Fault detection and precedent-free localization in thermal-fluid systems

This thesis presents a method for fault detection and precedent-free isolation for two types of channel flow systems, which were modeled with the finite element method. Unlike previous fault detection methods, this method requires no a priori knowledge or training pertaining to any particular fault...

Full description

Bibliographic Details
Main Author: Carpenter, Katherine Patricia
Format: Others
Language:English
Published: 2011
Subjects:
Online Access:http://hdl.handle.net/2152/ETD-UT-2010-12-2608
id ndltd-UTEXAS-oai-repositories.lib.utexas.edu-2152-ETD-UT-2010-12-2608
record_format oai_dc
spelling ndltd-UTEXAS-oai-repositories.lib.utexas.edu-2152-ETD-UT-2010-12-26082015-09-20T16:57:44ZFault detection and precedent-free localization in thermal-fluid systemsCarpenter, Katherine PatriciaFault detectionFault localizationThermal-fluid systemsChannel flowThis thesis presents a method for fault detection and precedent-free isolation for two types of channel flow systems, which were modeled with the finite element method. Unlike previous fault detection methods, this method requires no a priori knowledge or training pertaining to any particular fault. The basis for anomaly detection was the model of normal behavior obtained using the recently introduced Growing Structure Multiple Model System (GSMMS). Anomalous behavior is then detected as statistically significant departures of the current modeling residuals away from the modeling residuals corresponding to the normal system behavior. Distributed anomaly detection facilitated by multiple anomaly detectors monitoring various parts of the thermal-fluid system enabled localization of anomalous partitions of the system without the need to train classifiers to recognize an underlying fault.text2011-02-16T20:06:29Z2011-02-16T20:06:48Z2011-02-16T20:06:29Z2011-02-16T20:06:48Z2010-122011-02-16December 20102011-02-16T20:06:48Zthesisapplication/pdfhttp://hdl.handle.net/2152/ETD-UT-2010-12-2608eng
collection NDLTD
language English
format Others
sources NDLTD
topic Fault detection
Fault localization
Thermal-fluid systems
Channel flow
spellingShingle Fault detection
Fault localization
Thermal-fluid systems
Channel flow
Carpenter, Katherine Patricia
Fault detection and precedent-free localization in thermal-fluid systems
description This thesis presents a method for fault detection and precedent-free isolation for two types of channel flow systems, which were modeled with the finite element method. Unlike previous fault detection methods, this method requires no a priori knowledge or training pertaining to any particular fault. The basis for anomaly detection was the model of normal behavior obtained using the recently introduced Growing Structure Multiple Model System (GSMMS). Anomalous behavior is then detected as statistically significant departures of the current modeling residuals away from the modeling residuals corresponding to the normal system behavior. Distributed anomaly detection facilitated by multiple anomaly detectors monitoring various parts of the thermal-fluid system enabled localization of anomalous partitions of the system without the need to train classifiers to recognize an underlying fault. === text
author Carpenter, Katherine Patricia
author_facet Carpenter, Katherine Patricia
author_sort Carpenter, Katherine Patricia
title Fault detection and precedent-free localization in thermal-fluid systems
title_short Fault detection and precedent-free localization in thermal-fluid systems
title_full Fault detection and precedent-free localization in thermal-fluid systems
title_fullStr Fault detection and precedent-free localization in thermal-fluid systems
title_full_unstemmed Fault detection and precedent-free localization in thermal-fluid systems
title_sort fault detection and precedent-free localization in thermal-fluid systems
publishDate 2011
url http://hdl.handle.net/2152/ETD-UT-2010-12-2608
work_keys_str_mv AT carpenterkatherinepatricia faultdetectionandprecedentfreelocalizationinthermalfluidsystems
_version_ 1716821643861426176