Observer-based stabilisation of some non-linear non-minimum phase systems using neural network

Abstract: This paper presents a neuro-adaptive output-feedback stabilization method for nonlinear non-minimum phase systems with partially known Lipschitz continuous functions in their arguments. The proposed controller is comprised of a linear, a neuro-adaptive, and an adaptive robustifying control term. The adaptation laws for the neural network weights are obtained using the Lyapunov’s direct method. These adaptation laws employ a suitable output of a linear state observer that is realizable. The ultimate boundedness of the error signals will be shown through analytical work using Lyapunov's method. The effectiveness of the proposed scheme will be shown in simulations for the benchmark Single Flexible Link Manipulator and Translation Oscillator Rotational Actuator (TORA) problems.