AI-embedded drone grid defect inspector wins APEC smart grid award
The award ceremony of the sixth Asia-Pacific Economic Cooperation (APEC) Energy Smart Communities Initiative Best Practices Awards Program held in Lima, Peru. In the photo: director of Electrical and Mechanical Services, Poon Kwok-ying (first row, fourth right), guests, winners from other APEC member economies and the Hong Kong, China delegation at the ceremony. Image courtesy government of the Hong Kong Special Administrative Region.
Power-hawk Inspector – a drone-based inspection system using embedded AI to identify power grid defects in real time – has been awarded in the 6th ESCI (Energy Smart Community Initiative) Awards Program.
The project, developed by the Hong Kong Productivity Council (HKPC), proposes an AI-based recognition technology using edge computation to detect the small and low-contrast defects of the electricity grid.
To enhance the capability to detect these defects in China’s power industry, the project team came up with solutions to overcome current bottlenecks of low identification accuracy and highly centralised calculations of existing defect identification models.
Specifically, the project proposed a defect recognition algorithm based on high-resolution networks under the framework of federated learning, as well as a few-shot learning method based on meta-learning to detect equipment defects.
Have you read:
Hong Kong PolyU establishes grid modernisation research centre
Hong Kong’s CLP Power reaches 2 million smart meters milestone
The project team carried out trials in several cities in China on the field transmission line sections of Shaoguan Power Supply Bureau, Heyuan Power Supply Bureau, Qingyuan Power Supply Bureau, Qujing Power Supply Bureau of Yunnan Power Grid and the National Engineering Research Center for Ultra-high Voltage Power Technology and New Electrical Equipment.
According to the ESCI, the project’s algorithm achieved high accuracy recognition of common small and weak defects such as transmission and distribution line defects and abnormal insulator surfaces in distribution lines and was experimentally validated in the power system.
Across 75.3km, a total of 13 defects, including power line damage, insulator lightning damage, and powerline foreign objects hanging, were discovered and identified in real time.
The prototype, states the ESCI, was easy to dismantle and carry, easy to use, with strong anti-interference ability, and easy to operate.
Trial results showed that the prototype developed in the project could stably identify the three typical defects in actual line environments, with a recognition accuracy of over 90%.
The 2024 ESCI
A gold award and a silver award are selected from each of the five categories: Smart Transport, Smart Buildings, Smart Grids, Smart Jobs and Consumers, and Low Carbon Model Towns.
Project Power-hawk Inspector won gold in this years Smart Grids category. The project is one of three winners coming from Hong Kong, China.
The other two include:
• E&M AI Lab: Driving Digital Transformation in Building Facilities Management, by the Hong Kong Government’s Electrical and Mechanical Services Department (EMSD), which received the silver award in the Smart Buildings category.
• Renewable Energy and Retired EV Battery Solution for Smart Grid Integration, also by the HKPC, which received the silver award in the Smart Grids category.
Commenting in a government of Hong Kong-issued release was director of Electrical and Mechanical Services, Poon Kwok-ying: “The three awards won in two categories not only acknowledge Hong Kong, China’s efforts in smart residential communities but also serve as a reminder to persist in our commitment to fostering innovation and technology to meet our carbon neutrality goal.”
The APEC Energy Working Group initiated the ESCI in 2010 and launched the biennial APEC ESCI Best Practices Awards in 2013 to recognise exemplary community-level projects that integrate renewable energy and energy efficiency technologies for sustainable development in the APEC region.
