journal article·2026-04-06Open access

Cavitation Monitoring in Rotating Hydraulic Machines Using Machine Learning—A Review

Elisa Sanchez, Axel Busboom

Applied Sciences· Volume 16· Issue 7

Abstract

Cavitation in rotating hydraulic machinery—such as industrial pumps and hydropower turbines—can cause blade and casing erosion, excessive vibration, noise and efficiency loss, posing significant operational and economic risks across industrial sectors. Reliable and scalable monitoring strategies are therefore essential, particularly under variable operating conditions in real-world environments. Recent advances in machine learning (ML) and deep learning (DL) have enabled data-driven approaches for cavitation detection based on operational sensor signals, yet a structured synthesis of these developments is lacking. This scoping review systematically analyzes measurement-based ML and DL approaches for cavitation monitoring, with the aim of identifying key trends, challenges and future research directions. Following PRISMA-ScR and JBI guidelines, 52 peer-reviewed studies published between 1996 and 2025 were evaluated, covering laboratory and field investigations across pumps and turbines and a wide range of model architectures. The analysis reveals that most studies are laboratory-based (∼80%), focus on pumps (∼70%) and rely on single-machine datasets (>80%), limiting generalization across machines and operating conditions. Classical ML approaches remain relevant due to interpretability and robustness with limited data, while DL enables end-to-end learning from raw or time–frequency transformed signals, frequently achieving diagnostic accuracy above 95%. Hybrid frameworks combining DL-based feature extraction with classical classifiers are increasingly adopted. Key limitations across the literature include domain shifts between laboratory and field data, scarce or inconsistent labeling and a predominant focus on categorical cavitation severity levels.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Cavitation Phenomena in Pumps · Water Systems and Optimization · Oil and Gas Production Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Engineering and Management, Munich University of Applied Sciences, 80335 Munich, Germany

Funding

European Union

References (63)

Show source-provided references
1. Avellan, F. (2004, January 24–26). Introduction to cavitation in hydraulic machinery. Proceedings of the 6th International Conference on Hydraulic Machinery and Hydrodynamics, Perth, WA, Australia.
2. Study of cavitation in hydro turbines—A review10.1016/j.rser.2009.07.024 ↗
3. Cavitation Effects in Centrifugal Pumps—A Review
4. Cavitation diagnosis for water distribution pumps: An early-stage approach combing vibration signal-based neural network with high-speed photography
5. Cavitation Status Recognition Method of Centrifugal Pump Based on Multi-Pointand Multi-Resolution Analysis
6. Cavitation recognition of axial piston pumps in noisy environment based on Grad-CAM visualization technique10.1049/cit2.12101 ↗
7. Cavitation intensity recognition for axial piston pump based on transient flow rate measurement and improved transfer learning method10.1016/j.ymssp.2025.112667 ↗
8. Cavitation detection for water hydraulic axial piston pump based on physics-informed CNN data augmentation and XGBoost10.1016/j.ymssp.2025.113512 ↗
9. The detection of cavitation in hydraulic machines by use of ultrasonic signal analysis10.5293/IJFMS.2015.8.4.264 ↗
10. Detection of cavitation in hydraulic turbines10.1016/j.ymssp.2004.08.006 ↗
11. Cavitation detection in hydraulic machinery by analyzing acoustic emissions under strong domain shifts using neural networks10.1063/5.0137068 ↗
12. Evaluation of supervised machine learning techniques for cavitation detection and diagnosis in a pump-as-turbine system10.1016/j.eswa.2025.129167 ↗
13. de Souza, J.C.S., Júnior, O.H., Filho, G.L.T., Carpinteiro, O.A.S., Biancardine Júnior, H.S.D., and Dos Santos, I.F.S. (2024). Application of machine learning models in predictive maintenance of Francis hydraulic turbines. Rev. Bras. Recur. Hidr., 3–14.10.1590/2318-0331.292420240056 ↗
14. Detecting Abnormal Events in Geothermal Power Plant Time-Series Data Using a Semi-Supervised Machine Learning Approach
15. Detection of abnormal operation in geothermal binary plant feed pumps using time-series analytics10.1016/j.eswa.2024.123305 ↗
16. Cavitation Identification Method of Centrifugal Pumps Based on Signal Demodulation and EfficientNet10.1007/s13369-024-09193-1 ↗
17. A review of cavitation in hydraulic machinery10.1016/S1001-6058(16)60638-8 ↗
18. Applications of machine learning to machine fault diagnosis: A review and roadmap10.1016/j.ymssp.2019.106587 ↗
19. A systematic literature review of deep learning for vibration-based fault diagnosis of critical rotating machinery: Limitations and challenges10.1016/j.jsv.2024.118562 ↗
20. Sha, Y., Liu, N., Liu, H., Tao, J., Niu, Z., Huang, G., Yao, Y., Liang, J., Qian, M., and Stoecker, H. (2025). A Review of Machine Learning for Cavitation Intensity Recognition in Complex Industrial Systems. arXiv.
21. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation10.7326/M18-0850 ↗
22. Aromataris, E., Lockwood, C., Porritt, K., Pilla, B., and Jordan, Z. (2024). Scoping Reviews. JBI Manual for Evidence Synthesis, JBI.10.46658/JBIMES-24-01 ↗
23. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews10.1136/bmj.n71 ↗
24. A carrier wave extraction method for cavitation characterization based on time synchronous average and time-frequency analysis10.1016/j.jsv.2020.115682 ↗
25. VMD-SE-DCNN-CBAM: An Intelligent Cavitation Recognition Method for Canned Motor Pump
26. Tan, Y., Wu, G., Qiu, Y., Fan, H., and Wan, J. (2023). Fault diagnosis of a mixed-flow pump under cavitation condition based on deep learning techniques. Front. Energy Res., 10.10.3389/fenrg.2022.1109214 ↗
27. Yu, L., and Cheng, L. (2026). Cavitation Coefficient Identification Model for an Axial Flow Pump Based on Pressure Signal Feature Extraction and Spider Wasp Optimization Algorithm. J. Mar. Sci. Eng., 14.10.3390/jmse14010018 ↗
28. Diagnostic method by using vibration analysis for pump fault detection10.1016/j.egypro.2018.08.013 ↗
29. Detecting cavitation in hydraulic pumps using artificial neural networks
30. Health monitoring of an electro-hydraulic system using ordered neural networks
31. Analysis of Optimal Parameters for Discriminating Cavitation Types by SSAE-RF10.1088/1742-6596/2242/1/012025 ↗
32. Interpretable fusion methodology of health indices with an application to industrial turbine cavitation condition monitoring10.1098/rsta.2022.0402 ↗
33. Look, A., Kirschner, O., and Riedelbauch, S. (2018, January 16–18). Building robust classifiers with generative adversarial networks for detecting cavitation in hydraulic turbines. Proceedings of the ICPRAM 2018—the 7th International Conference on Pattern Recognition Applications and Methods, Madeira, Portugal.10.5220/0006636304560462 ↗
34. Stacked sparse autoencoder in cavitation noise signal data classification of hydro turbine based on power spectrum10.1177/1461348419830815 ↗
35. Powar, S.K., Cohen, S., Ratnaparkhi, S., and Satpute, N. (2025, January 21–22). Vortex to Cavitation: Enhancing Turbine Safety and Efficiency. Proceedings of the 2025 International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA), Aurangabad, India.10.1109/ICAMIDA64673.2025.11209187 ↗
36. Optimizing cavitation fault forecasting in pump-turbine systems through gated recurrent units10.1063/5.0251643 ↗
37. He, J., Hao, J., and Cao, Z. (2023, January 16–19). SGST: A Novel Approach Based on Machine Learning for Cavitation Fault Diagnosis. Proceedings of the IECON 2023—The 49th Annual Conference of the IEEE Industrial Electronics Society, Singapore.10.1109/IECON51785.2023.10312299 ↗
38. Development of a Novel Cavitation Monitoring System for Hydro Turbines Based on Machine Learning Algorithms10.1088/1755-1315/1079/1/012015 ↗
39. Dutta, N., Subramaniam, U., Sanjeevikumar, P., Bharadwaj, S.C., Leonowicz, Z., and Holm-Nielsen, J.B. (2020, January 9–12). Comparative Study of Cavitation Problem Detection in Pumping System Using SVM and K-Nearest Neighbour Method. Proceedings of the 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Madrid, Spain.10.1109/EEEIC/ICPSEurope49358.2020.9160689 ↗
40. Hasanpour, M.A., Engholm, R., and Fafoutis, X. (2024, January 24–26). Pump Cavitation Detection with Machine Learning: A Comparative Study of SVM and Deep Learning. Proceedings of the 2024 IEEE Annual Congress on Artificial Intelligence of Things (AIoT), Melbourne, Australia.10.1109/AIoT63253.2024.00050 ↗
41. Online Current Signature Analysis Approach for Cavitation Assessment in Hydraulic Pumps
42. Identification of full-load cavitation surge onset in hydropower units through the clustering of monitoring data10.1088/1755-1315/1483/1/012005 ↗
43. Song, M., Zhi, Y., An, M., Xu, W., Li, G., and Wang, X. (2024). Centrifugal Pump Cavitation Fault Diagnosis Based on Feature-Level Multi-Source Information Fusion. Processes, 12.10.3390/pr12010196 ↗
44. Cavitation Detection in Centrifugal Pump Based on Interior Flow-Borne Noise Using WPD-PCA-RBF10.1155/2019/8768043 ↗
45. Cavitation state recognition of centrifugal pumps across various working conditions by Multi-Adversarial Attention Network10.1016/j.ymssp.2025.113336 ↗
46. Cavitation state recognition method of centrifugal pump based on multi-dimensional feature fusion and convolutional gate recurrent unit10.1063/5.0232330 ↗
47. Prediction of cavitation using machine learning techniques on centrifugal pump10.1088/1742-6596/2854/1/012014 ↗
48. Won, I.H., Gao, R., Tsoukalas, L.H., Eryurek, E., and Kavaklioglu, K. (2005, January 15–19). Incipient cavitation detection methodology using current sensor based on a neural wavelet approach. Proceedings of the American Nuclear Society—International Congress on Advances in Nuclear Power Plants 2005, ICAPP’05, Seoul, Republic of Korea.
49. A new online approach for classification of pumps vibration patterns based on intelligent IoT system10.1016/j.measurement.2019.107138 ↗
50. Investigating pump cavitation based on audio sound signature recognition using artificial neural network10.1088/1742-6596/1569/3/032044 ↗
51. Karagiovanidis, M., Pantazi, X.E., Papamichail, D., and Fragos, V. (2023). Early Detection of Cavitation in Centrifugal Pumps Using Low-Cost Vibration and Sound Sensors. Agriculture, 13.10.3390/agriculture13081544 ↗
52. Vibration-based cavitation detection in centrifugal pumps
53. Prediction of cavitation vortex dynamics in the draft tube of a francis turbine using radial basis neural networks10.1007/s00521-004-0458-4 ↗
54. Nasiri, M., Mahjoob, M., and Vahid-Alizadeh, H. (2011, January 13–15). Vibration signature analysis for detecting cavitation in centrifugal pumps using neural networks. Proceedings of the 2011 IEEE International Conference on Mechatronics, Istanbul, Turkey.10.1109/ICMECH.2011.5971192 ↗
55. Improving accuracy of cavitation severity detection in centrifugal pumps using a hybrid feature selection technique10.1016/j.measurement.2017.05.020 ↗
56. Cavitation Analysis in Centrifugal Pumps Based on Vibration Bispectrum and Transfer Learning10.1155/2021/6988949 ↗
57. Lang, T., Ni, C., Chen, K., Xu, E., Yin, J., Shen, X., Wu, X., and Zhang, D. (2023). Recognition of cavitation characteristics in non-clogging pumps based on the improved Lévy flight bat algorithm. Front. Energy Res., 11.10.3389/fenrg.2023.1335227 ↗
58. Cavitation fault diagnosis of centrifugal pump based on RIME-SDAE10.21595/vp.2024.24039 ↗
59. Identification of cavitation in centrifugal pump by artificial immune network10.1177/09544089211028402 ↗
60. Detection of Vortex Cavitation with The Method Adaptive Neural Fuzzy Networks in the Deep Well Pumps
61. Machine Learning-Based Prediction of NPSH, Noise, and Vibration Levels in Radial Pumps Under Cavitation Conditions
62. Sparrow search algorithm-optimized variational mode decomposition-based multiscale convolutional network for cavitation diagnosis of hydro turbines10.1016/j.oceaneng.2024.119055 ↗
63. An adaptive Industrial Internet of things (IIOts) based technology for prediction and control of cavitation in centrifugal pumps10.1016/j.procir.2020.03.125 ↗