Wed
12
Feb
Seminars and Conferences
A Tutorial on Data-Driven Methods in Nonlinear Dynamics | with Professor Keith Worden from the University of Sheffield (UK)
On Wednesday 12 February from 3,00 p.m. it will be possible to participate in the seminar organised by Department of Structural, Geotechnical and Building Engineering-DISEG of Politecnico, with a talk by professor Keith Worden of the University of Sheffield (UK).
Professor Keith Worden is a world-renowned expert in structural dynamics, specialising in non-linear dynamics and structural health monitoring (SHM). A pioneer in data-driven monitoring, his methodologies are widely applied in industry and academia. He is a Professor in the Department of Mechanical Engineering at the University of Sheffield, where he leads one of the largest structural dynamics groups in the world and directs the Sheffield Laboratory for Verification and Validation. Professor Worden is also a Fellow of the Royal Academy of Engineering.
Over the last two decades, the use of machine learning technologies, or data-driven methods, has exploded throughout the field of engineering, including structural dynamics. A modern dynamics practitioner must have at least some familiarity with these technologies.
This seminar provides an overview of the main ideas in data-based engineering, focusing on non-linear dynamics and, in particular, on the identification of non-linear systems. A viewpoint based on modern Bayesian regression methods is adopted. Much attention is paid to the importance of combining measured data with physical intuition in modelling dynamic systems and structures. This approach starts with the concept of ‘grey-box’ models and generalises it in the emerging field of physics-informed machine learning. Although the tutorial focuses on a narrow application context, the numerous references provided will allow the curious reader to explore further.
For more information, please contact cecilia.surace@polito.it.
Professor Keith Worden is a world-renowned expert in structural dynamics, specialising in non-linear dynamics and structural health monitoring (SHM). A pioneer in data-driven monitoring, his methodologies are widely applied in industry and academia. He is a Professor in the Department of Mechanical Engineering at the University of Sheffield, where he leads one of the largest structural dynamics groups in the world and directs the Sheffield Laboratory for Verification and Validation. Professor Worden is also a Fellow of the Royal Academy of Engineering.
Over the last two decades, the use of machine learning technologies, or data-driven methods, has exploded throughout the field of engineering, including structural dynamics. A modern dynamics practitioner must have at least some familiarity with these technologies.
This seminar provides an overview of the main ideas in data-based engineering, focusing on non-linear dynamics and, in particular, on the identification of non-linear systems. A viewpoint based on modern Bayesian regression methods is adopted. Much attention is paid to the importance of combining measured data with physical intuition in modelling dynamic systems and structures. This approach starts with the concept of ‘grey-box’ models and generalises it in the emerging field of physics-informed machine learning. Although the tutorial focuses on a narrow application context, the numerous references provided will allow the curious reader to explore further.
For more information, please contact cecilia.surace@polito.it.