Estimation of bending behavior of an ionic polymer metal composite actuator using a nonlinear black-box model

Abstract

An ion polymer metal composite (IPMC) is an electro-active polymer that bends in response to a small applied electrical field as a result of mobility of cations in the polymer network and vice versa. This paper presents a novel accurate nonlinear black-box model (NBBM) for estimating the bending behavior of IPMC. The NBBM is based on a recurrent multi-layer perceptron neural network (RMLPNN) and a self-adjustable learning mechanism (SALM). The model parameters are optimized by using training data. A comparison of the estimated and real IPMC bending characteristic has been done to investigate the modeling ability of the designed NBBM.