A self-structuring fuzzy controller(SFC) is proposed for the non-affine nonlinear SISO system. The controller consists of a robust controller and a self-structuring fuzzy system(SFS). The fuzzy system employed to approximate nonlinear system uncertainty has one rule initially. Two criteria are used for generating rules and membership functions, system error and ??-completeness. The new rules are initialized by using the “pseudo fuzzy output” method. And considering the practical
computing ability, an algorithm is proposed to replace the membership function, so that the number of rules never exceeds a predefined upper bound. The closed-loop stability is guaranteed. Theoretical simulation results and semi-physical simulation results show the effectiveness of the proposed approach.