1-2 of 2
Yuichi Kato
Close
Save search
Follow your search
Access your saved searches in your account
Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Journal Articles

Development of an Artificial Intelligence-Based Predictive Anomaly Detection System to Nuclear Power Plant

Ryota Miyake, Shinya Tominaga, Yusuke Terakado, Naoyuki Takado, Toshio Aoki, Chikashi Miyamoto, Susumu Naito, Yasunori Taguchi, Yuichi Kato, Kota Nakata
Journal: Journal of Nuclear Engineering and Radiation Science
Publisher: ASME
Article Type: Research-Article
ASME J of Nuclear Rad Sci. January 2025, 11(1): 011701.
Paper No: NERS-23-1062
https://doi.org/10.1115/1.4064123
Published Online: May 10, 2024
View Article titled, Development of an Artificial Intelligence-Based Predictive Anomaly Detection System to Nuclear Power Plant
Open the PDF for Development of an Artificial Intelligence-Based Predictive Anomaly Detection System to Nuclear Power Plant in another window
Topics: Artificial intelligence, Nuclear power stations, Power stations, Pumps, Fluctuations (Physics), Signals, Feedwater, Linkages, Time series, Transients (Dynamics)
Proceedings Papers

A New Data Driven Method for Monitoring a Large Number of Process Values and Detecting Anomaly Signs With a Two-Stage Model Composed of a Time Window Autoencoder and a Deviation Autoencoder

Susumu Naito, Yasunori Taguchi, Yuichi Kato, Kouta Nakata, Ryota Miyake, Isaku Nagura, Shinya Tominaga, Toshio Aoki
Proc. ASME. ICONE2020, Volume 2: Nuclear Policy; Nuclear Safety, Security, and Cyber Security; Operating Plant Experience; Probabilistic Risk Assessments; SMR and Advanced Reactors, V002T09A002, August 4–5, 2020
Publisher: American Society of Mechanical Engineers
Paper No: ICONE2020-16150
https://doi.org/10.1115/ICONE2020-16150
View Paper titled, A New Data Driven Method for Monitoring a Large Number of Process Values and Detecting Anomaly Signs With a Two-Stage Model Composed of a Time Window Autoencoder and a Deviation Autoencoder
Open the PDF for A New Data Driven Method for Monitoring a Large Number of Process Values and Detecting Anomaly Signs With a Two-Stage Model Composed of a Time Window Autoencoder and a Deviation Autoencoder in another window
Topics: Boiling water reactors, Machine learning, Noise (Sound), Nuclear power stations, Temperature, Time series, Transients (Dynamics)