Accurate estimation of the power consumption of electric vehicles in the future driving route will help to reduce the user's range anxiety, which results from short all electric range of electric vehicles and the lack of charging facilities. The existing research methods mainly focus on three aspects: vehicle energy consumption, driving cycle identification and driving cycle prediction. In this paper, a method of estimating mileage power consumption based on driving cycle identification and prediction is proposed. Firstly, driving cycle categories and energy consumption of each category are obtained through conducting screening, sectioning, principal component analysis and fuzzy C clustering to the vehicle's historical operation data. Then, the future vehicle speed curve is predicted based on historical data, elevation information and real-time road congestion information, and the mileage consumption estimation model is established based on the identification and prediction of the driving cycle. Finally, 10 groups of real vehicle tests were carried out on the experimental vehicle. And the results showed that the average error between the estimated value of the mileage power consumption and the test value is 4.15%, which met the requirements of the daily use of electric vehicles.
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.