An adaptive ECMS with driving style recognition for energy optimization of parallel hybrid electric buses

Abstract

In this paper, an adaptive energy management system consisting of off-line and online parts is presented to improve the energy efficiency of a parallel hybrid electric bus. The off-line part discusses how to precisely recognize the driver's driving style based on the hybrid algorithm. Specially, K nearest neighbor method is applied to reduce the number of samples as the preprocessor, and the expectation maximization method is leveraged to speculate the class using similar training samples. Furthermore, the driving style recognition module is built and employed to classify the driver's driving style from aggressive to conservative at each time step. On the other hand, the online part performs the involved energy management strategy, which incorporates driver's driving style into the equivalent consumption minimization strategy (ECMS). Simulation results demonstrate that the performance of charging sustainability and equivalent fuel consumption in the proposed strategy exceed those in the ECMS, as for both aggressive and conservative drivers. Comparative results obtained from HIL tests also indicate that the fuel economy of the proposed strategy is improved by 9.54% and 7.03% for aggressive and conservative drivers compared with ECMS, respectively.