Computational Technology Resources - CCC

B. Miller, L. Ziemianski, "Multi-objective Optimisation of Dynamic Properties and Cost of a Composite Shell", in P. Iványi, J. Logo, B.H.V. Topping, (Editors), "Proceedings of the Sixth International Conference on Soft Computing, Machine Learning and Optimisation in Civil, Structural and Environmental Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 5, Paper 2.3, 2023, doi:10.4203/ccc.5.2.3

Keywords: multi-objective optimisation, surrogate models, deep neural networks, genetic algorithms, mode shapes identification.

Abstract

This paper presents multi-objective optimisation of a laminated cylinder’s dynamic behaviour and cost through stacking sequence, geometry, and appropriate materials choice. The optimized dynamic parameters are the width of a band in the frequency spectrum free of natural frequencies and the cost of applied materials. The multiobjective procedure involves mode shape identification, genetic algorithm-based optimisation, and deep neural networks-based surrogate model. The novel elements proposed are a detailed analysis of the number of initial finite element method calls necessary to train the neural network-based surrogate model, a study concerning different surrogate model schemes (one network or a network ensemble), error function applied during surrogate model training, and the application of high-fidelity (and time consuming) or low-fidelity (but very fast) finite element models.

download the full-text of this paper (PDF, 9 pages, 255 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: 5 PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON SOFT COMPUTING, MACHINE LEARNING AND OPTIMISATION IN CIVIL, STRUCTURAL AND ENVIRONMENTAL ENGINEERING Edited by: P. Iványi, J. Logo and B.H.V. Topping Paper 2.3 Multi-objective Optimisation of Dynamic Properties and Cost of a Composite Shell B. Miller and L. Ziemianski Rzeszow University of Technology, Poland doi:10.4203/ccc.5.2.3 Full Bibliographic Reference for this paper B. Miller, L. Ziemianski, "Multi-objective Optimisation of Dynamic Properties and Cost of a Composite Shell", in P. Iványi, J. Logo, B.H.V. Topping, (Editors), "Proceedings of the Sixth International Conference on Soft Computing, Machine Learning and Optimisation in Civil, Structural and Environmental Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 5, Paper 2.3, 2023, doi:10.4203/ccc.5.2.3 Keywords: multi-objective optimisation, surrogate models, deep neural networks, genetic algorithms, mode shapes identification. Abstract This paper presents multi-objective optimisation of a laminated cylinder’s dynamic behaviour and cost through stacking sequence, geometry, and appropriate materials choice. The optimized dynamic parameters are the width of a band in the frequency spectrum free of natural frequencies and the cost of applied materials. The multiobjective procedure involves mode shape identification, genetic algorithm-based optimisation, and deep neural networks-based surrogate model. The novel elements proposed are a detailed analysis of the number of initial finite element method calls necessary to train the neural network-based surrogate model, a study concerning different surrogate model schemes (one network or a network ensemble), error function applied during surrogate model training, and the application of high-fidelity (and time consuming) or low-fidelity (but very fast) finite element models. download the full-text of this paper (PDF, 9 pages, 255 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