Abstract
An improved adaptive neuro‐sliding mode control scheme that incorporated a completely adaptive radial basis function (RBF) neural network into a sliding‐mode controller to approximate the control of a static synchronous series compensator device is presented in this paper. The proposed nonlinear controller does not require the full state of the nonlinear system nor the full knowledge of the bounds of uncertainty, disturbance, and approximation error. It makes use of a reduced number of hidden units, and the weights, centers, and widths are all updated through an on‐line learning mechanism. The effectiveness of the proposed control scheme has been verified on a three‐machine, nine‐bus Institute of Electrical and Electronics Engineers (IEEE) power system with a static synchronous series compensator in MATLAB/Simulink software. The stability of the system and adaptive control laws have been proven using the Lyapunov stability theorem. Simulation results show that the robustness of the proposed controller can satisfactorily alleviate the chattering effects as well as the internal and external perturbations considered.

This publication has 27 references indexed in Scilit: