Predictive Energy Management for Hybrid Electric Vehicle Considering Driver’s Intention

Menglin Li, Hongwen He, Jiankun Peng, Yong Chen, Mei Yan

Abstract


The driver's intention determines the vehicle's Macrodriving state. On the premise of ensuring that the driving state of the vehicle conforms to the driver's intention, it is of practical significance to study the energy-saving of the vehicle. Through the correlation analysis of acceleration / brake pedal signal with vehicle speed and acceleration under real working conditions, the strong correlation between driver input and vehicle speed appears in the range of 4-6 seconds. The mapping relationship between driver’s intention and driver's expected speed is constructed by extreme learning machine. Based on this, the model predictive control for hybrid electric vehicle is carried out. It is compared with the global optimal control strategy solved by dynamic programming and the instantaneous optimal control strategy under the same discrete precision. The results show that compared with the instantaneous optimal control strategy, model predictive control based on driver’s intention can save 9.92% of the energy consumption while meeting the driver’s intention (RMSE 0.9995m/s).

Keywords


model predictive control, driver’s intention, extreme learning machine network, energy management


DOI
10.12783/dteees/iceee2019/31801

Full Text:

PDF

Refbacks

  • There are currently no refbacks.