Open Access

ARTICLE

Quantifying Uncertainty in Dielectric Solids’ Mechanical Properties Using Isogeometric Analysis and Conditional Generative Adversarial Networks

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

1 College of Civil Engineering & Architecture, Dalian University, Dalian, 116622, China
2 Research Center for Geotechnical and Structural Engineering Technology of Liaoning Province, Dalian University, Dalian, 116622, China

* Corresponding Author: Xiaodong Zhao. Email:

Computer Modeling in Engineering & Sciences 2024, 140(3), 2587-2611. https://doi.org/10.32604/cmes.2024.052203

Received 26 March 2024; Accepted 20 May 2024; Issue published 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, specifically adapting to targeted design requirements and constraints. Then, the CGAN-IGA is adopted to calculate the electric potential of optimum models with different parameters to accelerate uncertainty quantification processes. The accuracy and feasibility of this method are verified through numerical experiments presented herein.

---

Keywords

---