The objective of this paper is to develop a hybrid scheme (nonlinear observer and fuzzy decision making) for fault detection and isolation (FDI) in the reaction wheels of a satellite. Specifically, the goal is to decide whether a bus voltage fault, a current fault or a temperature fault has occurred in one of the three reaction wheels and further to localize which fault has occurred. In order to achieve these objectives, high fidelity model is used to exhibit the dynamics of the wheels on each of the three axes independently. First using the dynamic equations, nonlinear observer is designed, and then comparing estimated and actual states, residual signals are generated. These two input signals comprise the decision making unit. Design of the decision making unit using fuzzy reasoning is implemented. The effectiveness of this nonlinear-fuzzy based FDI scheme is investigated and a comparative study is conducted with the performance of a generalized observer-based scheme.