Current Research into Applications of Tomography for Fusion Diagnostics

Mlynář, J.; Sundén, E. Andersson; Binda, Federico; Cecconello, M.; Conroy, S.; Dzysiuk, N.; Ericsson, Göran; Eriksson, J.; Hellesen, C.; Hjalmarsson, Anders; Possnert, Göran; Sjöstrand, Henrik; Skiba, Mateusz; Weiszflog, M.; Zychor, I.

doi:10.1007/s10894-018-0178-x

Cited by 40 publications

(40 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An improvement of this result could be achieved by an increase in the amount of sub-chambers or by the use of a different method, which could potentially perform spectral deconvolution and tomography simultaneously, as described in Ref. 26. In a plasma with a higher temperature, this method should be valid in a wider region.…”

Section: Estimation Of the Electron Temperaturementioning

confidence: 99%

Conceptual study of energy resolved x-ray measurement and electron temperature reconstruction on ITER with low voltage ionization chambers

Colette

Mazon

Barnsley

et al. 2021

Review of Scientific Instruments

View full text Add to dashboard Cite

In tokamaks with tungsten-based plasma facing components, such as ITER, pollution of the plasma by heavy impurities is a major concern as it can lead to radiative breakdown. The radiation emitted by such impurities is mainly composed of x-rays in the [0.1; 100] keV range. A diagnostic allowing for the reconstruction of the impurity distribution is of high interest. The ITER requirements for the x-ray measurement system make it mandatory for the detector to provide spectral information. Due to the radiation environment during the ITER nuclear phase, advanced detectors exhibiting high resilience to neutrons and gamma rays, such as gas-filled detectors, are required. The use of Low Voltage Ionization Chambers (LVICs) for this purpose is investigated in this paper. Several anodes have been added to the detector in order to allow for spectral deconvolution. This article presents a conceptual study of the use of a multi-anode LVIC for energy resolved x-ray measurement on ITER. It covers the design of the multi-anode LVIC and its modeling, the method for spectral deconvolution, and its application to energy resolved x-ray tomography, as well as the computation of the electron temperature from the reconstructed local x-ray emissivity.

show abstract

Section: Estimation Of the Electron Temperaturementioning

confidence: 99%

Conceptual study of energy resolved x-ray measurement and electron temperature reconstruction on ITER with low voltage ionization chambers

Colette

Mazon

Barnsley

et al. 2021

Review of Scientific Instruments

View full text Add to dashboard Cite

show abstract

“…This arrangement is illustrated in figure 1. From the bolometer measurements, it is possible to reconstruct the 2D plasma radiation profile using different tomography techniques [14]. The underlying principle is the same as computed tomography (CT) in medical applications [15], but the reconstruction method is different due to the scarce number of lines of sight available.…”

Section: The Jet Bolometer Diagnosticmentioning

confidence: 99%

Using HPC infrastructures for deep learning applications in fusion research

Ferreira

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the fusion community, the use of high performance computing (HPC) has been mostly dominated by heavy-duty plasma simulations, such as those based on particle-in-cell and gyrokinetic codes. However, there has been a growing interest in applying machine learning for knowledge discovery on top of large amounts of experimental data collected from fusion devices. In particular, deep learning models are especially hungry for accelerated hardware, such as graphics processing units (GPUs), and it is becoming more common to find those models competing for the same resources that are used by simulation codes, which can be either CPU-or GPU-bound. In this paper, we give examples of deep learning models -such as convolutional neural networks, recurrent neural networks, and variational autoencoders -that can be used for a variety of tasks, including image processing, disruption prediction, and anomaly detection on diagnostics data. In this context, we discuss how deep learning can go from using a single GPU on a single node to using multiple GPUs across multiple nodes in a large-scale HPC infrastructure.

show abstract

“…From the bolometer measurements, there are several different tomography techniques that can be applied to reconstruct the plasma radiation profile [17]. The method that is used at JET uses an iterative constrained optimization algorithm that minimizes the error with respect to the bolometer measurements, while requiring the solution to be non-negative [18].…”

Section: Bolometer Tomography At Jetmentioning

confidence: 99%

Deep Learning for the Analysis of Disruption Precursors based on Plasma Tomography

Ferreira¹,

Carvalho²,

Sozzi³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The JET baseline scenario is being developed to achieve high fusion performance and sustained fusion power. However, with higher plasma current and higher input power, an increase in pulse disruptivity is being observed. Although there is a wide range of possible disruption causes, the present disruptions seem to be closely related to radiative phenomena such as impurity accumulation, core radiation, and radiative collapse. In this work, we focus on bolometer tomography to reconstruct the plasma radiation profile and, on top of it, we apply anomaly detection to identify the radiation patterns that precede major disruptions.The approach makes extensive use of machine learning. First, we train a surrogate model for plasma tomography based on matrix multiplication, which provides a fast method to compute the plasma radiation profiles across the full extent of any given pulse. Then, we train a variational autoencoder to reproduce the radiation profiles by encoding them into a latent distribution and subsequently decoding them. As an anomaly detector, the variational autoencoder struggles to reproduce unusual behaviors, which includes not only the actual disruptions but their precursors as well. These precursors are identified based on an analysis of the anomaly score across all baseline pulses in two recent campaigns at JET.

show abstract

Current Research into Applications of Tomography for Fusion Diagnostics

Cited by 40 publications

References 32 publications

Conceptual study of energy resolved x-ray measurement and electron temperature reconstruction on ITER with low voltage ionization chambers

Conceptual study of energy resolved x-ray measurement and electron temperature reconstruction on ITER with low voltage ionization chambers

Using HPC infrastructures for deep learning applications in fusion research

Deep Learning for the Analysis of Disruption Precursors based on Plasma Tomography

Contact Info

Product

Resources

About