Inverse NN Modelling of a Piezoelectric Stage with Dominant Variable

TL;DR

This paper develops an inverse neural network model for a piezoelectric stage with hysteresis, identifying velocity as the dominant variable to improve prediction accuracy and avoid over-fitting, validated through experiments.

Contribution

It introduces a method to identify the dominant variable in a hysteretic system and uses it to enhance neural network inverse modeling accuracy.

Findings

Neural network with velocity input accurately predicts stage behavior.

Using the dominant variable reduces over-fitting compared to multiple inputs.

Experimental results confirm the model's effectiveness.

Abstract

This paper presents an approach for developing a neural network inverse model of a piezoelectric positioning stage, which exhibits rate-dependent, asymmetric hysteresis. It is shown that using both the velocity and the acceleration as inputs results in over-fitting. To overcome this, a rough analytical model of the actuator is derived and by measuring its response to excitation, the velocity signal is identified as the dominant variable. By setting the input space of the neural network to only the dominant variable, an inverse model with good predictive ability is obtained. Training of the network is accomplished using the Levenberg-Marquardt algorithm. Finally, the effectiveness of the proposed approach is experimentally demonstrated.