Marcus Omori Yano | PhD Candidate, São Paulo State University (UNESP), Ilha Solteira, Brazil
December 14, 2022 | 11h00-12h00 | Room U.0.6 | https://videoconf-colibri.zoom.us/j/93285885760 | Lusófona University, Lisbon, Portugal
Abstract: The number of bridges worldwide is extensive, making it financially and technically challenging for the authorities to install a structural health monitoring (SHM) system and collect large quantities of data for every single bridge. Transfer learning has gained relevance in the last few years to extend the SHM concept for most bridges while minimizing costs with monitoring systems and time with data measurement. It can be especially suitable for those types of bridges that are structurally similar and replicated extensively, like overpasses and bridges integrated into highways. In the presentation, the effectiveness of transfer learning methods is compared through the classification performance using real-world monitoring data sets collected from the Z-24 Bridge in Switzerland and the PI-57 Bridge in France.
Short Bio: Marcus Omori Yano is PhD candidate at São Paulo State University (UNESP) and visiting researcher at Faculty of Engineering of the Lusófona University. He holds BSc (2017) and MSc (2019) degree in Mechanical Engineering from UNESP. His main research projects are related to transfer learning applied to structural health monitoring cases to assess the structural condition of different types of structures using the knowledge from a known structure. Recently, Marcus has been developing his work on knowledge transfer applications in civil structures with the collaboration of the research team.