Rea Press null Rea Press3042-13573042-1357 Rea Press https://doi.org/10.48313/mtei.v1i3.65 Research Article Large-scale public aquarium, Structural optimization, Finite element method, Artificial neural network, Genetic algorithm, Hydrostatic loading, Acrylic structure Multi-Objective Structural Optimization of a Large-Scale Spherical Public Aquarium Using FEM, ANN, and Genetic AlgorithmsMulti-Objective Structural Optimization of a Large-Scale Spherical Public Aquarium Using FEM, ANN, and Genetic Algorithms Masoomi Hassan Department of Civil Engineering, University of California, Los Angeles (UCLA), USA. Nejati Faezeh Research Institute of Earthquake Engineering, Faculty of Civil Engineering, Isfahan, Iran. 09 2024 26 09 2024 1 3 © 2024 Rea Press 2024

This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

 Multi-Objective Structural Optimization of a Large-Scale Spherical Public Aquarium Using FEM, ANN, and Genetic Algorithms

This paper discusses the design process and multi-objective optimization of a large public spherical aquarium with a cuboid inner viewing tunnel. The structural geometry of the space frame, composed of steel combined with acrylic panels supported by reinforced concrete, is modeled using the Finite Element Method (FEM). The hydrostatic pressure acting on the surface, the load due to visitors, and the dynamic force due to impacts from aquatic animals are accounted for in the structural analysis. To minimize computational cost, an Artificial Neural Network (ANN) surrogate model is created using Finite Element Analysis (FEA) output. After creating an ANN model, the problem is solved using a multi-objective Genetic Algorithm (GA), and the safety factor is maximized by minimizing structural weight. This research shows that the proposed hybrid FEM-ANN-GA model effectively determines the optimal acrylic panel thickness that meets the safety criteria. The optimal solution achieved has a total structural weight of approximately 9569 tons.

null