|Title||Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection|
|Publication Type||Journal Article|
|Year of Publication||2010|
|Authors||L. Makili, J. Vega, S. Dormido-Canto, I. Pastor, A. Pereira, G. Farias, A. Portas, D. Perez-Risco, M.C Rodriguez-Fernandez, P. Busch|
|Journal||Fusion Engineering and Design|
|Type of Article||Proceedings Paper|
|Keywords||Classifier, Multi-class, Support vector machines, Wavelet|
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have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid.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. (C) 2009 Elsevier B.V. All rights reserved.
|URL||<Go to ISI>://000281190000030|
|Alternate Title||Fusion Eng. Des.|
Go back one page.