Journal Article10.1109/TNS.2017.2697919
Nuclear Power Plant Thermocouple Sensor-Fault Detection and Classification Using Deep Learning and Generalized Likelihood Ratio Test
111
TL;DR: An online fault detection and classification method is proposed for thermocouples used in nuclear power plants and a technique is proposed to identify the faulty sensor from the fault data.
read more
Abstract: In this paper, an online fault detection and classification method is proposed for thermocouples used in nuclear power plants. In the proposed method, the fault data are detected by the classification method, which classifies the fault data from the normal data. Deep belief network (DBN), a technique for deep learning, is applied to classify the fault data. The DBN has a multilayer feature extraction scheme, which is highly sensitive to a small variation of data. Since the classification method is unable to detect the faulty sensor; therefore, a technique is proposed to identify the faulty sensor from the fault data. Finally, the composite statistical hypothesis test, namely generalized likelihood ratio test, is applied to compute the fault pattern of the faulty sensor signal based on the magnitude of the fault. The performance of the proposed method is validated by field data obtained from thermocouple sensors of the fast breeder test reactor.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Sensor-Fault Detection, Isolation and Accommodation for Digital Twins via Modular Data-Driven Architecture
TL;DR: A general machine-learning-based architecture for sensor validation built upon a series of neural-network estimators and a classifier is proposed, which aims at detecting anomalies in measurements from sensors, identifying the faulty ones and accommodating them with appropriate estimated data, thus paving the way to reliable digital twins.
218
Recent advances in sensor fault diagnosis: a review
TL;DR: A comprehensive review on the contemporary fault diagnosis techniques is provided and helps researchers and practitioners to understand the current state of the art development in this emerging field.
215
A Review on Deep Learning Applications in Prognostics and Health Management
TL;DR: The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data and suggests the possibility of transfer learning across PHM applications.
Digitalisation and Innovation in the Steel Industry in Poland—Selected Tools of ICT in an Analysis of Statistical Data and a Case Study
Bożena Gajdzik,Radosław Wolniak +1 more
TL;DR: In this paper, the authors present the tools used in the steel industry in Poland on its way to the full digitalisation that is needed for the development of Industry 4.0.
Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review
TL;DR: In this paper, the authors reviewed the state-of-the-art progress on data-driven machine learning (DDML) for fault diagnosis and detection (FDD) in the nuclear power plant (NPP).
References
Pattern Recognition and Machine Learning
TL;DR: This book covers a broad range of topics for regular factorial designs and presents all of the material in very mathematical fashion and will surely become an invaluable resource for researchers and graduate students doing research in the design of factorial experiments.
30.8K
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
•Book
Probabilistic graphical models : principles and techniques
Daniel L. Koller,Nir Friedman +1 more
- 31 Jul 2009
TL;DR: The framework of probabilistic graphical models, presented in this book, provides a general approach for causal reasoning and decision making under uncertainty, allowing interpretable models to be constructed and then manipulated by reasoning algorithms.
Training products of experts by minimizing contrastive divergence
TL;DR: A product of experts (PoE) is an interesting candidate for a perceptual system in which rapid inference is vital and generation is unnecessary because it is hard even to approximate the derivatives of the renormalization term in the combination rule.
Training restricted Boltzmann machines
Asja Fischer,Christian Igel +1 more
TL;DR: This tutorial introduces RBMs from the viewpoint of Markov random fields, starting with the required concepts of undirected graphical models and reviewing the state-of-the-art in training restricted Boltzmann machines from the perspective of graphical models.
546