Fault detection using online selected data and updated regression models

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Since their increasing complexity and the impossibility of monitoring the data manually, fault detection is of special interest at engine test beds. The work with research data presents yet another challenge. First, it is hard to establish physical models, at least for all variables of interest. Second, prior knowledge of all data settings is not available. Hence, this paper introduces statistical models with no a priori knowledge which are updated online to adapt to new data settings. In order to reduce the amount of time and memory required, incoming data is filtered according to different criteria. Several data selection criteria based on well-known statistical measures such as leverage or Cook's distance have been tested on four different data sets. Our new proposal, a proper combination of the leverage measure and the forecast residual, performs the best. The models are still applicable to forecasting yet even more suitable for error detection.

Translated title of the contributionFehlererkennung durch online selektierte Daten und aktualisierte Regressionsmodelle
LanguageEnglish
Pages437-449
Number of pages13
JournalMeasurement
Volume140
DOIs
StatusPublished - Jul 2019

Fingerprint

fault detection
Fault Detection
Fault detection
regression analysis
Regression Model
forecasting
Error detection
engine tests
test stands
Engines
Data storage equipment
proposals
Monitoring
Leverage
Cook's Distance
Error Detection
Physical Model
Prior Knowledge
Testbed
Statistical Model

Keywords

  • Data selection
  • Fault detection
  • Online model updating
  • Regression model

ASJC Scopus subject areas

  • Statistics and Probability
  • Mechanical Engineering
  • Instrumentation
  • Electrical and Electronic Engineering

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Experimental

Cite this

Fault detection using online selected data and updated regression models. / Schadler, Doris; Stadlober, Ernst.

In: Measurement, Vol. 140, 07.2019, p. 437-449.

Research output: Contribution to journalArticleResearchpeer-review

@article{843121193cd84d12ac10840d9abdfafa,
title = "Fault detection using online selected data and updated regression models",
abstract = "Since their increasing complexity and the impossibility of monitoring the data manually, fault detection is of special interest at engine test beds. The work with research data presents yet another challenge. First, it is hard to establish physical models, at least for all variables of interest. Second, prior knowledge of all data settings is not available. Hence, this paper introduces statistical models with no a priori knowledge which are updated online to adapt to new data settings. In order to reduce the amount of time and memory required, incoming data is filtered according to different criteria. Several data selection criteria based on well-known statistical measures such as leverage or Cook's distance have been tested on four different data sets. Our new proposal, a proper combination of the leverage measure and the forecast residual, performs the best. The models are still applicable to forecasting yet even more suitable for error detection.",
keywords = "Fehlererkennung, Regressionsmodelle, Online Modellierung, Datenselektion, Data selection, Fault detection, Online model updating, Regression model",
author = "Doris Schadler and Ernst Stadlober",
year = "2019",
month = "7",
doi = "10.1016/j.measurement.2019.04.010",
language = "English",
volume = "140",
pages = "437--449",
journal = "Measurement",
issn = "0263-2241",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Fault detection using online selected data and updated regression models

AU - Schadler, Doris

AU - Stadlober, Ernst

PY - 2019/7

Y1 - 2019/7

N2 - Since their increasing complexity and the impossibility of monitoring the data manually, fault detection is of special interest at engine test beds. The work with research data presents yet another challenge. First, it is hard to establish physical models, at least for all variables of interest. Second, prior knowledge of all data settings is not available. Hence, this paper introduces statistical models with no a priori knowledge which are updated online to adapt to new data settings. In order to reduce the amount of time and memory required, incoming data is filtered according to different criteria. Several data selection criteria based on well-known statistical measures such as leverage or Cook's distance have been tested on four different data sets. Our new proposal, a proper combination of the leverage measure and the forecast residual, performs the best. The models are still applicable to forecasting yet even more suitable for error detection.

AB - Since their increasing complexity and the impossibility of monitoring the data manually, fault detection is of special interest at engine test beds. The work with research data presents yet another challenge. First, it is hard to establish physical models, at least for all variables of interest. Second, prior knowledge of all data settings is not available. Hence, this paper introduces statistical models with no a priori knowledge which are updated online to adapt to new data settings. In order to reduce the amount of time and memory required, incoming data is filtered according to different criteria. Several data selection criteria based on well-known statistical measures such as leverage or Cook's distance have been tested on four different data sets. Our new proposal, a proper combination of the leverage measure and the forecast residual, performs the best. The models are still applicable to forecasting yet even more suitable for error detection.

KW - Fehlererkennung

KW - Regressionsmodelle

KW - Online Modellierung

KW - Datenselektion

KW - Data selection

KW - Fault detection

KW - Online model updating

KW - Regression model

UR - http://www.scopus.com/inward/record.url?scp=85064243460&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2019.04.010

DO - 10.1016/j.measurement.2019.04.010

M3 - Article

VL - 140

SP - 437

EP - 449

JO - Measurement

T2 - Measurement

JF - Measurement

SN - 0263-2241

ER -