Hybrid intelligent methods for modelling and tuning of crt (cathode ray tube) deflection yoke systems

Development of computationally efficient, hybrid intelligent
methods for analysis, modelling and tuning of cathode ray
tube deflection yoke systems.

Electronics and telecommunications equipment are the key industries of the 21st century. As electronic component suppliers, European firms exhibit greater prowess, especially in the production of cathode ray tubes (CRTs) and their components. Colour CRTs are the most widely used display devices for television and computer monitors. The production of CRTs and their electronic components is one of the most competitive and efficient manufacturing operations in the world today. European firms compete with Japanese consumer electronic giants such as SONY and Korean firms such as SAMSUNG. Therefore improvement in device performances are needed to survive in today's market. The objective of this project is to design hybrid intelligent methods for the analysis, modelling and tuning of CRT DY (deflection yoke) systems. In the manufacturing process of monitors and TV, a high quality DY is an essential factor in achieving high performance CRT. A DY of the CRT supplying the vertical and horizontal magnetic fields makes the scanning process possible. In the colour CRTs, three electron guns producing three beams of electrons are used. If the magnetic fields are not correctly formed misconvergence of the beams may occur, resulting in blurred image on the monitor screen. The magnetic fields can be corrected by sticking one or several ferrite sheets on the inner part of the DY. The correction is usually done manually by human experts. Manual correction is a very tedious and time consuming procedure. Due to the complexity of this process there is a shortage of experts. Moreover, the adjustment quality depends heavily upon the shape and the expert's experience. Therefore, intelligent automating systems capable of replacing human experts are highly appreciated. In this project, hybrid intelligent methods are proposed to systematically deal with several sources of information including the expert's knowledge, input/output data, neural networks and traditional math-models in the adjustment/ tuning process of the DY system. Hybrid intelligent methods combining traditional mathematical model based methods, genetic/evolutionary programming algorithms, fuzzy logic, neural networks and expert systems are proving their effectiveness in a wide variety of real-world problems. Every intelligent technique has particular computational properties (e.g. ability to learn, explanation of decisions) that make them suitable for certain problems and not for others. From a knowledge of their strengths and weaknesses we can construct hybrid methods to mitigate the limitations and take advantage of the opportunities to produce systems that are more powerful than those that could be built with single technologies. More specifically, the objectives of the project can be listed as follows: 1) Examine different hybrid intelligent methods for analysis, modelling and tuning of DY systems; 2) Construct and develop efficient software tools, for the integration of different pieces of information (input/ output data, neural networks, mathematical models, expert's knowledge) in a highly modular software package; 3) Apply the hybrid intelligent methods for tuning of DY in an industrial DY manufacturing process. Keywords: intelligent methods, deflection yokes, tuning.
Project ID: 
2 374
Start date: 
Project Duration: 
Project costs: 
900 000.00€
Technological Area: 
Electrical Technology related to measurements
Market Area: 

Raising the productivity and competitiveness of European businesses through technology. Boosting national economies on the international market, and strengthening the basis for sustainable prosperity and employment.