This study presents an adaptive energy management control strategy developed by optimally adjusting the equivalent factor (EF) in real-time based on driving pattern recognition (DPR), to guarantee the plug-in hybrid electric vehicle (PHEV) can adapt to various driving cycles and different expected trip distances and to further improve the fuel economy performance. First, the optimization model for the EF with the battery state of charge (SOC) and trip distance were developed based on the equivalent consumption minimization strategy (ECMS). Furthermore, a methodology of extracting the globally optimal EF model from genetic algorithm (GA) solution is proposed for the design of the EF adaptation strategy. The EF as the function of trip distances and SOC in various driving cycles is expressed in the form of map that can be applied directly in the corresponding driving cycle. Finally, the algorithm of DPR based on learning vector quantization (LVQ) is established to identify the driving mode and update the optimal EF. Simulation and hardware-in-loop experiments are conducted on synthesis driving cycles to validate the proposed strategy. The results indicate that the optimal adaption EF control strategy will be able to adapt to different expected trip distances and improve the fuel economy performance by up to 13.8% compared to the ECMS with constant EF.