Real-time disruption handling at ASDEX upgrade

Autor:	Gerhard Raupp, G. Pautasso, V. Mertens, D. Zasche, C. Tichmann, G. Neu, W. Treutterer, Th. Zehetbauer, A. Lorenz, S. Egorov
Rok vydání:	2001
Předmět:	ComputingMilieux_GENERAL Nuclear Energy and Engineering ASDEX Upgrade Soft landing Artificial neural network Computer science Mechanical Engineering Control system Plasma control system General Materials Science Real-time operating system Simulation Civil and Structural Engineering
Zdroj:	Fusion Engineering and Design. :721-725
ISSN:	0920-3796
Popis:	A neural network for prediction of disruptions has been developed at ASDEX Upgrade with the goal to mitigate or avoid these. The novel idea is to compute the remaining time-to-disruption to indicate the stability level of the discharge. The neural network has been specified, trained and then implemented within the real-time plasma control system. The current version of the system terminates the discharge with an impurity pellet when the computed time-to-disruption falls below a threshold of 80 ms. Routine operation shows that disruptions are recognized reliably. Vessel currents and forces are considerably reduced. The system will be enhanced to avoid disruptions with a soft landing initiated in time.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::a78bef7088d41c04b7f51550036296fb https://doi.org/10.1016/s0920-3796(01)00392-1 Zobrazit plný text záznamu Full Text from ScienceDirect