The extended-range electric vehicle (E-REV) can solve the problems of short driving range and long charging time of pure electric vehicles, but it is necessary to control the engine working points and allocate the power of the energy sources reasonably. In order to improve the fuel economy of the vehicle, an energy management strategy (EMS) that can adapt to the daily driving characteristics of the driver and adjust the control parameters online is proposed in this paper. Firstly, through principal component analysis (PCA) and iterative self-organizing data analysis techniques algorithm (ISODATA) of historical driving data, a typical driving cycle which can describe driving characteristics of the driver is constructed. Then offline optimization of control parameters by adaptive simulated annealing under each typical driving cycle and online recognition of driving cycles by extreme learning machine (ELM) are applied to the adaptive multi-workpoints energy management strategy (A-MEMS) of E-REV. In the end, compared with traditional rule-based control strategies, A-MEMS achieves good fuel-saving and emission-reduction result by simulation verification, and it explores a new and feasible solution for the continuous upgrade of the EMS.