Machine learning tools in SHM from single structures to populations
Tracks
Day of Tutorials
Monday, June 24, 2024 |
3:40 PM - 4:50 PM |
408-409 |
Overview
Dr. Nikolaos Dervilis | University of Sheffield, United Kingdom
Details
In Structural Health Monitoring (SHM), measured data that correspond to an wide set of operational and damage conditions are rarely available or very expensive to obtain. A way of probabilistic framework for the classification, investigation and labelling of data is discussed as an online strategy for SHM to aid both damage detection and identification, while using a limited number of the most informative labelled data.
A way of including physics knowledge and grey box modelling will also be discussed. Another, potential solution considers that information might be transferred, in some sense, between systems. A population-based approach to SHM (PBSHM) looks to both model and transfer this missing information, by considering data collected from groups of similar structures. A framework will be proposed to model a population of systems, such that datasets are only available from a subset of members. The ideas will be presented in a variety of engineering systems from experimental (test-rig) members to bridges and operational wind farms.
Speaker
Dr. Nikolaos Dervilis
University of Sheffield
Machine learning tools in SHM from single structures to populations
Biography
Nikolaos Dervilis is a Professor in the Department of Mechanical Engineering at the University of Sheffield and a member of the Dynamics Research Group (DRG). He studied physics in the National and Kapodistrian University of Athens. Later, he obtained his MSc in Sustainable and Renewable Energy Systems from the University of Edinburgh in the Department of Electronics and Electrical Engineering. He obtained his PhD from the University of Sheffield, Mechanical Engineering Department in the field of machine learning for Structural Health Monitoring (SHM). His expertise focuses on SHM, pattern recognition, data analysis and nonlinear dynamics. He is especially engaged with renewable energy research, particularly wind turbine farms.