[2K01-05] Advancement of the Maintenance and Preservation Technology of the Plant 2

[2K03] Development of Abnormal Sign Detection System using AI for Nuclear Power Plant

(5)Study of user interface for nuclear power plant

*Shinya Tominaga¹, Isaku Nagura¹, Ryota Miyake¹, Toshio Aoki¹, Susumu Naito², Yasunori Taguchi², Yuichi Kato², Kouta Nakata² (1. TOSHIBA ESS, 2. TOSHIBA)

Keywords:early detection of anormaly signs, AI, deep learning , user interface, plant operation monitoring

In 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 health of various systems so it is difficult for plant operators to constantly monitor all of the process values. We have developed the detection algorithm based on the autoencoder and confirmed its detection performance by using the full-scope simulator. To introduce this system to nuclear power plant, this system is required not only to detect abnormality but to inform appropriately and contribute to the conservativeness of plant, and the improvement in safety by supporting user's correspondence. We report the user interface and configuration of this system to introduce this system to nuclear power plant.