CN111862600A - Traffic efficiency assessment method based on vehicle-road cooperation - Google Patents
Traffic efficiency assessment method based on vehicle-road cooperation Download PDFInfo
- Publication number
- CN111862600A CN111862600A CN202010575980.3A CN202010575980A CN111862600A CN 111862600 A CN111862600 A CN 111862600A CN 202010575980 A CN202010575980 A CN 202010575980A CN 111862600 A CN111862600 A CN 111862600A
- Authority
- CN
- China
- Prior art keywords
- road
- vehicle
- index
- traffic efficiency
- traffic
- 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.)
- Pending
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Strategic Management (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a traffic efficiency assessment method based on vehicle-road cooperation, which aims at the problems that the urban road traffic efficiency based on the vehicle-road cooperative organization lacks a comprehensive system effective and quantitative assessment method in the development of the vehicle networking technology and the promotion of the vehicle-road cooperative application, establishes an urban road traffic efficiency assessment index system, and provides a comprehensive assessment method of a hierarchical analysis-BP neural network, and the specific steps are as follows: 1. establishing an intersection efficiency evaluation index of a vehicle road cooperative organization; 2. preprocessing evaluation index data; 3. determining the weight of the evaluation index based on a multi-level analysis method; 4. and establishing a BP neural network model to comprehensively evaluate the traffic state and efficiency. The method provided by the invention has the characteristics of science, comprehensiveness and conciseness, and can be used for objectively evaluating the traffic efficiency of the vehicle-road cooperative organization.
Description
Technical Field
The invention belongs to the technical field of road traffic efficiency assessment, and particularly relates to a traffic efficiency assessment method based on vehicle-road cooperation.
Background
Along with the continuous increase of the automobile holding rate of cities, the traffic load is also continuously increased, so that the traffic accident rate is high, the traffic jam condition is more serious, the traffic efficiency is influenced, the environment is polluted, the energy is wasted, the living quality of residents is reduced, and the travel cost of the residents is improved. With the emergence of the car networking and car road cooperation technology, real-time information interaction is carried out by improving a road information diversified extraction mode in a complex traffic flow environment, collision can be effectively avoided, congestion is relieved, and traffic efficiency is improved. With the implementation of the strong national traffic strategy and the acceleration of new construction in China, a 5G and C-V2X intelligently fused vehicle-road cooperative system is rapidly deployed on urban roads, particularly at urban road intersections in complex traffic states, however, traffic efficiency improvement and traffic state improvement brought by the vehicle-road cooperative system are not systematically and effectively evaluated, and a series of problems brought by the characteristics of the vehicle-road cooperative system also influence the performance of the traffic system to a certain extent.
The ultimate goal of traffic organization under the cooperation of the vehicle and the road is to realize the safe and real-time communication between vehicles and between vehicles and roadside equipment; the traffic control equipment is in seamless connection with the vehicle, and the traffic safety, efficiency, emission, oil consumption and riding comfort level can reach the comprehensive optimal level. In the intersection based on the cooperative organization of the vehicle and the road, the traffic efficiency is the degree of satisfaction of the input of traffic related resources on traffic service levels such as traffic safety degree, road service level, road network traffic capacity, resident trip comfort and the like. The traffic efficiency is regarded as one of the important performances of the vehicle-road cooperative system in the traffic environment, and is more and more valued by domestic and foreign scholars and automobile researchers. At present, most of researches are conducted on traffic efficiency in urban common environments, traffic efficiency conditions in a vehicle-road cooperative environment are rarely evaluated, complete theoretical support is not provided, evaluation indexes are not comprehensive, and the evaluation indexes are single.
With the continuous deepening of the vehicle-road cooperation research, the application requirements of the vehicle networking are more urgent, so that an intersection traffic efficiency evaluation index system and a comprehensive evaluation method of the vehicle-road cooperation organization need to be established, the influence of key indexes of the vehicle-road cooperation system is considered, the traffic efficiency of different instances of the system under the vehicle-road cooperation environment is evaluated, and the evaluation is used for guiding the construction of the vehicle-road cooperation system.
Disclosure of Invention
In order to solve the technical problem, the invention provides a traffic efficiency evaluation method based on vehicle-road cooperation, which comprises the following steps:
s1: comprehensively and comprehensively selecting traffic efficiency evaluation indexes, selecting urban roads with the vehicle-road cooperative system, acquiring historical data of traffic flow parameters of the urban roads, and establishing a traffic efficiency evaluation index system of a vehicle-road cooperative organization;
s2: carrying out dimensionless standardization preprocessing on the traffic efficiency indexes to establish a standardization matrix;
s3: constructing a multi-index decision model of a three-layer structure of a target layer, a criterion layer and an index layer based on an analytic hierarchy process, establishing a judgment matrix, and obtaining the relative weight of each index based on the relative importance degree of each parameter of the index layer;
s4: determining the structural parameters of the BP neural network for comprehensive evaluation, constructing a BP neural network model, training the BP neural network model to obtain a traffic efficiency evaluation model for evaluating the cooperative organization of the vehicle and the road, and realizing the quantitative evaluation of the traffic efficiency.
Preferably, the urban road selection comprises three levels of intersections, road sections and road networks, and comprehensive selection is performed from different micro and macro angles and different directions according to the traffic efficiency evaluation requirement.
Preferably, the traffic efficiency evaluation index may be an intersection evaluation index such as an average delay of a signalized intersection, an average delay of a non-signalized intersection, an average saturation of an intersection, an average overload capacity of an intersection, and a turning flow of an intersection, or may be a road section evaluation index such as an average delay time of a road section, an average delay ratio of a road section, an average number of stops of a road section, an average stop time of a road section, an average density of a road section, an average speed of a road section, and an average flow of a road section, or a road network evaluation index such as an average travel time of a road network, a maximum number of vehicles queued in a road network, a collision situation of vehicles in a road network, a.
Preferably, the dimensionless normalization of the evaluation index is performed by building an mxn matrix with different dimensions and different indexes, and the original data matrix is X ═ (X ═ Xij)m×bWherein x isijFor the j evaluation index raw data in the i evaluation dimension, let xijHas a maximum value ofjMinimum value of bjThe normalized data matrix is Y ═ Yij)m×nAnd for output type indexFor input type index
Preferably, the multi-index decision-making model with a three-layer structure of a target layer, a criterion layer and an index layer is constructed based on an analytic hierarchy process, wherein the target layer is the overall traffic efficiency, the criterion layer is the intersection traffic efficiency, the road section traffic efficiency and the road network traffic efficiency, and the index layer is the traffic efficiency evaluation index.
Preferably, the method for establishing the judgment matrix is to establish the element B of the previous level based on a multi-index decision model established by an analytic hierarchy processkAs a criterion, comparing the importance of each index in the next layer, introducing a proper scale value to represent, and using CijIndicates the relative importance of the i index and the j index, Cij>0,Cij=1(i=1,2,...,n),Cij=1/Cji(i ≠ j), a decision matrix scale value is defined to identify the relationship of importance of each index.
Preferably, the step of calculating, by the determination matrix, a weight value of an index that each layer dominates the next layer is: firstly, the product of each row element in the judgment matrix is calculated as MiWherein(i ═ 1, 2,. n); recalculating MiRoot of cubic (n times) For vectorIs normalized, whereinThe value of the weight in the upper criteria is indexed for that i.
Preferably, the quantitative evaluation of the traffic efficiency is to analyze relevant factors of specific efficiency under the cooperation of the vehicle and the road, and determine parameters of the comprehensively evaluated input node, hidden layer node and output node of the BP neural network structure, wherein the number of the input nodes is the number of evaluation indexes established in step S1, and the number of the output nodes is the number of final traffic efficiency evaluation parameters.
Preferably, the training data set of the BP neural network model is traffic data acquired in step S1, the training algorithm selects a bayesian regularization algorithm, and the BP neural network model for evaluating urban road traffic efficiency of the vehicle-road cooperative organization is obtained based on forward and reverse training and accuracy requirement injection.
Preferably, the BP neural network model is injected with traffic road operation data, and the traffic road operation data can be directly used for traffic efficiency evaluation.
The invention has the beneficial effects that: the weight coefficient and the evaluation result of the evaluation index are determined based on an analytic hierarchy process, the data after standardization processing is used as an input parameter, the obtained evaluation result is used as an expected value to be output, a BP neural network model is trained, the obtained training result can obtain a result more conveniently, and the method can be directly used for evaluating the traffic efficiency of a vehicle-road cooperative organization.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a schematic diagram of a multi-index decision model according to the present invention;
FIG. 3 is a schematic diagram of a decision matrix according to the present invention;
FIG. 4 is a graph of the relationship of the importance of the indicators of the present invention;
FIG. 5 is a schematic diagram of the traffic efficiency of the present invention;
FIG. 6 is a smaller-scale road network diagram of embodiment 1 of the present invention;
FIG. 7 is a larger-scale road network graph according to embodiment 1 of the present invention;
fig. 8 is a schematic view of a traffic efficiency evaluation result of a smaller-scale road network according to embodiment 1 of the present invention;
fig. 9 is a schematic diagram illustrating a traffic efficiency evaluation result of a large-scale road network according to embodiment 1 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention is further described below:
as shown in fig. 1, a traffic efficiency assessment method based on vehicle-road cooperation includes:
s1: comprehensively and comprehensively selecting a traffic efficiency evaluation index, selecting an urban road with a car-road cooperative system deployed in a certain urban car networking pilot area, and acquiring a plurality of sets of traffic flow parameter historical data and real-time data, wherein the selection of the urban road comprises three levels of intersections, road sections and road networks, so that comprehensive and comprehensive analysis from a microscopic angle to a macroscopic angle is realized; the traffic flow parameter data comprise traffic volume, speed and density, delay, time headway, time occupancy, saturated headway and lost time, and meanwhile, system characteristic parameters such as positioning error, communication delay and permeability are used as influence factors for evaluating the traffic efficiency of the intersection based on the characteristics of the vehicle-road cooperative system, and an intersection efficiency evaluation index system of vehicle-road cooperative organization is established;
S2: carrying out dimensionless standardization pretreatment on the traffic efficiency index, wherein the dimensionless standardization treatment mode of the evaluation index is to establish an m multiplied by n matrix by using different dimensions and different indexes, and the original data matrix is X ═ X (X)ij)m×nWherein x isijFor the j evaluation index raw data in the i evaluation dimension, let xijHas a maximum value ofjMinimum value of bjThe normalized data matrix is Y ═ Yij)m×nAnd for output type indexFor input type index
S3: as shown in fig. 2, a multi-index decision model with a three-layer structure of a target layer, a criterion layer and an index layer is constructed based on an analytic hierarchy process, wherein the target layer is traffic efficiency of the whole traffic scene, the criterion layer is intersection traffic efficiency, road section traffic efficiency and road network traffic efficiency, and the index layer is a traffic efficiency evaluation index; wherein the target layer has a domination relation to the intersection traffic efficiency, the road section traffic efficiency and the road network traffic efficiency of the criterion layer, and similarly, the intersection traffic efficiency, the road section traffic efficiency and the road network traffic efficiency of the criterion layer have a domination relation to each index of the lower layer, as shown in fig. 3, a judgment matrix is established through a relatively important relation between the dominated indexes, and the establishment method of the judgment matrix is based on a hierarchy layer intersection traffic efficiency, road section traffic efficiency and road network traffic efficiency The multi-index decision model established by the analytical method is used for converting the element B of the previous layerkAs a criterion, comparing the importance of each index in the next layer, introducing a proper scale value to represent, and using CijIndicates the relative importance of the i index and the j index, Cij>0,Cij=1(i=1,2,...,n),Cij=1/Cji(i ≠ j), defining the scale values of a judgment matrix, as shown in fig. 4, identifying the relationship of the importance of each index, establishing the relative weight of each parameter of the index layer, and obtaining the relative weight of each total index, wherein the step of calculating the weight value of the index dominated by each layer to the next layer by the judgment matrix is as follows: firstly, the product of each row element in the judgment matrix is calculated as MiWherein(i ═ 1, 2,. n); recalculating MiRoot of cubic (n times) For vector Is normalized, whereinThe weight value of the i index in the upper-level criterion is shown in figure 5, so that the weight value of each level of traffic efficiency is established;
s4: analyzing relevant factors of specific efficiency under vehicle-road cooperation, determining comprehensively evaluated BP neural network structure input nodes, hidden layer nodes and output node parameters, wherein the number of the input nodes is the number of the evaluation indexes established in the step S1, the number of the output nodes is the number of the final traffic efficiency evaluation parameters, constructing a neural network model, training the BP neural network model, a training data set of the BP neural network model is traffic data flow data collected in the step S1, the training algorithm selects a Bayesian regularization algorithm, and the BP neural network model for evaluating urban road traffic efficiency evaluation of the vehicle-road cooperative organization is obtained by injecting traffic road operation data based on forward and reverse training and precision requirements, wherein the traffic road operation data is injected into the BP neural network model and can be directly used for traffic efficiency evaluation and is based on vehicle-road cooperative characteristic parameters and different traffic characteristics, and realizing quantitative evaluation on traffic efficiency.
Specifically, the traffic efficiency evaluation index may be an intersection evaluation index such as an average delay of a signalized intersection, an average delay of a non-signalized intersection, an average saturation of an intersection, an average overload capacity of an intersection, and an intersection turning flow, or may be a road section evaluation index such as an average delay time of a road section, an average delay ratio of a road section, an average number of stops of a road section, an average stop time of a road section, an average density of a road section, an average speed of a road section, and an average flow of a road section, or a road section evaluation index such as an average travel time of a road network, a maximum number of queued vehicles of a road network, a collision situation of vehicles of a road network, a maximum queuing.
Specifically, according to the established traffic efficiency assessment index system, the input node is set to be 19; the method mainly researches traffic efficiency as an evaluation result and outputs nodes as 1 based on an empirical optimization relation of hidden layer nodes and input and output nodes, builds a BP neural network model based on Matlab, injects a plurality of groups of obtained training samples and expected value output values into the model, and operates by using a Bayesian regularization algorithm.
Specifically, for sample data, forward propagation training is performed firstly, the sample data is transmitted into an input layer, a hidden layer and an output layer, if an actual output value of the output layer is not consistent with an expected value, the backward propagation training is continued, errors are transmitted into each layer in a backward direction, weights of units of each layer are corrected, a multidimensional mapping scheme is used, accuracy requirements are injected through the model, function information is excited, training is performed, and therefore a successfully trained BP neural network model is obtained.
Specifically, the BP neural network model established by the invention inputs road data, realizes the traffic efficiency evaluation of the vehicle-road cooperative organization, and the traffic state under the vehicle-road cooperative system meets the following requirements:
(1) and (3) intersection: under the cooperative vehicle-road system, the signalized intersection can maximally utilize the green time, the non-signalized intersection can timely identify the traffic condition of the intersection, early warning can be timely carried out, and collision is avoided.
(2) Road section: the self-adaptive speed control can be carried out based on the road surface state, the road congestion can be identified in time, the traffic accident can be avoided, and early warning decisions such as following, lane changing and the like can be carried out in time.
(3) Road network: the traffic flow control can be carried out, early warning can be timely provided for vehicles under the condition of local congestion, and new path planning can be carried out.
Specifically, the control strategy of the intersection and the road section in the vehicle-road cooperative environment is as follows: when the vehicle enters the range of the intersection detector at the signalized intersection, the roadside device detects that the distance between the vehicle and the stop line is S, t1 seconds remain in the green light time, the time when the vehicle passes the stop line when accelerating to the specified maximum speed is calculated to be t2, and if t2<t1, the roadside device sends information to the vehicle, the vehicle can pass through the intersection at the highest speed, the vehicle accelerates at the moment, and the vehicle passes through the intersection before the green light is finished; if t2>t1, the roadside device sends a message to the vehicle informing the vehicle to decelerate uniformly to the stop line, and on a certain road section, the front vehicle A is in V shapeaAt speed, rear vehicle B at VbSpeed running when Va>VbAnd the early warning distance is the distance required when the vehicle A decelerates to the speed of the vehicle B, and when the distance between the two vehicles reaches the early warning distance, the vehicle A receives early warning information and decelerates in time to follow the vehicle.
Example 1
Two road networks with different scales are established according to the number of the road intersections, as shown in figure 6, the first road network is a small-scale road network formed by 9 intersections, as shown in figure 7, and the second road network is a larger-scale road network formed by a plurality of intersections. As shown in the attached figures 8 and 9, for a small-scale road network, the total flow of selected areas is 2160vehicles/h, 2880vehicles/h, 3610vehicles/h, 4330vehicles/h, 5040vehicles/h and 7910vehicles/h for traffic efficiency evaluation; for a large-scale road network, the total flow of selected areas is 2640vehicles/h, 3960vehicles/h, 5280vehicles/h, 6590 vehicles/h, 7910vehicles/h and 9210vehicles/h, traffic efficiency evaluation is carried out, obtained evaluation index data are subjected to standardization processing, an obtained standardization matrix is analyzed by a trained BP neural network model, and the traffic efficiency of roads of a non-vehicle road cooperative organization is compared. In road networks of different scales, quantitative evaluation data can be obtained based on the evaluation method provided by the invention, the traffic efficiency under the vehicle-road cooperative system is generally higher than that under the common system, and meanwhile, the degree of improving the traffic efficiency by the vehicle-road cooperative system is more obvious when the traffic flow in the road network is increased.
It should be noted that, in this document, moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A traffic efficiency assessment method based on vehicle-road cooperation is characterized by comprising the following steps:
s1: comprehensively and comprehensively selecting traffic efficiency evaluation indexes, selecting urban roads with the vehicle-road cooperative system, acquiring historical data of traffic flow parameters of the urban roads, and establishing a traffic efficiency evaluation index system of a vehicle-road cooperative organization;
s2: carrying out dimensionless standardization preprocessing on the traffic efficiency indexes to establish a standardization matrix;
S3: constructing a multi-index decision model of a three-layer structure of a target layer, a criterion layer and an index layer based on an analytic hierarchy process, establishing a judgment matrix, and obtaining the relative weight of each index based on the relative importance degree of each parameter of the index layer;
s4: analyzing relevant factors of specific efficiency under vehicle-road cooperation, determining structural parameters of a BP neural network for comprehensive evaluation, constructing a BP neural network model, training the BP neural network model to obtain a traffic efficiency evaluation model for evaluating vehicle-road cooperative organization, and realizing quantitative evaluation of traffic efficiency.
2. The traffic efficiency assessment method based on vehicle-road cooperation according to claim 1, wherein the urban road is selected from three levels of intersections, road sections and road networks, and the urban road is comprehensively selected from different angles in micro and macro and in different directions according to the traffic efficiency assessment requirements.
3. The method as claimed in claim 2, wherein the traffic efficiency evaluation index may be an intersection evaluation index such as an average delay of a signalized intersection, an average saturation of an intersection, an average overload capacity of an intersection, and an intersection turning flow, or may be a road network evaluation index such as an average delay time of a road section, an average delay ratio of a road section, an average number of stops of a road section, an average stop time of a road section, an average density of a road section, an average speed of a road section, and an average flow of a road section, or a road network evaluation index such as an average travel time of a road network, a maximum number of queued vehicles of a road network, a collision situation of vehicles of a road network, a maximum queuing length of a road network, and a degree of smooth traffic network.
4. The traffic efficiency assessment method based on vehicle-road coordination according to claim 1, characterized in that the assessment index is dimensionless standardizedThe processing mode is to establish an m × n matrix with different dimensions and different indexes, and the original data matrix is X ═ X (X)ij)m×nWherein x isijFor the j evaluation index raw data in the i evaluation dimension, let xijHas a maximum value ofjMinimum value of bjThe normalized data matrix is Y ═ Yij)m×nAnd for output type indexFor input type index
5. The traffic efficiency assessment method based on vehicle-road cooperation according to claim 1, wherein a multi-index decision model with a three-layer structure of a target layer, a criterion layer and an index layer is constructed based on an analytic hierarchy process, wherein the target layer is the overall traffic efficiency, the criterion layer is the intersection traffic efficiency, the road section traffic efficiency and the road network traffic efficiency, and the index layer is the traffic efficiency assessment index.
6. The method as claimed in claim 1, wherein the decision matrix is created by applying a multi-index decision model created by a hierarchical analysis method to the element B of the previous levelkAs a criterion, comparing the importance of each index in the next layer, introducing a proper scale value to represent, and using C ijIndicates the relative importance of the i index and the j index, Cij>0,Cij=1(i=1,2,...,n),Cij=1/Cji(i ≠ j), a decision matrix scale value is defined to identify the relationship of importance of each index.
7. The method as claimed in claim 6, wherein the judgment matrix is used to calculate the next layer of each layer pairThe steps of the weight value of the dominant indicator are: firstly, the product of each row element in the judgment matrix is calculated as MiWhereinRecalculating MiRoot of cubic (n times)For vectorIs normalized, whereinThe value of the weight in the upper criteria is indexed for that i.
8. The traffic efficiency assessment method based on vehicle-road coordination according to claim 1, wherein the analysis of the relevant factors of specific efficiency under vehicle-road coordination determines the parameters of the input nodes, hidden layer nodes and output nodes of the BP neural network structure under comprehensive evaluation, wherein the number of the input nodes is the number of the assessment indexes established in step S1, and the number of the output nodes is the number of the final traffic efficiency assessment parameters.
9. The traffic efficiency assessment method based on vehicle-road coordination according to claim 1, wherein the training data set of the BP neural network model is traffic data flow data collected in step S1, the training algorithm selects a Bayesian regularization algorithm, and traffic road operation data is injected based on forward and reverse training and accuracy requirements to obtain the BP neural network model for assessing urban road traffic efficiency assessment of the vehicle-road coordination organization.
10. The traffic efficiency assessment method based on vehicle-road coordination according to claim 9, wherein the traffic road operation data is injected into the BP neural network model and can be directly used for traffic efficiency assessment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010575980.3A CN111862600A (en) | 2020-06-22 | 2020-06-22 | Traffic efficiency assessment method based on vehicle-road cooperation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010575980.3A CN111862600A (en) | 2020-06-22 | 2020-06-22 | Traffic efficiency assessment method based on vehicle-road cooperation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111862600A true CN111862600A (en) | 2020-10-30 |
Family
ID=72988056
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010575980.3A Pending CN111862600A (en) | 2020-06-22 | 2020-06-22 | Traffic efficiency assessment method based on vehicle-road cooperation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111862600A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112614344A (en) * | 2020-12-14 | 2021-04-06 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
CN113112790A (en) * | 2021-03-09 | 2021-07-13 | 华东师范大学 | Urban road operation situation monitoring method combined with knowledge graph |
CN114120638A (en) * | 2021-11-09 | 2022-03-01 | 北京航空航天大学 | Intersection traffic condition evaluation element extraction method based on hierarchical decoupling |
CN114708746A (en) * | 2022-04-01 | 2022-07-05 | 河北金锁安防工程股份有限公司 | Traffic signal prompting method and system for smart city |
CN115689259A (en) * | 2023-01-04 | 2023-02-03 | 交通运输部公路科学研究所 | Method, device, equipment and medium for determining road section, vehicle and road collaborative scene priority |
CN116107915A (en) * | 2023-04-14 | 2023-05-12 | 国汽(北京)智能网联汽车研究院有限公司 | Quantification method and device for safety controllability index of vehicle expressway cruising function |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
CN102708677A (en) * | 2012-05-30 | 2012-10-03 | 杭州师范大学 | Traffic state evaluation rule extracting method based on rough set theory |
CN103606266A (en) * | 2013-06-28 | 2014-02-26 | 长沙理工大学 | Road network traffic improvement scheme efficiency evaluation method based on data envelope analysis |
CN107591004A (en) * | 2017-11-01 | 2018-01-16 | 中原智慧城市设计研究院有限公司 | A kind of intelligent traffic guidance method based on bus or train route collaboration |
-
2020
- 2020-06-22 CN CN202010575980.3A patent/CN111862600A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101604479A (en) * | 2009-07-14 | 2009-12-16 | 北京交通大学 | The evaluation method of service level of plane signal intersection under mixed traffic environment |
CN102708677A (en) * | 2012-05-30 | 2012-10-03 | 杭州师范大学 | Traffic state evaluation rule extracting method based on rough set theory |
CN103606266A (en) * | 2013-06-28 | 2014-02-26 | 长沙理工大学 | Road network traffic improvement scheme efficiency evaluation method based on data envelope analysis |
CN107591004A (en) * | 2017-11-01 | 2018-01-16 | 中原智慧城市设计研究院有限公司 | A kind of intelligent traffic guidance method based on bus or train route collaboration |
Non-Patent Citations (1)
Title |
---|
张立爽: "车路协同系统交通仿真环境构建及效率评估方法", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112614344A (en) * | 2020-12-14 | 2021-04-06 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
CN112614344B (en) * | 2020-12-14 | 2022-03-29 | 中汽研汽车试验场股份有限公司 | Hybrid traffic system efficiency evaluation method for automatic driving automobile participation |
CN113112790A (en) * | 2021-03-09 | 2021-07-13 | 华东师范大学 | Urban road operation situation monitoring method combined with knowledge graph |
CN113112790B (en) * | 2021-03-09 | 2023-04-18 | 华东师范大学 | Urban road operation situation monitoring method combined with knowledge graph |
CN114120638A (en) * | 2021-11-09 | 2022-03-01 | 北京航空航天大学 | Intersection traffic condition evaluation element extraction method based on hierarchical decoupling |
CN114708746A (en) * | 2022-04-01 | 2022-07-05 | 河北金锁安防工程股份有限公司 | Traffic signal prompting method and system for smart city |
CN115689259A (en) * | 2023-01-04 | 2023-02-03 | 交通运输部公路科学研究所 | Method, device, equipment and medium for determining road section, vehicle and road collaborative scene priority |
CN116107915A (en) * | 2023-04-14 | 2023-05-12 | 国汽(北京)智能网联汽车研究院有限公司 | Quantification method and device for safety controllability index of vehicle expressway cruising function |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111862600A (en) | Traffic efficiency assessment method based on vehicle-road cooperation | |
CN108198415B (en) | A kind of city expressway accident forecast method based on deep learning | |
CN108364467B (en) | Road condition information prediction method based on improved decision tree algorithm | |
CN108109382B (en) | Congestion point, congestion line and congestion area discovery method based on composite network | |
CN103413263B (en) | Travel time index entropy traffic circulation evaluation method | |
CN111861274A (en) | Water environment risk prediction and early warning method | |
CN108492557A (en) | Highway jam level judgment method based on multi-model fusion | |
CN106205156A (en) | A kind of crossing self-healing control method for the sudden change of part lane flow | |
CN106887141B (en) | Queuing theory-based continuous traffic node congestion degree prediction model, system and method | |
CN110979342B (en) | Working condition information acquisition method for vehicle global energy management control | |
CN113837446B (en) | Airport land side area traffic situation prediction method based on multi-source heterogeneous data | |
CN107180534B (en) | The express highway section average speed estimation method of support vector regression fusion | |
CN108682149A (en) | The linear causation analysis method in highway accident stain section based on binary logistic regression | |
CN112509328B (en) | Method for analyzing conflict behavior of intersection right-turning motor vehicle and electric bicycle | |
CN106021902B (en) | A kind of stage division for urban track traffic for passenger flow congestion index | |
CN104851287A (en) | Method for urban road link travel time detection based on video detector | |
CN106651181A (en) | Bus passenger flow congestion risk evaluation method under network operation condition | |
CN105869398A (en) | Road traffic open degree judging method based on K-means cluster | |
CN103646533B (en) | Traffic accident modeling and control method based on sparse multi-output regression | |
CN111907523B (en) | Vehicle following optimizing control method based on fuzzy reasoning | |
CN112926768A (en) | Ground road lane-level traffic flow prediction method based on space-time attention mechanism | |
CN116597642A (en) | Traffic jam condition prediction method and system | |
CN116050742A (en) | Intelligent scheduling configuration method and system for shared vehicle operation and maintenance personnel | |
CN113642162B (en) | Urban road traffic emergency plan simulation comprehensive analysis method | |
CN109147320B (en) | Road section traffic state discrimination method based on checkpoint data |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201030 |
|
RJ01 | Rejection of invention patent application after publication |