Design and verification of a non-linear black-box model for ionic polymer metal composite actuators

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 article presents a novel accurate nonlinear black-box model (NBBM) for estimating the bending behavior of IPMC actuators. The NBBM is a combination of two advanced designs which are a general multi-layer perceptron neural network (GMLPNN) and a self-adjustable learning mechanism (SALM). Here, the GMLPNN is constructed with an ability to auto-adjust its structure based on its characteristic vector, while the SALM is built to take part in training the GMLPNN decisive parameters. For the model verification, an IPMC actuator is set up to investigate the IPMC characteristics as well as to generate training data. Next, the advanced NBBM model for the IPMC system is performed with suitable inputs to estimate the IPMC tip displacement. Finally, the model parameters are optimized by using the SALM mechanism with training data. The NBBM model ability is evaluated by a comparison of the estimated and real IPMC bending characteristics