A framework for robust neural network-based control of nonlinear servomechanisms

A framework for robust neural network-based control of nonlinear servomechanisms is proposed and presented. This framework utilizes a general controller structure that comprises a nonlinear compensation block and a robust control block. Two different strategies for designing the control laws for these are discussed and it is shown that uniform stability of the overall system even in the presence of modeling mismatches and non-parametric uncertainly is achieved. The effectiveness of this proposed framework is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load.