Informatics-based design of polyaniline-carbon nanotube thermoelectric nanocomposite using ANN and GA

Abstract

Abstract Conducting polymer and carbon nanotube (CNT) based nanocomposites have emerged as prospective thermoelectric (TE) materials due to their potential application in flexible electronics. Non-conventional charge and heat transport in these nanocomposites, presents the possibility to enhance the TE conversion efficiency, given by Z T . However, the highly non-linear and complex association of structure and composition with the overall TE properties have hindered the development of any general strategy to develop high Z T nanocomposites. Here, we implement artificial neural network and genetic algorithm to develop data driven models followed by optimization to design high efficiency nanocomposites based on CNT dispersed in polyaniline (PANI) matrix. Our models suggest that CNT concentration plays the most crucial role in determining Z T . Non-dominated Pareto optimal solutions consisting of different combinations of design variables are obtained by multi-objective optimization. Although a range of optimal solutions span over different regions of the search space, in general we note that longer CNTs boost Seebeck coefficient ( S ) and electrical conductivity ( σ ) , and smaller length lowers thermal conductivity ( k ), while higher diameter of CNTs increase S and lowers σ and k . The results provide a general guideline for developing CNT-PANI nanocomposites with enhanced TE figure of merit.