A prototype of a mobile system that detects and geolocates damaged and downed utility poles in the aftermath of a natural disaster — such as a hurricane — has been developed by researchers from the Department of Energy's Oak Ridge National Laboratory (ORNL).

According to its developers, the system runs on edge computing hardware that is mounted on a quadcopter or drone, which can be deployed in the event that local infrastructure is damaged or destroyed following a natural disaster.

Source: ORNLSource: ORNL

To accomplish this, the researchers employed machine learning algorithms and onboard imaging hardware so that the system accurately detects and assesses damage to utility poles. Information about the location of the damaged utility poles is then uploaded to a central processing hub, called the Environment for Analysis of Geo-Located Energy Information (EAGLE-I), which further relays that data to utility companies and first responders, among others.

Dubbed a real-time situational awareness tool for the nation's energy infrastructure, EAGLE-I reportedly monitors energy infrastructure assets, displays possible threats to energy infrastructure, reports energy outages and coordinates emergency response and recovery.

Currently, the ORNL team is attempting to obtain training data to improve the accuracy of the system by capturing images of energy infrastructure damage left behind in the wake of a disaster.

To contact the author of this article, email mdonlon@globalspec.com