Survey, Experiment and Improvement of Micro Actuator Positioning for Precise Grinding by Neural Network

Precise grinding of fine shaped pieces with various arithmetic needs micro positioning and rapid movement of a work piece. Moreover, with regard to dressing of super abrasive grinding wheels, precise positioning of a dresser on the grinding wheel for achieving desired depth is needed. Piezoelectric actuators are convenient for micro positioning systems. Inherent hysteresis is one of the drawbacks in the use of these actuators. Neural networks can be used for this modeling. Ignoring the force can increase the positioning error remarkably. In this paper, the neural network is used for hysteresis modeling with attention to the important effect of loaded force. After modeling, the inverse hysteresis model is used as a compensator in a feed forward way to linearize the input-output relationship. Then using a PID closed loop controller and selecting a suitable coefficient for it, the maximum error was decreased to less than 2 percent of the working amplitude.