;
d. three-stage traffic accident: 99% quantiles of mean square error of all time periods or more.
In the step S3, the established constraint conditions are as follows:
s31, shortest green lamp time constraint:
；
wherein: g min For the shortest green lamp time, L p For the width of crosswalk at intersection, V P The average speed of the pedestrian crossing is that I is the green light time interval;
in the manual for controlling urban road traffic signals, the shortest green light time of the straight traffic flow is regulated to be not less than 15s, the straight phase of the secondary road is regulated to be not less than 12s, and the special phase of left turn is regulated to be not less than 8s.
S32, saturation constraint:
；
wherein: x is X k,l Saturation for k-phase l lane group; q k The traffic flow actually reached by the k phase in one period; c is the signal period duration; s is S k,l Saturated flow rate for k-phase l lane group; g k Is the effective green time of k phase;
s33, constraint of period duration:
；/>；
wherein C is A The period duration of the traffic accident intersection A; c (C) B The period duration of the intersection B at the upstream of the traffic accident intersection; c (C) Min Setting the minimum period duration to 90s; c (C) Max For the maximum period duration, 180s is set.
When each level of emergency control strategy is set, the first level of emergency control strategy is to set up a signal timing optimization scheme with minimum delay as a target; the secondary emergency control strategy is a signal timing optimization scheme established by taking the minimum number of upstream input vehicles as a target on the basis of the primary emergency control strategy; the third-level emergency management and control strategy is to implement path induction based on the second-level emergency management and control strategy, and construct a signal control and path induction cooperative strategy.
In the step S4, aiming at the primary traffic accident, the minimum delay of the traffic accident phase is taken as an optimization target, the green light time without the traffic accident phase is sacrificed, the green light time of the traffic accident phase is adjusted in the constraint condition of the step S3, and the blocked vehicles are evacuated in time, so that a signal timing optimization model of the primary emergency management and control strategy is established as follows:
；
；
wherein: d, d k,l The average delay for k-phase/lane group, units s/pcu (pcu is equivalent traffic); lambda (lambda) k,l Green-to-signal ratio for k-phase l lane group; t is the duration of the traffic accident, in s; CAP k,l For the traffic capacity of the k-phase l lane group, the unit pcu/h, e is a correction coefficient of a single intersection signal control type, and the timing signal takes e=0.5; g Ak The effective green light time of k phases of the traffic accident intersection A; g Max The maximum green time was set to 60s.
In the step S4, aiming at the secondary traffic accident, the step of establishing a signal timing optimization model of a secondary emergency management and control strategy is as follows:
s421, adopting a signal timing optimization model of a primary emergency management and control strategy to perform signal timing optimization on the traffic accident intersection;
s422, under the constraint condition of S3, signal timing optimization is carried out on the traffic accident intersection by taking the shortest green time of the relevant phase of the upstream intersection of the traffic accident intersection as an optimization target, and the signal timing optimization model of the upstream intersection of the traffic accident intersection is as follows:
；
；
wherein: k is the intersection ofThe sum of the effective green light time of the related phases of the intersection at the upstream of the accident intersection; g Bs The effective green time of the relevant straight-going phase of the intersection B at the upstream intersection of the traffic accident is given by a unit s; g Bz The effective green time of the relevant left-turning phase of the intersection B at the upstream intersection of the traffic accident is given by a unit s; g Bk Is the effective green time of k phase of the upstream intersection B of the traffic accident intersection, in s.
In the step S4, aiming at the three-level traffic accident, path induction is carried out on the basis of a two-level emergency management and control strategy, and a three-level emergency management and control strategy combining signal control and path induction is constructed, specifically:
s431, setting an L criterion: defining the length of a road section between two adjacent intersections as 1 cell, wherein the L-shaped rule indicates that after a traffic accident occurs in an entrance road of a certain intersection, the upstream intersection of the intersection is L1, and the upstream intersection of the upstream intersection is named L2 because the length of the road section away from the traffic accident intersection is 2 cells;
s432, establishing an induction screen system induction method: after three-level traffic accidents occur, the induction screen at the upstream L2 intersection displays that the traffic accident intersection is blocked, traffic accident information is provided for a driver, the driver actively changes a driving route after acquiring the information, the input of the traffic accident intersection is reduced, and the dredging pressure of the intersection is reduced;
s434, establishing an intelligent path induction method: after the traffic accident of the entrance road of the intersection is identified, starting from the traffic accident road section, searching for the affected vehicles in the road section with the length of 2 cells along the reverse traffic flow direction, and firstly selecting the vehicles needing to change the driving route from the upstream road section directly connected with the traffic accident road section; then selecting vehicles needing to change the driving route from the road sections connected with the upstream road sections, and sequentially carrying out the steps;
the vehicle navigation system is used for directionally sending warning information to the searched vehicles to prompt a driver to have traffic accidents in front, and the driver is required to plan a route again; meanwhile, an optimized route is provided according to the information of the positions, the destinations and the like of the vehicles, so that a certain number of vehicles change the driving route, and the purpose of relieving traffic jam of the traffic accident road section is achieved.
In the step S5, the step of solving through a genetic algorithm is as follows:
s51, setting initial parameters as population scale x, crossover probability, mutation probability and evolution algebra t;
s52, performing chromosome coding, and adopting a floating point number coding method, wherein the coding length of an individual is equal to the bit number of a decision variable in a signal timing optimization model;
s53, setting a fitness function to enable the green light time g to be effective in k phases k As optimization variables, the average delay minimum value of the intersection k-phase/lane group and the minimum value of the effective green time of the intersection related phase at the upstream of the traffic accident intersection are solved, and the fitness function formula is as follows:
，/>；
wherein: d (D) k,l 、For the fitness function, d is respectively k,l Inverse of K;
s54, selecting, namely selecting a random selection method as a selection operator, randomly selecting an individual according to probability, wherein the probability of the individual with high fitness being selected is larger, and a probability calculation formula is as follows:
；
wherein: z is the z-th individual; x is the number of population individuals; f (F) z Fitness for individual z; w (W) z Probability of being selected for individual z;
s55, crossing, namely dividing gene sequences of two individuals into a plurality of parts through a plurality of random positions by adopting a multipoint crossing method, and then exchanging the parts to generate new individuals;
s56, performing mutation, namely introducing a nonlinear mutation probability function in mutation operation by adopting non-uniform mutation, so that the mutation probability is reduced along with the increase of iteration times, and the convergence of an algorithm is improved;
and S57, setting an evolution termination condition, setting the maximum evolution algebra as G, and when the iteration times meet the condition of t=G, setting the optimal solution based on the genetic algorithm as an individual with the highest fitness value in the population, and finally, performing individual decoding to obtain a signal timing optimization scheme.
The algorithm related to the present invention may be executed by an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the algorithm being implemented by the processor executing the program.
The invention has the beneficial effects that:
the invention firstly sets the traffic accident identification method suitable for the entrance way of the urban road intersection, can effectively identify the traffic accident of the entrance way of the intersection and determine the traffic accident level, then establishes the corresponding emergency management and control strategy comprising the signal timing optimization model according to the traffic accident level, can effectively implement emergency management and control on the traffic accident of the urban road intersection, and more fully utilizes space-time resources.
The invention provides a scientific and effective post-treatment measure for traffic accidents at the entrance of the urban road intersection, and achieves the aim of reducing the influence degree of the traffic accidents through a formulated multilevel emergency management and control strategy; not only can traffic accidents of the entrance road of the urban road intersection be processed more rapidly, but also different emergency management and control strategies can be adopted for traffic accidents of different severity grades, so that space-time resources of the intersection are utilized more fully; the traffic accident handling efficiency is improved, the blocking time of the intersection is reduced, the traveling experience of residents is improved, the urban road traffic safety environment is improved, and the urban intersection can operate more efficiently, scientifically and effectively.
Drawings
FIG. 1 is a flow chart of a method of the emergency management and control strategy of the present invention;
FIG. 2 is a schematic diagram of a method for implementing a multi-level emergency management and control strategy in an embodiment of the present invention;
FIG. 3 is a flow chart of a path induction strategy in an embodiment of the invention;
FIG. 4 is a flow chart of a method of genetic algorithm solution in an embodiment of the invention.
Detailed Description
Embodiments of the invention are further described below with reference to the accompanying drawings:
the invention adopts scientific and effective post-hoc remedial measures aiming at the traffic accidents of the entrance road of the intersection, and adopts corresponding emergency management and control strategies according to different traffic accident levels of the identification and judgment. The intersection can be restored to operate more quickly, and the congestion is relieved.
As shown in fig. 1, the emergency control method for the traffic accident at the entrance of the urban road intersection comprises the following steps:
s1, acquiring traffic flow data of each lane of a road intersection through an electronic police, and calculating traffic flow standard deviation of an entrance lane;
s2, determining a traffic accident level by using a self-coding-based entrance road traffic accident identification method, wherein the self-coding-based entrance road traffic accident identification method comprises the following steps:
s21, extracting an inlet lane traffic flow standard deviation feature vector in the S1 through an encoder;
s22, reconstructing the feature vector of the S21 by using a decoder;
s23, calculating the mean square error of the reconstruction data and the input current period data, and calculating the mean square error of all periods;
s24, determining a threshold value, and identifying the traffic accident level of the entrance road according to the threshold value;
the specific method for identifying the traffic accident level of the entrance road according to the threshold value comprises the steps of calculating the mean square error of the reconstruction data and the input data of the current period, and comparing the mean square error with the mean square error of all periods:
a. normal, no traffic accident: less than 90% quantiles of the mean square error for all time periods;
b. first-level traffic accident: 90% quantiles of the mean square error of all time periods are more than or equal to, and less than 95% quantiles of the mean square error of all time periods;
c. secondary traffic accident: 95% quantiles of the mean square error of all time periods are larger than or equal to, and 99% quantiles of the mean square error of all time periods are smaller than;
d. three-stage traffic accident: 99% quantiles of mean square error of all time periods or more.
S3, establishing constraint conditions of a signal timing optimization model;
s4, establishing a corresponding emergency management and control strategy containing a signal timing optimization model according to the constraint condition in the S3 and the traffic accident level;
and S5, solving a signal timing optimization model in the emergency management and control strategy through a genetic algorithm.
The electronic police equipment can identify license plates, record vehicle information and the like, so that the invention adopts the electronic police data to extract traffic flow parameters.
In S1, the method for calculating the traffic flow standard deviation of the entrance lane comprises the following steps:
taking 5min as a period, counting traffic flow data of each lane by an electronic police, calculating a traffic flow average value according to traffic flow of each lane within 5min, and further calculating an inlet lane flow standard deviation, wherein the calculation formula is as follows:
；
wherein: sigma (sigma) j The standard deviation of traffic flow of the entrance lane is n, the number of the entrance lanes is i, i is the ith entrance lane, j is the jth period, Q ij The traffic flow of the ith entrance lane of the jth period, Q j Is the average value of traffic flow of the inlet lane in the j-th period.
Before the signal timing optimization model of the urban road intersection entrance road traffic accident emergency management and control strategy is established, basic constraint conditions need to be established for the signal timing optimization model in order to avoid the extremely unreasonable condition of intersection signal control.
In S3, the established constraint conditions are as follows:
s31, the shortest green lamp time constraint needs to meet the street crossing requirements of pedestrians and non-motor vehicles. The shortest green lamp time at the intersection is therefore designed as follows:
；
wherein: g min For the shortest green lamp time, L p For the width of crosswalk at intersection, V P The average speed of the pedestrian crossing is that I is the green light time interval;
s32, saturation constraint, wherein the phase saturation represents the ratio of traffic flow to traffic capacity actually reached by the phase, and the saturation of the traffic accident-free phase is required to be ensured to meet the requirement on the premise of ensuring the maximum traffic capacity of a lane group where traffic accidents are located, so that the saturation is controlled to be 0.7-0.9, and the saturation constraint can be represented as:
；
wherein: x is X k,l Saturation for k-phase l lane group; q k The traffic flow actually reached by the k phase in one period; c is the signal period duration; s is S k,l Saturated flow rate for k-phase l lane group; g k Is the effective green time of k phase;
s33, constraint of period duration, wherein the traffic accident intersection and the upstream intersection adopt the same signal period, and the period duration of the traffic accident intersection and the upstream intersection is between the minimum period duration and the maximum period duration, which can be expressed as:
；/>；
wherein C is A The period duration of the traffic accident intersection A; c (C) B The period duration of the intersection B at the upstream of the traffic accident intersection; c (C) Min Setting the minimum period duration to 90s; c (C) Max For the maximum period duration, 180s is set.
The traffic accidents with different severity degrees can be fully utilized by adopting emergency management and control measures with different grades, and after the constraint conditions of the signal timing optimization model in the emergency management and control strategy are established, the invention establishes a three-level emergency management and control strategy according to the constraint conditions. The third-level emergency control strategy is not independent of each other, as shown in fig. 2, the first-level emergency control strategy is used for optimizing signal timing of the traffic accident intersection, the second-level emergency control strategy is used for providing an upstream intersection signal timing optimization method on the basis of the first-level emergency control strategy, and the third-level emergency control strategy is used for further providing a path induction scheme on the basis of the second-level emergency control strategy.
According to the road traffic capability manual, the average delay at a planar intersection can be expressed as the sum of the vehicle uniform delay and the random additional delay. The invention provides a signal timing optimization model which aims at minimizing traffic accident phase delay by combining a primary emergency management and control strategy with an average delay calculation method of a plane intersection.
In S4, aiming at the primary traffic accident, taking the minimum delay of the traffic accident phase as an optimization target, sacrificing the green time without the traffic accident phase, adjusting the green time of the traffic accident phase in the constraint condition of S3, and timely evacuating the blocked vehicles, thereby establishing a signal timing optimization model of the primary emergency management and control strategy as follows:
；
；
wherein: d, d k,l Average delay in k-phase/lane group, units s/pcu; lambda (lambda) k,l Green-to-signal ratio for k-phase l lane group; t is the duration of the traffic accident, in s; CAP k,l For the traffic capacity of the k-phase l lane group, the unit pcu/h, e is a correction coefficient of a single intersection signal control type, and the timing signal takes e=0.5; g Ak Effective green light for k phase of traffic accident intersection ATime; g Max The maximum green time was set to 60s.
On one hand, the traffic capacity of the phase of the traffic accident of the intersection is improved by maximizing the green light time of the phase of the traffic accident of the intersection; on the other hand, on the basis that the saturation of each phase of the upstream intersection is controlled to be 0.7-0.9, the green light time of the relevant phase is minimized by adopting the upstream intersection, and the vehicle input to the traffic accident intersection is reduced.
In order to ensure that overflow cannot occur on a road section where a traffic accident intersection is connected with an upstream intersection, the invention takes the shortest green time of the relevant phase of the upstream intersection as the optimal target to control the number of vehicles entering an entrance road of the traffic accident intersection. Therefore, in S4, the step of establishing the signal timing optimization model of the second-level emergency management and control strategy for the second-level traffic accident is as follows:
s421, adopting a signal timing optimization model of a primary emergency management and control strategy to perform signal timing optimization on the traffic accident intersection;
s422, under the constraint condition of S3, signal timing optimization is carried out on the traffic accident intersection by taking the shortest green time of the relevant phase of the upstream intersection of the traffic accident intersection as an optimization target, and the signal timing optimization model of the upstream intersection of the traffic accident intersection is as follows:
；
；
wherein: k is the sum of effective green light time of the related phases of the intersection at the upstream of the traffic accident intersection; g Bs The effective green time of the relevant straight-going phase of the intersection B at the upstream intersection of the traffic accident is given by a unit s; g Bz The effective green time of the relevant left-turning phase of the intersection B at the upstream intersection of the traffic accident is given by a unit s; g Bk Is the effective green time of k phase of the upstream intersection B of the traffic accident intersection, in s.
According to the invention, after the traffic accident is fully identified, a path induction strategy is designed aiming at the traffic accident with three-level severity. The third-level emergency control strategy is to implement path induction based on the second-level emergency control strategy, and construct a cooperative strategy of signal control and path induction.
S4, aiming at the three-level traffic accident, carrying out path induction on the basis of a two-level emergency management and control strategy, and constructing a three-level emergency management and control strategy with cooperative signal control and path induction, wherein the three-level emergency management and control strategy specifically comprises the following steps:
s431, setting an L criterion: defining the length of a road section between two adjacent intersections as 1 cell, wherein the L-shaped rule indicates that after a traffic accident occurs in an entrance road of a certain intersection, the upstream intersection of the intersection is L1, and the upstream intersection of the upstream intersection is named L2 because the length of the road section away from the traffic accident intersection is 2 cells;
s432, establishing an induction screen system induction method: after three-level traffic accidents occur, the induction screen at the upstream L2 intersection displays that the traffic accident intersection is blocked, traffic accident information is provided for a driver, the driver actively changes a driving route after acquiring the information, the input of the traffic accident intersection is reduced, and the dredging pressure of the intersection is reduced;
s434, establishing an intelligent path induction method: after the traffic accident of the entrance road of the intersection is identified, starting from the traffic accident road section, searching for the affected vehicles in the road section with the length of 2 cells along the reverse traffic flow direction, and firstly selecting the vehicles needing to change the driving route from the upstream road section directly connected with the traffic accident road section; then selecting vehicles needing to change the driving route from the road sections connected with the upstream road sections, and sequentially carrying out the steps;
the vehicle navigation system is used for directionally sending warning information to the searched vehicles to prompt a driver to have traffic accidents in front, and the driver is required to plan a route again; meanwhile, an optimized route is provided according to the information of the position, the destination and the like of the vehicle, and a specific route guidance implementation process is shown in fig. 3. When the driver is notified, the vehicle navigation system and the like can calculate the alternative paths and select whether to change the paths, so that a certain number of vehicles change the driving route, and the purpose of relieving traffic jam of the traffic accident road section is achieved.
As shown in fig. 4, in S5, the step of solving by the genetic algorithm is:
s51, setting initial parameters as population scale x, crossover probability, mutation probability and evolution algebra t;
s52, performing chromosome coding, and adopting a floating point number coding method, wherein the coding length of an individual is equal to the bit number of a decision variable in a signal timing optimization model;
s53, setting a fitness function to enable the green light time g to be effective in k phases k As optimization variables, the average delay minimum value of the intersection k-phase/lane group and the minimum value of the effective green time of the intersection related phase at the upstream of the traffic accident intersection are solved, and the fitness function formula is as follows:
，/>；
wherein: d (D) k,l 、For the fitness function, d is respectively k,l Inverse of K;
s54, selecting, namely selecting a random selection method as a selection operator, randomly selecting an individual according to probability, wherein the probability of the individual with high fitness being selected is larger, and a probability calculation formula is as follows:
；
wherein: z is the z-th individual; x is the number of population individuals; f (F) z Fitness for individual z; w (W) z Probability of being selected for individual z;
s55, crossing, namely dividing gene sequences of two individuals into a plurality of parts through a plurality of random positions by adopting a multipoint crossing method, and then exchanging the parts to generate new individuals;
s56, performing mutation, namely introducing a nonlinear mutation probability function in mutation operation by adopting non-uniform mutation, so that the mutation probability is reduced along with the increase of iteration times, and the convergence of an algorithm is improved;
and S57, setting an evolution termination condition, setting the maximum evolution algebra as G, and when the iteration times meet the condition of t=G, setting the optimal solution based on the genetic algorithm as an individual with the highest fitness value in the population, and finally, performing individual decoding to obtain a signal timing optimization scheme.
Claims (8)
1. The urban road intersection entrance road traffic accident emergency control method is characterized by comprising the following steps of:
s1, acquiring traffic flow data of each lane of a road intersection through an electronic police, and calculating traffic flow standard deviation of an entrance lane;
s2, determining a traffic accident level by using a self-coding-based entrance road traffic accident identification method, wherein the self-coding-based entrance road traffic accident identification method comprises the following steps:
s21, extracting an inlet lane traffic flow standard deviation feature vector in the S1 through an encoder;
s22, reconstructing the feature vector of the S21 by using a decoder;
s23, calculating the mean square error of the reconstruction data and the input current period data, and calculating the mean square error of all periods;
s24, determining a threshold value, and identifying the traffic accident level of the entrance road according to the threshold value;
s3, establishing constraint conditions of a signal timing optimization model;
s4, establishing a corresponding emergency management and control strategy containing a signal timing optimization model according to the constraint condition in the S3 and the traffic accident level;
and S5, solving a signal timing optimization model in the emergency management and control strategy through a genetic algorithm.
2. The urban road intersection entrance road traffic accident emergency management and control method according to claim 1, wherein the method comprises the following steps: in the step S1, the method for calculating the traffic flow standard deviation of the entrance lane comprises the following steps:
taking 5min as a period, counting traffic flow data of each lane by an electronic police, calculating a traffic flow average value according to traffic flow of each lane within 5min, and further calculating an inlet lane flow standard deviation, wherein the calculation formula is as follows:
；
wherein: sigma (sigma) j The standard deviation of traffic flow of the entrance lane is n, the number of the entrance lanes is i, i is the ith entrance lane, j is the jth period, Q ij The traffic flow of the ith entrance lane of the jth period, Q j Is the average value of traffic flow of the inlet lane in the j-th period.
3. The urban road intersection entrance road traffic accident emergency management and control method according to claim 1, wherein the method comprises the following steps: in the step S24, the specific method for identifying the traffic accident level of the entrance road according to the threshold value is that the mean square error of the reconstructed data and the input current period data is calculated and compared with the mean square error of all the periods:
a. normal, no traffic accident: less than 90% quantiles of the mean square error for all time periods;
b. first-level traffic accident: 90% quantiles of the mean square error of all time periods are more than or equal to, and less than 95% quantiles of the mean square error of all time periods;
c. secondary traffic accident: 95% quantiles of the mean square error of all time periods are larger than or equal to, and 99% quantiles of the mean square error of all time periods are smaller than;
d. three-stage traffic accident: 99% quantiles of mean square error of all time periods or more.
4. The urban road intersection entrance road traffic accident emergency management and control method according to claim 3, wherein the method comprises the following steps: in the step S3, the established constraint conditions are as follows:
s31, shortest green lamp time constraint:
；
wherein: g min For the shortest green lamp time, L p For the width of crosswalk at intersection, V P The average speed of the pedestrian crossing is that I is the green light time interval;
s32, saturation constraint:
；
wherein: x is X k,l Saturation for k-phase l lane group; q k The traffic flow actually reached by the k phase in one period; c is the signal period duration; s is S k,l Saturated flow rate for k-phase l lane group; g k Is the effective green time of k phase;
s33, constraint of period duration:
；/>；
wherein C is A The period duration of the traffic accident intersection A; c (C) B The period duration of the intersection B at the upstream of the traffic accident intersection; c (C) Min Setting the minimum period duration to 90s; c (C) Max For the maximum period duration, 180s is set.
5. The urban road intersection entrance road traffic accident emergency management and control method according to claim 4, wherein the method comprises the following steps: in the step S4, aiming at the primary traffic accident, the minimum delay of the traffic accident phase is taken as an optimization target, the green light time without the traffic accident phase is sacrificed, the green light time of the traffic accident phase is adjusted in the constraint condition of the step S3, and the blocked vehicles are evacuated in time, so that a signal timing optimization model of the primary emergency management and control strategy is established as follows:
；
；
wherein: d, d k,l Average delay in k-phase/lane group, units s/pcu; lambda (lambda) k,l Green-to-signal ratio for k-phase l lane group; t is the duration of the traffic accident, in s; CAP k,l For the traffic capacity of the k-phase l lane group, the unit pcu/h, e is a correction coefficient of a single intersection signal control type, and the timing signal takes e=0.5; g Ak The effective green light time of k phases of the traffic accident intersection A; g Max The maximum green time was set to 60s.
6. The urban road intersection entrance road traffic accident emergency management and control method according to claim 5, wherein the method comprises the following steps: in the step S4, aiming at the secondary traffic accident, the step of establishing a signal timing optimization model of a secondary emergency management and control strategy is as follows:
s421, adopting a signal timing optimization model of a primary emergency management and control strategy to perform signal timing optimization on the traffic accident intersection;
s422, under the constraint condition of S3, signal timing optimization is carried out on the traffic accident intersection by taking the shortest green time of the relevant phase of the upstream intersection of the traffic accident intersection as an optimization target, and the signal timing optimization model of the upstream intersection of the traffic accident intersection is as follows:
；
；
wherein: k is the sum of effective green light time of the related phases of the intersection at the upstream of the traffic accident intersection; g Bs Effective green light time for relevant straight-going phase of intersection B at upstream intersection of traffic accidentUnits s; g Bz The effective green time of the relevant left-turning phase of the intersection B at the upstream intersection of the traffic accident is given by a unit s; g Bk Is the effective green time of k phase of the upstream intersection B of the traffic accident intersection, in s.
7. The urban road intersection entrance road traffic accident emergency management and control method according to claim 6, wherein the method comprises the following steps: in the step S4, aiming at the three-level traffic accident, path induction is carried out on the basis of a two-level emergency management and control strategy, and a three-level emergency management and control strategy combining signal control and path induction is constructed, specifically:
s431, setting an L criterion: defining the length of a road section between two adjacent intersections as 1 cell, wherein the L-shaped rule indicates that after a traffic accident occurs in an entrance road of a certain intersection, the upstream intersection of the intersection is L1, and the upstream intersection of the upstream intersection is named L2 because the length of the road section away from the traffic accident intersection is 2 cells;
s432, establishing an induction screen system induction method: after three-level traffic accidents occur, the induction screen at the upstream L2 intersection displays that the traffic accident intersection is blocked, traffic accident information is provided for a driver, the driver actively changes a driving route after acquiring the information, the input of the traffic accident intersection is reduced, and the dredging pressure of the intersection is reduced;
s434, establishing an intelligent path induction method: after the traffic accident of the entrance road of the intersection is identified, starting from the traffic accident road section, searching for the affected vehicles in the road section with the length of 2 cells along the reverse traffic flow direction, and firstly selecting the vehicles needing to change the driving route from the upstream road section directly connected with the traffic accident road section; then selecting vehicles needing to change the driving route from the road sections connected with the upstream road sections, and sequentially carrying out the steps;
the vehicle navigation system is used for directionally sending warning information to the searched vehicles to prompt a driver to have traffic accidents in front, and the driver is required to plan a route again; meanwhile, an optimized route is provided according to the information of the positions, the destinations and the like of the vehicles, so that a certain number of vehicles change the driving route, and the purpose of relieving traffic jam of the traffic accident road section is achieved.
8. The urban road intersection entrance road traffic accident emergency management and control method according to claim 7, wherein the method comprises the following steps: in the step S5, the step of solving through a genetic algorithm is as follows:
s51, setting initial parameters as population scale x, crossover probability, mutation probability and evolution algebra t;
s52, performing chromosome coding, and adopting a floating point number coding method, wherein the coding length of an individual is equal to the bit number of a decision variable in a signal timing optimization model;
s53, setting a fitness function to enable the green light time g to be effective in k phases k As optimization variables, the average delay minimum value of the intersection k-phase/lane group and the minimum value of the effective green time of the intersection related phase at the upstream of the traffic accident intersection are solved, and the fitness function formula is as follows:
，/>；
wherein: d (D) k,l 、For the fitness function, d is respectively k,l Inverse of K;
s54, selecting, namely selecting a random selection method as a selection operator, randomly selecting an individual according to probability, wherein the probability of the individual with high fitness being selected is larger, and a probability calculation formula is as follows:
；
wherein: z is the z-th individual; x is the number of population individuals; f (F) z Fitness for individual z; w (W) z Probability of being selected for individual z;
s55, crossing, namely dividing gene sequences of two individuals into a plurality of parts through a plurality of random positions by adopting a multipoint crossing method, and then exchanging the parts to generate new individuals;
s56, performing mutation, namely introducing a nonlinear mutation probability function in mutation operation by adopting non-uniform mutation, so that the mutation probability is reduced along with the increase of iteration times, and the convergence of an algorithm is improved;
and S57, setting an evolution termination condition, setting the maximum evolution algebra as G, and when the iteration times meet the condition of t=G, setting the optimal solution based on the genetic algorithm as an individual with the highest fitness value in the population, and finally, performing individual decoding to obtain a signal timing optimization scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311548753.1A CN117275260B (en) | 2023-11-21 | 2023-11-21 | Emergency control method for urban road intersection entrance road traffic accident |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311548753.1A CN117275260B (en) | 2023-11-21 | 2023-11-21 | Emergency control method for urban road intersection entrance road traffic accident |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117275260A true CN117275260A (en) | 2023-12-22 |
| CN117275260B CN117275260B (en) | 2024-02-02 |
Family
ID=89218023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311548753.1A Active CN117275260B (en) | 2023-11-21 | 2023-11-21 | Emergency control method for urban road intersection entrance road traffic accident |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117275260B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080133136A1 (en) * | 1997-10-22 | 2008-06-05 | Intelligent Technologies International, Inc. | Intersection Collision Avoidance Techniques |
| CN101251953A (en) * | 2008-04-03 | 2008-08-27 | 同济大学 | Unsymmetrical space-time optimizing control method for rotary intersection |
| CN103680127A (en) * | 2013-08-29 | 2014-03-26 | 中国科学院地理科学与资源研究所 | A method for calculating signal lamp control road intersection delays through the utilization of low sampling rate floating vehicle data |
| CN205564050U (en) * | 2016-04-14 | 2016-09-07 | 山东理工大学 | Crossroad turns right vehicle and keeps away and hit device based on bus or train route in coordination |
| CN108470444A (en) * | 2018-03-21 | 2018-08-31 | 特斯联（北京）科技有限公司 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
| US20210201672A1 (en) * | 2018-03-22 | 2021-07-01 | Hefei Gelv Information Technology Co., Ltd. | Video-based main road cooperative signal machine control method |
| CN116994428A (en) * | 2023-07-05 | 2023-11-03 | 山东理工大学 | Intersection entrance road traffic accident identification method based on parameter change rate |
-
2023
- 2023-11-21 CN CN202311548753.1A patent/CN117275260B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080133136A1 (en) * | 1997-10-22 | 2008-06-05 | Intelligent Technologies International, Inc. | Intersection Collision Avoidance Techniques |
| CN101251953A (en) * | 2008-04-03 | 2008-08-27 | 同济大学 | Unsymmetrical space-time optimizing control method for rotary intersection |
| CN103680127A (en) * | 2013-08-29 | 2014-03-26 | 中国科学院地理科学与资源研究所 | A method for calculating signal lamp control road intersection delays through the utilization of low sampling rate floating vehicle data |
| CN205564050U (en) * | 2016-04-14 | 2016-09-07 | 山东理工大学 | Crossroad turns right vehicle and keeps away and hit device based on bus or train route in coordination |
| CN108470444A (en) * | 2018-03-21 | 2018-08-31 | 特斯联（北京）科技有限公司 | A kind of city area-traffic big data analysis System and method for based on genetic algorithm optimization |
| US20210201672A1 (en) * | 2018-03-22 | 2021-07-01 | Hefei Gelv Information Technology Co., Ltd. | Video-based main road cooperative signal machine control method |
| CN116994428A (en) * | 2023-07-05 | 2023-11-03 | 山东理工大学 | Intersection entrance road traffic accident identification method based on parameter change rate |
Non-Patent Citations (2)
| Title |
|---|
| 廖诗琪;汪云龙;: "单点交叉口交通信号配时模型及遗传算法", 公路与汽运, no. 03 * |
| 肖文妮;: "基于VISSIM的城市道路交通信号配时优化", 兰州工业学院学报, no. 06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117275260B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971566B (en) | Self-adaptive control method based on genetic algorithm | |
| CN104134356B (en) | Control method of city intersection model reference self-adaptive signals | |
| CN107393319B (en) | Signal optimization control method for preventing single cross port queuing overflow | |
| CN105046956A (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN111238521A (en) | Path planning method and system for unmanned vehicle | |
| CN106558226B (en) | Signal lamp timing evaluation and real-time adjustment method | |
| CN103150911A (en) | Method for optimizing signal timing of single intersection based on genetic algorithm | |
| CN109544922B (en) | Traffic network distributed predictive control method based on region division | |
| CN111126687B (en) | Single-point offline optimization system and method for traffic signals | |
| CN104916142A (en) | Adaptive intersection traffic signal control method of trunk road priority | |
| CN103198648A (en) | Self-adaption dispatching method used for public traffic system | |
| CN113780624B (en) | Urban road network signal coordination control method based on game equilibrium theory | |
| LU503042B1 (en) | Multi-model learning particle swarm-based intelligent city signal light timing optimization method | |
| CN113421439B (en) | Single intersection traffic signal timing optimization method based on Monte Carlo algorithm | |
| WO2021238189A1 (en) | Lane allocation method for single-point signal intersection | |
| CN111524345B (en) | Induction control method for multi-objective optimization under constraint of real-time queuing length of vehicle | |
| Odeh | Hybrid algorithm: fuzzy logic-genetic algorithm on traffic light intelligent system | |
| CN112950934A (en) | Road congestion reason identification method | |
| CN112562363B (en) | Intersection traffic signal optimization method based on V2I | |
| CN117275260B (en) | Emergency control method for urban road intersection entrance road traffic accident | |
| CN104809890A (en) | Traffic signal timing optimization method based on principal component analysis and local search improvement orthogonality genetic algorithm | |
| CN114120670A (en) | Method and system for traffic signal control | |
| Tamimi et al. | Intelligent traffic light based on genetic algorithm | |
| CN113506442A (en) | Urban road network traffic signal lamp control method based on expected income estimation | |
| CN106600990B (en) | Dynamic signal lamp evaluation method and system based on genetic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |