This study aimed to develop a cost-effective, environmentally sustainable, and technologically advanced dielectric fluid by utilizing the beneficial properties of natural ester-based vegetable oils, offering a promising alternative for transformer insulation and cooling applications. The novelty of this research lies in the formulation of a nanofluid that combines three distinct vegetable oils—castor, flaxseed, and blackseed—creating a unique base fluid. SiO₂ nanoparticles were incorporated into the fluid to leverage their multiple advantageous characteristics. Extensive experiments were conducted to evaluate the superior properties of the proposed nanofluid, focusing on key dielectric properties, such as relative permittivity (ε_r) and the dielectric dissipation factor (tan δ). Comparative analyses with conventional mineral oil, which was used as a benchmark, demonstrated the significant advantages of the vegetable oil-based nanofluid. The novel formulation outperformed all other tested samples, highlighting its exceptional performance. Additionally, three preparation methods were examined, with the green synthesis technique producing the nanofluid with better dielectric properties. Through a detailed presentation of empirical data and compelling arguments, this study confirms the potential of natural ester-based vegetable oil nanofluids as a highly promising alternative, driven by their intrinsic properties and the environmentally friendly synthesis method employed.

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.