A hyper-intelligent framework for large-scale structural optimisation
File(s)
Published version
Author(s)
Jalili, Shahin
Talatahari, Siamak
Type
Journal Article
Abstract
This study introduces a new algorithmic framework, termed the hyper-intelligent (HI) framework, designed to address diverse structural optimisation problems with improved statistical consistency. In this framework, a set of meta-heuristics in the low-level heuristic (LLH) space is applied concurrently by individuals during the optimisation process. Each individual is equipped with a high-level heuristic (HLH) subspace that provides an online, feedback-driven learning mechanism. Two variants are proposed based on the learning strategy: the hyper-intelligent algorithm with a choice function (HIA-CF) and the hyper-intelligent algorithm with a multi-armed bandit (HIA-MAB). The performance of the proposed approach is evaluated using three large-scale structural design examples with static and frequency constraints. The results demonstrate that the HI framework achieves more consistent performance than conventional meta-heuristics. This highlights the advantages of intelligently and adaptively integrating multiple search strategies simultaneously for complex structural design optimisation. The study emphasises the necessity of a paradigm shift in intelligent structural design optimisation.
Date Issued
2026-01-01
Date Acceptance
2025-12-04
Citation
Structures, 2026, 83
ISSN
2352-0124
Publisher
Elsevier
Journal / Book Title
Structures
Volume
83
Copyright Statement
© 2025 The Authors. Published by Elsevier Ltd on behalf of Institution of Structural Engineers. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Publication Status
Published
Article Number
110858
Date Publish Online
2025-12-11