Exploring Environmental and Operational Variations in SHM Data Using Heteroscedastic Gaussian Processes
The higher levels of Structural Health Monitoring (SHM)—localisation, classification, severity assessment—are only accessible using supervised learning in the data-based approach. Unfortunately, one does not often have data from damaged structures; this forces a dependence on unsupervised learning i.e. novelty detection. This means that detection is sensitive to benign environmental and operational variations (EOVs) in or around the structure. In this paper a two-stage procedure is presented: identify EOVs in training data using a nonlinear manifold approach and remove EOVs by utilising the interesting tool of heteroscedastic Gaussian processes (GPs). In Classical GPs models, the data noise is assumed to have constant variance throughout the input space. This assumption is a drawback most of the time, and a more robust Bayesian regression tool where GP inference is tractable is needed. In this work a combination of data projection and a non-standard heteroscedastic GP is presented as means of visualising and exploring SHM data.
KeywordsEnvironmental and operational variations Manifold learning Pattern recognition Gaussian processes
The support of the UK Engineering and Physical Sciences Research Council (EPSRC) through grant reference number EP/J016942/1 and EP/K003836/2 is gratefully acknowledged.
- 2.Titsias, M.K., Lázaro-gredilla, M.: Variational heteroscedastic gaussian process regression. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 841–848 (2011)Google Scholar
- 4.Cross, E.J.: On structural health monitoring in changing environmental and operational conditions. Ph.D Thesis, University of Sheffield (2012)Google Scholar
- 11.Reynders, E., Wursten, G., De Roeck, G.: Output-only structural health monitoring in changing environmental conditions by means of nonlinear system identification. Struct. Health Monit. 13(1), 82–93 (2014)Google Scholar
- 12.Dervilis, N., Worden, K., Cross, E.J.: On robust regression analysis as a means of exploring environmental and operational conditions for SHM data. J. Sound Vib. 347(0), 279–296 (2015)Google Scholar
- 15.Peeters, B., Maeck, J., De Roeck, G.: Vibration-based damage detection in civil engineering: excitation sources and temperature effects. Smart Mat. Struct. 10(3), 518 (2001)Google Scholar
- 20.Nabney,. I.T.: NETLAB: Algorithms for Pattern Recognition. Springer, New York (2004)Google Scholar
- 21.Saul, L.K., Roweis, S.T.: An introduction to locally linear embedding. Available at: http://www.cs.toronto.edu/~roweis/lle/publications.html (2000)
- 24.Scholz, M., Vigário, R.: Nonlinear PCA: a new hierarchical approach. In: Proceedings ESANN, pp. 439–444 (2002)Google Scholar
- 29.Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning.MIT, Cambridge (2006)Google Scholar