機械学習手法を活用した CRDM 作動分析技術の高度化について
Improvement of CRDM Motion Analysis using Machine Learning
著者:
西村 卓也 Takuya NISHIMURA 山嵜 將平 Shohei YAMASAKI 斎藤 真由美 Mayumi SAITOH 中山 博之 Hiroyuki NAKAYAMA 矢口 誓児 Seiji YAGUCHI
発刊日:
公開日:
CRDMMachine Learningmaintenancemotion analysis
概要
Control Rod Drive Mechanism (CRDM) for pressurized water reactor (PWR) plant operates control rods in response to electrical signals from a reactor control system. CRDM operability is evaluated by characteristic of CRDM operational data. MHI has already developed an automatic CRDM motion analysis and applied it to actual plants so far. However, CRDM operational data has wide variation and noise depending on their characteristics such as plant condition, address, plant, and so on. In the existing motion analysis, detecting characteristics was conducted using manually adjusted criteria. In some operational data with wide variation and noise, detecting accuracy was not so high due to this limitation. In this study, MHI investigated motion analysis using machine learning (Random Forests) which is flexibly accommodated to CRDM operational data with wide variation and noise, and improved analysis accuracy.
