Fault detection and diagnosis in a heat exchanger

Juan C. Tudon Martinez, Ruben Morales-Menendez, Luis E. Garza Castañon

Research output: Contribution to conferencePaper

2 Citations (Scopus)

Abstract

A comparison between the Dynamic Principal Component Analysis (DPCA) method and a bank of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the performance of both methods when sensors and/or actuators fail. Different metrics are discussed (i.e. robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability). DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it cannot identify two or more sequential faults.
Original languageEnglish
Pages265-270
Number of pages6
Publication statusPublished - 1 Dec 2009
Externally publishedYes
EventICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings -
Duration: 1 Dec 2009 → …

Conference

ConferenceICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings
Period1/12/09 → …

Fingerprint

Fault detection
Principal component analysis
Failure analysis
Heat exchangers
Actuators
Sensors

Cite this

Tudon Martinez, J. C., Morales-Menendez, R., & Garza Castañon, L. E. (2009). Fault detection and diagnosis in a heat exchanger. 265-270. Paper presented at ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings, .
Tudon Martinez, Juan C. ; Morales-Menendez, Ruben ; Garza Castañon, Luis E. / Fault detection and diagnosis in a heat exchanger. Paper presented at ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings, .6 p.
@conference{b211f0dba8b04f4489c883bc7684d04b,
title = "Fault detection and diagnosis in a heat exchanger",
abstract = "A comparison between the Dynamic Principal Component Analysis (DPCA) method and a bank of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the performance of both methods when sensors and/or actuators fail. Different metrics are discussed (i.e. robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability). DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it cannot identify two or more sequential faults.",
author = "{Tudon Martinez}, {Juan C.} and Ruben Morales-Menendez and {Garza Casta{\~n}on}, {Luis E.}",
year = "2009",
month = "12",
day = "1",
language = "English",
pages = "265--270",
note = "ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings ; Conference date: 01-12-2009",

}

Tudon Martinez, JC, Morales-Menendez, R & Garza Castañon, LE 2009, 'Fault detection and diagnosis in a heat exchanger' Paper presented at ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings, 1/12/09, pp. 265-270.

Fault detection and diagnosis in a heat exchanger. / Tudon Martinez, Juan C.; Morales-Menendez, Ruben; Garza Castañon, Luis E.

2009. 265-270 Paper presented at ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Fault detection and diagnosis in a heat exchanger

AU - Tudon Martinez, Juan C.

AU - Morales-Menendez, Ruben

AU - Garza Castañon, Luis E.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - A comparison between the Dynamic Principal Component Analysis (DPCA) method and a bank of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the performance of both methods when sensors and/or actuators fail. Different metrics are discussed (i.e. robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability). DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it cannot identify two or more sequential faults.

AB - A comparison between the Dynamic Principal Component Analysis (DPCA) method and a bank of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the performance of both methods when sensors and/or actuators fail. Different metrics are discussed (i.e. robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability). DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it cannot identify two or more sequential faults.

M3 - Paper

SP - 265

EP - 270

ER -

Tudon Martinez JC, Morales-Menendez R, Garza Castañon LE. Fault detection and diagnosis in a heat exchanger. 2009. Paper presented at ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings, .