Neural modeling of relative humidity on IP2C vibrating transducer

IP2Cs (Ionic Polymer-Polymer Composites) are electro-active polymers which can be used both as sensors and as actuators. In this work Neural Network models of IP2Cs working as actuators and with water as the solvent are developed using experimental data. Moreover, models proposed here take into account the humidity dependence of the device as modifying input. Three different Neural Network models, i.e. Feed-forward neural network, Radial-basis neural network and recurrent neural network based models are developed and a comparison of proposed model is reported.