A machine-learning approach for damage detection in aircraft structures using self-powered sensor data

Hadi Salehi, Saptarshi Das, Shantanu Chakrabartty, Subir Biswas, Rigoberto Burgueño

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

17 Scopus citations

Abstract

This study proposes a novel strategy for damage identification in aircraft structures. The strategy was evaluated based on the simulation of the binary data generated from self-powered wireless sensors employing a pulse switching architecture. The energy-aware pulse switching communication protocol uses single pulses instead of multi-bit packets for information delivery resulting in discrete binary data. A system employing this energy-efficient technology requires dealing with time-delayed binary data due to the management of power budgets for sensing and communication. This paper presents an intelligent machine-learning framework based on combination of the low-rank matrix decomposition and pattern recognition (PR) methods. Further, data fusion is employed as part of the machine-learning framework to take into account the effect of data time delay on its interpretation. Simulated time-delayed binary data from self-powered sensors was used to determine damage indicator variables. Performance and accuracy of the damage detection strategy was examined and tested for the case of an aircraft horizontal stabilizer. Damage states were simulated on a finite element model by reducing stiffness in a region of the stabilizer's skin. The proposed strategy shows satisfactory performance to identify the presence and location of the damage, even with noisy and incomplete data. It is concluded that PR is a promising machine-learning algorithm for damage detection for time-delayed binary data from novel self-powered wireless sensors.

Original languageEnglish
Title of host publicationSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017
EditorsJerome P. Lynch
PublisherSPIE
ISBN (Electronic)9781510608214
DOIs
StatePublished - 2017
EventSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017 - Portland, United States
Duration: Mar 26 2017Mar 29 2017

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10168
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceSensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2017
Country/TerritoryUnited States
CityPortland
Period03/26/1703/29/17

Keywords

  • aerospace structures
  • Damage identification
  • machine learning
  • pattern recognition
  • self-powered sensors

Fingerprint

Dive into the research topics of 'A machine-learning approach for damage detection in aircraft structures using self-powered sensor data'. Together they form a unique fingerprint.

Cite this