Abstract: As the key direction of development in the automobile field, Plug-in hybrid electric vehicles (PHEV) are energy-saving, environmental friendly and free from anxieties of endurance mileage. However, the control strategy of PHEV is relatively complex, involving the energy distribution of multiple power sources. How to design an efficient and reliable energy management strategy has become a hot and difficult issue in PHEV research. In order to improve the fuel economy and vehicle performance of PHEV, a PHEV energy management control strategy based on weighted double-Q learning is proposed, and the weighted double-Q learning algorithm is used to solve the energy distribution of PHEV in this paper. Furthermore, a vehicle model is built and simulated in Matlab/Simulink to verify the effectiveness and reliability of the proposed strategy. The results show that, compared with the rule-based CD/CS strategy, the fuel economy of the proposed strategy improves by 6.38% on average under different driving conditions. The fuel economy of the weighted double-Q learning strategy can reach 98% of that of the stochastic dynamic programming strategy under different driving conditions. The above results verify that the proposed strategy has good fuel economy and adaptability to different driving conditions.