Hysteresis compensation for Piezoelectric tube scanner in atomic force microscopy

In this paper, a radial basis function neural network (RBFNN) is designed and used for such purpose. The network is used in conjunction with a self-tuning PID controller. The differential equation of Jenkine element is adopted for hysteresis modeling. The simulation results show that the proposed controller improves the system performance better than open loop system and direct closed loop system by minimizing the effect of hysteresis.