Deep belief network based state classification for structural health diagnosis
Tamilselvan, Prasanna Wang, Yibin Wang, Pingfeng
Tamilselvan, Prasanna
Wang, Yibin
Wang, Pingfeng
Citations
Altmetric:
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2012
Type
Conference paper
Genre
Keywords
Fault diagnosis,Artificial intelligence in diagnostic classification,Deep belief networks
Subjects (LCSH)
Citation
Tamilselvan, Prasanna; Wang, Yibin; Wang, Pingfeng. 2012. Deep belief network based state classification for structural health diagnosis. 2012 IEEE Aerospace Conference
Abstract
Effective health diagnosis provides multifarious benefits such as improved safety, improved reliability and reduced costs for the operation and maintenance of complex engineered systems. This paper presents a novel multi-sensor health diagnosis method using Deep Belief Networks (DBN). The DBN has recently become a popular approach in machine learning for its promised advantages such as fast inference and the ability to encode richer and higher order network structures. The DBN employs a hierarchical structure with multiple stacked Restricted Boltzmann Machines and works through a layer by layer successive learning process. The proposed multi-sensor health diagnosis methodology using the DBN based state classification can be structured in three consecutive stages: first, defining health states and preprocessing the sensory data for DBN training and testing; second, developing DBN based classification models for the diagnosis of predefined health states; third, validating DBN classification models with testing sensory dataset. The performance of health diagnosis using DBN based health state classification is compared with support vector machine technique and demonstrated with aircraft wing structure health diagnostics and aircraft engine health diagnosis using 2008 PHM challenge data.
Table of Contents
Description
Click on the DOI link to access the article (may not be free).
Publisher
IEEE
Journal
Book Title
Series
IEEE Aerospace Conference
Digital Collection
Finding Aid URL
Use and Reproduction
Archival Collection
PubMed ID
DOI
ISSN
1095-323X