Disruption forecasting at JET using neural networks

Abstract

Neural networks are trained to evaluate the risk of plasma disruptions in a tokamak experiment using several diagnostic signals as inputs. A saliency analysis confirms the goodness of the chosen inputs, all of which contribute to the network performance. Tests that were carried out refer to data collected from succesfully terminated and disruption terminated pulses performed during two years of JET tokamak experiments. Results show the possibility of developing a neural network predictor that intervenes well in advance in order to avoid plasma disruption or mitigate its effects.

Geometrical Kernel Machine for Prediction and Novelty Detection of Disruptive Events in TOKAMAK Machines

“…In order to avoid or to mitigate the disruptive events a number of disruption prediction techniques have been developed. In many cases neural networks approaches are used and they seems to be the most suitable to predict the event or, more precisely, to build an impending disruption warning indicator [12][13][14][15][16].…”

“…The performance of the proposed approach are reported in terms of False Alarms, i.e., wrong predictions on safe pulses, and Missed Alarms, i.e., wrong predictions on disruptive pulses. A disruption prediction system, based on neural networks, is presented in [13] for JET. An MLP has been trained using 9 plasma parameters.…”

Detection of Disruptions in the High-β Spherical Torus NSTX

“…Neural networks are typically trained, in the sense that a predetermined sample of input and output data are used to determine the optimal values of the coefficients of the network. Neural networks have been used to predict various forms of disruptions on ASDEX Upgrade [84][85][86], DIII-D [87], ADITYA [88,89], TEXT [90,91], JET [85,92,93], and JT-60 [94,95].…”

“…Typical input data to the network include a measure of the plasma β (the normalized β (β N ) [96,97] or poloidal β (β P )), edge safety factor, plasma density (or Greenwald fraction [98,99]), locked mode amplitude, input power, radiated power, shape parameters, internal inductance, confinement time, and neutron emission. Some early work also used soft X-ray emission [87][88][89]91], high(er) frequency magnetic probes [87][88][89][90], or Dα monitors [87][88][89] though these diagnostics have typically not been used in more recent studies [85,86,92,93,95].…”

A Disruption Predictor Based on Fuzzy Logic Applied to JET Database

“…Further works in this direction is reported in Cannas [8] where an ANN was used to estimate the risk of disruption. An ANN was trained using both disrupted and safe pulses with the following characteristics: I pla > 1.5 MA, X-point configuration and flat-top plasma-current profile.…”