On-line condition monitoring of boiling water reactors: A symbolic dynamic data-driven approach

Miltiadis Alamaniotis, Xin Jin, Asok Ray

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

4 Citations (Scopus)

Abstract

As a paradigm of dynamic data-driven application systems (DDDAS) in nuclear power generation, this paper addresses the critical issue of on-line condition monitoring and early detection of anomalous behavior in boiling water reactor (BWR) nuclear power plants. The operation and maintenance in BWR plants are characterized by plethora of synergistic complex systems, where the energy is generated via a single heat removal loop and thus the real-time execution of condition monitoring and early detection of anomalous behavior become very challenging tasks. From the above perspectives, DDDAS methods have the potential of providing attractive solutions to the problems of on-line condition monitoring and anomaly detection. A symbolic data analysis (SDA) method has been adopted in this paper, where symbol sequences are generated by partitioning (finite-length) time series of plant data. Then, a special class of probabilistic finite state automata (PFSA), called D-Markov machine, is constructed to extract pertinent features from the statistics of time series as state probability vectors that serve as features for classification of different anomaly patterns. The proposed method is validated on a set of measurements taken from three different experiments on a BWR test facility, which emulate various types of loss-of-coolant-accidents (LOCA). Results exhibit the ability of SDA to extract, in a fast and accurate way, pertinent features for identifying the type of LOCA that may occur in a commercial-scale BWR.

Original languageEnglish (US)
Title of host publication9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015
PublisherAmerican Nuclear Society
Pages722-732
Number of pages11
ISBN (Electronic)9781510808096
StatePublished - Jan 1 2015
Event9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015 - Charlotte, United States
Duration: Feb 22 2015Feb 26 2015

Publication series

Name9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015
Volume1

Other

Other9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015
CountryUnited States
CityCharlotte
Period2/22/152/26/15

Fingerprint

Boiling water reactors
Condition monitoring
Loss of coolant accidents
Time series
Finite automata
Test facilities
Nuclear energy
Nuclear power plants
Power generation
Large scale systems
Statistics
Experiments

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Human-Computer Interaction

Cite this

Alamaniotis, M., Jin, X., & Ray, A. (2015). On-line condition monitoring of boiling water reactors: A symbolic dynamic data-driven approach. In 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015 (pp. 722-732). (9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015; Vol. 1). American Nuclear Society.
Alamaniotis, Miltiadis ; Jin, Xin ; Ray, Asok. / On-line condition monitoring of boiling water reactors : A symbolic dynamic data-driven approach. 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015. American Nuclear Society, 2015. pp. 722-732 (9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015).
@inproceedings{db48b482a15b4ed8a48fc4ff0705610d,
title = "On-line condition monitoring of boiling water reactors: A symbolic dynamic data-driven approach",
abstract = "As a paradigm of dynamic data-driven application systems (DDDAS) in nuclear power generation, this paper addresses the critical issue of on-line condition monitoring and early detection of anomalous behavior in boiling water reactor (BWR) nuclear power plants. The operation and maintenance in BWR plants are characterized by plethora of synergistic complex systems, where the energy is generated via a single heat removal loop and thus the real-time execution of condition monitoring and early detection of anomalous behavior become very challenging tasks. From the above perspectives, DDDAS methods have the potential of providing attractive solutions to the problems of on-line condition monitoring and anomaly detection. A symbolic data analysis (SDA) method has been adopted in this paper, where symbol sequences are generated by partitioning (finite-length) time series of plant data. Then, a special class of probabilistic finite state automata (PFSA), called D-Markov machine, is constructed to extract pertinent features from the statistics of time series as state probability vectors that serve as features for classification of different anomaly patterns. The proposed method is validated on a set of measurements taken from three different experiments on a BWR test facility, which emulate various types of loss-of-coolant-accidents (LOCA). Results exhibit the ability of SDA to extract, in a fast and accurate way, pertinent features for identifying the type of LOCA that may occur in a commercial-scale BWR.",
author = "Miltiadis Alamaniotis and Xin Jin and Asok Ray",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
series = "9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015",
publisher = "American Nuclear Society",
pages = "722--732",
booktitle = "9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015",
address = "United States",

}

Alamaniotis, M, Jin, X & Ray, A 2015, On-line condition monitoring of boiling water reactors: A symbolic dynamic data-driven approach. in 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015. 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015, vol. 1, American Nuclear Society, pp. 722-732, 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015, Charlotte, United States, 2/22/15.

On-line condition monitoring of boiling water reactors : A symbolic dynamic data-driven approach. / Alamaniotis, Miltiadis; Jin, Xin; Ray, Asok.

9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015. American Nuclear Society, 2015. p. 722-732 (9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015; Vol. 1).

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

TY - GEN

T1 - On-line condition monitoring of boiling water reactors

T2 - A symbolic dynamic data-driven approach

AU - Alamaniotis, Miltiadis

AU - Jin, Xin

AU - Ray, Asok

PY - 2015/1/1

Y1 - 2015/1/1

N2 - As a paradigm of dynamic data-driven application systems (DDDAS) in nuclear power generation, this paper addresses the critical issue of on-line condition monitoring and early detection of anomalous behavior in boiling water reactor (BWR) nuclear power plants. The operation and maintenance in BWR plants are characterized by plethora of synergistic complex systems, where the energy is generated via a single heat removal loop and thus the real-time execution of condition monitoring and early detection of anomalous behavior become very challenging tasks. From the above perspectives, DDDAS methods have the potential of providing attractive solutions to the problems of on-line condition monitoring and anomaly detection. A symbolic data analysis (SDA) method has been adopted in this paper, where symbol sequences are generated by partitioning (finite-length) time series of plant data. Then, a special class of probabilistic finite state automata (PFSA), called D-Markov machine, is constructed to extract pertinent features from the statistics of time series as state probability vectors that serve as features for classification of different anomaly patterns. The proposed method is validated on a set of measurements taken from three different experiments on a BWR test facility, which emulate various types of loss-of-coolant-accidents (LOCA). Results exhibit the ability of SDA to extract, in a fast and accurate way, pertinent features for identifying the type of LOCA that may occur in a commercial-scale BWR.

AB - As a paradigm of dynamic data-driven application systems (DDDAS) in nuclear power generation, this paper addresses the critical issue of on-line condition monitoring and early detection of anomalous behavior in boiling water reactor (BWR) nuclear power plants. The operation and maintenance in BWR plants are characterized by plethora of synergistic complex systems, where the energy is generated via a single heat removal loop and thus the real-time execution of condition monitoring and early detection of anomalous behavior become very challenging tasks. From the above perspectives, DDDAS methods have the potential of providing attractive solutions to the problems of on-line condition monitoring and anomaly detection. A symbolic data analysis (SDA) method has been adopted in this paper, where symbol sequences are generated by partitioning (finite-length) time series of plant data. Then, a special class of probabilistic finite state automata (PFSA), called D-Markov machine, is constructed to extract pertinent features from the statistics of time series as state probability vectors that serve as features for classification of different anomaly patterns. The proposed method is validated on a set of measurements taken from three different experiments on a BWR test facility, which emulate various types of loss-of-coolant-accidents (LOCA). Results exhibit the ability of SDA to extract, in a fast and accurate way, pertinent features for identifying the type of LOCA that may occur in a commercial-scale BWR.

UR - http://www.scopus.com/inward/record.url?scp=84946200378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946200378&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84946200378

T3 - 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015

SP - 722

EP - 732

BT - 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015

PB - American Nuclear Society

ER -

Alamaniotis M, Jin X, Ray A. On-line condition monitoring of boiling water reactors: A symbolic dynamic data-driven approach. In 9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015. American Nuclear Society. 2015. p. 722-732. (9th International Topical Meeting on Nuclear Plant Instrumentation, Control, and Human-Machine Interface Technologies, NPIC and HMIT 2015).