Comparison of machine learning methods for crack localization

DOI10.12697/ACUTM.2019.23.13MaRDI QIDQ5205437zbMATH OpenOpenAlexFDO

Authors H. Hein, Ljubov Jaanuska

Publication date 11 December 2019

Published in Acta et Commentationes Universitatis Tartuensis de Mathematica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.12697/acutm.2019.23.13

zbMATH Keywords

backpropagation networkcracksEuler-Bernoulli beamfree vibrationHaar waveletrandom forest

Mathematics Subject Classification ID

Numerical methods for wavelets (65T60) Learning and adaptive systems in artificial intelligence (68T05) Vibrations in dynamical problems in solid mechanics (74H45) Rods (beams, columns, shafts, arches, rings, etc.) (74K10)

Recommendations

• Solution of the fracture detection problem by machine learning methods
• Detection of cracks using neural networks and computational mechanics
• Crack Identification as an Optimization Task
• Deep multimodal autoencoder for crack criticality assessment
• Crack detection by the topological gradient method
• scientific article; zbMATH DE number 2151305

Cites work

• Analytical methods in rotor dynamics
• Exact solution of the multi-cracked Euler-Bernoulli column
• Random forests
• Using genetic algorithms and finite element methods to detect shaft crack for rotor-bearing system.
• Vibration of cracked beams

Cited in

(4)

• Rotor crack identification based on neural networks and modal data
• Quantification of cracks in beams on the Pasternak foundation using Haar wavelets and machine learning
• Advances in Neural Networks – ISNN 2005
• The poroelastic layer with an axisymmetric cylindrical hole under different types of loading

This page was built for publication: Comparison of machine learning methods for crack localization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5205437)