We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Comparison of machine learning methods for crack localization.
- Authors
HELLE HEIN; JAANUSKA, LJUBOV
- Abstract
In this paper, the Haar wavelet discrete transform, the artificial neural networks (ANNs), and the random forests (RFs) are applied to predict the location and severity of a crack in an Euler-Bernoulli cantilever subjected to the transverse free vibration. An extensive investigation into two data collection sets and machine learning methods showed that the depth of a crack is more difficult to predict than its location. The data set of eight natural frequency parameters produces more accurate predictions on the crack depth; meanwhile, the data set of eight Haar wavelet coefficients produces more precise predictions on the crack location. Furthermore, the analysis of the results showed that the ensemble of 50 ANN trained by Bayesian regularization and Levenberg- Marquardt algorithms slightly outperforms RF.
- Subjects
MACHINE learning; FREE vibration; MARQUARDT algorithm; LOCALIZATION (Mathematics); ARTIFICIAL neural networks; ACQUISITION of data; DISCRETE wavelet transforms; WAVELETS (Mathematics)
- Publication
Acta et Commentationes Universitatis Tartuensis de Mathematica, 2019, Vol 23, Issue 1, p125
- ISSN
1406-2283
- Publication type
Article
- DOI
10.12697/ACUTM.2019.23.13