A neuro-genetic controller for nonminimum phase systems

This paper investigates a neurocontroller for nonminimum phase systems which is trained off-line with genetic algorithm (GA) and is combined in parallel with a conventional linear controller of proportional plus integral plus derivative (PID) type. Training of this kind of a neuro-genetic controller provides a solution under a given global evaluation function, which is devised based on the desired control performance during the whole training time interval. Empirical simulation results illustrate the efficacy of the proposed controller compared with a conventional linear controller in point of learning capability of adaptation and improvement of performances of a step response like fast settling time, small undershoot, and small overshoot