TY - GEN
T1 - Structural damage detection with insufficient data using transfer learning techniques
AU - Chakraborty, Debejyo
AU - Kovvali, Narayan
AU - Chakraborty, Bhavana
AU - Papandreou-Suppappola, Antonia
AU - Chattopadhyay, Aditi
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
KW - damage classification
KW - hidden Markov models
KW - matching pursuit decomposition
KW - structural health monitoring
KW - time-frequency analysis
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=79956336485&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79956336485&partnerID=8YFLogxK
U2 - 10.1117/12.882025
DO - 10.1117/12.882025
M3 - Conference contribution
AN - SCOPUS:79956336485
SN - 9780819485434
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
T2 - Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2011
Y2 - 7 March 2011 through 10 March 2011
ER -