Modelling the Correlation Function of Wall Pressure Fluctuations Under Turbulent Boundary Layers with Machine Learning Methods
Marika DI MEO, Alessandro CASABURO, Arthur Diniz FLOR TORQUATO FERNANDES, Francesco FRANCO
Abstract. The structural vibrations and aerodynamic noise induced by the wall-pressure fluctuations due to a turbulent boundary layer have received great attention in recent years. Nowadays, the prediction of the vibroacoustic response of structures subjected to this type of source relies on the use of statistical quantities and semi-empirical spectral models in the frequency-wavenumber domain. This work explores machine learning techniques to reconstruct the complex coherence function from the structural response. The behaviour of a rectangular plate under stochastic loading is simulated using the Chase model for four flow conditions, and the resulting response at grid points is used to train an encoder-only transformer. The results show that the algorithm satisfactorily reproduces the Chase-like coherence trends at all the flow conditions.
Keywords
Turbulent Boundary Layer, Wall-Pressure Fluctuations, Chase Model, Deep Learning, Transformers
Published online 7/20/2026, 6 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Marika DI MEO, Alessandro CASABURO, Arthur Diniz FLOR TORQUATO FERNANDES, Francesco FRANCO, Modelling the Correlation Function of Wall Pressure Fluctuations Under Turbulent Boundary Layers with Machine Learning Methods, Materials Research Proceedings, Vol. 69, pp 60-65, 2026
DOI: https://doi.org/10.21741/9781644904251-11
The article was published as article 11 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] A. Casaburo, G. Petrone, E. Ciappi, F. Franco, S. De Rosa, Data-Driven Symbolic Regression for the Modelling of Correlation Functions of Wall Pressure Fluctuations Under Turbulent Boundary Layers, in C. Doolan, D. Moreau, A. Wills (Eds.), Flinovia – Flow Induced Noise and Vibration Issues and Aspects – IV. FLINOVIA 2023, Springer Cham, 2025, pp. 277-304, https://doi.org/10.1007/978-3-031-73935-4 14
[2] D. M. Chase, Modeling the wavevector-frequency spectrum of turbulent boundary layer wall pressure, Journal of Sound and Vibration 70(1), 29-67 (1980), https://doi.org/10.1016/0022-460X(80)90553-2
[3] J. Dominique, J. Van den Berghe, C. Schram, M. A. Mendez, Artificial neural networks modeling of wall pressure spectra beneath turbulent boundary layers, Physics of Fluids, 34(3), 035119 (2022), https://doi.org/10.1063/5.0083241
[4] S. Raschka, Y. Liu, V. Mirjalili, Machine Learning with PyTorch and Scikit-Learn, 2022, Packt, Birmingham.
[5] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin, Attention Is All You Need, in I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, R. Garnett (Eds.) 31st Conference on Neural Information Processing Systems (NIPS). Advances in Neural Information Processing Systems. Vol. 30, 2023, Curran Associates, Inc., 1706.03762.
[6] E. Ciappi, F. Magionesi, S. De Rosa, F. Franco, Hydrodynamic and hydroelastic analyses of a plate excited by the turbulent boundary layer, Journal of Fluids and Structures, 25(2), 321-342 (2009), https://doi.org/10.1016/j.jfluidstructs.2008.04.006
[7] I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, in International Conference on Learning Representations (ICLR), 2019, https://doi.org/10.48550/arXiv.1711.05101
