Damage classification of composites using machine learning

Shweta Dabetwar, Stephen Ekwaro-Osire, João Paulo Dias

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Composite materials have tremendous and ever-increasing applications in complex engineering systems; thus, it is important to develop non-destructive and efficient condition monitoring methods to improve damage prediction, thereby avoiding catastrophic failures and reducing standby time. Nondestructive condition monitoring techniques when combined with machine learning applications can contribute towards the stated improvements. Thus, the research question taken into consideration for this paper is “Can machine learning techniques provide efficient damage classification of composite materials to improve condition monitoring using features extracted from acousto-ultrasonic measurements?” In order to answer this question, acoustic-ultrasonic signals in Carbon Fiber Reinforced Polymer (CFRP) composites for distinct damage levels were taken from NASA Ames prognostics data repository. Statistical condition indicators of the signals were used as features to train and test four traditional machine learning algorithms such as K-nearest neighbors, support vector machine, Decision Tree and Random Forest, and their performance was compared and discussed. Results showed higher accuracy for Random Forest with a strong dependency on the feature extraction/selection techniques employed. By combining data analysis from acoustic-ultrasonic measurements in composite materials with machine learning tools, this work contributes to the development of intelligent damage classification algorithms that can be applied to advanced online diagnostics and health management strategies of composite materials, operating under more complex working conditions.

Original languageEnglish
Title of host publicationSafety Engineering, Risk, and Reliability Analysis
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791883501
DOIs
StatePublished - 2019
EventASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019 - Salt Lake City, United States
Duration: Nov 11 2019Nov 14 2019

Publication series

NameASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
Volume13

Conference

ConferenceASME 2019 International Mechanical Engineering Congress and Exposition, IMECE 2019
CountryUnited States
CitySalt Lake City
Period11/11/1911/14/19

Keywords

  • Composite materials
  • Damage classification
  • Health management
  • Machine learning

Fingerprint Dive into the research topics of 'Damage classification of composites using machine learning'. Together they form a unique fingerprint.

Cite this