Show simple item record

contributor authorMiyake, Ryota
contributor authorTominaga, Shinya
contributor authorTerakado, Yusuke
contributor authorTakado, Naoyuki
contributor authorAoki, Toshio
contributor authorMiyamoto, Chikashi
contributor authorNaito, Susumu
contributor authorTaguchi, Yasunori
contributor authorKato, Yuichi
contributor authorNakata, Kota
date accessioned2025-04-21T10:33:22Z
date available2025-04-21T10:33:22Z
date copyright5/10/2024 12:00:00 AM
date issued2024
identifier issn2332-8983
identifier otherners_011_01_011701.pdf
identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4306433
description abstractIn a large-scale plant such as a nuclear power plant, thousands of process values are measured for the purpose of monitoring the plant performance and the system health. It is difficult for plant operators to constantly monitor all of the process values. We present a data-driven method to comprehensively monitor a large number of process values and detect early signs of anomalies, including unknown events, with few false positives. In order to learn the complex changing internal state of a nuclear power plant and accurately predict the normal process values, we have developed a two-stage auto-encoder (TSAE), a type of neural network, composed of a time window auto-encoder and a deviation auto-encoder. TSAE realizes to detect anomalous signals during the plant transient conditions by collecting time-series data and learning the nonlinear temporal correlation among them. In the actual plant, some process values which are physically uncorrelated with each other happen to behave similarly (pseudo-correlation). Learning the pseudo-correlation by the algorithm causes false positives because the predicted values of unrelated process values are incorrectly correlated. Therefore, Toshiba has proposed the model classification concept of separating the process values into two groups based on physical correlation and applied a model structure of TSAE. As a result, it becomes possible to learn only with the process values that are physically correlated and enhance the performance of prediction/detection. We assessed the improved TSAE with simulated process values of a nuclear power plant and showed excellent performances with early detection and few false positives.
publisherThe American Society of Mechanical Engineers (ASME)
titleDevelopment of an Artificial Intelligence-Based Predictive Anomaly Detection System to Nuclear Power Plant
typeJournal Paper
journal volume11
journal issue1
journal titleJournal of Nuclear Engineering and Radiation Science
identifier doi10.1115/1.4064123
journal fristpage11701-1
journal lastpage11701-11
page11
treeJournal of Nuclear Engineering and Radiation Science:;2024:;volume( 011 ):;issue: 001
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record