Real-Time Energy Management Strategy Based on Driving Conditions Using a Feature Fusion Extreme Learning Machine

To address the problem that a single energy management strategy cannot adapt to complex driving conditions, in this paper, real-time for different conditions is proposed improve fuel economy. First, order accuracy and stability of condition identifier, feature fusion extreme learning machine (FFELM) used identification. Secondly, equivalent consumption minimization (ECMS) offline optimization conducted types cycles, effect cycle type distance on under result analyzed. A combining type, distance, optimal power allocation factor proposed. demonstrate effectiveness strategy, combined cycles were testing. The simulation results show can by 10.21% compared conventional CD-CS. economy be improved 2.5% ECMS with less computational burden. Thus, it demonstrated effectively adapted shows better economic performance.