This paper addresses the energy management strategy (EMS) for a fuel cell hybrid electric vehicle (FC-HEV). The purpose of this paper is to ensure an optimal power splitting between the fuel cell system (FCS) and the battery pack, taking into account the operating conditions of the FCS. The FCS is a multi-physics system, and consequently, its energetic performances depend on the operating conditions (i.e., temperature, gas relative humidity, gas stoichiometry, pressure and ageing). Specific techniques must be used to reach the best performances of the FCS. In this work, models are identified online by using the adaptive recursive least square (ARLS) method to seek a variation in the FCS performances. Then, an optimization algorithm is used on the updated model to find the best efficiency and power operating points. This process is used into an optimal EMS based on Pontryagin’s minimum principle, for a FC-HEV. The effectiveness of the proposed EMS is demonstrated by conducting studies on two FCSs with different levels of degradation.