Conceptual modeling of hysteresis in piezo crystals using neural networks

Abstract

Piezoelectric materials are a subset of a larger class of materials known as ferroelectric materials. Ferroelectricity is the characteristic of certain materials that have a spontaneous electrical polarization that can be reversed by the application of an electric field. Like the magnetic equivalent (ferromagnetic materials), ferroelectric materials exhibit hysteresis loops based on the applied electric field and the history of that applied electric field. Hysteresis compensation is necessary wherever high precision positioning or piezo control of the mechanism is required. For forecasting purposes, of hysteresis, the Bouc-Ven model was most often used, and more recently, hysteresis modeling using neural networks has begun. The paper will show a way of conceptual predicting, and then for hysteresis, using a neural network.