[图书][B] Conformal prediction for reliable machine learning: theory, adaptations and applications
The conformal predictions framework is a recent development in machine learning that can
associate a reliable measure of confidence with a prediction in any real-world pattern …
associate a reliable measure of confidence with a prediction in any real-world pattern …
Classification of tokamak plasma confinement states with convolutional recurrent neural networks
During a tokamak discharge, the plasma can vary between different confinement regimes:
low (L), high (H) and, in some cases, a temporary (intermediate state), called dithering (D). In …
low (L), high (H) and, in some cases, a temporary (intermediate state), called dithering (D). In …
Plasma confinement mode classification using a sequence-to-sequence neural network with attention
F Matos, V Menkovski, A Pau, G Marceca… - Nuclear …, 2021 - iopscience.iop.org
In a typical fusion experiment, the plasma can have several possible confinement modes. At
the tokamak à configuration variable, aside from the low (L) and high (H) confinement …
the tokamak à configuration variable, aside from the low (L) and high (H) confinement …
The JET real-time plasma-wall load monitoring system
DF Valcárcel, D Alves, P Card, BB Carvalho… - Fusion Engineering and …, 2014 - Elsevier
In the past, the Joint European Torus (JET) has operated with a first-wall composed of
Carbon Fibre Composite (CFC) tiles. The thermal properties of the wall were monitored in …
Carbon Fibre Composite (CFC) tiles. The thermal properties of the wall were monitored in …
Selección de características para el reconocimiento de patrones con datos de alta dimensionalidad en fusión nuclear
A Pereira González - 2015 - e-spacio.uned.es
La mayoría de los dispositivos experimentales de fusión, investigan el comportamiento del
plasma, isótopos de hidrógeno ionizados a muy elevadas temperaturas, mediante su …
plasma, isótopos de hidrógeno ionizados a muy elevadas temperaturas, mediante su …
[PDF][PDF] Implementation of a IMM Kalman Filter-based real-time event detector on the TCV tokamak
R Shousha - 2022 - pure.tue.nl
In this thesis, an existing Interacting Multiple Model Kalman filter for real-time modelbased
detection of LH-transitions, HL-transitions and ELMs has been implemented in the plasma …
detection of LH-transitions, HL-transitions and ELMs has been implemented in the plasma …
Advanced techniques of disruption prediction, application to JET and extrapolation to ITER
RM Salinas - 2015 - dialnet.unirioja.es
Esta tesis aborda las bases de datos masivas generadas por los dispositivos
experimentales de fusión nuclear. Se utilizan técnicas de inteligencia artificial y algoritmos …
experimentales de fusión nuclear. Se utilizan técnicas de inteligencia artificial y algoritmos …
Deep Learning for Tomography, State Classification and Event Detection in Nuclear Fusion Plasmas
F Duarte Pinto de Almeida Matos - 2021 - mediatum.ub.tum.de
Nuclear fusion experiments regularly generate large amounts of data that can constitute a
rich source of information for new scientific and engineering insights. Yet in many cases, the …
rich source of information for new scientific and engineering insights. Yet in many cases, the …
[PDF][PDF] Deep Learning for Tomography, State Classification and Event Detection in Nuclear Fusion Plasmas
FDP de Almeida Matos - mediatum.ub.tum.de
Nuclear fusion experiments regularly generate large amounts of data that can constitute a
rich source of information for new scientific and engineering insights. Yet in many cases, the …
rich source of information for new scientific and engineering insights. Yet in many cases, the …
[PDF][PDF] LH přechod a H-mód v tokamakovém plazmatu
BO Grover - indico.fjfi.cvut.cz
Termojaderná fúze patří mezi nadějné alternativní zdroje budoucnosti a je předmětem
intenzivního výzkumu. Na zařízeních typu tokamak se dosahuje zatím nejlepších výsledků …
intenzivního výzkumu. Na zařízeních typu tokamak se dosahuje zatím nejlepších výsledků …