Engineering Papers⌕ Search

Engineering topics

Pereira, A

Publications and source records attributed to Pereira, A.

Support vector machine-based feature extractor for L/H transitions in JET

Support vector machines (SVM) are machine learning tools originally developed in the field of artificial intelligence to perform both classification and regression. In this paper, we show how SVM can be used to determine the most relevant quantities to characterize the confinement transition from low to high confinement regimes in tokamak plasmas. A set of 27 signals is used as starting point. The signals are discarded one by one until an optimal number of relevant waveforms is reached, which is the best tradeoff between keeping a limited number of quantities and not loosing essential information. The method has been applied to a database of 749 JET discharges and an additional database of 150 JET discharges has been used to test the results obtained.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Reflectance of polytetrafluoroethylene for xenon scintillation light

Gaseous and liquid xenon particle detectors are being used in a number of applications including dark matter search and neutrino-less double beta decay experiments. Polytetrafluoroethylene (PTFE) is often used in these detectors both as electrical insulator and as a light reflector to improve the efficiency of detection of scintillation photons. However, xenon emits in the vacuum ultraviolet (VUV) wavelength region ({lambda}{approx_equal}175 nm) where the reflecting properties of PTFE are not sufficiently known. In this work, we report on measurements of PTFE reflectance, including its angular distribution, for the xenon scintillation light. Various samples of PTFE, manufactured by different processes (extruded, expanded, skived, and pressed) have been studied. The data were interpreted with a physical model comprising both specular and diffuse reflections. The reflectance obtained for these samples ranges from about 47% to 66% for VUV light. Other fluoropolymers, namely, ethylene tetrafluoroethylene (ETFE), fluorinated ethylene propylene (FEP), and perfluoro-alkoxyalkane (PFA) were also measured.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Intelligent technique to search for patterns within images in massive databases

An image retrieval system for JET has been developed. The image database contains the images of the JET high speed visible camera. The system input is a pattern selected inside an image and the output is the group of frames (defined by their discharge numbers and time slices) that show patterns similar to the selected one. This approach is based on morphological pattern recognition and it should be emphasized that the pattern is found independently of its location in the frame. The technique encodes images into characters and, therefore, it transforms the pattern search into a character-matching problem.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Structural Pattern Recognition Techniques for Data Retrieval in Massive Fusion Databases

Diagnostics of present day reactor class fusion experiments, like the Joint European Torus (JET), generate thousands of signals (time series and video images) in each discharge. There is a direct correspondence between the physical phenomena taking place in the plasma and the set of structural shapes (patterns) that they form in the signals: bumps, unexpected amplitude changes, abrupt peaks, periodic components, high intensity zones or specific edge contours. A major difficulty related to data analysis is the identification, in a rapid and automated way, of a set of discharges with comparable behavior, i.e. discharges with 'similar' patterns. Pattern recognition techniques are efficient tools to search for similar structural forms within the database in a fast an intelligent way. To this end, classification systems must be developed to be used as indexation methods to directly fetch the more similar patterns.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗