Adaptive backstepping control using neural networks

This paper proposes an adaptive backstepping design method for a kind of affine nonlinear system with unknown nonlinearity and/or uncertainty. The neural network is used to approximate the unknown nonlinear function and/or uncertainty in the system. Then the neural adaptive backstepping controller without off-line training is obtained using conventional adaptive backstepping. According to the Lyapunov stability theory, the weight update law of neural network, the adaptive law of error bound, the stabilizing function and the control are obtained, thus the stability of closed-loop control system is ensured. The simulation result shows the effectiveness of adaptive backstepping control using neural networks