Prediction of Dielectric Properties of Polypropylene/Polyaniline Composite Films By Artificial Neural Networks Model

Abstract

In this study, the change of the frequency dependence of the real and imaginary components of the complex dielectric function of the polypropylene (PP) polymer depending on the addition of 0.3%, 0.4%, 0.6% and 0.7% polyaniline (PANI) was investigated by using dielectric spectroscopy method. Dielectric measurements were performed at room temperature in the frequency range of 100 Hz to 15 MHz by impedance analyzer. Experimental results have shown that the dielectric parameters of PP exhibit non-linear variation with the PANI contribution. In this context, firstly, it has been shown that the frequency dependence of real and virtual components of complex dielectric functions of PP / PANI composites can be estimated with Artificial Neural Network (ANN) model. Then, the frequency dependences of the real and imaginary components of the complex dielectric function of the PP/PANI composites with different PANI additive concentrations (0.1, 0.2, 0.5, 0.8, and 1.0%), which were not prepared experimentally, were calculated by using ANN method. The results obtained with the YSA model were also found to be consistent with the nonlinear variation of the real and imaginary components of complex dielectric function with increasing PANI doping. Hence, suitable PP and PANI mass percentages can be predicted in the production of PP/PANI composites with desired dielectric parameters for various dielectric applications such as capacitor.

Keywords

• Artificial Neural Networks
• Dielectric Spectroscopy
• Polypropylene
• Polyaniline