In view of the diversity and complexity of the existing travel time prediction methods, travel time is an important indicator to quantify the state of road traffic congestion. In this paper, based on the analysis of various travel time prediction methods, a network model based on the idea of BP algorithm is constructed by SPSS software, and the method of travel time prediction of urban road is studied by combining BP neural network with three indexes affecting vehicle speed. Firstly, taking Jinshui road of Zhengzhou as the research object, this paper obtains the data of three factors that affect the vehicle speed, namely, vehicle spacing, flow and density; then, it constructs the neural network model and analyzes the data with the help of SPSS; finally, the experimental results are obtained, and the analysis shows that the error between the predicted speed and the real speed is very small, the average predicted error value is 0.3, and the average error rate is 2.35%, the result has better accuracy and feasibility, which can further realize the effective prediction of the travel time of the car. The model established in this paper has better practicability for travel time prediction, and the data can be used as reference value for travel time prediction of intelligent transportation system and other systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.