Artificial intelligence detects abnormalities in substation equipment

TEPCO Power Grid and NTT DATA Corporation have announced that they will begin installing a solution equipped with artificial intelligence (AI) for visual/sound analysis to detect and diagnose abnormalities in distribution substation equipment of TEPCO PG. 

By installing the solution in 1,300 distribution substations during the 2019 fiscal year, TEPCO PG expects to reduce time spent on inspection patrols in the field by more than 50%.

Image/video-analysis AI, codeveloped by NTT DATA and TEPCO PG, will learn substation operational data to detect abnormalities such as oil leaks in oil-immersed transformers and damage to substation facilities, including barrier fences. 

The technology will also be able to read analogue meters, while sound-detecting AI will detect abnormalities such as damaged or worn bearings.

TEPCO PG, like many other grid companies in Japan, is faced with the challenge of managing ageing facilities at a time when available labour is declining. 

The two companies decided to install the solution after its efficiency was confirmed in demonstration tests involving both underground and aboveground substations in 2017.

NTT DATA’s Digital Maintenance Solution integrates processes for facility maintenance planning and implementation. Image/video-analysis AI, which combines deep-learning and video-analysis technologies, is based on the 

“AMY INSIGHT” AI solution of Automagi Inc, a developer of technologies that automate visual-analysis functions, which humans normally perform, to detect abnormalities, identify objects and diagnose damage.

The sound-analysis AI learns normal sounds using NTT DATA’s Monone solution, which is built on various technologies of the NTT Group. 

Monone visualises and analyses sound using abnormal-sound-detection technology, one of the NTT Group’s corevo AI technologies, to detect signs of wear/damage, optimise maintenance costs and raise operational uptime.

Going forward, TEPCO PG aims to leverage its collaboration with NTT DATA to further advance its power equipment maintenance technologies, reduce wheeling charge, and enhance power-supply stability. 

NTT DATA will continue enhancing the solution by integrating various analytical models and robotics technologies that support equipment inspections and operations. 

NTT DATA will also develop a digital maintenance IoT platform to help power, gas and railroad companies maintain their equipment more efficiently. The platform will use an architecture model that stores and utilises various sensing data obtained from user companies, open sources and the field.

Commenting on the TEPCO PG solution, Simon Driscoll, Practice Lead, Data & Intelligence at NTT DATA UK, said: “Japan is not the only country facing issues with managing ageing facilities and infrastructures. In the UK, many utility companies and telco operators face the same issue of outdated physical presences, in need of frequent and costly repair or maintenance. At the same time, both industries are under immense pressures to keep costs low, while delivering exceptional and seamless customer service. 

“AI-enabled solutions allow these companies to increase efficiency and improve customer service, while avoiding many of the health and safety issues that come with workers physically checking this equipment. Our solution represents a tangible example of AI being put into practice in an everyday way that will benefit thousands. There is a huge opportunity for UK-based companies to reap the rewards of this technology and form similar, mutually-beneficial partnerships within numerous industries.”