Application of the nonlinear H¥ identification method to identify a synchronous generator model is investigated in this paper. The linear H¥ identification method has been well established in the literature for robust modeling despite noise and system uncertainities. Since many practical systems such as synchronous generators are nonlinear, linear models identified for particular operating conditions do not perform well for other operating conditions. To overcome this shortcoming, the linear H¥ identification method has been modified to cover some nonlinearities of the systems such as saturation in synchronous machines. The derived proposed algorithm is then applied to a seventh order nonlinear model of a synchronous machine with saturation effect . In this study, the field voltage is considered as the input and the active output power and the terminal voltage are considered as the outputs of the synchronous machine. Simulation results show good accuracy of the identified models.