Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This paper reports an algorithm to automatically identify the chain of events leading to a disruption, evaluating the so-called reference warning time. This time separates the plasma current flat-top of each disrupted discharge into two parts: a non-disrupted part and a pre-disrupted one. The algorithm can be framed into the anomaly detection techniques as it aims to detect the off-normal behavior of the plasma. It is based on a statistical analysis of a set of dimensionless plasma parameters computed for a selection of discharges from the JET experimental campaigns. In every data-driven model, such as the generative topographic mapping (GTM) predictor proposed in this paper, it is indeed necessary to label the samples needed for training the model itself. The samples describing the disruption-free behavior are extracted from the plasma current flat-top phase of the regularly terminated discharges. The disrupted space is described by all the samples belonging to the pre-disruptive phase of each disruptive discharge in the training set. Note that a proper selection of the pre-disruptive phase plays a key role in the prediction performance of the model. Moreover, these models, which are highly dependent on the training input space, may be particularly prone to degradation as the operational space of any experimental machine is continuously evolving. Hence, a regular schedule of model review and retrain must be planned. The proposed algorithm avoids the cumbersome and time-consuming manual identification of the warning times, helping to implement a continuous learning system that could be automated, despite being offline. In this paper, the automatically evaluated warning times are compared with those obtained with a manual analysis in terms of the impact on the mapping of the JET input parameter space using the GTM methodology. Moreover, the algorithm has been used to build the GTM of recent experimental campaigns, with promising results.
Alexandre Massoud Alahi, Yuejiang Liu, Parth Ashit Kothari
Jian Wang, Olivier Schneider, Yiming Li, Yi Zhang, Aurelio Bay, Guido Haefeli, Christoph Frei, Frédéric Blanc, Tatsuya Nakada, Michel De Cian, Luca Pescatore, François Fleuret, Elena Graverini, Chitsanu Khurewathanakul, Renato Quagliani, Maria Vieites Diaz, Federico Betti, Andrea Merli, Aravindhan Venkateswaran, Luis Miguel Garcia Martin, Vitalii Lisovskyi, Sebastian Schulte, Mingkui Wang, Zhirui Xu, Lei Zhang, Jessica Prisciandaro, Mark Tobin, Minh Tâm Tran, Niko Neufeld, Matthew Needham, Marc-Olivier Bettler, Greig Alan Cowan, Maurizio Martinelli, Vladislav Balagura, Donal Patrick Hill, Liang Sun, Pietro Marino, Mirco Dorigo, Jean Wicht, Xiaoxue Han, Liupan An, Federico Leo Redi, Plamen Hristov Hopchev, Thibaud Humair, Maxime Schubiger, Hang Yin, Guido Andreassi, Violaine Bellée, Olivier Göran Girard, Axel Kuonen, Preema Rennee Pais, Pavol Stefko, Tara Nanut, Maria Elena Stramaglia, Tommaso Colombo, Vladimir Macko, Guillaume Max Pietrzyk, Evgenii Shmanin, Dipanwita Dutta, Zheng Wang, Yi Wang, Hans Dijkstra, Gerhard Raven, Peter Clarke, Frédéric Teubert, Giovanni Carboni, Victor Coco, Adam Davis, Paolo Durante, Wenyu Zhang, Yu Zheng, Anton Petrov, Maxim Borisyak, Feng Jiang, Chen Chen, Zhipeng Tang