Open AccessBattery SOC Prediction for HEV based on Extreme Learning Machine
Author(s) -
Elin Jing,
Ping Mao,
Hengping Dong,
Qi Wang
Publication year - 2019
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/332/4/042009
Subject(s) - battery (electricity) , dynamometer , automotive engineering , extreme learning machine , state of charge , electric vehicle , regenerative brake , mode (computer interface) , schedule , computer science , engineering , simulation , brake , artificial neural network , artificial intelligence , power (physics) , physics , quantum mechanics , operating system
The extreme learning machine (ELM) is proposed based on the prediction of the battery’s state of charge (SOC) of the hybrid electric vehicles (HEV). The HEV simulation system is developed under the environment of advanced vehicle simulator (ADVISOR). Considering the influence of working condition to SOC, the Urban Dynamometer Driving Schedule (UDDS) is adopted as the working condition. At the same time, the energy feedback is also taken into consideration when HEV under regenerative braking mode is working. The working voltages, currents and surface temperature of battery are employed to predict the real-time value of SOC, and the results indicate that the prediction model possesses higher predicted accuracy.