An article from Oak Ridge National Laboratory describes how researchers there are using sensors, drones, and machine learning to both prevent wildfires and reduce their damage to critical infrastructure.
In terms of prevention, sensors placed near power lines or in power electronics equipment can register variations in power flow that lead to superheated sparks, the kind that can trigger wildfires. Additionally, utilities and universities are contributing wave form “signatures” that show spikes in voltage or current caused by anomalies such as arcing. The next steps will involve training a software program to recognize similar signatures and pinpoint where the arcing is happening. Drones come in by providing access to rugged areas that are difficult to reach. Equipped with the right sensors and other devices, they can record video and audio and detect heat and radio frequency emissions from small arcs. Researchers are also working on technology for drones that would enable them to detect sparks ahead of a large blaze and even help direct fire fighting efforts.
While much of the focus of these efforts is on electricity infrastructure, there are also clear benefits to other sectors. When electricity infrastructure ignites or is damaged or destroyed by a wildfire, water and wastewater utilities may experience power outages or direct impacts to their facilities and operations. Additionally, concerns of arcing electric equipment, potentially fed by the challenges of accurately monitoring this infrastructure, have prompted electricity providers to implement public safety power shutoffs, which have affected water and wastewater utilities.
