A machine learning approach to model interdependencies between dynamic response and crack propagation

Thomas Fleet, Khangamlung Kamei, Feiyang He, Muhammad A. Khan, Kamran A. Khan, Andrew Starr

Research output: Contribution to journalLetterpeer-review

13 Scopus citations

Abstract

Accurate damage detection in engineering structures is a critical part of structural health monitoring. A variety of non-destructive inspection methods has been employed to detect the presence and severity of the damage. In this research, machine learning (ML) algorithms are used to assess the dynamic response of the system. It can predict the damage severity, damage location, and fundamental behaviour of the system. Fatigue damage data of aluminium and ABS under coupled mechanical loads at different temperatures are used to train the model. The model shows that natural frequency and temperature appear to be the most important predictive features for aluminium. It appears to be dominated by natural frequency and tip amplitude for ABS. The results also show that the position of the crack along the specimen appears to be of little importance for either material, allowing simultaneous prediction of location and damage severity.

Original languageBritish English
Article number6847
Pages (from-to)1-13
Number of pages13
JournalSensors (Switzerland)
Volume20
Issue number23
DOIs
StatePublished - 1 Dec 2020

Keywords

  • Damage detection
  • Fatigue crack growth
  • Machine learning
  • Thermomechanical fatigue

Fingerprint

Dive into the research topics of 'A machine learning approach to model interdependencies between dynamic response and crack propagation'. Together they form a unique fingerprint.

Cite this