A fuzzy neural approach to plasma disruption prediction in tokamak reactors
Francesco Carlo Morabito, Mario Versaci · 2003
This paper proposes the use of Fuzzy Neural Network approaches for the early detection of disruption in tokamak plasmas. Neural Networks can be used for classifying plasma shots and defecting disruptive shots as well as for estimating the time left before disrupting. The use of fuzzy logic concept is suggested because it offers a framework for embodying expert knowledge about predicting the onset of disruption. Moreover, learning approaches allow to tune the model expressed in terms of fuzzy statements. The proposed method appears to be a step forward with respect to more conventional NN approach.