Computational Technology Resources - CCP

Keywords: differential evolution, particle swarm optimization, genetic algorithms, identification, Bouc-Wen.

Summary

In this paper, several evolutionary algorithms (EAs) are employed for the identification of an unknown hysteretic system which represents a full-scale bolted-welded steel connection. The identification is based on actual experimental data. The model structure is assumed known; in particular, the Bouc-Wen model [1,2] is used which is assumed to be able to capture all the major system characteristics.

The algorithms implemented include the standard genetic algorithm (SGA) [3]; the micro-GA (µGA) [4]; a hybrid method proposed by Charalampakis and Koumousis [5]; two variants of particle swarm optimization (PSO) [6], namely simple PSO and enhanced PSO; and, finally, three variants of differential evolution (DE) [7]. In particular, the first DE variant (DE1) is the classic DE; the second variant (DE2) utilizes the currently best vector as base for the evolution and, thus, is even more greedy than DE1; and finally the third variant (DE3), proposed herein, is a mix of DE1 and DE2.

The results indicate that DE is the best algorithm for the specific problem. In particular, the DE3 combines exceptional exploration and exploitation capabilities. On the other hand, the DE1 exhibited impressive robustness and produced excellent results after a small number of function evaluations. The enhanced PSO algorithm also performs satisfactorily. The hybrid method is better suited for more difficult problems, as its bounding method, which gradually diminishes the size of the Design Space, is hardly even used in this problem. The worst performing algorithm for this problem is µGA.

References

1: R. Bouc, "Forced vibration of mechanical systems with hysteresis", in "Proceedings of the Fourth Conference on Non-linear oscillations", Prague, Czechoslovakia, 1967.
2: Y.K. Wen, "Method for Random Vibration of Hysteretic Systems", Journal of Engineering Mechanics Division, ASCE, 102(EM2), 249-263, 1976.
3: D.L. Carroll, "FORTRAN Genetic Algorithm (GA) Driver", 1999. http://www.cuaerospace.com/carroll/ga.html
4: D.E. Goldberg, "Sizing populations for serial and parallel genetic algorithms", In D.J. Schaffer, (Editor), "Proceedings of the Third International Conference on Genetic Algorithms (ICGA 89)", George Mason University, United States, Morgan Kaufmann Publishers Inc., 70-79, 1989.
5: A.E. Charalampakis, V.K. Koumousis, "Identification of Bouc-Wen hysteretic systems by a hybrid evolutionary algorithm", Journal of Sound and Vibration, 314, 571-585, 2008. doi:10.1016/j.jsv.2008.01.018
6: A.E. Charalampakis, C.K. Dimou, "Identification of Bouc-Wen hysteretic systems using particle swarm optimization", Computers and Structures, 88, 1197-1205, 2010. doi:10.1016/j.compstruc.2010.06.009
7: R. Storn, K. Price, "Differential Evolution - A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces", Journal of Global Optimization, 11, 341-359, 1997.

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £70 +P&P)

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Proceedings ISSN 1759-3433 CCP: 97 PROCEEDINGS OF THE SECOND INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNOLOGY IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING Edited by: Y. Tsompanakis, B.H.V. Topping Paper 48 A Comparison of Differential Evolution, Particle Swarm Optimization and Genetic Algorithms for the Identification of Bouc-Wen Hysteretic Systems A.E. Charalampakis and C.K. Dimou National Technical University of Athens, Greece doi:10.4203/ccp.97.48 purchase the full-text of this paper Full Bibliographic Reference for this paper A.E. Charalampakis, C.K. Dimou, "A Comparison of Differential Evolution, Particle Swarm Optimization and Genetic Algorithms for the Identification of Bouc-Wen Hysteretic Systems", in Y. Tsompanakis, B.H.V. Topping, (Editors), "Proceedings of the Second International Conference on Soft Computing Technology in Civil, Structural and Environmental Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 48, 2011. doi:10.4203/ccp.97.48 Keywords: differential evolution, particle swarm optimization, genetic algorithms, identification, Bouc-Wen. Summary In this paper, several evolutionary algorithms (EAs) are employed for the identification of an unknown hysteretic system which represents a full-scale bolted-welded steel connection. The identification is based on actual experimental data. The model structure is assumed known; in particular, the Bouc-Wen model [1,2] is used which is assumed to be able to capture all the major system characteristics. The algorithms implemented include the standard genetic algorithm (SGA) [3]; the micro-GA (µGA) [4]; a hybrid method proposed by Charalampakis and Koumousis [5]; two variants of particle swarm optimization (PSO) [6], namely simple PSO and enhanced PSO; and, finally, three variants of differential evolution (DE) [7]. In particular, the first DE variant (DE1) is the classic DE; the second variant (DE2) utilizes the currently best vector as base for the evolution and, thus, is even more greedy than DE1; and finally the third variant (DE3), proposed herein, is a mix of DE1 and DE2. The results indicate that DE is the best algorithm for the specific problem. In particular, the DE3 combines exceptional exploration and exploitation capabilities. On the other hand, the DE1 exhibited impressive robustness and produced excellent results after a small number of function evaluations. The enhanced PSO algorithm also performs satisfactorily. The hybrid method is better suited for more difficult problems, as its bounding method, which gradually diminishes the size of the Design Space, is hardly even used in this problem. The worst performing algorithm for this problem is µGA. References 1 R. Bouc, "Forced vibration of mechanical systems with hysteresis", in "Proceedings of the Fourth Conference on Non-linear oscillations", Prague, Czechoslovakia, 1967. 2 Y.K. Wen, "Method for Random Vibration of Hysteretic Systems", Journal of Engineering Mechanics Division, ASCE, 102(EM2), 249-263, 1976. 3 D.L. Carroll, "FORTRAN Genetic Algorithm (GA) Driver", 1999. http://www.cuaerospace.com/carroll/ga.html 4 D.E. Goldberg, "Sizing populations for serial and parallel genetic algorithms", In D.J. Schaffer, (Editor), "Proceedings of the Third International Conference on Genetic Algorithms (ICGA 89)", George Mason University, United States, Morgan Kaufmann Publishers Inc., 70-79, 1989. 5 A.E. Charalampakis, V.K. Koumousis, "Identification of Bouc-Wen hysteretic systems by a hybrid evolutionary algorithm", Journal of Sound and Vibration, 314, 571-585, 2008. doi:10.1016/j.jsv.2008.01.018 6 A.E. Charalampakis, C.K. Dimou, "Identification of Bouc-Wen hysteretic systems using particle swarm optimization", Computers and Structures, 88, 1197-1205, 2010. doi:10.1016/j.compstruc.2010.06.009 7 R. Storn, K. Price, "Differential Evolution - A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces", Journal of Global Optimization, 11, 341-359, 1997. purchase the full-text of this paper (price £20) go to the previous paper go to the next paper return to the table of contents return to the book description purchase this book (price £70 +P&P)
Back to top	©Civil-Comp Limited 2023 - terms & conditions