https://doi.org/10.1140/epjd/s10053-022-00511-6
Regular Article – Plasma Physics
Simulation of hard X-ray time evolution in plasma tokamak by using the NARX-GA hybrid neural network
1
Department of Physics, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran
2
Department of Basic Sciences, Garmsar Branch, Islamic Azad University, Garmsar, Iran
3
Department of Computer Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
4
Earth Sciences Department, Faculty of Natural Sciences, University of Tabriz, Tabriz, Iran
Received:
8
June
2022
Accepted:
20
September
2022
Published online:
27
October
2022
The NARX-GA hybrid neural network was applied to simulate the time evolution of runaway electrons (REs) in the plasma tokamak. This particular type of artificial neural network was created specifically for time series prediction. The NARX-GA network was built using inputs from some plasma diagnostic signals (loop voltage, hard X-ray) collected during all phases of plasma tokamak discharges. The network output predicts the time evolution of hard X-ray (HXR) signals up to 500 μs, which can be achieved with high accuracy (MSE = 
). The real-time application of this methodology can pave the way for prompt REs control action. The confinement time increases as the REs generation decreases, and their destructive effects on the tokamak wall decrease as well. Early prediction of RE behavior is critical in attempting to mitigate their potentially dangerous effects.
Copyright comment Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, SIF and Springer-Verlag GmbH Germany, part of Springer Nature 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
