This paper addresses an adaptive control approach for a maximum efficiency tracking of a proton exchange membrane fuel cell. The adaptive control has an online identification system that estimates the fuel cell efficiency behavior parameters and an optimization module that is responsible for providing the best operating conditions. The proposed approach does not require a cell-precise model and is not sensitive to the initial operating conditions and has been successfully tested on a 500-W proton exchange membrane fuel cell. A comparative study with the airflow control strategy shows that this adaptive control can improve the fuel cell efficiency up to 10%. Since the proposed adaptive control requires little knowledge of the fuel cell model, it can be easily used for similar fuel cells.