Computational Technology Resources - CCC

P. Grubits, M. Movahedi Rad, "Geometrically Nonlinear Shape Optimization of Elasto-Plastic Trusses Using a Neural Network-Assisted Genetic Algorithm", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 2.4, 2025, doi:10.4203/ccc.11.2.4

Keywords: structural optimization, neural network, genetic algorithm, elasto-plastic design, large deformations, trusses.

Abstract

This paper presents a novel optimization framework for trusses that incorporates elasto-plastic material behavior and accounts for geometric nonlinearity to determine the optimal structural shape, thereby minimizing plastic deformations and material usage to ensure a safe and cost-effective design. To achieve this objective and to guarantee reliable structural behavior, Geometrical and Material Nonlinear Analysis (GMNA) was performed using the Finite Element Method (FEM), and the complementary strain energy was calculated to evaluate the structure’s plastic performance. Due to the high computational demand of GMNA, a Neural Network-Assisted Genetic Algorithm (NNAGA) was applied, which learns intelligently from the data generated during the iterative design process and significantly accelerates the convergence of the optimization. The proposed methodology was validated through a benchmark numerical example involving a 33-bar truss. The obtained results demonstrated the efficiency of the developed framework in minimizing plastic deformations while simultaneously reducing material usage, outperforming a conventional genetic algorithm (GA) in terms of effectiveness.

download the full-text of this paper (PDF, 13 pages, 692 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 11 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING Edited by: P. Iványi, J. Kruis and B.H.V. Topping Paper 2.4 Geometrically Nonlinear Shape Optimization of Elasto-Plastic Trusses Using a Neural Network-Assisted Genetic Algorithm P. Grubits and M. Movahedi Rad Department of Structural and Geotechnical Engineering, Széchenyi István University, Győr, Hungary doi:10.4203/ccc.11.2.4 Full Bibliographic Reference for this paper P. Grubits, M. Movahedi Rad, "Geometrically Nonlinear Shape Optimization of Elasto-Plastic Trusses Using a Neural Network-Assisted Genetic Algorithm", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 2.4, 2025, doi:10.4203/ccc.11.2.4 Keywords: structural optimization, neural network, genetic algorithm, elasto-plastic design, large deformations, trusses. Abstract This paper presents a novel optimization framework for trusses that incorporates elasto-plastic material behavior and accounts for geometric nonlinearity to determine the optimal structural shape, thereby minimizing plastic deformations and material usage to ensure a safe and cost-effective design. To achieve this objective and to guarantee reliable structural behavior, Geometrical and Material Nonlinear Analysis (GMNA) was performed using the Finite Element Method (FEM), and the complementary strain energy was calculated to evaluate the structure’s plastic performance. Due to the high computational demand of GMNA, a Neural Network-Assisted Genetic Algorithm (NNAGA) was applied, which learns intelligently from the data generated during the iterative design process and significantly accelerates the convergence of the optimization. The proposed methodology was validated through a benchmark numerical example involving a 33-bar truss. The obtained results demonstrated the efficiency of the developed framework in minimizing plastic deformations while simultaneously reducing material usage, outperforming a conventional genetic algorithm (GA) in terms of effectiveness. download the full-text of this paper (PDF, 13 pages, 692 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions