Nikunj C. Oza's Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category •

Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring

Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring. Mark Schwabacher, Nikunj C. Oza, and Bryan Matthews. In AIAA Infotech@Aerospace Conference, 2007.

Download

[PDF]770.3kB  

Abstract

This paper describes the initial results of applying four machine-learning-based unsupervised anomaly detection algorithmsÑOrca, GritBot, the Inductive Monitoring System, and one-class Support Vector MachinesÑto historical data from the Space Shuttle Main Engine. The paper describes five anomalies detected by the four algorithms.

BibTeX Entry

@inproceedings{scoz07,
	author = {Mark Schwabacher, Nikunj C. Oza, and Bryan Matthews},
	title = {Unsupervised Anomaly Detection for Liquid-Fueled Rocket Propulsion Health Monitoring},
	booktitle={AIAA Infotech@Aerospace Conference},
	abstract={This paper describes the initial results of applying four machine-learning-based unsupervised anomaly detection algorithmsÑOrca, GritBot, the Inductive Monitoring System, and one-class Support Vector MachinesÑto historical data from the Space Shuttle Main Engine. The paper describes five anomalies detected by the four algorithms.},
	bib2html_pubtype = {Other Conference},
	bib2html_rescat = {Fault Detection},
	year = {2007}
}

Generated by bib2html.pl (written by Patrick Riley ) on Sun Jan 13, 2008 22:02:08