Research on noise prediction methods for sound barriers based on the integration of conditional generative adversarial networks and numerical methods DOI Creative Commons
Qian Hu, Zhiwei Cui, Hongxue Liu

et al.

Frontiers in Physics, Journal Year: 2025, Volume and Issue: 13

Published: March 31, 2025

This study proposes a novel approach utilizing Conditional Generative Adversarial Networks (CGANs) to accelerate wideband acoustic state analysis, addressing the computational challenges in traditional Boundary Element Method (BEM) approaches. Traditional BEM-based analysis requires repeated computation of frequency-dependent system matrices across multiple frequencies, leading significant costs. The asymmetry and full-rank nature BEM coefficient further increase demands, particularly large-scale problems. To overcome these challenges, this paper introduces CGAN-based modeling framework that significantly reduces time while maintaining high predictive accuracy. demonstrates exceptional adaptability when handling datasets with varying characteristics, effectively capturing underlying patterns within data. Numerical experiments validate effectiveness proposed method, highlighting its advantages both accuracy efficiency. provides promising alternative for efficient reducing ensuring

Language: Английский

Research on noise prediction methods for sound barriers based on the integration of conditional generative adversarial networks and numerical methods DOI Creative Commons
Qian Hu, Zhiwei Cui, Hongxue Liu

et al.

Frontiers in Physics, Journal Year: 2025, Volume and Issue: 13

Published: March 31, 2025

This study proposes a novel approach utilizing Conditional Generative Adversarial Networks (CGANs) to accelerate wideband acoustic state analysis, addressing the computational challenges in traditional Boundary Element Method (BEM) approaches. Traditional BEM-based analysis requires repeated computation of frequency-dependent system matrices across multiple frequencies, leading significant costs. The asymmetry and full-rank nature BEM coefficient further increase demands, particularly large-scale problems. To overcome these challenges, this paper introduces CGAN-based modeling framework that significantly reduces time while maintaining high predictive accuracy. demonstrates exceptional adaptability when handling datasets with varying characteristics, effectively capturing underlying patterns within data. Numerical experiments validate effectiveness proposed method, highlighting its advantages both accuracy efficiency. provides promising alternative for efficient reducing ensuring

Language: Английский

Citations

0