Disruption prediction at JET through deep convolutional neural networks using spatiotemporal information from plasma profiles

Abstract

In view of the future high power nuclear fusion experiments, the early identification of disruptions is a mandatory requirement, and presently the main goal is moving from the disruption mitigation to disruption avoidance and control. In this work, a Deep-Convolutional Neural Network (CNN) is proposed to provide early detection of disruptive events at JET. The CNN ability to learn relevant features, avoiding hand-engineered feature extraction, has been exploited to extract the spatiotemporal information from 1D plasma profiles. The model is trained with regularly terminated discharges and automatically selected disruptive phase of disruptions, coming from the recent ITER-Like-Wall (ILW) experiments. The prediction performance is evaluated using a set of discharges representative of different operating scenarios, and an in-depth analysis is made to evaluate the performance evolution with respect to the considered experimental conditions. Finally, as real-time triggers and termination schemes are being developed at JET, the proposed model has been tested on a set of recent experiments dedicated to plasma termination for disruption avoidance and mitigation. The CNN model demonstrates very high performance, and the exploitation of 1D plasma profiles as model input allows us to understand the underlying physical phenomena behind the predictor decision.

A hybrid physics/data-driven logic to detect, classify, and predict anomalies and disruptions in tokamak plasmas

“…With regard to real-time signal processing, the methods implemented have explored practically all known data analysis techniques for time series in the time domain, in the frequency domain, and in the combined time/frequency domains [18,19]. Machine learning predictors with various technologies have been developed for all the following Tokamaks: TCV [20], ADITYA [21], AUG [19,[22][23][24][25], DIII-D [26][27][28], J-TEXT [29], NSTX [30], EAST [28,31], ALCATOR C-MOD [27,28], JT-60 U [32,33] and JET [19,[34][35][36][37][38][39][40][41][42][43][44]. The advanced predictor of disruptions is the first disruption predictor that on JET obtained success rates >98%, false alarm rates <2% and average warning times of hundreds of ms [45].…”

Recent progress on deep learning-based disruption prediction algorithm in HL-2A tokamak

“…In recent years, many data-driven algorithms have been de-veloped on various tokamaks, such as DIII-D, JET, C-Mod, J-TEXT and EAST. [7][8][9][10][11][12][13][14] The data-driven method has been tried in HL-2A at around 2010. A multi-layer perceptron model is built to predict the disruptions according to the evolution of signals from bolometer array.…”

Comparison of machine learning systems trained to detect Alfvén eigenmodes using the CO2 interferometer on DIII-D

“…Machine Learning (ML) applications in magnetic confinement fusion energy are growing and exciting opportunities exist in the fast-ion physics research field. Currently, the largest application of ML is in the area of disruption mitigation, where models are trained to prevent the rapid loss of thermal and magnetic energy during a quench of the plasma [20][21][22][23][24][25][26][27]. Surrogate model generation and experimental planning also benefit from data-driven methods [28].…”