A Morlet wavelet neural network-based online identification and control of coupled MIMO systems

A new approach has been developed for the control of a coupled, non-linear MIMO system. A quasi-diagonal wavelet neural network (QDWNN)-based online identification and control scheme for coupled, non-linear MIMO system is presented in this paper. The new algorithm is based on control error process and does not need accurate mathematical model of the system to be controlled. Firstly an online parameter-tuning algorithm for multivariable PID-controllers is described and then it has been tested for two model systems. Simulation results show that the proposed control scheme minimises mean square error (MSE) and mean absolute error (MAE) remarkably, with reduced control effort, without slowing down the rise time.