ABSTRACT
The method proposed consists of two phases, namely learning and operating. In the learning phase, the radial basis function neural network is trained to learn a mapping: correction shunt position .changes in misconvergence. In the operating phase, the trained neural network is used to predict changes in misconvergence depending on a correction shunt position. The decision about DY tuning with correction shunts is based upon the results of those predictions. During the experimental investigations, 98% of the deflection yokes analysed have been tuned correctly using the technique proposed. The software developed is easily adapted for deflection yokes of different types.
Keywords: Deflection Yokes, Neural networks, colour beam, colours misconvergence
Download the article in PDF: .....
Contact the authors by e-mails:
Antanas Verikas mailto://antanas.verikas[eta]ide.hh.se
Alvydas Dosinas mailto://[email protected]
Marija Bacauskiene mailto://mabaca[eta]eaf.ktu.lt
Vacys Bartkevicius mailto://vacys.bartkevicius[eta]eaf.ktu.lt
Adas Gelzinis mailto://adgel[eta]eaf.ktu.lt
Mindaugas Vaitkunas mailto://minvait[eta]eaf.ktu.lt
Arunas Lipnickas mailto://lipnick[eta]soften.ktu.lt
Department of Applied Electronics,
Kaunas University of Technology,
Studentu 50,
LT-3031 Kaunas,
LITHUANIA