遺伝的アルゴリズムを学習手段としたニューラルネットワークの原子炉異常診断への応用

抄録

Several nuclear reactor diagnostic systems using neural networks have been proposed in recent years. Neural networks trained by backpropagation, the standard training algorithm, have certain problems such as local minima and long training times. In this paper, neural networks trained by genetic algorithms were used in nuclear reactor diagnostic system to solve these problems. The system was tested by simulated data modeled on the experimental fast reactor JOYO, and two categories of abnormality (abnormal control rod vibration and abnormal coolant flow) were identified. The comparisons to networks trained by backpropagation were also discussed.