Hidden Markov model-based real-time transient identifications in nuclear power plants

Kwon, Kee-Choon; Kim, Jinhyung; Seong, Poong Hyun

doi:10.1002/int.10050

Cited by 17 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed in Section II, the proposed modular identifier has advantage of selection of the plant variables for transients training independent of each other. In the previously developed methods, selection of common plant variables was necessary [19], [20]. The selected BNPP variables are listed in Table II.…”

Section: B Selection Of the Plant Variables For Transients Trainingmentioning

confidence: 99%

Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients

Moshkbar-Bakhshayesh

Ghofrani

2016

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

This study introduces a new identifier for nuclear power plants (NPPs) transients. The proposed identifier performs its function in two steps. First, the transient is identified by the previously developed supervised classifier combining ARIMA model and EBP algorithm. In the second step, the patterns of unknown transients are fed to the identifier based on the semi-supervised learning (SSL). The transductive support vector machine (TSVM) as a semi-supervised algorithm is trained by the labeled data of transients to predict some unlabeled data. The labeled and newly predicted data is then used to train the TSVM for another portion of unlabeled data. Training and prediction is continued until the change of targets is less than a desired value. The last targets (i.e., the final predicted for unlabeled data) identify the type of unknown transient. To analyze the ability of the proposed identifier, Bushehr nuclear power plant (BNPP) transients are examined. Results show good performance of the proposed identifier. Noticeable advantages are: clustering of unknown transients by labeled and unlabeled data, transductive approach of identifier without need to cluster all data, and sole dependency of identifier on sign of output signal due to the modular networks. Recognition of transient based on similarity of its statistical properties to the reference one, more robustness against noisy data, and improvement balance between memorization and generalization are other advantages of the identifier.Index Terms-Bushehr nuclear power plant, clustering, semisupervised learning, supervised, transductive support vector machine.

show abstract

Section: B Selection Of the Plant Variables For Transients Trainingmentioning

confidence: 99%

Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients

Moshkbar-Bakhshayesh

Ghofrani

2016

IEEE Trans. Nucl. Sci.

View full text Add to dashboard Cite

show abstract

“…In addition, DTMCs have been used as tools for fault detection and diagnosis [1,2,4,[29][30][31] and for long-term condition monitoring of equipment [5,7,8,32,33]. For example, Hidden Markov models have been used to represent the behavior of a target system, in which the current state of the system and the direction in which it is evolving are estimated using external signals and data [29,31]. Again, our approach differs, because it is geared toward discovering critical state transitions in a DTMC model, which when perturbed, reveal execution paths that lead system failures.…”

Section: Previous Workmentioning

confidence: 99%

Identifying Failure Scenarios in Complex Systems by Perturbing Markov Chain Models

Dabrowski

Hunt

2011

Volume 6: Materials and Fabrication, Parts a and B

View full text Add to dashboard Cite

In recent years, substantial research has been devoted to monitoring and predicting performance degradations in real-world complex systems within large entities such as nuclear power plants, electrical grids, and distributed computing systems. Special challenges are posed by the fact that such systems operate in uncertain environments, are highly dynamic, and exhibit emergent behaviors that can lead to catastrophic failure. Discrete Time Markov chains (DTMCs) provide important tools for analysis of such systems, because they represent dynamic behavior succinctly, provide a means to measure uncertainty, and can be used to make quantitative measurements of the potential for change to system performance. Moreover, DTMCs can be extended to be time-inhomogeneous, i.e. to represent behavior that varies over long durations. To date, DTMCs have been proposed for tasks such as fault detection and long-term condition equipment monitoring in realworld complex systems. However, the scope of these models has generally been restricted to describing states and state transitions that directly concern fault conditions or states of degradation. Less work has been done on using DTMCs to represent a more complete range of states a system may enter into during normal operation. Of special interest are sequences of states that involve failure scenarios, in which a system evolves from a normal operating state into undesirable state that leads to widespread performance degradation. Unfortunately, use of large DTMCs often involves large search spaces, a problem which in part motivates our work. This paper describes progress made on developing an approach for using larger, more detailed DTMC models of operational complex systems to uncover potential failure scenarios. The approach uses a combination of methods to perturb a DTMC, simulate alternative system evolutions, and identify scenarios in which a system proceeds from normal operation to failure. Key to the approach is the use of graph theory techniques to reduce the size of the search space involved in exploring alternative behaviors. We show how graph theory techniques can be used to identify critical state transitions which can be perturbed to simulate performance degradation. Using critical transitions, it is also possible to estimate the rate of performance degradation and to understand how this rate is likely to change in response to increased failure incidence. Examples are provided of the use of this approach on a DTMC of significant size to identify failure scenarios in a distributed resource allocation system.

show abstract

“…Zajam et al performed wavelet analysis on natural gas pipeline vibration data to obtain the frequency and spectrum of the running data and then made health assessment using support vector machine classifiers 4 . Kwon et al proposed a transient identification method based on a stochastic approach with the hidden Markov model, then evaluated nine transient states in nuclear power plants 5 . Sheng constructed the Gaussian nonlinear feature association mapping model of lithium‐ion battery health characteristics, combined with the SOH double exponential decay model and weighted Kalman filter algorithm to assess the health of lithium‐ion batterie 6 .…”

Section: Introductionmentioning

confidence: 99%

“…4 Kwon et al proposed a transient identification method based on a stochastic approach with the hidden Markov model, then evaluated nine transient states in nuclear power plants. 5 Sheng constructed the Gaussian nonlinear feature association mapping model of lithium-ion battery health characteristics, combined with the SOH double exponential decay model and weighted Kalman filter algorithm to assess the health of lithiumion batterie. 6 Deebak et al proposed a digital-twin-assisted fault diagnosis using deep transfer learning to analyze the operational conditions of machining tools.…”

mentioning

confidence: 99%

HMM‐TCN‐based health assessment and state prediction for robot mechanical axis

Hong

Zeng

Jiang

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Aiming at the problems of high manual cost, low efficiency, and low precision of the mechanical axis health management in industrial robot applications, this paper proposes a health assessment and state prediction algorithm based on hidden Markov model (HMM) and temporal convolutional networks (TCN). First, the MPdist similarity comparison algorithm is used to construct the mechanical axis health index. Then the hidden Markov model is trained with observable sensor data. After that, the temporal convolution neural network is used to predict state transition time iteratively, and the predicted results are decoded by HMM. The experimental results show that the HMM‐TCN model can accurately assess the health state of the mechanical axis and predict the state transition in real‐time. The prediction accuracy of this method reaches 87.5%, and the error interval locates in [−3,9] time steps. The accuracy, early/late prediction indicators are better than HMM‐RNN, HMM‐LSTM, and HMM‐GRU.

show abstract

Hidden Markov model-based real-time transient identifications in nuclear power plants

Cited by 17 publications

References 21 publications

Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients

Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients

Identifying Failure Scenarios in Complex Systems by Perturbing Markov Chain Models

HMM‐TCN‐based health assessment and state prediction for robot mechanical axis

Contact Info

Product

Resources

About