中国舰船研究2023，Vol.18Issue(6)：186-196,11.DOI:10.19693/j.issn.1673-3185.03127
基于三维N型卷积神经网络和频域注意力-亥姆霍兹正则化的近场声源重建方法
Near-field acoustic reconstruction method based on three-dimensional N-shaped convolution neural network and frequency focal-KH regularization
籍宇阳 1王德禹1
作者信息
- 1. 上海交通大学 海洋工程国家重点实验室,上海 200240||上海交通大学 海洋装备研究院,上海 200240
- 折叠
摘要
Abstract
[Objectives]Low sampling rates on reconstruction surfaces cause high reconstruction error in near-field acoustic holography.Therefore,a deep learning-based approach which is applicable to planar sound sources and high-precision reconstruction with low sampling rates is put forward.[Methods]A three-dimensional N-shaped convolution neural network for near-field acoustic reconstruction is established to ex-tract features in the frequency dimension in order to make up for sparse sampling in the spatial dimension.A frequency focal mechanism,namely an adaptive frequency weight focus mechanism,is put forward to improve reconstruction precision in the natural frequency and high frequency.Moreover,this paper also raises fre-quency-scaled focal loss and frequency-scaled focal Kirchhoff-Helmholtz(KH)loss,which are considered regularization.To validate the proposed methods,datasets are created with COMSOL Multiphysics and Matlab.[Results]The mean error range of 100-2 000 Hz of the algorithm proposed in this paper is only 4.96%,high-er than those of SRCNN and PV-NN.[Conclusions]The proposed method is verified as having the potential to reconstruct the accurate velocity fields of sound sources under low sampling rates.关键词
近场声源重建/声源识别/三维卷积/亥姆霍兹正则化Key words
near-field acoustic reconstruction/sound source recognition/3D convolution/Kirchhoff-Helmholtz(KH)regularization分类
通用工业技术引用本文复制引用
籍宇阳,王德禹..基于三维N型卷积神经网络和频域注意力-亥姆霍兹正则化的近场声源重建方法[J].中国舰船研究,2023,18(6):186-196,11.
