A functional modelling based methodology for testing the predictions of fault detection and identification systems

Nikolaos Papakonstantinou, Scott Proper, Douglas L. Van Bossuyt, Bryan O'Halloran, Irem Y. Tumer

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

Fault detection and identification (FDI) systems, which are based on data mining and artificial intelligence techniques, cannot guarantee a perfect success rate or provide analytical proof for their predictions. This characteristic is problematic when such an FDI system is monitoring a safety-critical process. In these cases, the predictions of the FDI system need to be verified by other means, such as tests on the process, to increase trust in the diagnosis. This paper contributes an extension of the Hierarchical Functional Fault Detection and Identification (HFFDI) system, a combination of a plant-wide and multiple function-specific FDI modules, developed in past research. A test preparation and test-based verification phase is added to the HFFDI methodology. The functional decomposition of the process and the type of the faulty components guides the preparation of specific tests for every fault to be identifiable by the HFFDI system. These tests have the potential to confirm or disprove the existence of the fault(s) in the target process. The target is minor automation faults in redundant systems of the monitored process. The proposed extension of the HFFDI system is applied to a case study of a generic Nuclear Power Plant model. Two HFFDI predictions are tested (a successful and an incorrect prediction) in single fault scenarios and one prediction is tested in a in a two fault scenario. The results of the case study show that the testing phase introduced in this paper is able to confirm correct fault predictions and reject incorrect fault predictions, thus the HFFDI extension presented here improves the confidence of the HFFDI output.
Original languageEnglish
Title of host publicationASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
Subtitle of host publication36th Computers and Information in Engineering Conference
PublisherAmerican Society of Mechanical Engineers ASME
Number of pages10
Volume1B
ISBN (Print)978-0-7918-5008-4
DOIs
Publication statusPublished - 2016
MoE publication typeA4 Article in a conference publication
Event36th Computers and Information in Engineering Conference, IDETC/CIE 2016 - Charlotte, United States
Duration: 21 Aug 201624 Aug 2016

Conference

Conference36th Computers and Information in Engineering Conference, IDETC/CIE 2016
Abbreviated titleIDETC/CIE 2016
CountryUnited States
CityCharlotte
Period21/08/1624/08/16

Fingerprint

Fault detection
Identification (control systems)
Testing
Nuclear power plants
Artificial intelligence
Data mining
Automation
Decomposition
Monitoring

Keywords

  • Modeling
  • Testing
  • Flaw detection

Cite this

Papakonstantinou, N., Proper, S., Van Bossuyt, D. L., O'Halloran, B., & Tumer, I. Y. (2016). A functional modelling based methodology for testing the predictions of fault detection and identification systems. In ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: 36th Computers and Information in Engineering Conference (Vol. 1B). [DETC2016-59916] American Society of Mechanical Engineers ASME. https://doi.org/10.1115/DETC2016-59916
Papakonstantinou, Nikolaos ; Proper, Scott ; Van Bossuyt, Douglas L. ; O'Halloran, Bryan ; Tumer, Irem Y. / A functional modelling based methodology for testing the predictions of fault detection and identification systems. ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: 36th Computers and Information in Engineering Conference. Vol. 1B American Society of Mechanical Engineers ASME, 2016.
@inproceedings{e83000e084d741a29cc5b419f290869b,
title = "A functional modelling based methodology for testing the predictions of fault detection and identification systems",
abstract = "Fault detection and identification (FDI) systems, which are based on data mining and artificial intelligence techniques, cannot guarantee a perfect success rate or provide analytical proof for their predictions. This characteristic is problematic when such an FDI system is monitoring a safety-critical process. In these cases, the predictions of the FDI system need to be verified by other means, such as tests on the process, to increase trust in the diagnosis. This paper contributes an extension of the Hierarchical Functional Fault Detection and Identification (HFFDI) system, a combination of a plant-wide and multiple function-specific FDI modules, developed in past research. A test preparation and test-based verification phase is added to the HFFDI methodology. The functional decomposition of the process and the type of the faulty components guides the preparation of specific tests for every fault to be identifiable by the HFFDI system. These tests have the potential to confirm or disprove the existence of the fault(s) in the target process. The target is minor automation faults in redundant systems of the monitored process. The proposed extension of the HFFDI system is applied to a case study of a generic Nuclear Power Plant model. Two HFFDI predictions are tested (a successful and an incorrect prediction) in single fault scenarios and one prediction is tested in a in a two fault scenario. The results of the case study show that the testing phase introduced in this paper is able to confirm correct fault predictions and reject incorrect fault predictions, thus the HFFDI extension presented here improves the confidence of the HFFDI output.",
keywords = "Modeling, Testing, Flaw detection",
author = "Nikolaos Papakonstantinou and Scott Proper and {Van Bossuyt}, {Douglas L.} and Bryan O'Halloran and Tumer, {Irem Y.}",
year = "2016",
doi = "10.1115/DETC2016-59916",
language = "English",
isbn = "978-0-7918-5008-4",
volume = "1B",
booktitle = "ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference",
publisher = "American Society of Mechanical Engineers ASME",
address = "United States",

}

Papakonstantinou, N, Proper, S, Van Bossuyt, DL, O'Halloran, B & Tumer, IY 2016, A functional modelling based methodology for testing the predictions of fault detection and identification systems. in ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: 36th Computers and Information in Engineering Conference. vol. 1B, DETC2016-59916, American Society of Mechanical Engineers ASME, 36th Computers and Information in Engineering Conference, IDETC/CIE 2016, Charlotte, United States, 21/08/16. https://doi.org/10.1115/DETC2016-59916

A functional modelling based methodology for testing the predictions of fault detection and identification systems. / Papakonstantinou, Nikolaos; Proper, Scott; Van Bossuyt, Douglas L.; O'Halloran, Bryan; Tumer, Irem Y.

ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: 36th Computers and Information in Engineering Conference. Vol. 1B American Society of Mechanical Engineers ASME, 2016. DETC2016-59916.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - A functional modelling based methodology for testing the predictions of fault detection and identification systems

AU - Papakonstantinou, Nikolaos

AU - Proper, Scott

AU - Van Bossuyt, Douglas L.

AU - O'Halloran, Bryan

AU - Tumer, Irem Y.

PY - 2016

Y1 - 2016

N2 - Fault detection and identification (FDI) systems, which are based on data mining and artificial intelligence techniques, cannot guarantee a perfect success rate or provide analytical proof for their predictions. This characteristic is problematic when such an FDI system is monitoring a safety-critical process. In these cases, the predictions of the FDI system need to be verified by other means, such as tests on the process, to increase trust in the diagnosis. This paper contributes an extension of the Hierarchical Functional Fault Detection and Identification (HFFDI) system, a combination of a plant-wide and multiple function-specific FDI modules, developed in past research. A test preparation and test-based verification phase is added to the HFFDI methodology. The functional decomposition of the process and the type of the faulty components guides the preparation of specific tests for every fault to be identifiable by the HFFDI system. These tests have the potential to confirm or disprove the existence of the fault(s) in the target process. The target is minor automation faults in redundant systems of the monitored process. The proposed extension of the HFFDI system is applied to a case study of a generic Nuclear Power Plant model. Two HFFDI predictions are tested (a successful and an incorrect prediction) in single fault scenarios and one prediction is tested in a in a two fault scenario. The results of the case study show that the testing phase introduced in this paper is able to confirm correct fault predictions and reject incorrect fault predictions, thus the HFFDI extension presented here improves the confidence of the HFFDI output.

AB - Fault detection and identification (FDI) systems, which are based on data mining and artificial intelligence techniques, cannot guarantee a perfect success rate or provide analytical proof for their predictions. This characteristic is problematic when such an FDI system is monitoring a safety-critical process. In these cases, the predictions of the FDI system need to be verified by other means, such as tests on the process, to increase trust in the diagnosis. This paper contributes an extension of the Hierarchical Functional Fault Detection and Identification (HFFDI) system, a combination of a plant-wide and multiple function-specific FDI modules, developed in past research. A test preparation and test-based verification phase is added to the HFFDI methodology. The functional decomposition of the process and the type of the faulty components guides the preparation of specific tests for every fault to be identifiable by the HFFDI system. These tests have the potential to confirm or disprove the existence of the fault(s) in the target process. The target is minor automation faults in redundant systems of the monitored process. The proposed extension of the HFFDI system is applied to a case study of a generic Nuclear Power Plant model. Two HFFDI predictions are tested (a successful and an incorrect prediction) in single fault scenarios and one prediction is tested in a in a two fault scenario. The results of the case study show that the testing phase introduced in this paper is able to confirm correct fault predictions and reject incorrect fault predictions, thus the HFFDI extension presented here improves the confidence of the HFFDI output.

KW - Modeling

KW - Testing

KW - Flaw detection

U2 - 10.1115/DETC2016-59916

DO - 10.1115/DETC2016-59916

M3 - Conference article in proceedings

SN - 978-0-7918-5008-4

VL - 1B

BT - ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference

PB - American Society of Mechanical Engineers ASME

ER -

Papakonstantinou N, Proper S, Van Bossuyt DL, O'Halloran B, Tumer IY. A functional modelling based methodology for testing the predictions of fault detection and identification systems. In ASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference: 36th Computers and Information in Engineering Conference. Vol. 1B. American Society of Mechanical Engineers ASME. 2016. DETC2016-59916 https://doi.org/10.1115/DETC2016-59916