Dr. Zhen Sun visits the Eptisa headquarters


From March 3 to 6, Eptisa will have the honor of receiving Dr. Zhen Sun at its headquarters. We will have the pleasure of enjoying several presentations related to the use of AI Technology in bridge testing, as well as in the inspection and supervision market in Portugal.
About the speaker
Zhen Sun is a postdoctoral researcher at the Department of Civil Engineering at the University of Porto (Portugal). He received his doctorate from Yokohama National University (Japan). His main research interests include vehicle-bridge interaction analysis, machine learning-based structural condition assessment, structural monitoring and signal processing, and damage detection / load-bearing capacity assessment. the bridges. He has published over 40 scholarly articles with over 400 citations. He is also the holder of six registered invention patents and has been involved in three standards/codes related to bridge condition assessment. He has contributed to the evaluation of the condition and load capacity of bridges in several countries, such as China, Japan and Portugal.
He is a supervisor of a doctoral student and co-supervisor of three master's students. He was a member of the technical committee of the ICSBOC (International Cable Supported Bridge Operators' Conference) 2022 in Kobe, Japan. He is also guest editor of a special issue "Failure mechanism and prevention of civil infrastructure under operational and extreme conditions" in Engineering Failure Analysis (Elsevier, Impact Factor: 3,634) and reviewer for more than 10 international journals.
Bridges play an essential role in the transport infrastructure network, and their safety guarantees the functioning of traffic and economic development. The collapse of the Morandi bridge in Genoa, Italy in August 2018 raised deep concern among highway and railway bridge management bodies. It is imperative to keep bridges safe and reliable for our society.
Today, visual inspection and structural health monitoring have provided a large volume of data on bridge aging, and such large data has posed a challenge for traditional structural analysis approaches. Thanks to advances in AI technology, sophisticated machine learning and deep learning methods have been developed and are increasingly being applied in bridge asset management.
This talk will present research on bridge condition assessment with physics-based machine learning methods. First, a condition classification method for highway bridges based on natural language processing and machine learning is introduced, which is verified with inspection reports from 263 bridges. Second, machine learning-based approaches are developed to categorize train loads and estimate fatigue damage in the truss girder of a suspension bridge in Portugal. Third, the weight limit of trucks on bridges is determined with a reliability-based method that takes into account the influence of stochastic traffic flow. Finally,