Robust Adaptive Neural Control for Nonlinear Uncertain Systems: Theory and Simulation Verification

Abstract

This paper investigates tracking control for second-order nonlinear systems with unknown dynamic functions and external disturbances. Unlike classical adaptive control requiring linear-in-parameter dynamics, this study employs Radial Basis Function (RBF) Neural Networks to approximate unstructured nonlinearities. A robust control scheme based on backstepping and σ-modification is proposed to address parameter drift, ensuring bounded adaptive weights and closed-loop stability via Lyapunov analysis.