INVESTIGATION AND ADAPTIVE NEURO-FUZZY ESTIMATION OF MECHANICAL / ELECTRICAL PROPERTIES OF CONDUCTIVE SILICONE RUBBER

Conductive silicone rubber has great advantages for strain sensing applications. The electrical behavior of the elastomeric material is rate-dependent and exhibit hysteresis upon cyclic loading. Several constitutive models were developed for mechanical simulation of this material upon loading and unloading. One of the successful approaches to model the time-dependent behavior of elastomers is Bergstrom-Boyce model. The paper summarizes the results of investigations on the conductive silicone rubber as strain sensor. An experimental investigation of the sensors subjected to different timedependent strain histories is presented. Three different tests have been developed to measure timedependent and strain-dependent behavior of the rubber. To investigate the electrical properties, the resistance of silicone was measured during the mechanical tests. An adaptive neuro-fuzzy inference system (ANFIS) is used to approximate 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.