Abstract
All damage identification activities inevitably involve uncertainties, and the resulting classification ambiguity in contaminated structural health monitoring (SHM) features can dramatically degrade the damage assessment capability. Probabilistic uncertainty quantification (UQ) models characterize the distribution of SHM features as random variables, and the UQ models facilitate making decisions on the occurrence, location, and type of the damages. A Bayesian framework will be adopted and the damage classification is transformed into a model selection process, in which the most plausible structural condition is determined by means of the recursively updated posterior confidence. In contrast to the probabilistic approach, machine learning is another candidate approach, which employs training data and extracts features from the recorded measurements. A support vector machine (SVM) is employed to classify the frequency response function data obtained from rotary machine under different damaged conditions. With different size of feature and different kernel functions, the classification of ball bearing damages are studied. Comparison between the Bayesian model selection approach and SVM is concluded in this paper.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Reference
Bendat JS, Piersol AG (1986) Random data: analysis and measurement procedures, 2nd edn. Wiley, New York
Brillinger DR (1981) Time series: data analysis and theory. McGraw-Hill, New York
Mace BR, Worden K, Manson G (2005) Uncertainty in structural dynamics. J Sound Vib 288:423–429
Mao Z, Todd MD (2012) A model for quantifying uncertainty in the estimation of noise-contaminated measurements of transmissibility. Mech Syst Signal Process 28:470–481
Mao Z, Todd MD (2013) Statistical modeling of frequency response function estimation for uncertainty quantification. Mech Syst Signal Process 38:333–345
Mao Z, Todd MD (2013) Optimal structural health monitoring feature selection via minimized performance uncertainty. Key Eng Mater 558:235–243
Welch PD (1967) The use of fast fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms. IEEE Trans Audio Electroacoust 15:70–73
Mao Z, Todd MD (2013) Bayesian updating of detection capability with frequency response function related structural health monitoring features. The proceedings of the 9th international workshop on structural health monitoring (IWSHM 2013), Stanford University, Palo Alto, CA
Acknowledgement
This research was supported by the research grant (UD130058JD) of the Agency for Defense Development of the Korean government and by the Leading Foreign Research Institute Recruitment Program through the National Research Foundation of Korea funded by the Ministry of Science, ICT and Future Planning (2011–0030065).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Mao, Z., Todd, M. (2015). Comparison of Damage Classification Between Recursive Bayesian Model Selection and Support Vector Machine. In: Atamturktur, H., Moaveni, B., Papadimitriou, C., Schoenherr, T. (eds) Model Validation and Uncertainty Quantification, Volume 3. Conference Proceedings of the Society for Experimental Mechanics Series. Springer, Cham. https://doi.org/10.1007/978-3-319-15224-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-15224-0_11
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-15223-3
Online ISBN: 978-3-319-15224-0
eBook Packages: EngineeringEngineering (R0)