Data-Driven Identification of Gearbox Housing Structures Using Acoustic Radiation Spectra

  • Authors

    • Krisztián Horváth Department of Whole Vehicle Engineering, Széchenyi István University, Hungary
    https://doi.org/10.14419/mnbhp030

    Received date: July 29, 2025

    Accepted date: August 15, 2025

    Published date: August 24, 2025

  • Gearbox Housing, Acoustic Radiation, Structural Design Classification, Machine Learning, Acoustic Spectra, PCA, K-means, NVH

  • Abstract

    The structural design of gearbox housing, such as ribbing and wall thickness, has a significant impact on its noise radiation characteristics, especially in electric vehicle applications where tonal noise is more perceptible. This study presents a novel methodology that uses machine learning and spectral analysis to distinguish between gearbox housing types based solely on their acoustic radiation data. Frequency-domain sound pressure spectra, simulated for multiple design variants, were interpolated and analyzed using Principal Component Analysis (PCA) and K-means clustering. The results reveal that construction types (e.g., fully ribbed, partially ribbed, or without ribs) exhibit distinct acoustic profiles. Furthermore, a Random Forest classifier achieved 88.9% accuracy in predicting structural configuration from the spectra alone. These findings demonstrate that structural design features can be inferred directly from acoustic data, offering a lightweight and geometry-free alternative to traditional NVH simulation workflows. The approach can be integrated as a lightweight plug-in in existing NVH workflows. It ingests acoustic spectra and returns a structural-stiffness label with uncertainty, supporting early-stage screening and late-phase regression checks.

  • References

    1. Abeßer, J. (2020). A review of deep learning based methods for acoustic scene classification. Applied Sciences, 10(6). 2020. https://doi.org/10.3390/app10062020
    2. Bianco, M. J.. Gerstoft, P.. Traer, J.. Ozanich, E.. Roch, M. A.. Gannot, S.. & Deledalle, C.-A. (2019). Machine learning in acoustics: Theory and applications. The Journal of the Acoustical Society of America, 146(5). 3590–3628. https://doi.org/10.1121/1.5133944
    3. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5 – 32. https://doi.org/10.1023/A:1010933404324
    4. Farshi Ghodsi, K., Petersen, M., Colangeli, C., & Mutschler, P. (2024). Effect of lightweight design on the NVH behavior of an electric vehicle gearbox housing [Dataset]. Karlsruhe Institute of Technology (KIT) RADAR. https://doi.org/10.35097/svJLbovVnTFAbJQV
    5. Horváth, K., & Zelei, A. (2024). Simulating noise, vibration, and harshness advances in electric vehicle powertrains: Strategies and challenges. World Electric Vehicle Journal, 15(8), 367. https://doi.org/10.3390/wevj15080367
    6. Jiang, H., Wu, Y., & Zhang, Y. (2022). Deep learning-based NVH performance prediction of automotive components using sound spectra. Me-chanical Systems and Signal Processing, 162, 108057. https://doi.org/10.1016/j.ymssp.2021.108057
    7. Jolliffe, I. T. (2016). Principal component analysis (2nd ed.). Springer. https://doi.org/10.1007/978-1-4757-1904-8
    8. Li, H., Hu, Q., & Wang, D. (2021). Data-driven modeling of radiated noise from gearboxes based on vibration–acoustic coupling. Applied Acous-tics, 182, 108260. https://doi.org/10.1016/j.apacoust.2021.108260
    9. Li, Y., Wang, J., & Zhao, H. (2023). Machine-learning approaches for NVH prediction in electric drivetrains. Applied Acoustics, 205, 109407. https://doi.org/10.1016/j.apacoust.2023.109407
    10. MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In L. M. Le Cam & J. Neyman (Eds.), Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability (Vol. 1, pp. 281–297). University of California Press. (No DOI)
    11. Ma, L., Xu, X., & Zhang, Q. (2023). Surrogate modeling for gearbox NVH optimization using machine-learning techniques. Engineering Applica-tions of Artificial Intelligence, 121, 105856. https://doi.org/10.1016/j.engappai.2023.105856
    12. Rajagopal, K., & Harsha, S. P. (2021). Vibro-acoustic analysis of a gearbox casing using coupled FEM–BEM and experimental validation. Journal of Vibration and Control, 27(13–14), 1601 – 1616. https://doi.org/10.1177/1077546320948694
    13. Randall, R. B.. & Antoni, J. (2011). Rolling element bearing diagnostics—A tutorial. Mechanical Systems and Signal Processing, 25(2). 485–520. https://doi.org/10.1016/j.ymssp.2010.07.017
    14. Zhao, L., Wang, C., & He, X. (2022). Digital twin-driven optimization of acoustic performance for lightweight structures. Structural and Multidis-ciplinary Optimization, 66, 94. https://doi.org/10.1007/s00158-022-03389-8.

  • Downloads

  • How to Cite

    Horváth, K. . (2025). Data-Driven Identification of Gearbox Housing Structures Using Acoustic Radiation Spectra. International Journal of Basic and Applied Sciences, 14(4), 619-623. https://doi.org/10.14419/mnbhp030