Automated Damage Assessment and Rapid Post-storm Recovery using LiDAR and Machine Learning
While many external factors influence resiliency, weather remains the single greatest threat to the electric power grid. When damage occurs, it is very time-consuming and costly to identify due to the vastness of T&D infrastructure and continued reliance on human teams to “walk the line” and physically inspect assets. In collaboration with Entergy and other utilities, we have developed a total solution to the problem of post-storm recovery that is currently being tested and deployed to hurricane-prone service territories in the southern United States. By leveraging flight vehicles, light detection and ranging (LiDAR) sensors, and machine learning, the time of post-storm damage assessment is reduced from days and weeks to hours. The presentation will offer an overview of the solution, how it works, its engineering, and a discussion of results to date.