Artificial neural network approach for predicting tunneling-induced and frequency-dependent electrical impedances of conductive polymeric composites

The conductive polymeric composites (CPCs) have been highlighted due to their various applications. However, their electrical impedances are sensitive to the external factors such as tunneling-induction, frequency-dependence, and applied mechanical strain amplitudes. Herein, the carbon nanotube (CNTs) and carbonyl iron powder (CIP)-embedded CPCs were fabricated, and their tunneling-induced and frequency-dependent electrical impedance values were investigated considering the different input voltages and frequencies, and mechanical strain amplitudes. Moreover, the machine learning-based artificial neural network (ANN) model was adopted to predict the electrical impedances of the fabricated CPCs, and the predicted values were compared to the experimental results, showing the high accuracy with R-square values of 0.9081.