Article: Robust methods for outlier detection and regression for SHM applications Journal: International Journal of Sustainable Materials and Structural Systems (IJSMSS) 2015 Vol.2 No.1/2 pp.3 - 26 Abstract: In this paper, robust 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. The paper is not, in any sense, a survey; it is an overview and summary of recent work by the authors. Inderscience Publishers - linking academia, business and industry through research

Title: Robust methods for outlier detection and regression for SHM applications

Authors: Nikolaos Dervilis; Ifigeneia Antoniadou; Robert J. Barthorpe; Elizabeth J. Cross; Keith Worden

Addresses: Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield S1 3JD, England, UK ' Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield S1 3JD, England, UK ' Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield S1 3JD, England, UK ' Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield S1 3JD, England, UK ' Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Mappin Street, Sheffield S1 3JD, England, UK

Abstract: In this paper, robust 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. The paper is not, in any sense, a survey; it is an overview and summary of recent work by the authors.

Keywords: structural health monitoring; SHM; environmental influences; operational influences; leverage points; outliers; novelty detection; outlier detection; robust regression.

DOI: 10.1504/IJSMSS.2015.078354

International Journal of Sustainable Materials and Structural Systems, 2015 Vol.2 No.1/2, pp.3 - 26

Received: 02 Aug 2015
Accepted: 28 Feb 2016
Published online: 15 Aug 2016 *

Title: Robust methods for outlier detection and regression for SHM applications

Keep up-to-date