Rapid Assessment of Distribution Line Damage via Autonomous UAV

Two-thirds of all electric outage minutes are weather-related, mostly the result of damage to above ground distribution lines. These outages close schools, shut down businesses and impede emergency services, costing the U.S. economy between $18 and $33 billion per year. Efforts to restore power start with the utility’s evaluation teams driving through flooded, icy, blocked, unlit roads to document the extent of storm damage to distribution lines. We propose an alternative method to rapidly assess line damage that will assist utility personnel to safely complete their mission. Evaluators often need access to hard-to-reach and unsafe locations after a storm. When this happens, they can launch an autonomous unmanned aerial vehicle (UAV) from their vehicle that will lock onto and follow the distribution lines. The UAV will use stereoscopic 3D depth perception to sense and avoid obstacles as it maintains a fixed distance from the overhead lines, collecting images as it travels the lines. Onboard algorithms will send a curated set of geo-tagged imagery to the Outage Management System (OMS). Other first responders can also be notified of unsafe conditions. In Phase I, we will develop pattern recognition algorithms to detect poles, crossarms and wires. We will analyze their geometry and flag anomalies that indicate structural damage, such as broken elements, downed lines or encroaching vegetation. In Phase II, we will detect more elements such as damaged pin-insulators, broken ties and blown fuses. We will also deploy our technology on the UAV and integrate with the OMS. Ultimately, the situational awareness provided by the UAV will reduce power restoration times by helping utilities prioritize repairs, better allocate resources and more efficiently deploy repair crews. While on standby, the UAV can be used for service calls, transmission line inspections, vegetation management, and substation monitoring.