Open Access

ARTICLE

CGAN Accelerated Subdivision Surface BEM for Acoustic Scattering

Ziyu Cui, Zijun Wei, Xiaohui Yuan, Pei Li^*

Centre for Industrial Mechanics, Institute of Mechanical and Electrical Engineering, University of Southern Denmark, Sønderborg, 6400, Denmark

* Corresponding Author: Pei Li. Email:

(This article belongs to the Special Issue: Integration of Physical Simulation and Machine Learning in Digital Twin and Virtual Reality)

Computer Modeling in Engineering & Sciences 2025, 144(1), 1045-1070. https://doi.org/10.32604/cmes.2025.066659

Received 14 April 2025; Accepted 08 July 2025; Issue published 31 July 2025

Abstract

At present, noise reduction has become an urgent challenge across various fields. Whether in the context of household appliances in daily life or in the enhancement of stealth performance in military equipment, noise control technologies play a critical role. This study introduces a computational framework for simulating Helmholtz equation-governed acoustic scattering using a boundary element method (BEM) integrated with Loop subdivision surfaces. By adopting the Loop subdivision scheme—a widely used computer-aided design (CAD) technique—the framework unifies geometric representation and physical field discretization, ensuring seamless compatibility with industrial CAD workflows. The core innovation lies in the novel integration of conditional generative adversarial networks (CGANs) into the subdivision surface BEM to assist and accelerate the numerical computation process. In this study, for the two cases examined, the results show that the CGAN-enhanced approach achieves substantial gains in computational efficiency without compromising accuracy. A hierarchical acceleration strategy is further proposed: the fast multipole method (FMM) first reduces baseline computational complexity, while CGAN-driven secondary acceleration and data augmentation enable real-time parameter exploration. Benchmark validations and practical engineering applications demonstrate the method’s robustness and scalability for large-scale structural-acoustic analysis.

---

Keywords

---