Southwestern Institute of Physics, Chengdu 610041, China; National Institute for Fusion Science, Toki, Gifu, 509-5292, Japan
Abstract:
Artificial neural networks are trained to forecast the plasma
disruption in HL-2A tokamak. Optimized network architecture is obtained.
Saliency analysis is made to assess the relative importance of different
diagnostic signals as network input. The trained networks can successfully
detect the disruptive pulses of HL-2A tokamak. The results obtained show the
possibility of developing a neural network predictor that intervenes well in
advance for avoiding plasma disruption or mitigating its effects.