A Holistic Integration of Machine Learning for Selecting Optimum Ratio of Nanoparticles in Epoxy-Based Nanocomposite Insulators

Abstract

Epoxy-based nanocomposites have drawn much interest in high-voltage insulation applications due to their improved dielectric properties. The determination of the optimal nanoparticle (NP) concentration required to achieve a significant enhancement in nanocomposite dielectric properties remains a subject of ongoing research. Previous work has employed iterative experimental methodologies, often characterized by the hit-and-trial method, in attempts to find the optimal nanoparticle concentration. However, these efforts have yielded suboptimal or inconsistent results. Moreover, experimental procedures for optimizing the nanoparticle concentration require significant time and cost. This research study proposed the predictive capabilities of machine learning (ML) for the selection of the nanoparticle concentration in epoxy-based nanocomposite insulators. The authors employed a novel systematic approach in this research work, comprising dataset preparation, ML model implementation, and experimental validation. A real-time dataset with varying concentrations of NPs (TiO2, SiO2, Al2O3) was developed in the High Voltage Lab, KFUEIT, Pakistan. Several advanced machine learning models are trained on this dataset. Support Vector Regression (SVR) exhibits the highest prediction accuracy, with an R2 score of 0.97. SVR predicted a breakdown voltage (BDV) of 46.26 kV, with a (w/w %) concentration of 5% TiO2, 1.17631% SiO2, and 3.95755% Al2O3. To validate the SVR prediction, a hardware prototype with predicted NP concentration is developed and tested. The experimentally measured BDV of the predicted nanocomposite sample, registering 44.72 kV, authenticates the predictive accuracy of machine learning. This work demonstrates the efficacy of machine learning as a viable and efficient alternative to traditional experimental methods for optimizing nanoparticle concentrations using a predictive approach in epoxy-based nanocomposites for high-voltage insulation applications.