Generalization of knowledge acquired by a reactor core monitoring system based on a neuro-fuzzy algorithm

Using recurrent neural networks for estimation of minor actinides’ transmutation in a high power density fusion reactor

“…Recently, there has been a significant interest on the use of ANNs in the nuclear engineering applications (Nissan, 1998;Uhrig & Tsoukalas, 1999). These applications consist of anomalies detection (Kozma & Nabeshima, 1995;Ogha & Seki, 1991;Reifman, 1997;S ßeker, Ayaz, & Türkcan, 2003), diagnostics (Bartlett & Uhrig, 1992;Kim, Aljundi, & Bartlett, 1992;Lee & Seong, 2005;Wroblewski, Jahns, & Leuer, 1997), signal validation (Fantoni & Mazzola, 1996a, 1996b, core monitoring (Kozma, Sato, Sakuma, Kitamura, & Sugiyama, 1995) and nuclear reactor control (Khajavi, Menhaj, & Suratgar, 2002;Vitela, 2007). Furthermore, Adalı, Bakal, Sönmez, Fakory, and Tsaoi (1997) worked on modeling a nuclear reactor core dynamics with recurrent neural networks (RNNs).…”