journal article·2026-06-15Open access

Robust Fault Diagnosis of Hydraulic Pumps Under Variable Load: A Machine Learning Approach with Signal Conditioning

Mikołaj Waksmundzki, Jerzy Stojek, Anna Stronczek

Applied Sciences· Volume 16· Issue 12

Abstract

In the era of digital transformation, the operational reliability of hydraulic energy conversion systems is paramount for the overall efficiency of sustainable integrated energy infrastructures. This study evaluates the robustness of machine learning-based fault diagnosis for positive displacement pumps, which are critical components in energy-intensive industrial applications. The research addresses a key challenge: the instability of diagnostic features under varying operational regimes. Using vibration signals from units at three distinct wear levels, we evaluated multiple machine learning architectures, including SVM, KNN, and ensemble trees. Our findings reveal that traditional data-driven models suffer a performance degradation of over 21% when subjected to domain shifts caused by load variability. To mitigate this, we implemented a frequency-domain signal conditioning layer that aligns extracted descriptors with physically meaningful wear phenomena. This enhanced feature representation improved classification accuracy to 93.5% under variable load conditions. The results demonstrate that improving the robustness of diagnostic models is essential for reliable operation, maintenance planning, and energy efficiency of hydraulic energy conversion systems within modern industrial energy infrastructures.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Hydraulic and Pneumatic Systems · Machine Fault Diagnosis Techniques · Water Systems and Optimization

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

Affiliations

Faculty of Mechanical Engineering and Robotics, AGH University of Krakow, 30-059 Kraków, Poland

Faculty of Management, AGH University of Krakow, 30-059 Kraków, Poland

Funding

AGH University of Krakow

References (47)

Show source-provided references
1. Physics-informed failure mechanism for hydraulic pumps: State-of-the-art review, challenges and trends10.1016/j.rser.2025.116610 ↗
2. Sensing technologies for condition monitoring of oil pump in harsh environment10.1016/j.sna.2022.113864 ↗
3. Fault diagnosis of an intelligent hydraulic pump based on a nonlinear unknown input observer10.1016/j.cja.2017.05.004 ↗
4. Intelligent fault identification of hydraulic pump using deep adaptive normalized CNN and synchrosqueezed wavelet transform10.1016/j.ress.2022.108560 ↗
5. Gerotor pump cavitation monitoring and fault diagnosis using vibration analysis through the employment of auto-regressive-moving-average technique10.1016/j.simpat.2016.11.005 ↗
6. Intelligent fault diagnosis of hydraulic piston pump based on deep learning and Bayesian optimization10.1016/j.isatra.2022.01.013 ↗
7. A fuzzy inference system for pump failure diagnosis to improve maintenance process: The case of a petrochemical industry10.1016/j.eswa.2009.06.018 ↗
8. Coupled fault diagnosis for centrifugal pumps through Boruta-Shap feature selection and rime-enhanced stacked denoised autoencoder10.1016/j.engappai.2025.112659 ↗
9. Zhu, Y., Zhou, T., Tang, S., and Yuan, S. (2023). A data-driven diagnosis scheme based on deep learning toward fault identification of the hydraulic piston pump. J. Mar. Sci. Eng., 11.10.3390/jmse11071273 ↗
10. Intelligent discharge state detection in micro-EDM process with cost-effective radio frequency (RF) radiation: Integrating machine learning and interpretable AI10.1016/j.eswa.2025.128607 ↗
11. Yang, Y., Li, Y., Cheng, L., and Yang, S. (2024). Short-Term Wind Power Prediction Based on a Modified Stacking Ensemble Learning Algorithm. Sustainability, 16.10.3390/su16145960 ↗
12. Piotrowski, P. (2026). Short-Term Forecasting of the Total Power Generation from Wind Farms and Solar Power Plants in the National Power System Using Advanced Ensemble Machine Learning Models. Energies, 19.10.3390/en19040930 ↗
13. Alazemi, F., Alazmi, A., Alrumaidhi, M., and Molden, N. (2025). Predicting Fuel Consumption and Emissions Using GPS-Based Machine Learning Models for Gasoline and Diesel Vehicles. Sustainability, 17.10.3390/su17062395 ↗
14. McKee, K.K., Forbes, G., Mazhar, I., Entwistle, R., and Howard, I. (2011, January 16–20). A review of major centrifugal pump failure modes with application to the water supply and sewerage industries. Proceedings of the ICOMS Asset Management Conference 2011, Gold Coast, Australia.
15. Discriminant feature extraction for centrifugal pump fault diagnosis10.1109/ACCESS.2020.3022770 ↗
16. Chao, Q., Gao, H., Tao, J., Liu, C., Wang, Y., and Zhou, J. (2022). Fault diagnosis of axial piston pumps with multi-sensor data and convolutional neural network. Front. Mech. Eng., 17.10.1007/s11465-022-0692-4 ↗
17. Layered clustering multi-fault diagnosis for hydraulic piston pump10.1016/j.ymssp.2012.10.020 ↗
18. Predictive maintenance for ballast pumps on ship repair yards via machine learning10.1016/j.treng.2020.100020 ↗
19. Vibration-sensor-free diagnosis for aviation piston pumps: A CWT-ViT approach with high-dimensional tensor fusion10.1016/j.measurement.2025.119050 ↗
20. Blockage and cavitation detection in centrifugal pumps from dynamic pressure signal using deep learning algorithm10.1016/j.measurement.2020.108676 ↗
21. A survey of fault diagnosis and fault-tolerant techniques—Part I: Fault diagnosis with model-based and signal-based approaches10.1109/TIE.2015.2417501 ↗
22. Acoustic signal-based fault detection of hydraulic piston pump using a particle swarm optimization enhancement CNN10.1016/j.apacoust.2022.108718 ↗
23. Early detection and classification of internal leakage in boom actuator of mobile hydraulic machines using SVM10.1016/j.engappai.2021.104492 ↗
24. Real-time fault diagnosis and fault-tolerant control10.1109/TIE.2015.2417511 ↗
25. A multi-sensor fault detection strategy for axial piston pump using the Walsh transform method10.1177/1550147718772531 ↗
26. Konieczny, J., Łatas, W., and Stojek, J. (2023). Classification of wear state for a positive displacement pump using deep machine learning. Energies, 16.10.3390/en16031408 ↗
27. A multi-fault diagnosis method for piston pump in construction machinery based on information fusion and PSO-SVM10.21595/jve.2019.20384 ↗
28. Fault diagnosis of hydraulic pump based on multi-sensor data fusion10.4028/www.scientific.net/AMM.33.539 ↗
29. Intelligent fault diagnosis of hydraulic piston pump combining improved LeNet-5 and PSO hyperparameter optimization10.1016/j.apacoust.2021.108336 ↗
30. Interpretable CNN models for computationally efficient bearing fault diagnosis using learnable Gaussian/Sinc filters
31. An EWT-PCA and extreme learning machine based diagnosis approach for hydraulic pump10.1016/j.ifacol.2020.11.008 ↗
32. Fault diagnosis for pump equipment based on transfer learning: The domain generalization method10.1038/s41598-025-25210-1 ↗
33. A hybrid deep learning model towards fault diagnosis of drilling pump10.1016/j.apenergy.2024.123773 ↗
34. An adaptive deep learning model towards fault diagnosis of hydraulic piston pump using pressure signal10.1016/j.engfailanal.2022.106300 ↗
35. A novel adaptive convolutional neural network for fault diagnosis of hydraulic piston pump with acoustic images10.1016/j.aei.2022.101554 ↗
36. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy10.1109/TPAMI.2005.159 ↗
37. Application of analysis of variance to determine important features of signals for diagnostic classifiers of displacement pumps10.1038/s41598-024-56498-0 ↗
38. A novel interpretable semi-supervised graph learning model for intelligent fault diagnosis of hydraulic pumps10.1016/j.knosys.2024.112598 ↗
39. Ma, W., Ma, S., Zou, Z., Fu, B., Ma, J., Liu, J., and Zhang, Q. (2025). Literature review on fault mechanism analysis and diagnosis methods for main pump systems. Machines, 13.10.3390/machines13111000 ↗
40. An improved convolutional neural network with an adaptable learning rate towards multi-signal fault diagnosis of hydraulic piston pump10.1016/j.aei.2021.101406 ↗
41. Vision-based fault diagnostics using explainable deep learning with class activation maps10.1109/ACCESS.2020.3009852 ↗
42. Few-shot fault diagnosis of axial piston pump based on prior knowledge-embedded meta learning vision transformer under variable operating conditions10.1016/j.eswa.2025.126452 ↗
43. Orrù, P.F., Zoccheddu, A., Sassu, L., Mattia, C., Cozza, R., and Arena, S. (2020). Machine learning approach using MLP and SVM algorithms for the fault prediction of a centrifugal pump in the oil and gas industry. Sustainability, 12.10.3390/su12114776 ↗
44. Review on fault diagnosis of electric submersible pump using machine learning10.1088/1742-6596/3129/1/012056 ↗
45. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016, January 27–30). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.319 ↗
46. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13–17). “Why should I trust you?” Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939778 ↗
47. Industrial artificial intelligence for industry 4.0-based manufacturing systems