Prediction of full-path operating conditions based on the characteristics of the driving environment

Abstract

ABSTRACT The prediction of driving conditions is an important basis for the energy management systems of new energy vehicles. Accurate predictions of driving conditions can help reduce the use of on-board energies such as gasoline and electricity, and improve the efficiency of energy use. Aiming at the limitations of existing driving condition prediction, this paper proposes a full-path driving condition prediction based on driving environment characteristics. BP neural network optimized by GA algorithm is used to establish a prediction model of driving condition characteristic parameters based on driving environment characteristics, and use road traffic environment information to predict driving condition characteristic parameters. And use the predicted characteristic parameters to perform fuzzy matching to predict the type of driving conditions of the vehicle for a period of time in the future. In this paper, some roads in Nanjing are used as an example to verify the prediction model. The results show that the prediction accuracy has reached 94.18%. When it is applied to energy consumption prediction, the prediction error is only 5.82%. This method provides a more accurate and reliable driving condition prediction method for new energy vehicles, which is conducive to the design of more reliable and efficient energy management strategies.