A Novel Composite Neural Network for Hysteresis Modeling in Piezoelectric Actuators

Abstract

Piezoelectric actuators are convenient for micro positioning systems. Inherent hysteresis is one of the drawbacks in use of these actuators. Precise control of this actuator under changing of environmental and operational conditions, without modeling of hysteresis, is impossible. Neural networks can be used for this modeling. The ordinary feed forward neural networks can not train time dynamic relationship between input and output. Thus a certain type of networks called time delay feed forward neural networks (TDNN), are developed and is used in this paper. In the previous researches in this field, the important effect of loaded force on the actuator is ignored. This can increase the positioning error remarkably. Especially when these actuators are used in the precise grinding or machining operations. In this paper, neural network is used for hysteresis modeling with attention to the important effect of loaded force. After modeling, inverse hysteresis model is used as compensator in a feed forward way to linearize the input-output relationship. Then using PI closed loop controller and selecting suitable coefficient for it, the maximum error was decreased to less than 2 percent of the working amplitude.