Method Of Travel Time Short-term Prediction Of Urban Road Based On Traffic Status Division

With the development of society and economy,the number of motor vehicles is increasing year by year.Therefore,traffic accidents and traffic jams are becoming increasingly serious.The problem of congestion is solved by formulating short-term and long-term plans and implementing strategies.Among the numerous solutions to alleviate vehicle congestion,it is considered to be a more efficient method to solve the congestion problem with the assistance of intelligent transportation.Travel time is an important element in Intelligent Transportation System.This indicator can directly provide road managers and users with intuitive traffic information.Travel time is widely used in route guidance,travel information services,traffic demand management,road performance evaluation,etc.Currently,there are still problems with the real-time and accuracy of travel time predictions.Especially when in the morning and evening rush hour,there will be many interference factors in the traffic management process.Therefore,the travel time fluctuates greatly.The stability of travel time is mainly affected by the relationship between supply and demand and signal control.This paper studies the travel time of urban road by analyzing the data of license plate recognition.First,this article will analyze and process the underlying data.According to the characteristics of license plate acquisition equipment,the four problems existing in the original data are analyzed and the corresponding solutions are proposed.Then,taking the actual data as an example,a set of methods for analyzing and processing license plate recognition data is proposed,the overall situation of the equipment is evaluated from the macro level,the accuracy of the identification and flow of the equipment is analyzed from the micro level,and the noise data of the travel time is analyzed from the point of view of the statistical data,and the scientific data is collected to predict the travel time of the intermittent section of the road.Secondly,the traffic state is divided according to the characteristics of the discontinuous flow travel time distribution.Through the verification,the three-component Gaussian mixture distribution is used to describe the travel time distribution of the case,and then the traffic state is divided according to the relevant judgment standards.Finally,according to the results of state division,the volatility indicator of travel time is used to illustrate the randomness and complexity of the oversaturated state.Finally,this paper proposes a combined algorithm suitable for different traffic conditions to predict travel time.By introducing new variables and analyzing the data,the input parameters of the machine learning algorithm can be determined.According to the predicted traffic conditions,the travel time accuracy and reliability indicators are used to select the best algorithms for different traffic conditions.In the supersaturated state,the PSO-SVR-Kalman algorithm obtains the best results.Then from a spatial perspective,the generalization ability of the algorithm is verified,and TVF-EMD is used to decompose the travel time error sequence to optimize the prediction results.