Hysteresis identification and compensation using a genetic algorithm with adaptive search space

A genetic algorithm with adaptive search space (GAASS) is proposed and applied to identify the hysteresis model parameters of an electromechanical-valve actuator installed on a pneumatic system. According to the normalized fitness distance in each generation, the proposed GAASS method consistently identifies the best search domains in the parameter space and adjusts the crossover and mutation rates in order to achieve fast convergence and high accuracy. Experiments have been conducted to investigate the effectiveness of the proposed hysteresis identification approach. Three different types of sensors have been used in the experimental studies, and the experimental results have demonstrated the effectiveness of the proposed approach.