Multi-Sensor Health Diagnosis Using Deep Belief Network Based
State Classification
Issue Date
Embargo End Date
Authors
Advisor
Citation
Tamilselvan, Prasanna (2011). Multi-Sensor Health Diagnosis Using Deep Belief Network Based State Classification. -- In Proceedings: 7th Annual Symposium: Graduate Research and Scholarly Projects. Wichita, KS: Wichita State University, p. 46-47
Abstract
Effective health diagnosis provides multifarious benefits such as improved safety, reliability and economical maintenance of complex engineered systems. This paper presents a novel multi-sensor health diagnosis method using Deep Belief Network (DBN) based state classification. 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 can be structured in three consecutive stages: first, defining health states and collecting 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 proposed DBN health state classification is compared with four other existing classification methods and demonstrated with a case study.
Table of Content
Description
Research completed at the Department of Industrial and Manufacturing Engineering