سیستم هوشمند برای تنظیم میدان مغناطیسی نگه دارنده انحراف یک لامپ اشعه کاتدی

This short communication concerns identification of the number of magnetic correction shunts and their positions for deflection yoke tuning to correct the misconvergence of colours of a cathode ray tube. The misconvergence of colours is characterised by the distances measured between the traces of red and blue beams. The method proposed consists of two phases, namely, learning and optimisation. In the learning phase, the radial basis function neural network is trained to learn a mapping: correction shunt position→changes in misconvergence. In the optimisation phase, the trained neural network is used to predict changes in misconvergence depending on a correction shunt position. An optimisation 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 analysed have been tuned successfully using the technique proposed.

This short communication concerns the use of image analysis and neural networks based techniques for tuning magnetic field of a deflection yoke of a cathode ray tube (CRT). Several prototypes of the system have been installed in the ‘Vilniaus Vingis’ company, Lithuania, and are successfully used on production line. The most widely used display device for television and computer monitors is the colour Cathode Ray Tube [1]. In the colour CRT, three electron guns producing three beams of electrons hitting three colour phosphors are used. The red (R), green (G), and blue (B) phosphors are placed on the inner part of a TV screen as dots or strips. In order to create a picture on a TV screen, the beams are scanned across the screen by electromagnetic deflection mechanisms. A deflection yoke of the CRT supplying the vertical and horizontal magnetic fields enables the scanning process. If the magnetic fields are not correctly formed, the misconvergence of the three beams may occur. The misconvergence is characterised by the actual distances measured on a TV screen between traces of the three electron beams when the distances are supposed to be zero. The misconvergence of the beams causes the misconvergence (mismatch) of the red, green, and blue components of a picture displayed on a TV screen (misconvergence of colours). The misconvergence is eliminated by sticking one or several magnetic shunts on the inner part of DY, as shown in Fig. 1. The tuning is usually done manually by human experts. Manual tuning is a very tedious and time-consuming procedure. Moreover, the tuning quality depends heavily upon the expert's experience, tiredness, and other factors.

This short communication concerns a method to identify the number of magnetic correction shunts and their positions for deflection yoke tuning to correct the residual misconvergence of colours of a CRT. The method proposed consists of two phases, namely, learning and optimisation. In the learning phase, the radial basis function neural network is trained to perform a mapping: correction shunt position→changes in misconvergence. In the optimisation phase, the trained neural network is used to predict changes in misconvergence depending on the correction shunt position. An optimisation 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 199 deflection yokes analysed have been tuned successfully using the technique proposed.