Power System Condition Monitoring and Inspection Across Multiple Geographical and Weather Conditions

Abstract

Power systems span a wide range of environments, including deserts, forests, mountainous regions, and tundra landscapes. These systems are exposed to extreme weather conditions like heavy snow, rain, fog, and heat, which can accelerate wear and lead to system failures. Traditional methods for inspecting power infrastructure are time-consuming, labor-intensive, and often dangerous, especially in remote or difficult-to-reach locations. -The stability and reliability of power systems are critical to modern infrastructure, but maintaining these systems in geographically diverse regions and under varying weather conditions poses significant challenges. This research proposes a geospatially adaptive framework that integrates Unmanned Aerial Vehicles (UAVs), advanced sensors, and machine learning techniques to monitor and inspect power systems in real-time. By leveraging UAVs and autonomous inspection methods, this research aims to enhance power system reliability through continuous monitoring in environments ranging from deserts to mountainous regions, and under weather conditions such as heavy rain, snow, and fog. This approach will enable more efficient, safe, and precise condition assessment of power grids in both urban and remote locations. -Objectives -Dynamic Monitoring Framework: Develop a Machine Vision-assisted framework capable of adapting to various geographical terrains (deserts, forests, mountains, tundra) and weather conditions (rain, fog, snow, extreme heat) -Safety Validation and Verification: Develop machine learning algorithms that take into account the geographical and environmental context to optimize UAV flight patterns, sensor positioning, and data collection strategies for different conditions. Ensure that UAVs can operate autonomously and safely under adverse weather conditions, minimizing the risk of system failures and reducing the need for manual inspections.

-The proposed research will span over three years with a budget allocated for equipment, personnel, and field testing. A detailed budget breakdown and timeline will be provided upon request.