Abstract
The analysis of cavitation pressure for high-speed underwater moving bodies is critical for hydrodynamic performance and stability. However, traditional methods relying on physical experiments or high-fidelity CFD simulations are computationally expensive and time-consuming, often resulting in small datasets that challenge data-driven approaches. This study aimed to evaluate efficient feature extraction techniques to overcome the limitations of small-sample scenarios. This paper systematically evaluated three feature extraction methods—Principal Component Analysis (PCA), Fast Independent Component Analysis (Fast ICA), and a customized 1-dimensional Convolutional Auto-encoder (Conv1D AE)—for processing cavitation pressure data. The evaluation was conducted through two experiments: the first assessed the ability of these methods to reconstruct the pressure evolution across the body surface in an unsupervised manner, while the second investigated their performance in predicting the peak pressure using a small set of labeled samples.The findings demonstrated a clear trade-off: Fast ICA exhibited the best performance in reconstructing the overall pressure evolution, followed closely by PCA, while the Conv1D AE showed limitations in capturing sharp pressure gradients. Conversely, for the critical task of peak pressure prediction from limited labeled data, the Conv1D AE model achieved a significant 10% increase in accuracy compared to the baseline model without feature extraction, with PCA providing a 3% improvement. Fast ICA, however, was less effective for this specific prediction task.These results underscore the effectiveness of tailored feature extraction in automating cavitation analysis. By reducing reliance on manual intervention and accelerating the extraction of key features like peak pressure, these methods offer a practical pathway to enhance the design and analysis cycle of underwater moving bodies. The study establishes a foundation for applying machine learning to small-sample fluid mechanics problems, with future work focused on optimizing network architectures for improved precision.
Similar content being viewed by others
Data availability
Available from the corresponding author upon reasonable request.
References
Pan, S. S. Modern research on cavitation mechanism. Adv. Mech. (4), 23. https://doi.org/10.6052/1000-0992-1979-4-J1979-034 (1979). (潘森森.空化机理的近代研究[J].力学进展, 1979 4.
Pan, S. S., Peng X, Et al. Physical Mechanism of Cavitation [M]. Beijing: National Defense Industry Press, 2013. (潘森森, 彭晓星, 等 (Physical mechanism of cavitation[M]. 国防工业出版社, 2013).
Zhang, D. X., et al. Optimization of underwater body’s shape. Adv. Mater. Res. 291–294. https://doi.org/10.4028/www.scientific.net/AMR.291-294.1856 (2011).
Zhao, C. G., et al. An experimental study on characteristics of cavitation and ballistic of axisymmetric slender body underwater movement. J. Phys. Confer. Series, 656: 012175. (2015). https://doi.org/10.1088/1742-6596/656/1/012175
LI, Y. & ZHANG, Y. The research of high-speed tunnel cavity image processing system[C]// 2011 International Conference on Electric Information and Control Engineering (ICEICE). (2011). https://doi.org/10.1109/ICEICE.2011.5778166. [Online]. (Accessed 2025-07-08).
Zhang, X. W., Z, H., A, N., G, L., et al. A calculation method for supercavity shape based on the Logvinovich independence principle of the cavity section expansion. Acta Armamentarii, 30(3): 361–365. (张学伟, 张亮, 王聪, 等. 基于 Logvinovich 独立膨胀原理的超空泡形态计算方法[J]. 兵工学报, 2009, 30(3): 361–365) (2009).
Chen, W. Q, Wang, B. S., Y. I. S., et al. A theoretical investigation on the maximum pressure of the unsteady cavity closure position. Chin. J. Theoret. Appl. Mech. 4(4): 701–708. (陈玮琪, 王宝寿, 易淑群, 等. 非定常空泡闭合区域最大压力的理论研究[J]. 力学学报, 2012, 44(4): 701–708.) (2012).
Chen, H. A high-efficiency theoretical model of von Karman–Generalized Wagner model–Modified Logvinovich model for solving water-impacting problem of wedge. J. Mar. Sci. Eng. 12 (7), 1125. https://doi.org/10.3390/jmse12071125 (2024).
KIM H T et al. A numerical study of effects of body shape on cavity and drag of underwater vehicle[J]. J. Soc. Naval Architects Korea. 55 (3), 252–264. https://doi.org/10.3744/SNAK.2018.55.3.252 (2018).
Liu, H. et al. Numerical simulation of cavitating flow around a slender body with slip boundary condition. Sci. Chin. Phys. Mech. Astronomy, 59(2): 624611. (2016). https://doi.org/10.1007/s11433-015-5750-z. (刘辉, 李定迪, 薛玉红, 等. Numerical simulation of cavitating flow around a slender body with slip boundary condition[J]. 中国科学: 物理学 力学 天文学, 2016(2): 6.).
LI, B. & Wang, Y. ICMMM. Flow mechanism and hydrodynamic characteristics of 3D cavity on the surface of the underwater vehicle. In Proceedings of the 2014 International Conference on Mechatronics, Materials and Manufacturing 2014. (2014).
Huang, P. F., Sun, H. Q., Wang, J. G. et al. Numerical simulation of cavitation characteristics of underwater vehicle model. Ship Electron. Eng. 33(11): 140–143. (2013). https://doi.org/10.3969/j.issn.1627-9730.2013.11.023. (黄鹏飞, 孙鹤泉, 王继光, 等. 水下航行体模型空化特性的数值模拟[J]. 舰船电子工程, 2013, 33(11): 140–143.).
Petitpas, F. et al. Modelling cavitating flow around underwater missiles. Int. J. Naval Archit. Ocean. Eng. 3 (4), 263–273. https://doi.org/10.2478/ijnaoe-2013-0070 (2011).
Xu, D. et al. A new method proposed for realizing human gait pattern recognition: inspirations for the application of sports and clinical gait analysis. Gait Posture. 107, 293–305. https://doi.org/10.1016/j.gaitpost.2023.10.019 (2024).
Huang, X., Cheng, C. & Zhang, X. B. Machine learning and numerical investigation on drag reduction of underwater serial multi-projectiles. Def. Technol. 18 (2), 230–238. https://doi.org/10.1016/j.dt.2020.12.002 (2022).
Kamali, H, A., P. A. S. A. N. D. I. D. E. H. F. A. R. D. M. Investigating the interaction parameters on ventilation supercavitation phenomena: experimental and numerical analysis with machine learning interpretation. Phys. Fluids. 35 (11), 113343. https://doi.org/10.1063/5.0172371 (2023).
Kamali, H. A., Erfanian, M. R. Characterization of ventilated supercavitation regimes using bayesian optimized random forest models[J]. Phys. Fluids, 37(1): (2025).
Oneto, L. et al. Deep learning for cavitating marine propeller noise prediction at design stage. In 2020 International Joint Conference on Neural Networks (IJCNN). : 1–8. (2020). https://doi.org/10.1109/IJCNN48605.2020.9207003
Wang, Z. et al. Data-driven insights into cavitation phenomena: from Spatiotemporal features to physical state transitions. Phys. Fluids, 36(9): (2024).
Guang, W. et al. Reduced order data-driven analysis of cavitating flow over hydrofoil with machine learning. J. Mar. Sci. Eng. 12 (1), 148. https://doi.org/10.3390/jmse12010148 (2024).
Shahshahani, B. M., Landgrebe, D. A. The effect of unlabeled samples in reducing the small sample size problem and mitigating the Hughes phenomenon. IEEE Trans. Geosci. Remote Sens. 32 (5), 1087–1095. https://doi.org/10.1109/36.312897 (1994).
Abdi, H. & Williams, L. J., Principal component analysis. Wiley Interdisciplinary Reviews: Comput. Stat. 2 (4), 433–459. https://doi.org/10.1002/wics.101 (2010).
Xu, D. et al. Data-driven deep learning for predicting ligament fatigue failure risk mechanisms. Int. J. Mech. Sci. 301, 110519. https://doi.org/10.1016/j.ijmecsci.2025.110519 (2025).
Hyvärinen, A. & Hurri, J. HOYER P O. Independent Component Analysis (Springer, 2009).
Girolami, M. Advances in Independent Component Analysis (Springer, 2000). https://doi.org/10.1007/978-1-4471-0443-8
Goodfellow, I. J., Technical report: Multidimensional, downsampled convolution for autoencoders. Montréal: Université de Montréal, (2010).
Phiphitphatpaisit, S., Surinta, O. Deep feature extraction technique based on Conv1D and LSTM network for food image recognition. In Proceedings of the … Conference details inferred from DOI source). 2021. DOI:10.14456/easr.2021.60.
Acknowledgements
The authors would like to thank National Key Laboratory of Hydrodynamics and Taihu laboratory of deepsea technological science for help and support related to this work.
Funding
Not applicable.
Author information
Authors and Affiliations
Contributions
Q.Y.M. conducted feature extraction model, analyzed the results, and wrote the original draft; H.Z.M. prepared the CFD results; C.W.Z. edited the paper, T.L. validated the sample and results; W.T.Q supervised the design of neural network.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval and consent to participate
Not applicable.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Qiang, Y., He, Z., Chen, W. et al. Effect of feature extraction on underwater moving body cavitation pressure reconstruction and prediction. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40012-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40012-9
