Abstract
We present an operational transfer path analysis (OTPA) formulation based on deep learning to solve structural problems. Deep neural networks (DNNs) with fully connected or convolutional layers model the transfer function from interfacial joints to the responses of points of interest in terms of forces, thereby eliminating the cross-coupling effects of conventional OTPA methods. Using an operational dataset, phase and cross-spectrum augmentation procedures were applied to train DNNs by reference to the required path contributions. A test structure with two plates and three transfer paths was used to experimentally validate the OTPA framework. The operational responses were quantified and used to train DNNs that engage in OTPA; we evaluated various hyperparameters. The path contributions were obtained from DNNs that had been trained to follow the required OTPA procedure and compared to those of classical transfer path analysis (TPA). Experimental identification of the path contributions revealed that the new OTPA method was as accurate as the classical TPA method and had good overall task efficiency.
Similar content being viewed by others
Abbreviations
- C ij :
-
Contribution through the j-th transfer path
- f :
-
Force vector
- H :
-
Receptance matrix
- \({\boldsymbol{\tilde H}}\) :
-
Modified transfer function matrix
- k :
-
Joint stiffness
- M :
-
Number of ROIs
- N :
-
Number of paths
- ϰ :
-
Training dataset
- ϰ 0 :
-
Measured dataset
- ϰ 1 :
-
Phase-augmented dataset
- ϰ 2 :
-
Input cross-spectra-augmented dataset
- ϰ 3 :
-
Output cross-spectra-augmented dataset
- R :
-
Response of interest (ROI)
- T :
-
Transformation function
- U :
-
Input layer vector or matrix
- u :
-
Displacement vector
- Δu I :
-
Relative displacement vector at interface
- γ :
-
Output layer vector
- η :
-
Loss factor
- ω :
-
Frequency
References
D.-H. Lee and W.-S. Hwang, Parametric optimization of complex systems using a multi-domain FRF-based substructuring method, Computers and Structures, 81(22–23) (2003) 2249–2257.
H. Van der Auweraer, P. Mas, S. Dom, A. Vecchio, K. Janssens and P. Van de Ponseele, Transfer path analysis in the critical path of vehicle refinement: the role of fast, hybrid and operational path analysis, SAE Technical Paper (2007) 2007-01-2352.
M. V. van der Seijs, D. de Klerk and D. J. Rixen, General framework for transfer path analysis: History, theory and classification of techniques, Mechanical Systems and Signal Processing, 68 (2016) 217–244.
D.-H. Lee, W.-S. Hwang and M.-E. Kim, Booming noise analysis in a passenger car using a hybrid-integrated approach, SAE Transactions (2000) 1069–1075.
K. Wyckaert and H. Van der Auweraer, Operational analysis, transfer path analysis, modal analysis: tools to understand road noise problems in cars, SAE Technical Paper (1995) 951151.
A. Oktav, G. Anlaş and Ç. Yılmaz, Assessment of vehicle noise variability through structural transfer path analysis, International Journal of Vehicle Design, 71(1–4) (2016) 300–320.
M. H. Janssens, J. W. Verheij and D. Thompson, The use of an equivalent forces method for the experimental quantification of structural sound transmission in ships, Journal of Sound and Vibration, 226(2) (1999) 305–328.
D. De Klerk and A. Ossipov, Operational transfer path analysis: Theory, guidelines and tire noise application, Mechanical Systems and Signal Processing, 24(7) (2010) 1950–1962.
K. Noumura and J. Yoshida, Method of transfer path analysis for vehicle interior sound with no excitation experiment, FISITA2006 Proceedings, Yokohama, Japan (2006) 1–10.
J. Putner, H. Fastl, M. Lohrmann, A. Kaltenhauser and F. Ullrich, Operational transfer path analysis predicting contributions to the vehicle interior noise for different excitations from the same sound source, The Proceedings of 41st International Congress and Exposition on Noise Control Engineering, INTER-NOISE, New York City, USA (2012).
K. Janssens, P. Gajdatsy, L. Gielen, P. Mas, L. Britte, W. Desmet and H. Van der Auweraer, OPAX: a new transfer path analysis method based on parametric load models, Mechanical Systems and Signal Processing, 25(4) (2011) 1321–1338.
P. Gajdatsy, K. Janssens, L. Gielen, P. Mas and H. Van Der Auweraer, Critical assessment of operational path analysis: mathematical problems of transmissibility estimation, Journal of the Acoustical Society of America, 123(5) (2008) 3869.
P. Gajdatsy, K. Janssens, L. Gielen, P. Mas and H. Van der Auweraer, Critical assessment of operational path analysis: effect of neglected paths, The Proceedings of The Proceedings of the 15th International Congress on Sound and Vibration, Daejean, Korea (2008) 1090–1097.
P. Gajdatsy, K. Janssens, L. Gielen, P. Mas and H. Van Der Auweraer, Critical assessment of operational path analysis: effect of coupling between path inputs, Journal of the Acoustical Society of America, 123(5) (2008) 3876–3876.
D. Tcherniak, Application of Transmissibility Matrix method to structure borne path contribution analysis, The Proceedings of Proceedings of NAG/DAGA Conference, Rotterdam, Holland (2009).
I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press (2016).
B. Z. Cunha, C. Droz, A.-M. Zine, S. Foulard and M. Ichchou, A review of machine learning methods applied to structural dynamics and vibroacoustic, Mechanical Systems and Signal Processing, 200 (2023) 110535.
B. Rezaeianjouybari and Y. Shang, Deep learning for prognostics and health management: state of the art, challenges, and opportunities, Measurement, 163 (2020) 107929.
K. Saigusa, F. Chauvicourt and H. Van der Auweraer, Application of neural networks for transfer path analysis, The Proceedings of The International Conference on Structural Engineering Dynamics (ICEDyn 2019), Viana do Castelo, Portugal (2019).
D. Lee and J. W. Lee, Operational transfer path analysis based on deep neural network: numerical validation, Journal of Mechanical Science and Technology, 34(3) (2020) 1023–1033.
D. E. Tsokaktsidis, C. Nau, M. Maeder and S. Marburg, Using rectified linear unit and swish based artificial neural networks to describe noise transfer in a full vehicle context, The Journal of the Acoustical Society of America, 150(3) (2021) 2088–2105.
U. Park and Y. J. Kang, Contribution analysis of road noise with transfer path analysis based on neural network, The Proceedings of INTER-NOISE and NOISE-CON Congress and Conference Proceedings (2023) 2373–2378.
A. N. Thite and D. J. Thompson, The quantification of structure-borne transmission paths by inverse methods, part 1: improved singular value rejection methods, Journal of Sound and Vibration, 264(2) (2003) 411–431.
Y. LeCun, L. Bottou, Y. Bengio and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86(11) (1998) 2278–2324.
S. Kiranyaz, T. Ince and M. Gabbouj, Real-time patient-specific ECG classification by 1-D convolutional neural networks, IEEE Transactions on Biomedical Engineering, 63(3) (2015) 664–675.
S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj and D. J. Inman, 1D convolutional neural networks and applications: a survey, Mechanical Systems and Signal Processing, 151 (2021) 107398.
W. Cheng, Y. Chu, X. Chen, G. Zhou, D. Blamaud and J. Lu, Operational transfer path analysis with crosstalk cancellation using independent component analysis, Journal of Sound and Vibration, 473 (2020) 115224.
F. Chollet, Keras: the python deep learning library, Astrophysics Source Code Library (2018).
M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving and M. Isard, Tensorflow: a system for large-scale machine learning, The Proceedings of 12th USENIX Symposium on Operating Systems Design and Implementation, Savannah, USA (2016) 265–283.
T. Tieleman and G. Hinton, Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude, Coursera: Neural Networks for Machine Learning, 4(2) (2012) 26–31.
Acknowledgments
This work was supported by a grant from the National Research Foundation of Korea (NRF) funded by the Korean government (MEST; grant no. NRF-2022R1A2C1006938).
Author information
Authors and Affiliations
Corresponding author
Additional information
Dooho Lee received his B.S. degree from Seoul National University (Korea) in 1988, his M.S. from KAIST (Korea) in 1990, and his Ph.D. from KAIST (Korea) in 1994. He worked for Samsung Motors, Inc. (1995-1999) and is currently a Professor at Dongeui University. His research includes optimization of structural-acoustic systems, evaluation of uncertainty propagation in dynamic systems, and the sound transfer characteristics of human hearing.
Rights and permissions
About this article
Cite this article
Lee, D., Park, YY. Transfer path analysis using deep neural networks trained by measured operational responses. J Mech Sci Technol 37, 5739–5750 (2023). https://doi.org/10.1007/s12206-023-1013-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-1013-5