Adaptive self-tuning control using neural networks for fast time-varying nonlinear systems

A fast and flexible adaptive self-tuning control is proposed in this paper for nonlinear, fast time-varying and multi-input multi-output (MIMO) systems using a novel output and error recurrent neural networks. The key point of this research for nonlinear control is to develop a fist tracker with a flexible adaptive control scheme which does not require previous knowledge about the plant to be controlled, i.e., plant dynamic equations. Hence its algorithms have a flexibility for diverse applications. In order to carry out this research goal, system identification has successfully been achieved based on a recurrent neural network model, and nonlinear quadratic optimal law has also been derived and tested to the fast tracking problem for a robotic manipulator.