Sensor recovery for robust multivariate condition monitoring

Haitao Liao, Jian Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The ability to predict and prevent equipment failures is essential to various industrial processes and military operations. In recent years, Condition Monitoring (CM) has been recognized as an effective paradigm in this regard. CM can be performed via several sensor channels with broad coverage to enhance monitoring capabilities. However, loss of sensor readings due to malfunction of connectors and/or sensor abnormalities is the hurdle to reliable fault diagnosis and prognosis in multichannel CM systems. The problem becomes more challenging when the sensor channels are not synchronized because of different and/or time-varying sampling/transmission rates. This paper provides a new sensor recovery technique to improve the robustness of multichannel CM systems. Specifically, the associated sensor signals are modeled through Functional Principal Component Analysis (FPCA). Based on the FPCA results obtained from historical data, the relationships among the signals can be constructed. In on-line implementation, such relationships along with parameters updated by real-time CM data can be used to recover lost sensor signals. To this end, a two-stage approach is developed to estimate the Functional Principal Component (FPC) scores and construct a functional regression model. The flexibility of FPC based models furnishes them with substantial potential for sensor recovery in multichannel CM environments. A turbofan aircraft engine simulation study is used to demonstrate the sensor recovery technique.

Original languageEnglish (US)
Title of host publicationProceedings - Annual Reliability and Maintainability Symposium
DOIs
StatePublished - 2011
Externally publishedYes
EventAnnual Reliability and Maintainability Symposium, RAMS 2011 - Lake Buena Vista, FL, United States
Duration: Jan 24 2011Jan 27 2011

Other

OtherAnnual Reliability and Maintainability Symposium, RAMS 2011
CountryUnited States
CityLake Buena Vista, FL
Period1/24/111/27/11

Fingerprint

Condition Monitoring
Condition monitoring
Recovery
Sensor
Sensors
Functional Principal Component Analysis
Principal Components
Monitoring System
Principal component analysis
Aircraft engines
Functional Model
Connector
Military operations
Prognosis
Historical Data
Fault Diagnosis
Military
Failure analysis
Aircraft
Regression Model

Keywords

  • condition monitoring
  • functional data analysis
  • sensor recovery

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Mathematics(all)
  • Computer Science Applications

Cite this

Liao, H., & Sun, J. (2011). Sensor recovery for robust multivariate condition monitoring. In Proceedings - Annual Reliability and Maintainability Symposium [5754495] https://doi.org/10.1109/RAMS.2011.5754495

Sensor recovery for robust multivariate condition monitoring. / Liao, Haitao; Sun, Jian.

Proceedings - Annual Reliability and Maintainability Symposium. 2011. 5754495.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liao, H & Sun, J 2011, Sensor recovery for robust multivariate condition monitoring. in Proceedings - Annual Reliability and Maintainability Symposium., 5754495, Annual Reliability and Maintainability Symposium, RAMS 2011, Lake Buena Vista, FL, United States, 1/24/11. https://doi.org/10.1109/RAMS.2011.5754495
Liao H, Sun J. Sensor recovery for robust multivariate condition monitoring. In Proceedings - Annual Reliability and Maintainability Symposium. 2011. 5754495 https://doi.org/10.1109/RAMS.2011.5754495
Liao, Haitao ; Sun, Jian. / Sensor recovery for robust multivariate condition monitoring. Proceedings - Annual Reliability and Maintainability Symposium. 2011.
@inproceedings{98182ac492844dc2ab1ae8de2e87111f,
title = "Sensor recovery for robust multivariate condition monitoring",
abstract = "The ability to predict and prevent equipment failures is essential to various industrial processes and military operations. In recent years, Condition Monitoring (CM) has been recognized as an effective paradigm in this regard. CM can be performed via several sensor channels with broad coverage to enhance monitoring capabilities. However, loss of sensor readings due to malfunction of connectors and/or sensor abnormalities is the hurdle to reliable fault diagnosis and prognosis in multichannel CM systems. The problem becomes more challenging when the sensor channels are not synchronized because of different and/or time-varying sampling/transmission rates. This paper provides a new sensor recovery technique to improve the robustness of multichannel CM systems. Specifically, the associated sensor signals are modeled through Functional Principal Component Analysis (FPCA). Based on the FPCA results obtained from historical data, the relationships among the signals can be constructed. In on-line implementation, such relationships along with parameters updated by real-time CM data can be used to recover lost sensor signals. To this end, a two-stage approach is developed to estimate the Functional Principal Component (FPC) scores and construct a functional regression model. The flexibility of FPC based models furnishes them with substantial potential for sensor recovery in multichannel CM environments. A turbofan aircraft engine simulation study is used to demonstrate the sensor recovery technique.",
keywords = "condition monitoring, functional data analysis, sensor recovery",
author = "Haitao Liao and Jian Sun",
year = "2011",
doi = "10.1109/RAMS.2011.5754495",
language = "English (US)",
isbn = "9781424451036",
booktitle = "Proceedings - Annual Reliability and Maintainability Symposium",

}

TY - GEN

T1 - Sensor recovery for robust multivariate condition monitoring

AU - Liao, Haitao

AU - Sun, Jian

PY - 2011

Y1 - 2011

N2 - The ability to predict and prevent equipment failures is essential to various industrial processes and military operations. In recent years, Condition Monitoring (CM) has been recognized as an effective paradigm in this regard. CM can be performed via several sensor channels with broad coverage to enhance monitoring capabilities. However, loss of sensor readings due to malfunction of connectors and/or sensor abnormalities is the hurdle to reliable fault diagnosis and prognosis in multichannel CM systems. The problem becomes more challenging when the sensor channels are not synchronized because of different and/or time-varying sampling/transmission rates. This paper provides a new sensor recovery technique to improve the robustness of multichannel CM systems. Specifically, the associated sensor signals are modeled through Functional Principal Component Analysis (FPCA). Based on the FPCA results obtained from historical data, the relationships among the signals can be constructed. In on-line implementation, such relationships along with parameters updated by real-time CM data can be used to recover lost sensor signals. To this end, a two-stage approach is developed to estimate the Functional Principal Component (FPC) scores and construct a functional regression model. The flexibility of FPC based models furnishes them with substantial potential for sensor recovery in multichannel CM environments. A turbofan aircraft engine simulation study is used to demonstrate the sensor recovery technique.

AB - The ability to predict and prevent equipment failures is essential to various industrial processes and military operations. In recent years, Condition Monitoring (CM) has been recognized as an effective paradigm in this regard. CM can be performed via several sensor channels with broad coverage to enhance monitoring capabilities. However, loss of sensor readings due to malfunction of connectors and/or sensor abnormalities is the hurdle to reliable fault diagnosis and prognosis in multichannel CM systems. The problem becomes more challenging when the sensor channels are not synchronized because of different and/or time-varying sampling/transmission rates. This paper provides a new sensor recovery technique to improve the robustness of multichannel CM systems. Specifically, the associated sensor signals are modeled through Functional Principal Component Analysis (FPCA). Based on the FPCA results obtained from historical data, the relationships among the signals can be constructed. In on-line implementation, such relationships along with parameters updated by real-time CM data can be used to recover lost sensor signals. To this end, a two-stage approach is developed to estimate the Functional Principal Component (FPC) scores and construct a functional regression model. The flexibility of FPC based models furnishes them with substantial potential for sensor recovery in multichannel CM environments. A turbofan aircraft engine simulation study is used to demonstrate the sensor recovery technique.

KW - condition monitoring

KW - functional data analysis

KW - sensor recovery

UR - http://www.scopus.com/inward/record.url?scp=79956363488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956363488&partnerID=8YFLogxK

U2 - 10.1109/RAMS.2011.5754495

DO - 10.1109/RAMS.2011.5754495

M3 - Conference contribution

AN - SCOPUS:79956363488

SN - 9781424451036

BT - Proceedings - Annual Reliability and Maintainability Symposium

ER -