A permanent magnet (PM) synchronous servo motor drive with integral-proportional (IP) position controller and a proposed on-line trained fuzzy neural network (FNN) controller is introduced in this paper, First, an IP position controller is designed according to the estimated plant model to match the time-domain command tracking specifications. Then the resulting closed-loop tracking transfer function is used as the reference model, and an adaptive signal generated from the proposed FNN controller, whose membership functions and connective weights are trained on-line according to the model-following error of the states, is added to the control system to preserve a favorable model-following characteristics under various operating conditions.