Applications and Adaptive Neuro-Fuzzy Estimation of Conductive Silicone Rubber Properties

Primljeno (Received): 2011-10-10 Prihvaćeno (Accepted): 2012-01-22 Original scientific paper The paper summarizes the results of investigations on the conductive silicone rubber as strain sensor and presents a segment of the project for developing the new principle of a universal gripper with adaptable shape morphing surfaces. An experimental investigation of the sensors subjected to different time-dependent strain histories is presented. To investigate the electrical properties, the resistance of silicone was measured during the mechanical tests. An adaptive neuro-fuzzy inference system (ANFIS) was used to approximate the correlation between these measured features of the material and to predict its unknown future behavior. ANFIS has unlimited approximation power to match any nonlinear function arbitrarily well on compact set and to predict a chaotic time series.