Search

Byline: A. Verikas (1,2), M. Bacauskiene (1), A. Dosinas (1), V. Bartkevicius (1), A. Gelzinis (1), M. Vaitkunas (1), A. Lipnickas (1) Keywords: Automation; learning; cathode ray tube; neural network; simulated annealing Abstract: This paper presents a method and a system to identify the number of magnetic correction shunts and their positions for deflection yoke tuning to correct the misconvergence of colors of a cathode ray tube. The method proposed consists of two phases, namely, learning and optimization. In the learning phase, the radial basis function neural network is trained to learn a mapping: correction shunt position [right arrow] changes in misconvergence. In the optimization phase, the trained neural network is used to predict changes in misconvergence depending on a correction shunt position. An optimization procedure based on the predictions returned by the neural net is then executed in order to find the minimal number of correction shunts needed and their positions. During the experimental investigations, 98% of the deflection yokes analyzed have been tuned successfully using the technique proposed. Author Affiliation: (1) Department of Applied Electronics, Kaunas University of Technology, Studentu 50, LT-3031, Kaunas, Lithuania (2) Intelligent Systems Laboratory, Halmstad University, Box 823, S-301 18, Halmstad, Sweden Article History: Registration Date: 30/09/2004