Neural network control of scanning probe microscope precision stage

A new control scheme based on neural network and traditional PID controller is proposed to improve the performance of precision stage in SPMs. The mathematical model is set up by analyzing the principle of the piezoelectric actuator. Mechanical parameters are identified online by a neural estimator. The traditional PID controller is replaced by a neural network PID controller. Weights in the network and parameters of the PID controller are adjusted by the function of self learning and adaptability. The performance of real control system is enhanced. The results of experiment show that the response time is reduced from 0.38 s to 0.18 s, and the steady state error is shorten from 4.2% to 1.9% under a displacement of 10 mum.