Home > Published Issues > 2023 > Volume 12, No. 3, August 2023 >
IJSCER 2023 Vol.12(3): 63-67
doi: 10.18178/ijscer.12.3.63-67

Performance-based, AI-ML-assisted Generative EA Design with Bio-inspired Topological Optimisations of a 50m, 3D-printed Steel Bridge

Thomas Spiegelhalter
College of Architecture, Communication and the Arts, Florida International University, Miami, FL, USA
*Corresponding author: tspiege@fiu.edu

Manuscript was received February 8, 2023; revised March 22, 2023; accepted May 25, 2023.

Abstract—AI-ML-assisted Generative Design (GD) using Evolutionary Algorithms (EA) techniques and Topology Optimization (TO) has undergone massive growth over the past few years. As a result, AI and GD have essential applications in many fields, such as Industrial & Product Design, Medicine, Synthetic Biology, Infrastructure, Architecture, Engineering & Construction (AEC). This research paper discusses the performance-based workflows for AI-ML assisted, cloud computation and EA-driven Generative Design with topological optimisation to reduce weight and cost. The discussed research is a lightweight real-world hybrid, awarded 50 m robot 3d-printed bluemint®steel bridge design and off-the-shelf steel tube prefabrication in Germany, completed in June 2023. [3] The generative bridge design with finite element structural analysis (FEA) and cloud-driven deep neural network (GNN) scenarios will demonstrate the largest 3d-printed Wire-and-arc Additive Manufacturing (WAAM) pedestrian/bicycle bridge inspired by biology worldwide.

Keywords—artificial intelligence, evolutionary algorithm, generative design, topological optimizations, additive manufacturing

Cite: Thomas Spiegelhalter, "Performance-based, AI-ML-assisted Generative EA Design with Bio-inspired Topological Optimisations of a 50m, 3D-printed Steel Bridge," International Journal of Structural and Civil Engineering Research, Vol. 12, No. 3, pp. 63-67, August 2023. doi: 10.18178/ijscer.12.3.63-67

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.