Journal
COMPUTERS & STRUCTURES
Volume 287, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compstruc.2023.107118
Keywords
Structural optimization; Constraint handling technique; Virtual samples; Support vector machine
Ask authors/readers for more resources
In order to improve the computational efficiency of structural optimization, this study proposes a boundary identification approach (BIA) to identify the feasible region boundary of search space by treating the feasibility evaluation as a two-class classification problem. The BIA includes a virtual sampling technique (VST), an improved Latin hypercube sampling (ILHS) method, and a support vector machine (SVM) classifier. Through numerical and truss examples, it is shown that the BIA can achieve high prediction accuracy and significantly reduce the number of structural analyses required.
To improve the computational efficiency of structural optimization, this study treats the feasibility evaluation of the solutions as a two-class classification problem and proposes a boundary identification approach (BIA) to identify the feasible region boundary of search space. The BIA includes a virtual sampling technique (VST), an improved Latin hypercube sampling (ILHS) method, and a support vector machine (SVM) classifier. The VST can generate cheap samples based on a mapping strategy from actual samples without time-consuming structural analysis. To enhance the global performance of the SVM, the ILHS yields the sample set on the normalized hypersphere of the original design space. An optimization framework based on the BIA hybridized with the harmony search algorithm is presented, and two numerical and three truss examples are utilized to examine the performances of the proposed optimization framework. The prediction accuracy of the BIA reaches about 99% in two numerical examples, and 97%, 90%, and 80% in the 10-bar, 72-bar, and 600-bar truss optimization examples, respectively. The results also show that the number of structural analyses required by the proposed optimization approach is reduced by more than 80% compared to the conventional metaheuristics optimization algorithms while obtaining a similar quality of optimal designs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available