Premium
A Non‐linear Manifold Strategy for SHM Approaches
Author(s) -
Dervilis N.,
Antoniadou I.,
Cross E. J.,
Worden K.
Publication year - 2015
Publication title -
strain
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.477
H-Index - 47
eISSN - 1475-1305
pISSN - 0039-2103
DOI - 10.1111/str.12143
Subject(s) - structural health monitoring , novelty detection , novelty , nonlinear dimensionality reduction , covariance , key (lock) , manifold (fluid mechanics) , computer science , gaussian , data mining , artificial intelligence , pattern recognition (psychology) , machine learning , mathematics , statistics , engineering , structural engineering , physics , mechanical engineering , philosophy , theology , computer security , quantum mechanics , dimensionality reduction
In the data‐based approach to structural health monitoring (SHM) when novelty detection is utilised as a means of diagnosis, benign operational and environmental variations of the structure can lead to false alarms and mask the presence of damage. The key element of this paper is to demonstrate a series of pattern recognition approaches which investigate complex correlations between the variables and thus potentially shed light on the variations within the data that are of interest for SHM. The non‐linear manifold learning techniques discussed here, like locally linear embedding combined with robust discordance measures like the minimum covariance determinant and regression techniques like Gaussian processes offer a strategy that includes reliable novelty detection analysis but also a method of investigating the space where structural data clusters are lying.