Abstract

The effective detection and classification of damage in complex structures is an important task in the realization of structural health monitoring (SHM) systems. Conventional information processing techniques utilize statistical modeling machinery that requires large amounts of 'training' data which is usually difficult to obtain, leading to compromised system performance under these data-scarce conditions. However, in many SHM scenarios a modest amount of data may be available from a few different but related experiments. In this paper, a new structural damage classification method is proposed that makes use of statistics from related task(s) to improve the classification performance on a data set with limited training examples. The approach is based on the framework of transfer learning (TL) which provides a mechanism for information transfer between related learning tasks. The utility of the proposed method is demonstrated for the classification of fatigue damage in an aluminum lug joint.

Original languageEnglish (US)
Title of host publicationSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
DOIs
StatePublished - May 26 2011
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011 - San Diego, CA, United States
Duration: Mar 7 2011Mar 10 2011

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7981
ISSN (Print)0277-786X

Other

OtherSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
CountryUnited States
CitySan Diego, CA
Period3/7/113/10/11

Keywords

  • damage classification
  • hidden Markov models
  • matching pursuit decomposition
  • structural health monitoring
  • time-frequency analysis
  • transfer learning

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Structural damage detection with insufficient data using transfer learning techniques'. Together they form a unique fingerprint.

  • Cite this

    Chakraborty, D., Kovvali, N., Chakraborty, B., Papandreou-Suppappola, A., & Chattopadhyay, A. (2011). Structural damage detection with insufficient data using transfer learning techniques. In Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011 [798147] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7981). https://doi.org/10.1117/12.882025