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

Research output: Contribution to journalArticlepeer-review

13 Scopus citations

Abstract

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have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid.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.

Original languageEnglish
Pages (from-to)415-418
Number of pages4
JournalFusion Engineering and Design
Volume85
Issue number3-4
DOIs
StatePublished - Jul 2010
Externally publishedYes

Keywords

  • Classifier
  • Multi-class
  • Support vector machines
  • Wavelet

Fingerprint

Dive into the research topics of 'Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection'. Together they form a unique fingerprint.

Cite this