Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Initialising ...
Sawada, Makoto; Sakurai, Naoto
Proceedings of International Symposium on Symbiotic Nuclear Power Systems for 21st Century (ISSNP) (CD-ROM), p.275 - 283, 2007/07
The prototype FBR Monju which caused a sodium leak accident in Dec. 1995 is now under remodeling to attain its re-initial criticality in 2008. The success or failure of its safety operation is an important issue which influences development of nuclear fuel cycle. So, a high quality educational training is strongly required in order to assure its future safety operation. Based on the teachings learned from the accident, Monju has revised its educational training structure extensively such as, a new building a framework of educational training, a new open of Monju FBR Training School, a reinforcement of simulator training, etc.. A total of 29 established training courses, based on the mentioned above improvements, have been conducting towards Monju restarting.
Mizuno, Manabu*; Okusa, Kyoichi; Tamayama, Kiyoshi
Proceedings of International Symposium on Symbiotic Nuclear Power Systems for 21st Century (ISSNP) (CD-ROM), p.148 - 153, 2007/07
In the nuclear plants, it is required to detect an anomaly as early as possible and to inhibit adverse consequences. This requirement is especially important for the prototype Fast Breeder Reactor "Monju". Therefore, the monitoring and diagnosis system is required to be developed for "Monju" plant equipments. In these days, such a monitoring and diagnosis system can be realized using web technology with rationalized system resources due to remarkable progress of computer network technology. Then, we developed a platform based on web technology for the monitoring and diagnosis system of "Monju". Distributed architecture, standardization and highly flexible system structure have been taken account of in development. This newly developed platform and the prototype monitoring and diagnosis system have been validated. The system on the platform acquires "Monju" plant data and displays the data on client computers using "Monju" intranet with acceptable delay times.
Nabeshima, Kunihiko; Nakagawa, Shigeaki; Makino, Jun*; Kudo, Kazuhiko*
Proceedings of International Symposium on Symbiotic Nuclear Power Systems for 21st Century (ISSNP) (CD-ROM), p.142 - 147, 2007/07
Two types of neural networks have been utilized for real-time condition monitoring of High Temperature Engineering Tested Reactor (HTTR) in JAEA, Japan. Multi-Layer Perceptron (MLP) in auto-associative mode could model the whole plant dynamics and detect many kind of abnormal conditions. Another neural network with feedback connection can estimate the occurrence time and amount of helium leakage after auto-associative MLP detects the anomaly.