A 3D convolutional neural network based near-field acoustical holography method with sparse sampling rate on measuring surface

被引:13
作者
Wang, Jiaxuan [1 ]
Zhang, Zhifu [1 ]
Huang, Yizhe [1 ]
Li, Zhuang [1 ]
Huang, Qibai [1 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Mech Sci & Engn, State Key Lab Digital Mfg Equipment & Technol, Wuhan, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
Near-field acoustical holography; Low sampling rate; Wraparound error; Convolutional neural network; Stacked autoencoder; FAULT-DIAGNOSIS; ROTATING MACHINERY; RECONSTRUCTION; REGULARIZATION; HEALTH; NOISE;
D O I
10.1016/j.measurement.2021.109297
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Near-field acoustical holography (NAH) is an efficient noise diagnosis method with the deficiencies including wraparound error, which will increase when the spatial sampling rate is reduced below the minimum specified by Shannon-Nyquist theorem. Based on 3D convolutional neural network (3D-CNN) and stacked autoencoder (SAE), a method called CSA-NAH is proposed to reduce the wraparound error under sparse measuring. Subsequently, numerical calculations are carried out to illustrate the feasibility and performance of CSA-NAH. The results show that when holographic measurement point number is 64, average reconstruction error of CSA-NAH on an aluminum plate for sound pressure within 2000 Hz is 4.32%, while the latest existing methods is greater than 10%. For error in 1200 Hz similar to 2000 Hz, the error is reduced from more than 15% of the existing methods to 5.5%. Therefore, the application of the proposed CSA-NAH can cut down the measuring cost by reducing the number of microphones without wraparound error.
引用
收藏
页数:16
相关论文
共 42 条
  • [1] Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks
    Abdeljaber, Osama
    Avci, Onur
    Kiranyaz, Serkan
    Gabbouj, Moncef
    Inman, Daniel J.
    [J]. JOURNAL OF SOUND AND VIBRATION, 2017, 388 : 154 - 170
  • [2] APPLICATION OF BEM (BOUNDARY ELEMENT METHOD)-BASED ACOUSTIC HOLOGRAPHY TO RADIATION ANALYSIS OF SOUND SOURCES WITH ARBITRARILY SHAPED GEOMETRIES
    BAI, MR
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1992, 92 (01) : 533 - 549
  • [3] Reconstruction and separation in a semi-free field by using the distributed source boundary point method-based nearfield acoustic holography
    Bi, C. X.
    Chen, X. Z.
    Zhou, R.
    Chen, J.
    [J]. JOURNAL OF VIBRATION AND ACOUSTICS-TRANSACTIONS OF THE ASME, 2007, 129 (03): : 323 - 329
  • [4] Sound field reconstruction using compressed modal equivalent point source method
    Bi, Chuan-Xing
    Liu, Yuan
    Xu, Liang
    Zhang, Yong-Bin
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2017, 141 (01) : 73 - 79
  • [5] Robust uncertainty principles:: Exact signal reconstruction from highly incomplete frequency information
    Candès, EJ
    Romberg, J
    Tao, T
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (02) : 489 - 509
  • [6] Near-optimal signal recovery from random projections: Universal encoding strategies?
    Candes, Emmanuel J.
    Tao, Terence
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (12) : 5406 - 5425
  • [7] Near-field acoustic holography using sparse regularization and compressive sampling principles
    Chardon, Gilles
    Daudet, Laurent
    Peillot, Antoine
    Ollivier, Francois
    Bertin, Nancy
    Gribonval, Remi
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2012, 132 (03) : 1521 - 1534
  • [8] Source visualization by using statistically optimized near-field acoustical holography in cylindrical coordinates
    Cho, YT
    Bolton, JS
    Hald, J
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2005, 118 (04) : 2355 - 2364
  • [9] Compressed sensing
    Donoho, DL
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (04) : 1289 - 1306
  • [10] A sparse equivalent source method for near-field acoustic holography
    Fernandez-Grande, Efren
    Xenaki, Angeliki
    Gerstoft, Peter
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2017, 141 (01) : 532 - 542