Qingrong Zeng, Xiaochen Liu, Xuefeng Zhu^*, Xiangkui Zhang, Ping Hu

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 2065-2085, 2024, DOI:10.32604/cmes.2024.052620 - 31 October 2024

Abstract Traditional topology optimization methods often suffer from the “dimension curse” problem, wherein the computation time increases exponentially with the degrees of freedom in the background grid. Overcoming this challenge, we introduce a real-time topology optimization approach leveraging Conditional Generative Adversarial Networks with Gradient Penalty (CGAN-GP). This innovative method allows for nearly instantaneous prediction of optimized structures. Given a specific boundary condition, the network can produce a unique optimized structure in a one-to-one manner. The process begins by establishing a dataset using simulation data generated through the Solid Isotropic Material with Penalization (SIMP) method. Subsequently, we More >

Shuai Li¹, Xiaodong Zhao^1,2,*, Jinghu Zhou¹, Xiyue Wang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.3, pp. 2587-2611, 2024, DOI:10.32604/cmes.2024.052203 - 08 July 2024

Abstract Accurate quantification of the uncertainty in the mechanical characteristics of dielectric solids is crucial for advancing their application in high-precision technological domains, necessitating the development of robust computational methods. This paper introduces a Conditional Generation Adversarial Network Isogeometric Analysis (CGAN-IGA) to assess the uncertainty of dielectric solids’ mechanical characteristics. IGA is utilized for the precise computation of electric potentials in dielectric, piezoelectric, and flexoelectric materials, leveraging its advantage of integrating seamlessly with Computer-Aided Design (CAD) models to maintain exact geometrical fidelity. The CGAN method is highly efficient in generating models for piezoelectric and flexoelectric materials, More >