Author: Manoj Bhattacharya
Abstract: In structural engineering, optimizing designs under multiple objectives, such as cost, performance, and safety, is essential to developing efficient structures. Multi-objective optimization (MOO) is a critical tool used to determine the best trade-off solutions between conflicting objectives. However, these problems are complex due to the non-linearity and high dimensionality involved. Statistical optimization techniques offer valuable approaches to handle uncertainties, improve the robustness of solutions, and efficiently explore solution spaces. This paper discusses various methods of statistical optimization applied to multi-objective problems in structural engineering. The study aims to provide a comprehensive review of different optimization techniques, including evolutionary algorithms, surrogate-based models, and hybrid methods, in the context of structural design. By examining several case studies, the paper demonstrates how statistical methods can enhance the quality and efficiency of solutions in structural engineering applications.
Keywords: Statistical optimization, multi-objective optimization, structural engineering, evolutionary algorithms, surrogate models, robust optimization, case study.
Full Issue
| View or download the full issue | PDF 101-109 |