You need JavaScript to view this

Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis

Abstract

A back-propagation neural network technique is used at JET to extract plasma parameters like ion temperature, rotation velocities or spectral line intensities from charge exchange (CX) spectra. It is shown that in the case of the C VI CX spectra, neural networks can give a good estimation (better than +-20% accuracy) for the main plasma parameters (Ti, V{sub rot}). Since the neural network approach involves no iterations or initial guesses the speed with which a spectrum is processed is so high (0.2 ms/spectrum) that real time analysis will be achieved in the near future. 4 refs., 8 figs.
Authors:
Koenig, R W.T.; Von Hellermann, M; [1]  Svensson, J [2] 
  1. Commission of the European Communities, Abingdon (United Kingdom). JET Joint Undertaking
  2. Royal Inst. of Tech., Stockholm (Sweden)
Publication Date:
Jul 01, 1994
Product Type:
Conference
Report Number:
JET-P-94-29; CONF-9406270-
Reference Number:
SCA: 700320; PA: AIX-28:032641; EDB-97:058876; SN: 97001766235
Resource Relation:
Conference: 21. EPS conference on controlled fusion and plasma physics, Montpellier (France), 27 Jun - 1 Jul 1994; Other Information: PBD: Jul 1994; Related Information: Is Part Of Controlled fusion and plasma physics; PB: 240 p.
Subject:
70 PLASMA PHYSICS AND FUSION; NEURAL NETWORKS; CHARGE EXCHANGE; PLASMA DIAGNOSTICS; DATA PROCESSING; ION TEMPERATURE; JET TOKAMAK; LEAST SQUARE FIT; REAL TIME SYSTEMS; ROTATING PLASMA; SPECTRA UNFOLDING
OSTI ID:
456171
Research Organizations:
Commission of the European Communities, Abingdon (United Kingdom). JET Joint Undertaking
Country of Origin:
France
Language:
English
Other Identifying Numbers:
Other: ON: DE97621358; TRN: FR9701780032641
Availability:
INIS; OSTI as DE97621358
Submitting Site:
FRN
Size:
pp. 175-180
Announcement Date:
Apr 21, 1997

Citation Formats

Koenig, R W.T., Von Hellermann, M, and Svensson, J. Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis. France: N. p., 1994. Web.
Koenig, R W.T., Von Hellermann, M, & Svensson, J. Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis. France.
Koenig, R W.T., Von Hellermann, M, and Svensson, J. 1994. "Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis." France.
@misc{etde_456171,
title = {Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis}
author = {Koenig, R W.T., Von Hellermann, M, and Svensson, J}
abstractNote = {A back-propagation neural network technique is used at JET to extract plasma parameters like ion temperature, rotation velocities or spectral line intensities from charge exchange (CX) spectra. It is shown that in the case of the C VI CX spectra, neural networks can give a good estimation (better than +-20% accuracy) for the main plasma parameters (Ti, V{sub rot}). Since the neural network approach involves no iterations or initial guesses the speed with which a spectrum is processed is so high (0.2 ms/spectrum) that real time analysis will be achieved in the near future. 4 refs., 8 figs.}
place = {France}
year = {1994}
month = {Jul}
}