NYPA adds AI to drone inspection and analysis of power lines

Already accustomed to using drones to inspect its enormous 1,400 circuit miles of transmission infrastructure, the New York Power Authority (NYPA) says it’s now turning to artificial intelligence (AI) analytics to both speed up and improve detection of weak points requiring repair, and take action to prevent costly outages.

To make infrastructure images brought back by its inspection drones more manageable and useful, the NYPA has turned to AI tech startup Buzz Solutions, whose platforms considerably speed the analysis process while maintaining an accuracy rate of 85%. 

In addition to automating what was previously a painstaking manual procedure, the self-learning capacities of AI create a virtuous spiral of increasingly quick and efficient monitoring of infrastructure data.

Read: Skyfire aids PG&E earn California-wide BVLOS drone infrastructure inspection waiver

NYPA tapped Palo Alto-based Buzz Solutions after 2021 bidding by companies offering AI tech to analyze the millions of images the utility’s fleet of inspection drones – as well as helicopters and planes – capture every year. Manual scrutiny to map those photos together to detect and report weakness or failings in them can take eight months to transform the raw data into actionable information. 

In the meantime, those defects risk deteriorating further, and eventually breaking down and causing power outages to customers that NYPA wants to avoid. Meanwhile, pro-active intervention to repair problems before they lead to system failures is less expensive – as is using drones and AI tech to collect and analyze infrastructure imagery over manual methods.

All of which is why NYPA turned to Buzz Solutions’ AI platforms to speed up and improve data management, processing, and anomaly detection of infrastructure captures its inspection drones collect. 

“Human labor is incredibly expensive and is also prone to a higher error rate over time, which is where AI really has the biggest advantage as it continues to improve at scale,” said Vikhyat Chaudhry, Buzz Solutions’ chief technology officer. “With a baseline accuracy of 85%, Buzz Power AI has great potential to improve and learn from NYPA’s datasets, leveraging subject-matter experts’ feedback via our human-in-the-loop tool.”

Read: American Robotics adds anomaly detection AI to automated Scout drones 

Inclusion of Buzz Solutions’ AI platforms in its infrastructure data processing is part of the same VISION2030 strategy striving to make NYPA the first fully digital utility by 2030 – an objective that earlier led the company to start using drones in the inspection process.

“Drone technology has the potential to streamline the way we analyze our transmission assets,” said Christina Park, NYPA’s director of asset intelligence solutions. “The proof-of-concept testing showed that using an artificial intelligence-based platform significantly reduced the time required for inspection and analysis. Asset images can be analyzed in hours or days rather than months and allow our maintenance groups to prioritize repairs and reduce the potential of failure to meet its mission of providing reliable, low-cost, and clean energy to customers.”