Cross-Domain Ai-Enhanced Imaging for Power Systems Diagnostics Using Medical AI Techniques, Inspired by Stanford's Mini-Fellowship Program

This paper explores the application of AI-powered medical imaging techniques, originally designed for Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) image enhancement, in the domain of energy systems monitoring. We introduce FusionScan-AI, a cross-domain methodology that applies convolutional denoising, adaptive contrast optimization, and GAN-based sharpening - previously validated in brain and chest diagnostics - to high-resolution energy infrastructure imaging. We simulate and evaluate its use in thermal imaging of electric substations, non-invasive inspections of transformer cores, and monitoring high-stress components in renewable energy systems such as wind turbines and solar inverters. This research establishes a framework to bridge advancements in medical AI and electrical energy system diagnostics, aligning with the goals of smart grid reliability, clean energy safety, and fault detection. We adapt a three-stage imaging pipeline - denoising, contrast enhancement, and edge sharpening via convolutional filters - from the medical domain to improve visual inspections of electrical infrastructure (e.g. transformers, solar panels). By reducing sensor noise, amplifying critical contrast, and sharpening fault-related edges, the enhanced images reveal latent defects, such as overheating hotspots, micro-cracks, and insulation degradation that are otherwise difficult to detect. We simulate experiments on infrared thermographic images of power equipment and demonstrate that our approach improves fault detection and condition monitoring. The results show clearer fault indicators, enabling more accurate identification of issues like transformer core hot-spots and photovoltaic (PV) panel cell failures. These improvements contribute to smarter maintenance decisions - reducing energy losses from undetected faults, supporting predictive maintenance in the smart grid, and ultimately enhancing the reliability and energy efficiency of electrical systems.