opti_electrod_ann_ga - 964 Lahiri and Chakraorti:...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Lahiri and Chakra © orti: Electrode-spacer Contour Optimization by ANN Aided Genetic Algorithm 964 Electrode-spacer Contour Optimization by ANN Aided Genetic Algorithm A. Lahiri and S. Chakravorti Electrical Engineering Department Jadavpur University, Kolkata, 700032, India ABSTRACT Optimization of contours of three dimensional electrode-spacer arrangements used () in gas insulated systems GIS has been carried out by ANN aided genetic algo - rithm GA to obtain desirable electric stress distribution along the insulator sur - face. Two cases have been studied and reported in detail. Multilayer feed-forward neural networks with error back-propagation algorithm have been applied to accel - erate the execution of GA loop. The training and the test data have been prepared by means of electric field calculations using indirect boundary element method BEM . The results show that optimized contours have been obtained with accept - able degree of accuracy with the help of GA aided by trained ANN. Index Terms — Optimization of 3D Electric Field, Indirect Boundary Element Method, Artificial Neural Network, Genetic Algorithm. LIST OF SYMBOLS Symbol Variable Unit Ž. E Maximum resultant stress V r mm r V Rmax E c Maximum resultant stress obtained Rmax from field calculation V r mm r V E o Maximum resultant stress obtained Rmax tained from a trained ANN V r mm r V P Crossover rate c P Mutation rate m P Population size s Rad Radius mm Sec Section 1 INTRODUCTION O meet the need of the power systems of the T present days, each component of a gas insulated sys- tems GIS should be as simple as possible for reliability and low cost of construction, which reduces the capital cost requirement considerably. Support insulators or spac- ers are one of the major components of GIS. One of the most important requirements of these spacers in GIS, to obtain better economy and stability of the system, is that the electric stresses in the dielectric media should be as low as practicable, within the constraints of minimum overall dimensions of the system. Hence often there is a need for optimizing the dimensions and hence the shapes of the electrode-spacer configuration that are used in GIS. Manuscript recei ® ed on 15 July 2003, in final form 6 March 2004. In modern GIS, intelligent algorithms have gained an edge over the conventional methods for design, maintenance and optimization of the system. In this paper, ANN aided genetic algorithm GA has been applied for optimizing the same to achieve optimum stress distribution on and around the two electrode-spacer arrangements consid- ered. During the past years, considerable efforts have been given on optimization of electrode-spacer configurations and several studies on electrode and insulator contour op- timization have been reported in literature. Singer and wx Grafoner 1 optimized electrode and insulator contours while Singer 2 proposed a computation method for opti- mizing electrode geometries. In both 1 ] 2, the ap- proaches are based on the application of conventional techniques. Stih 3 reported optimization of high voltage
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/08/2011 for the course ELECTRICAL 124 taught by Professor Ghjk during the Spring '11 term at Institute of Technology.

Page1 / 12

opti_electrod_ann_ga - 964 Lahiri and Chakraorti:...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online