报告人简介：Dr. Zili Li is a Senior Lecturer (Associate Professor) in Civil Engineering Discipline, School of Engineering and Architecture at University College Cork, and a Visiting Scientist / Professor at Massachusetts Institute of Technology (MIT), USA. He holds a PhD degree from the University of Cambridge, UK and a bachelor degree from Tongji University, China. So far, he hasSecured €2.6+million research grant as the PI, including prestigious SFI Frontiers for the Future Programme (€612.8k total budget)(top-tier independent research grant). He is the chair of ISMLG 2023 (the 4th International Symposium of Machine Learning and Big Data in Geoscience),https://ismlg2023.comand has wonInternational (ISSMGE) Bright Spark Lecture Award. Currently, Dr. Li is mentoring 3 Postdocs, supervising 8 PhDs and hosting 3 visiting PhDs at University College Cork.

报告内容：The world-famous Large Hadron Collider (LHC) particle accelerator is housed in a large-scale underground tunnel network at the European Centre for Nuclear Research (CERN). 70 kilometres of deep CERN tunnels were excavated four decades ago lined with spray shotcrete, posing a risk to tunnel serviceability for high-accuracy particle collision experiments. To this end, a network of Distributed Fibre Optic Sensing (DFOS) cables was deployed around critical Tunnel TT10 section to measure the deformation development of tunnel structure with time. In comparison to conventional discrete point sensors, DFOS enables spatially continuous strain measurement along a single standard optical fibre over miles with better resistance to corrosion, electromagnetic interference and etc. In addition, a series of CERN robotics (e.g., automatic drone system) have gathered a large of amount of tunnel image data, which was then analysed using deep learning algorithms. Both DFOS and image big data brings new insights into tunnel ageing conditions and deformation modes at different sections than previously available. Results show thatthe proposed monitoring system allows the identification of severe crack-damaged tunnel sections and specific deformation patterns for the geotechnical & structural assessment of large-scale tunnel network.