Innovative signal processing and data analysis methods on JET for control in the perspective of next-step devices

Abstract

In the last few years, it has been realized that more sophisticated control schemes are necessary to push the boundaries of tokamak operation and the performance of reactor-like machines. In addition, JET needs to operate safely with the new metallic wall and such protection will be needed for ITER. These objectives have motivated the development, benchmark and validation of new signal processing and data analysis methods. Two new approaches for the determination of the magnetic topology in real time have been validated on an extensive database of JET discharges, including advanced tokamak scenarios. Robust methods of confinement regime identification and disruption prediction are a prerequisite for safe, general control schemes. New identifiers have been developed and their success rates exceed 99% in determining whether plasmas are in the L or H mode. A new disruption predictor is being developed and has already provided success rates higher than 90% in realistic real-time conditions. Moreover, the generalization capability of this new predictor has been confirmed by applying it to new experimental campaigns not used for the training. The success rate remains high even more than ten campaigns, or about four years, after the last one used for the training. The deployment of video cameras in real time requires the development of new image processing algorithms, which have already been implemented and validated successfully on JET for the real-time identification of hot spots with a time resolution of tens of milliseconds. A series of new feedback schemes has also been explicitly developed not much to control the plasma but to really improve the physics understanding of some phenomena. Particularly interesting are the simultaneous control of the safety factor and pressure profiles and the real-time tracking of toroidal Alfven eigenmode instabilities. These advanced feedback schemes for physics understanding often require more advanced signal processing techniques like adaptive filtering, which have already been implemented. The paper concludes by discussing the use of these real-time analysis and control developments in next-step machines such as ITER.

Prediction of unusual plasma discharge by using Support Vector Machine

“…Some studies have attempted to detect disruption by taking signal processing approaches, including the Wavelet transformation [3][4][5][6]. Others have attempted to predict disruption by using machine learning methods, among which the Support Vector Machine (SVM) and the Neural Network (NN) stand out [7][8][9][10][11][12][13][14]. Nakagawa et al proposed methods for predicting unusual light emission using the SVM and the NN [7,[15][16][17].…”

“…Many disruption prediction methods using machine learning methods have been reported. Murari et al proposed a disruption prediction method using the SVM [8-10] and found three best SVMs [9]. Farias et al attempted to predict the time to the occurrence of a disruption using multilayer NNs and multilayer SVMs [11].…”

Contribution of ASDEX Upgrade to disruption studies for ITER

“…Several publications on disruption prediction based on statistical methods have appeared in the last decade (see for example [18][19][20][21][22][23][24] published after 2005). They have shown that with a limited number of machine and plasma parameters, available in real time, and a database of safe and disruptive discharge phases, it is possible to build a complex function which can predict the disruption occurrence with a relatively small rate of false alarms (some %) and a large success rate (80-90%).…”

Identification of Confinement Regimes in Tokamak Plasmas by Conformal Prediction on a Probabilistic Manifold

“…[9] for a recent overview at the JET tokamak. However, pattern recognition for fusion data is a veritable challenge, for several reasons that are discussed in this paper.…”