CN117746626A - Intelligent traffic management method and system based on traffic flow - Google Patents
Intelligent traffic management method and system based on traffic flow Download PDFInfo
- Publication number
- CN117746626A CN117746626A CN202311742862.7A CN202311742862A CN117746626A CN 117746626 A CN117746626 A CN 117746626A CN 202311742862 A CN202311742862 A CN 202311742862A CN 117746626 A CN117746626 A CN 117746626A
- Authority
- CN
- China
- Prior art keywords
- road condition
- traffic
- traffic flow
- historical
- condition evaluation
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 30
- 238000011156 evaluation Methods 0.000 claims abstract description 91
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000012544 monitoring process Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims description 34
- 238000012360 testing method Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 230000004308 accommodation Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 206010039203 Road traffic accident Diseases 0.000 abstract description 12
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of traffic management, and particularly discloses an intelligent traffic management method based on traffic flow, which comprises the following steps: firstly, collecting historical traffic flow data of a monitoring area in a specific time period; then, the road section vehicle information parameters monitored by the historical monitoring images of the congested road sections are retrieved in real time, state prediction analysis is carried out on the road section vehicle information parameters, road condition change information is estimated, and historical road condition estimation coefficients are obtained; finally, inputting the historical traffic flow data into a traffic prediction model to obtain a predicted road condition evaluation coefficient, comparing and analyzing the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient, and carrying out early warning according to an analysis result to inform and adjust the traffic running state in advance; the invention combines the traffic flow change analysis and the intelligent traffic management method to predict and analyze the next road condition in advance, thereby reducing the occurrence probability of traffic jams and traffic accidents.
Description
Technical Field
The invention relates to the technical field of traffic management, in particular to an intelligent traffic management method and system based on traffic flow.
Background
With the development of high and new technologies such as big data, cloud computing, internet of things and the like, some developed countries actively develop research on intelligent traffic system projects, aim to create a more intelligent and informationized traffic management system, improve the management level of traffic departments and provide a better traffic environment for daily life travel of people; the intelligent traffic system has important application value in improving the intelligent management level of traffic departments and improving the road traffic environment.
As the quantity of the automobile is continuously increased, the automobile exceeds the bearable capacity of most roads, and the problems of road traffic jams, traffic accidents, environmental pollution and the like are increasingly serious; the existing intelligent traffic information management system can improve the occurrence probability of traffic jam and traffic accident as much as possible, but can not directly predict errors according to the change of traffic flow, so that the problems of increasing the traffic jam road section and continuously increasing the traffic pressure caused by further predicting and evaluating the change of the following road condition in advance are solved.
Disclosure of Invention
The invention aims to provide an intelligent traffic management method and system based on traffic flow, which solve the following technical problems:
how to combine the traffic flow variation analysis and the intelligent traffic management method to predict and analyze the next road condition in advance, thereby reducing the occurrence probability of traffic jams and traffic accidents.
The aim of the invention can be achieved by the following technical scheme:
an intelligent traffic management method based on traffic flow, the method comprising:
s1, collecting historical traffic flow data of a monitoring area in a specific time period;
s2, acquiring road section vehicle information parameters monitored by a historical monitoring image of the congested road section in real time, carrying out state prediction analysis on the road section vehicle information parameters, evaluating road condition change information, and acquiring a historical road condition evaluation coefficient;
s3, inputting the historical traffic flow data into a traffic prediction model to obtain a predicted road condition evaluation coefficient, comparing the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and performing early warning according to an analysis result.
Preferably, the state prediction analysis process in step S2 is:
evenly dividing the acquisition time of the monitoring image information into n different time periods, and counting the number of the traffic flow of the congested road section in any different time periodAccording to f i Wherein i is [1, n ]]；
Traffic flow data f i And a corresponding preset interval [ f ] A ，f B ]F, comparing A 、f B Are all experience constants;
if f i Is greater than a preset interval f A ，f B ]Judging that the traffic flow is greater than a critical state, and generating early warning information;
if f i Is smaller than a preset interval [ f ] A ，f B ]Judging that the traffic flow is not in a critical state and the road condition is stable;
if f i In a preset interval [ f A ，f B ]And if the traffic flow reaches the critical state, judging the traffic flow to be in the critical state, and carrying out road condition evaluation analysis.
Preferably, the road condition evaluation analysis is:
according to the formula:acquiring road condition evaluation coefficient R hi Wherein->A monotonically increasing conversion function, k being a time period selected from the total time periods n, and k > 1; m is the completion of vehicle speed from V within a selected period of time max Down to V min The quantity of road vehicles in the process of (a) is accumulated to be accommodated; m is M 0 To complete the vehicle speed from V within a selected period of time max Down to V min The road section vehicle quantity in the process of (a) accumulates the accommodation quantity standard value; />Is that f i to f k An arithmetic mean of (a); />Is a vehicle information deviation coefficient.
Preferably, the road condition evaluation analysis process includes:
estimating the road condition evaluation coefficient R hi And a preset interval [ R ] i low，R i up]Comparing the sizes:
when R is hi ∈[R i low，P i up]Judging that the road condition state changes greatly, and outputting the current road condition evaluation coefficient as a historical road condition evaluation coefficient;
when R is hi ＜R i When the road condition state is low, judging that the road condition state is less in change, and keeping the current running state;
when R is hi ＞R i And when the road condition is up, judging that the road condition state is extremely changed, and generating early warning information.
Preferably, the establishing process of the traffic prediction model in the step S3 is as follows:
s31, collecting historical traffic flow of a plurality of time periods of a monitoring area, selecting traffic flow data of corresponding time periods of each congestion road section, and generating a training set and a testing set;
s32, building a model by using a circulating neural network, training the model by using a vehicle flow training set, testing the trained model by using a test set, and adjusting iteration times according to test errors;
s33, repeating the step S32, fitting the training set again, adjusting the test error to a smaller combined model, and turning to the step S32 when the test error result is bigger;
s34, outputting an estimated predicted value.
Preferably, the formula of the predicted value is:
calculating to obtain a traffic flow prediction coefficient P f The method comprises the steps of carrying out a first treatment on the surface of the Wherein maxf (t) and minf (t) respectively represent a maximum value parameter and a minimum value parameter of the historical vehicle flow in a certain time period; f (f) imt (t) a deviation parameter value representing a historical vehicle flow rate over a certain period of time; θ is a prediction coefficient.
Preferably, the prediction coefficient P is based on the vehicle flow f The method for obtaining the predicted road condition evaluation coefficient is as follows:
by the formula R pred ＝τ*P f Calculating a predicted road condition evaluation coefficient R pred Wherein τ is the road condition conversion coefficient.
Preferably, in the step S3, the comparison and analysis process is as follows:
the road condition prediction evaluation coefficient R pred And historical road condition evaluation coefficient R hi And (3) performing comparison:
if R is pred ≥R hi Sending out an early warning signal; adjusting the traffic flow;
otherwise, the operation is continued.
An intelligent traffic management system based on traffic flow, the system comprising:
the data acquisition module is used for acquiring historical traffic flow data of the monitoring area in a specific time period;
the real-time monitoring module is used for retrieving road section vehicle information parameters monitored by the historical monitoring images of the congested road sections in real time;
the analysis module is used for carrying out state prediction analysis on road section vehicle information parameters, evaluating road condition change information and obtaining historical road condition evaluation coefficients;
the traffic prediction model is used for obtaining a predicted road condition evaluation coefficient according to the historical traffic flow data;
the comparison module is used for comparing and analyzing the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient;
the early warning module is used for sending early warning information when the traffic flow state of the monitoring vehicle is not in accordance with the requirements, the road condition evaluation analysis result is not in accordance with the requirements and the comparison analysis result is not in accordance with the requirements;
and the information synchronization module is used for synchronizing the vehicle and the road condition traffic information to the query platform in real time.
The invention has the beneficial effects that: according to the method, road section vehicle information parameters monitored by a historical monitoring image of a congested road section are retrieved in real time, state prediction analysis is carried out, road condition change information is estimated, and a historical road condition estimation coefficient is obtained; inputting the historical traffic flow data into a traffic prediction model, and calculating to obtain a predicted road condition evaluation coefficient; the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient are used; the traffic critical accommodation amount is timely adjusted by adjusting the road condition change under the current monitoring state, so that traffic accidents are avoided, and the larger influence of traffic jams on the next traffic flow is reduced; the occurrence of serious congestion is reduced through the advanced diversion and guiding of the traffic flow, the deceleration reminding, the traffic light time adjustment and the like, the traffic running efficiency is improved, and the occurrence probability of traffic accidents is reduced.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a step diagram of a traffic flow-based intelligent traffic management method according to the present invention;
FIG. 2 is a block diagram of the intelligent traffic management system based on traffic flow according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
At present, although the development of many mature software can monitor road conditions in real time, most of the software adopts vehicle navigation or GPS positioning to carry out information data feedback, but the instability in the link transmission process easily causes data loss when depending on a vehicle-mounted system, and the inaccuracy of the road condition information is finally monitored; the prediction accuracy can be improved to a certain extent by means of the big data system for the extracted mass traffic flow data, the characteristics of data rules are found, the intelligent decision making capability can be improved in the aspect of influencing road conditions by the traffic flow, however, the real-time road conditions are known to have larger error by means of single analysis prediction of the big data system, the effect of early warning is not greatly influenced, serious traffic jam is easily caused, even traffic accidents occur, and the life and property safety of travel people is influenced.
Referring to fig. 1, the present invention is an intelligent traffic management method based on traffic flow, which specifically includes:
s1, collecting historical traffic flow data of a monitoring area in a specific time period;
s2, acquiring road section vehicle information parameters monitored by a historical monitoring image of the congested road section in real time, carrying out state prediction analysis on the road section vehicle information parameters, evaluating road condition change information, and acquiring a historical road condition evaluation coefficient;
s3, inputting the historical traffic flow data into a traffic prediction model to obtain a predicted road condition evaluation coefficient, comparing the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and performing early warning according to an analysis result.
Through the above technical scheme, in order to solve the above technical problems, this embodiment is achieved by designing an intelligent traffic management method based on traffic flow: firstly, collecting historical traffic flow data of a monitoring area in a specific time period, acquiring massive traffic information data according to a big data technology, and locking traffic flow data information of the monitoring area in the specific time period; then, the road section vehicle information parameters monitored by the historical monitoring images of the congested road sections are retrieved in real time, state prediction analysis is carried out on the road section vehicle information parameters, road condition change information is estimated, and historical road condition estimation coefficients are obtained; road section vehicle information parameters are obtained through image detection, and road condition change information is estimated through state prediction analysis of the road section vehicle information parameters, because the traffic flow is mainly the continuously increased traffic flow, the greater the vehicle density is, the more easily congestion is caused, so that the occurrence probability of traffic accidents is improved, the traffic accidents can be effectively and scientifically and reasonably arranged and scheduled through reasonable monitoring and prediction of the traffic flow, and the traffic congestion is a powerful measure for preventing the traffic accidents.
It should be noted that, the road condition information here includes: smooth, slow running, congestion and severe congestion, and fitting according to the congestion degree to obtain a congestion index; predicting the road condition state according to the congestion index, and analyzing and obtaining a historical road condition evaluation coefficient by evaluating road condition change information; and finally, inputting the historical traffic flow data into a traffic prediction model to obtain a predicted road condition evaluation coefficient, comparing and analyzing the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and carrying out early warning according to an analysis result, so that timely adjustment of the road condition evaluation coefficient and timely prediction and update of the real-time road condition state are ensured through timely early warning.
As an embodiment of the present invention, the state prediction analysis process in step S2 is as follows:
evenly dividing the acquisition time of the monitoring image information into n different time periods, and counting the traffic flow data f of the congested road section in any different time period i Wherein i is [1, n ]]；
Traffic flow data f i And a corresponding preset interval [ f ] A ，f B ]F, comparing A 、f B Are all experience constants;
if f i Is greater than a preset interval f A ，f B ]Judging that the traffic flow is greater than a critical state, and generating early warning information;
if f i Is smaller than a preset interval [ f ] A ，f B ]Judging that the traffic flow is not in a critical state and the road condition is stable;
if f i In a preset interval [ f A ，f B ]And if the traffic flow reaches the critical state, judging the traffic flow to be in the critical state, and carrying out road condition evaluation analysis.
Through the above technical solution, in this embodiment, the state prediction analysis is performed in step S2, specifically, first, the time for obtaining the monitoring image information is uniformly divided into n different time periods, and traffic flow data f of the congested road section in any different time period is counted i Wherein i is [1, n ]]The method comprises the steps of carrying out a first treatment on the surface of the Then, the vehicle flow data f i And a corresponding preset interval [ f ] A ，f B ]Ratio of progressPair, f A 、f B Are all experience constants; judging if f i Is greater than a preset interval f A ，f B ]Judging that the traffic flow is greater than a critical state, and generating early warning information; judging if f i Is smaller than a preset interval [ f ] A ，f B ]Judging that the traffic flow is not in a critical state and the road condition is stable; judging if f i In a preset interval [ f A ，f B ]And if the traffic flow reaches the critical state, judging the traffic flow to be in the critical state, and carrying out road condition evaluation analysis.
The preset section [ f ] A ，f B ]According to different road surface information and vehicle information; traffic rules and the like, and section ranges obtained by analyzing and judging past experiences; the critical state is the serious congestion degree reached by the quantity of judging traffic flow, and the critical state can be directly judged according to the set congestion index.
As one embodiment of the present invention, the road condition evaluation analysis is:
according to the formula:acquiring road condition evaluation coefficient R hi Wherein->A monotonically increasing conversion function, k being a time period selected from the total time periods n, and k > 1; m is the completion of vehicle speed from V within a selected period of time max Down to V min The quantity of road vehicles in the process of (a) is accumulated to be accommodated; m is M 0 To complete the vehicle speed from V within a selected period of time max Down to V min The road section vehicle quantity in the process of (a) accumulates the accommodation quantity standard value; />Is f i To f k An arithmetic mean of (a); />Is a vehicle information deviation coefficient.
Through the above technical scheme, in this embodiment, the road condition evaluation analysis is performed by the following formula:acquiring road condition evaluation coefficient R hi As the analysis basis, specifically, by analyzing the road condition evaluation coefficient R hi Further adjusting the running state of the road condition and promoting the accurate selection of the evaluation coefficient of the historical road condition; wherein (1)>A monotonically increasing conversion function, and the conversion function value belongs to the threshold interval [0,1 ]]The method comprises the steps of carrying out a first treatment on the surface of the k is a time period selected from the total time period n; />Is f i To f k An arithmetic mean of (a); />To f k Is a standard deviation of f 1 To f k The degree of data dispersion of (a), i.e. the guaranteed pair f with a small standard deviation i Trimming or maintaining within a threshold interval; m is the completion of the vehicle speed from V in k time periods max Accumulating the accommodation quantity of the road section vehicle quantity in the process of reducing to the approach speed to 0; m is M 0 To complete the vehicle speed from V within a selected period of time max Down to V min The road section vehicle quantity in the process of (a) accumulates the accommodation quantity standard value; when->The larger the impact on the road condition congestion degree is, the larger the impact is; />Is f i To f k An arithmetic mean of (a); />For a selected timeIs a vehicle information deviation coefficient of (a).
As one embodiment of the invention, the road condition evaluation and analysis process comprises the following steps:
estimating the road condition evaluation coefficient R hi And a preset interval [ R ] i low，R i up]Comparing the sizes:
when R is hi ∈[R i low，R i up]Judging that the road condition state changes greatly, and outputting the current road condition evaluation coefficient as a historical road condition evaluation coefficient;
when R is hi ＜R i When the road condition state is low, judging that the road condition state is less in change, and keeping the current running state;
when R is hi ＞R i And when the road condition is up, judging that the road condition state is extremely changed, and generating early warning information.
Through the above technical solution, the road condition evaluation and analysis process in this embodiment includes: estimating the road condition evaluation coefficient R hi And a preset interval [ R ] i low，R i up]Comparing the sizes: when R is hi ∈[R i low，R i up]Judging that the road condition state changes greatly, and outputting the current road condition evaluation coefficient as a historical road condition evaluation coefficient; when R is hi ＜R i When the road condition state is low, judging that the road condition state is less in change, and keeping the current running state; when R is hi ＞R i And when the road condition is up, judging that the road condition state is extremely changed, and generating early warning information.
As an embodiment of the present invention, the process of establishing the traffic prediction model in step S3 is as follows:
s31, collecting historical traffic flow of a plurality of time periods of a monitoring area, selecting traffic flow data of corresponding time periods of each congestion road section, and generating a training set and a testing set;
s32, building a model by using a circulating neural network, training the model by using a vehicle flow training set, testing the trained model by using a test set, and adjusting iteration times according to test errors;
s33, repeating the step S32, fitting the training set again, adjusting the test error to a smaller combined model, and turning to the step S32 when the test error result is bigger;
s34, outputting an estimated predicted value.
Through the technical scheme, the specific establishment process of the traffic prediction model in the step S3 is analyzed, and the traffic flow of most cities is mainly influenced by various factors such as congestion places, external weather, vehicles and the like; the present embodiment emphasizes that the continuous vehicle congestion condition in a certain time range is particularly emphasized, and the continuous vehicle congestion condition continuously affects the running speed of the next wave vehicle and the continuous increasing state of the road traffic, and the traffic prediction error caused by the influence can be synthesized to a certain extent by constructing a traffic prediction model, which specifically includes the following steps: firstly, collecting historical traffic flow of a plurality of time periods of a monitoring area, selecting traffic flow data of corresponding time periods of each congestion road section, and generating a training set and a testing set; then, building a model by using a circulating neural network, training the model by using a vehicle flow training set, testing the trained model by using a test set, and adjusting the iteration times according to a test error; then, repeating the step S32, fitting the training set again, adjusting the test error to a smaller combined model, and turning to the step S32 when the test error result is bigger; finally, the estimated predictive value is output.
As one embodiment of the present invention, the formula of the predicted value is:
calculating to obtain a traffic flow prediction coefficient P f The method comprises the steps of carrying out a first treatment on the surface of the Wherein maxf (t) and minf (t) respectively represent a maximum value parameter and a minimum value parameter of the historical vehicle flow in a certain time period; f (f) imt (t) a deviation parameter value representing a historical vehicle flow rate over a certain period of time; θ is a prediction coefficient.
Through the above technical solution, the predicted value of the embodiment is a traffic flow prediction coefficient, and the predicted value is calculated by the formulaCalculating to obtain a traffic flow prediction coefficient P f By means of the traffic flow prediction coefficient P f The influence of the predicted traffic flow on the road condition state can be reflected to a great extent, the congestion road condition of the next road section is predicted in advance, and the prediction efficiency is improved; wherein maxf (t) and minf (t) respectively represent a maximum value parameter and a minimum value parameter of the historical vehicle flow in a certain time period; f (f) imt (t) a deviation parameter value representing a historical vehicle flow rate over a certain period of time; θ is a prediction coefficient.
The following is noted: the prediction coefficient theta is obtained by fitting according to prediction regression calculation, and has close relation with the accuracy of prediction; deviation parameter value f imt (t) is obtained by real-time analysis according to an intelligent algorithm system.
As one embodiment of the present invention, the coefficient P is predicted from the vehicle flow rate f The method for obtaining the predicted road condition evaluation coefficient is as follows:
by the formula R pred ＝τ*P f Calculating a predicted road condition evaluation coefficient R pred Wherein τ is the road condition conversion coefficient.
Through the above technical solution, in this embodiment, the vehicle flow prediction coefficient P is used f Obtaining a predicted road condition evaluation coefficient, specifically through a formula R pred ＝τ*P f Calculating a predicted road condition evaluation coefficient R pred Evaluating the coefficient R by predicting road conditions pred The prediction road condition can be analyzed in advance to a large extent, and whether the current evaluation state accords with the historical evaluation coefficient state is judged, wherein tau is a road condition conversion coefficient, and the road condition conversion coefficient tau is converted according to the correlation between the traffic flow prediction coefficient and the road condition evaluation, and is not described in detail herein.
In step S3, as an embodiment of the present invention, the comparison and analysis process is as follows:
the road condition prediction evaluation coefficient R pred And historical road condition evaluation coefficient R hi And (3) performing comparison:
if R is pred ≥R hi Sending out an early warning signal; adjusting the traffic flow;
otherwise, the operation is continued.
Through the above technical scheme, the embodiment estimates the coefficient R by predicting the road condition pred And historical road condition evaluation coefficient R hi The method comprises the steps of carrying out a first treatment on the surface of the The traffic critical accommodation amount is timely adjusted by adjusting the road condition change under the current monitoring state, so that traffic accidents are avoided, and the larger influence of traffic jams on the next traffic flow is reduced; the occurrence of serious congestion is reduced through the advanced diversion and guiding of the traffic flow, the deceleration reminding, the traffic light time adjustment and the like, the traffic running efficiency is improved, and the occurrence probability of traffic accidents is reduced.
Also designed is an intelligent traffic management system based on traffic flow, referring to FIG. 1, the system comprises:
the data acquisition module is used for acquiring historical traffic flow data of the monitoring area in a specific time period;
the real-time monitoring module is used for retrieving road section vehicle information parameters monitored by the historical monitoring images of the congested road sections in real time;
the analysis module is used for carrying out state prediction analysis on road section vehicle information parameters, evaluating road condition change information and obtaining historical road condition evaluation coefficients;
the traffic prediction model is used for obtaining a predicted road condition evaluation coefficient according to the historical traffic flow data;
the comparison module is used for comparing and analyzing the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient;
the early warning module is used for sending early warning information when the traffic flow state of the monitoring vehicle is not in accordance with the requirements, the road condition evaluation analysis result is not in accordance with the requirements and the comparison analysis result is not in accordance with the requirements;
and the information synchronization module is used for synchronizing the vehicle and the road condition traffic information to the query platform in real time.
Through the technical scheme, the intelligent traffic management system based on the traffic flow is arranged, and the data acquisition module is specifically arranged and used for acquiring historical traffic flow data of the monitoring area in a specific time period; setting a real-time monitoring module for real-time retrieving road section vehicle information parameters monitored by a historical monitoring image of the congested road section; the system comprises a setting analysis module, a road condition analysis module and a road condition analysis module, wherein the setting analysis module is used for carrying out state prediction analysis on road section vehicle information parameters, evaluating road condition change information and acquiring historical road condition evaluation coefficients; setting a traffic prediction model for obtaining a predicted road condition evaluation coefficient according to historical traffic flow data; the comparison module is used for comparing and analyzing the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient; the method comprises the steps of setting an early warning module, and sending early warning information when the traffic flow state is not in accordance with the requirements, when the road condition evaluation analysis result is not in accordance with the requirements and when the comparison analysis result is not in accordance with the requirements; and the information synchronization module is used for synchronizing the vehicles and the road condition traffic information to the query platform in real time.
The foregoing is merely illustrative and explanatory of the principles of the invention, as various modifications and additions may be made to the specific embodiments described, or similar thereto, by those skilled in the art, without departing from the principles of the invention or beyond the scope of the appended claims.
Claims (9)
1. An intelligent traffic management method based on traffic flow, which is characterized by comprising the following steps:
s1, collecting historical traffic flow data of a monitoring area in a specific time period;
s2, acquiring road section vehicle information parameters monitored by a historical monitoring image of the congested road section in real time, carrying out state prediction analysis on the road section vehicle information parameters, evaluating road condition change information, and acquiring a historical road condition evaluation coefficient;
s3, inputting the historical traffic flow data into a traffic prediction model to obtain a predicted road condition evaluation coefficient, comparing the predicted road condition evaluation coefficient with the historical road condition evaluation coefficient, and performing early warning according to an analysis result.
2. The intelligent traffic management method according to claim 1, wherein the state prediction analysis process in step S2 is:
evenly dividing the acquisition time of the monitoring image information into n different time periods, and counting the congestion in any different time periodRoad section traffic flow data f i Wherein i is [1, n ]]；
Traffic flow data f i And a corresponding preset interval [ f ] A ，f B ]F, comparing A 、f B Are all experience constants;
if f i Is greater than a preset interval f A ，f B ]Judging that the traffic flow is greater than a critical state, and generating early warning information;
if f i Is smaller than a preset interval [ f ] A ，f B ]Judging that the traffic flow is not in a critical state and the road condition is stable;
if f i In a preset interval [ f A ，f B ]And if the traffic flow reaches the critical state, judging the traffic flow to be in the critical state, and carrying out road condition evaluation analysis.
3. The traffic-based intelligent traffic management method according to claim 2, wherein the road condition evaluation analysis is:
according to the formula:acquiring road condition evaluation coefficient R hi Wherein->A monotonically increasing conversion function, k being a time period selected from the total time periods n, and k > 1; m is the completion of vehicle speed from V within a selected period of time max Down to V min The quantity of road vehicles in the process of (a) is accumulated to be accommodated; m is M 0 To complete the vehicle speed from V within a selected period of time max Down to V min The road section vehicle quantity in the process of (a) accumulates the accommodation quantity standard value; />Is f i To f k An arithmetic mean of (a); θ k Is a vehicle information deviation coefficient.
4. The traffic flow-based intelligent traffic management method according to claim 3, wherein the road condition evaluation analysis process comprises:
estimating the road condition evaluation coefficient R hi And a preset interval [ R ] i low，R i up]Comparing the sizes:
when R is hi ∈[R i low，R i up]Judging that the road condition state changes greatly, and outputting the current road condition evaluation coefficient as a historical road condition evaluation coefficient;
when R is hi ＜R i When the road condition state is low, judging that the road condition state is less in change, and keeping the current running state;
when R is hi ＞R i And when the road condition is up, judging that the road condition state is extremely changed, and generating early warning information.
5. The intelligent traffic management method based on traffic flow according to claim 1, wherein the process of establishing the traffic prediction model in step S3 is as follows:
s31, collecting historical traffic flow of a plurality of time periods of a monitoring area, selecting traffic flow data of corresponding time periods of each congestion road section, and generating a training set and a testing set;
s32, building a model by using a circulating neural network, training the model by using a vehicle flow training set, testing the trained model by using a test set, and adjusting iteration times according to test errors;
s33, repeating the step S32, fitting the training set again, adjusting the test error to a smaller combined model, and turning to the step S32 when the test error result is bigger;
s34, outputting an estimated predicted value.
6. The traffic-based intelligent traffic management method according to claim 5, wherein the formula of the predicted value is:
calculation and acquisitionObtaining a traffic flow prediction coefficient P f The method comprises the steps of carrying out a first treatment on the surface of the Wherein maxf (t) and minf (t) respectively represent a maximum value parameter and a minimum value parameter of the historical vehicle flow in a certain time period; f (f) imt (t) a deviation parameter value representing a historical vehicle flow rate over a certain period of time; θ is a prediction coefficient.
7. The traffic-based intelligent traffic management method according to claim 6, wherein the prediction coefficient P is based on the traffic flow f The method for obtaining the predicted road condition evaluation coefficient is as follows:
by the formula R pred ＝τ*P f Calculating a predicted road condition evaluation coefficient R pred Wherein τ is the road condition conversion coefficient.
8. The intelligent traffic management method according to claim 7, wherein in the step S3, the comparison and analysis process is as follows:
the road condition prediction evaluation coefficient R pred And historical road condition evaluation coefficient R hi And (3) performing comparison:
if R is pred ≥R hi Sending out an early warning signal; adjusting the traffic flow;
otherwise, the operation is continued.
9. An intelligent traffic management system based on traffic flow, the system comprising:
the data acquisition module is used for acquiring historical traffic flow data of the monitoring area in a specific time period;
the real-time monitoring module is used for retrieving road section vehicle information parameters monitored by the historical monitoring images of the congested road sections in real time;
the analysis module is used for carrying out state prediction analysis on road section vehicle information parameters, evaluating road condition change information and obtaining historical road condition evaluation coefficients;
the traffic prediction model is used for obtaining a predicted road condition evaluation coefficient according to the historical traffic flow data;
the comparison module is used for comparing and analyzing the predicted road condition evaluation coefficient and the historical road condition evaluation coefficient;
the early warning module is used for sending early warning information when the traffic flow state of the monitoring vehicle is not in accordance with the requirements, the road condition evaluation analysis result is not in accordance with the requirements and the comparison analysis result is not in accordance with the requirements;
and the information synchronization module is used for synchronizing the vehicle and the road condition traffic information to the query platform in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311742862.7A CN117746626A (en) | 2023-12-18 | 2023-12-18 | Intelligent traffic management method and system based on traffic flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311742862.7A CN117746626A (en) | 2023-12-18 | 2023-12-18 | Intelligent traffic management method and system based on traffic flow |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117746626A true CN117746626A (en) | 2024-03-22 |
Family
ID=90250289
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311742862.7A Pending CN117746626A (en) | 2023-12-18 | 2023-12-18 | Intelligent traffic management method and system based on traffic flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117746626A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953693A (en) * | 2024-03-27 | 2024-04-30 | 广东工业大学 | Expressway traffic intelligent monitoring system based on video ai |
-
2023
- 2023-12-18 CN CN202311742862.7A patent/CN117746626A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117953693A (en) * | 2024-03-27 | 2024-04-30 | 广东工业大学 | Expressway traffic intelligent monitoring system based on video ai |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114783183B (en) | Traffic situation algorithm-based monitoring method and system | |
| CN105023433B (en) | A kind of traffic abnormal events of expressway coverage predictor method | |
| CN113947905B (en) | Traffic operation situation sensing method, module and system | |
| CN107610464A (en) | A kind of trajectory predictions method based on Gaussian Mixture time series models | |
| CN113420414B (en) | Short-term traffic flow prediction model based on dynamic space-time analysis | |
| CN116935654B (en) | Smart city data analysis method and system based on data distribution value | |
| CN110266528B (en) | Traffic prediction method for Internet of vehicles communication based on machine learning | |
| CN117746626A (en) | Intelligent traffic management method and system based on traffic flow | |
| CN102346964A (en) | Real-time jam prediction and intelligent management system for road traffic network area | |
| CN103942953A (en) | Urban road network dynamic traffic jam prediction method based on floating vehicle data | |
| CN111710161B (en) | Road network congestion propagation situation prediction method and system based on infectious disease model | |
| CN106781486A (en) | Traffic behavior evaluation method based on floating car data | |
| CN113496314B (en) | Method for predicting road traffic flow by neural network model | |
| CN113963539B (en) | Highway traffic accident identification method, module and system | |
| Qian et al. | Short-term traffic prediction based on genetic algorithm improved neural network | |
| CN116631186B (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
| CN112542049A (en) | Comprehensive management and control platform for intelligent traffic | |
| Qi et al. | Stochastic approach for short-term freeway traffic prediction during peak periods | |
| CN116597642A (en) | Traffic jam condition prediction method and system | |
| CN102819956B (en) | Detecting method for road traffic accident on basis of single-section annular coil detector | |
| CN116580565B (en) | Government affair big data analysis system based on cloud computing | |
| CN116721550B (en) | Traffic management system based on grid computing | |
| CN117351734A (en) | Intelligent regulation and control method and system for vehicle delay | |
| Feng et al. | Traffic Flow Prediction of Urban Intersection Based on Environmental Impact Factors and Markov Chains | |
| Lv et al. | A history data based traffic incident impact analyzing and predicting method |
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 |