Le 20 mai 2019

Outlier statistics as a means of exploring and visualising structural health monitoring (SHM ) data

  Nikolaos Dervilis *

* senior lecturer in the Department of Mechanical Engineering at the University of Sheffield (UK)

Abstract:

Statistical methods are presented for the data-based approach to structural health monitoring (SHM). The discussion initially focuses on the high level removal of the ‘masking effect’ of inclusive outliers. Multiple outliers commonly occur when novelty detection in the form of unsupervised learning is utilised as a means of damage diagnosis; then benign variations in the operating or environmental conditions of the structure must be handled very carefully, as it is possible that they can lead to false alarms. It is shown that recent developments in the field of robust regression can provide a means of exploring and visualising SHM data as a tool for exploring the different characteristics of outliers, and removing the effects of benign variations.

Nikolaos Dervilis is a senior lecturer 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.

He works with SFD team.