Administrator by China Associction for Science and Technology
Sponsored by China Society of Automotive Engineers
Published by AUTO FAN Magazine Co. Ltd.

Automotive Engineering ›› 2020, Vol. 42 ›› Issue (9): 1174-1182.doi: 10.19562/j.chinasae.qcgc.2020.09.005

Previous Articles     Next Articles

Prediction of Continued Driving Range of Battery Electric Vehicle Based on Map Information and Cyclic SVR Model

Tian Huixin1,2, Li Xiaoyu1 , Liu Fang3   

  1. 1. School of Electrical Engineering & Automatic, Tiangong University, Tianjin 300387;
    2. Tiangong University, Key Laboratory of Advanced Electrical Engineering and Energy Technology, Tianjin 300387;
    3. School of Computational Science and Technology, Tiangong University, Tianjin 300387
  • Online:2020-09-25 Published:2020-10-19

Abstract: In view of the situation that the prediction accuracy of continued driving mileage is hard to enhanced due to the unknown driving conditions in the future, a prediction method for the driving mileage of battery electric vehicle based on map information and cyclic SVR model is proposed. The method predicts the future driving conditions according to map information, and takes the corresponding parameters of working conditions as the input of SVR model to calculate the SOC decline value and the remaining SOC value of the unit mileage in that working condition. The process is iterated repeatedly until the SOC value returns to zero, then the number of SVR runs is the remaining driving range. Finally, a simulation is carried out using ADVISOR based on actual driving data, and the results show that the method has a high prediction accuracy of continued driving mileage.

Key words: battery electric vehicle, remaining mileage, SVR model, driving condition, map information