Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection

L. Makili, J. Vega, S. Dormido-Canto, I. Pastor, A. Pereira, G. Farias, A. Portas, D. Pérez-Risco, M. C. Rodríguez-Fernández, P. Busch

Resultado de la investigación: Contribución a una revistaArtículorevisión exhaustiva

13 Citas (Scopus)

Resumen

An automatic image classification system based on support vector machines (SVM) has been in operation for years in the TJ-II Thomson Scattering diagnostic. It recognizes five different types of images: CCD camera background, measurement of stray light without plasma or in a collapsed discharge, image during ECH phase, image during NBI phase and image after reaching the cut off density during ECH heating. Each kind of image implies the execution of different application software. Due to the fact that the recognition system is based on a learning system and major modifications have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid. A new SVM model has been developed with the current conditions. Also, specific error conditions in the data acquisition process can automatically be detected and managed now. The recovering process has been automated, thereby avoiding the loss of data in ensuing discharges.

Idioma originalInglés
Páginas (desde-hasta)415-418
Número de páginas4
PublicaciónFusion Engineering and Design
Volumen85
N.º3-4
DOI
EstadoPublicada - jul. 2010
Publicado de forma externa

Huella

Profundice en los temas de investigación de 'Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection'. En conjunto forman una huella única.

Citar esto