Professor Kai-leung Yung, BBS is Director of Research Centre for Deep Space Explorations, Sir Sze-yuen Chung Professor in Precision Engineering, Chair Professor of Precision Engineering and Associate Head of Department of Industrial and Systems Engineering of The Hong Kong Polytechnic University. He has strong expertise and a wealth of practical experience in making sophisticated space tools for both national and international deep space exploration missions. These include the "Mars Rock Corer" for the European Space Agency's Mars Express Mission (2003), the "Soil Preparation System" for the historic Sino-Russian Phobos-Grunt Mission (2011), the “Jovian Plasma Dynamics and Composition” and “Jovian Neutral Atoms” analyzers for the Jupiter Icy Moons Explorer Mission (2023) and advanced precision robotic systems for the China Lunar Exploration Missions such as the Camera Pointing System for Chang’e3 and 4 (2013, 2019) on both the front side and far side of the Moon, the “Surface Sampling and Packing System” for Change’5, the national first Lunar Sample Return Mission (2020), and the “Mars Landing Surveillance Camera” for the first national Mars Soft Landing and Exploration “Tianwen-1” Mission (2020-21). He has received many local and international awards, and has been successful in the transfer of space technology for applications on Earth.

Intelligent Non-invasive Structural Health Inspection System for Multi-part Covers

Abstract:

In Hong Kong, numerous multi-part covers are installed on large drains, chambers, and box culverts to cover the entrance for regular inspections or maintenance. Many are across main roads taking the full brunt of heavy traffic. Opening a multi-part cover for underneath structural inspection is costly and causes traffic disruptions. Various inspection methods including using robots are restricted by the types of piping/channels, configurations, and unknown distances from entry ports. Measuring vibrational signals has been shown in many publications to be a viable means for sensing structural faults within a distance, and the latest artificial intelligence (AI) technology could be deployed to analyse the signal.

This project aims to conduct a feasibility study on developing an intelligent non-invasive structural health inspection system for scanning the multi-part covers on main roads without traffic interruptions. Several state-of-the-art AI technologies are adopted to identify acoustic emissions from a problematic multi-part cover admit background environmental and traffic noises. The system will generally narrow down a problematic multi-part cover in stages. AI technologies can help distinguish a problematic multipart cover from the complexity of environmental and traffic noises.

This project result will be a non-invasive inspection method for examining structures underneath a multi-part cover. The approach enables examining the multi-part cover underneath the structure at low cost and reduces traffic disruptions.