Xiaofeng Liu^*, Yubin Bao, Fangling Leng

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3503-3517, 2025, DOI:10.32604/cmc.2025.064544 - 03 July 2025

Abstract The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search (NAS) algorithms designed to optimize neural network structures. However, these algorithms often face significant computational costs due to the time-consuming process of training neural networks and evaluating their performance. Traditional NAS approaches, which rely on exhaustive evaluations and large training datasets, are inefficient for solving complex image classification tasks within limited time frames. To address these challenges, this paper proposes a novel NAS algorithm that integrates a hierarchical evaluation strategy based on Surrogate models, specifically using supernet to… More >

João Pedro Ceniz, Rodrigo de Sá Martins, Marco Antonio Luersen^*, Tiago Cousseau

CMES-Computer Modeling in Engineering & Sciences, Vol.133, No.3, pp. 601-618, 2022, DOI:10.32604/cmes.2022.021011 - 03 August 2022

Abstract Ore conveyor belt rollers operate in harsh environments, making them prone to premature failure. Their service lives are highly dependent on the stress field and bearing misalignment angle, for which limit values are defined in a standard. In this work, an optimization methodology using metamodels based on radial basis functions is implemented to reduce the mass of two models of rollers. From a structural point of view, one of the rollers is made completely of metal, while the other also has some components made of polymeric material. The objective of this study is to develop… More >

Fangyi Li^1,2, Zhen Luo³, Jianhua Rong¹, Lin Hu¹

CMES-Computer Modeling in Engineering & Sciences, Vol.95, No.6, pp. 453-482, 2013, DOI:10.3970/cmes.2013.095.453

Abstract This paper aims to propose a non-probabilistic reliability-based multiobjective optimization method for structures with uncertain-but-bounded parameters. A combination of the interval and ellipsoid convex models is used to account for the different groups of uncertain parameters, in which the interval model accounts for uncorrelated parameters, while the ellipsoid model is applied to correlated parameters. The design is then formulated as a nested double-loop optimization problem. A multi-objective genetic algorithm is used in the out loop optimization to optimize the design vector for evaluating the objectives, and the Sequential Quadratic Programming (SQP) algorithm is applied in… More >