GENETIC ALGORITHM FOR FATIGUE CRACK DETECTION IN TIMOSHENKO BEAM Marek Krawczuk 1 , Magdalena Palacz 2 , Wies aw Ostachowicz 3 1 Gda sk University of Technology, Faculty of Electrical and Control Engineering, Narutowicza 11/12, 80-952 Gda sk, Poland and Institute of Fluid Flow Machinery Polish Academy of Sciences, Fiszera 14, 80-952 Gda sk, Poland, e-mail:mk@imp.gda.pl, 2,3 Institute of Fluid Flow Machinery Polish Academy of Sciences, Fiszera 14, 80-952 Gda sk, Poland, e-mail: 2 mpal@imp.gda.pl, 3 wieslaw@imp.gda.pl Abstract: Presented paper deals with a method of detecting fatigue cracks in their early state of growth. The method uses optimisation tool consisting of genetic algorithm and gradient method. The applied fitness function is based on the changes in propagating waves. Keywords: genetic algorithm, crack detection, spectral element method, Timoshenko beam 1. INTRODUCTION In order to improve the safety, reliability and operational life, it is urgent to monitor the integrity of structural systems. Techniques of non-destructive damage detection in mechanical engineering structures are essential [1], [2], [3]. Previous approaches to non-destructive evaluation of structures to assess their integrity typically involved some form of human interaction. Recent advances in smart materials and structures technology has resulted in a renewed interest in developing advanced self-diagnostic capability for assessing the state of structure without any human interaction. The goal is to reduce human interaction while at the same time monitor the integrity of the structure. With this goal in mind, many researchers have made significant 197 T. Burczy ski and A. Osyczka (eds), IUTAM Symposium on Evolutionary Methods in Mechanics, 197–206. © 2004 Kluwer Academic Publishers. Printed in the Netherlands.