Fault detection in axial piston hydraulic pumps: integrating principal component analysis with silhouette-based cluster evaluation

Authors

DOI:

https://doi.org/10.29019/enfoqueute.1120

Keywords:

Principal Component Analysis, Silhouette Analysis, Failure Detection, hydraulic piston pump

Abstract

This paper presents an approach integrating principal component and silhouette analysis with clustering algorithms for fault detection in hydraulic systems. The methodology was validated through a study in which vibration and pressure signals were collected under normal and fault conditions. These signals were then processed through filtering and normalization, followed by dimensionality reduction using principal component analysis. The resulting lower-dimensional feature vectors retained the critical characteristics of both normal and faulty conditions and were subsequently fed into a clustering algorithm. The quality of the resulting clusters was evaluated using silhouette analysis, which offers a reliable means of assessing cluster quality and visualising the outcomes of fault classification. The study demonstrates the effectiveness of this method in accurately representing the patterns of normal and malfunctioning hydraulic pump conditions, ultimately leading to successful diagnostic results.

Downloads

Download data is not yet available.

References

[1] S. Liu et al., A new test method for simulating wear failure of hydraulic pump slipper pair under high-speed and high-pressure conditions, Front. Energy Res., vol. 10, no. January, pp. 1-14, 2023, https://doi.org/10.3389/fenrg.2022.1096633

[2] M. T. Amin, F. Khan, S. Imtiaz and S. Ahmed, Robust Process Monitoring Methodology for Detection and Diagnosis of Unobservable Faults, Ind. Eng. Chem. Res., vol. 58, no. 41, pp. 19149-19165, 2019. https://doi.org/10.1021/acs.iecr.9b03406

[3] G. Patterson-hine, G. Aaseng, S. Biswas, S.Narasimhan and K. Pattipati, “A Review of Diagnostic Techniques for ISHM Applications”, NASA Ames Res. Cent. Honeywell Def. Sp. Electron. Syst., vol. 1, 2005.

[4] J. Watton, Modelling, Monitoring and Diagnostic Techniques for Fluid Power Systems. Wales: Springer, 2007.

[5] V. K. Kandula, Fault detection in process control plants using principal component analysis (LSU Master’s Theses). 2011.

[6] I. T. Jolliffe, “Principal Component Analysis, Second Edition”, Encycl. Stat. Behav. Sci., vol. 30, no. 3, pp. 487, 2002. https://doi.org/10.2307/1270093

[7] J. Mina and C. Verde, Detección de fallas usando análisis de componentes principales, pp. 431-436, 2004. Instituto de Ingeniería, UNAM.

[8] L. Siyuan et al., “Application of PCA for fault detection in Hydraulic Pumps,” Journal of Hydraulic Engineering, vol. 15, no. 4, pp. 234-245, 2010.

[9] L. Siyuan et al., “Rough Set and PCA for fault diagnosis in hydraulic systems”, International Journal of Fluid Power, vol. 10, no. 2, pp. 50-160, 2012.

[10] M. A. Atoui et al., “Bayesian Networks and PCA for fault detection in Tennessee Eastman Process,” AI in Manufacturing, vol. 5, no. 1, pp. 45-58, 2015.

[11] Villegas et al., “PCA application for fault detection in real plants”, IEEE Transactions on Industrial Applications, vol. 29, pp. 255-263, 2017.

[12] A. Hichri, M. Hajji, M. Mansouri, H. Nounou and K. Bouzrara, “Supervised machine learning-based salp swarm algorithm for fault diagnosis of photovoltaic systems”, J. Eng. Appl. Sci., vol. 71, no. 1, pp. 1-17, 2024, https://doi.org/10.1186/s44147-023-00344-z

[13] X. Ying Huang, H. Xia, W. zhe Yin and Y. kuo Liu, “Research on fault diagnosis and fault location of nuclear power plant equipment”, Ann. Nucl. Energy, vol. 205, no. April, p. 110556, 2024, https://doi.org/10.1016/j.anucene.2024.110556

[14] H. Zhao et al., “PCA and Salp Swarm Algorithm for fault detection in photovoltaic systems”, Renewable Energy, vol. 23, pp. 98-107, 2019.

[15] Y. Cardenas, G. Carrillo, A. Alviz, A. Alviz, I. Portnoy, J. Fajardo, E. Ocampo and E. Da-Costa, “Application of a Pca-Based Fault Detection and Diagnosis Method in a Power Generation System With a 2 Mw Natural Gas Engine”, EUREKA, Phys. Eng., vol. 2022, no. 6, pp. 84-98, 2022, https://doi.org/10.21303/2461-4262.2022.002701

[16] B. Xu, X. Huang, J. Zhang, W. Huang, F. Lyu and H. Xu, “A Fault Detection Method for a Practical Electro-Hydraulic Variable-Displacement Pump with Unknown Swashplate Moment”, IEEE Trans. Instrum. Meas., vol. 72, pp. 1-11, 2023, https://doi.org/10.1109/TIM.2023.3265090

[17] J. G. Maradey Lázaro and C. Borrás Pinilla, “A methodology for detection of wear in hydraulic axial piston pumps”, Int. J. Interact. Des. Manuf., vol. 14, no. 3, pp. 1103-1119, 2020, https://doi.org/10.1007/s12008-020-00681-w

[18] H. Yu, H. Li, and Y. Li, “Vibration signal fusion using improved empirical wavelet transform and variance contribution rate for weak fault detection of hydraulic pumps”, ISA Trans., vol. 107, pp. 385-401, 2020, https://doi.org/10.1016/j.isatra.2020.07.025

[19] A. Dabrowska, R. Stetter, H. Sasmito and S. Kleinmann, “Extended Kalman Filter algorithm for advanced diagnosis of positive displacement pumps”, IFAC Proceedings, vol. 45, no. 20, https://doi.org/10.3182/20120829-3-MX-2028.00068

[20] J. Konieczny and J. Stojek, “Use of the k-nearest neighbour classifier in wear condition classification of a positive displacement pump”, Sensors, vol. 21, no. 18, 2021, https://doi.org/10.3390/s21186247

[21] J. M. Liu, L. C. Gu, and B. L. Geng, “A practical signal processing approach for fault detection of axial piston pumps using instantaneous angular speed”, Proc. Inst. Mech. Eng. Part C J. Mech. Eng. Sci., vol. 234, no. 19, pp. 3935-3947, 2020, https://doi.org/10.1177/0954406220917704

[22] J. Konieczny, W. Łatas, and J. Stojek, “Classification of Wear State for a Positive Displacement Pump Using Deep Machine Learning †”, Energies, vol. 16, no. 3, pp. 1-19, 2023, https://doi.org/10.3390/en16031408

[23] R. A. Galo Fernandes, P. M. Silva Rocha Rizol, A. Nascimento, and J. A. Matelli, “A Fuzzy Inference System for Detection of Positive Displacement Motor (PDM) Stalls during Coiled Tubing Operations”, Appl. Sci., vol. 12, no. 19, 2022, https://doi.org/10.3390/app12199883

[24] C. Liu, J. Bai, and F. Wu, “Fault Diagnosis Using Dynamic Principal Component Analysis and GA Feature Selection Modeling for Industrial Processes”, Processes, vol. 10, no. 12, 2022, https://doi.org/10.3390/pr10122570

[25] Y. Huo, Y. Cao, Z. Wang, Y. Yan, Z. Ge, and Y. Yang, “Traffic anomaly detection method based on improved GRU and EFMS-Kmeans clustering”, Comput. Model. Eng. Sci., vol. 126, no. 3, pp. 1053-1091, 2021, https://doi.org/10.32604/cmes.2021.013045

[26] J. Wu, Advances in K-means Clustering a Data Mining Thinking. Springer-Verlag Berlin Heidelberg, 2012.

[27] C. Dong, J. Tao, H. Sun, Q. Wei, H. Tan, and C. Liu, “Innovative fault diagnosis for axial piston pumps: A physics-informed neural network framework predicting pump flow ripple”, Mech. Syst. Signal Process., vol. 225, no. January, p. 112274, 2025, https://doi.org/10.1016/j.ymssp.2024.112274

[28] Z. Dong, H. An, S. Liu, S. Ma, Y. G, H. Pan and Ch. Ai, “Domain adversarial transfer fault diagnosis method of an axial piston pump based on a multi-scale attention mechanism”, Meas. J. Int. Meas. Confed., vol. 239, no. July 2024, p. 115455, 2025, https://doi.org/10.1016/j.measurement.2024.115455

[29] D. Ling, T. Jiang, Y. Zheng and Y. Wang, “An adaptive mode identification and fault detection scheme for nonlinear multimode process monitoring using improved DPC-KPCA”, J. Taiwan Inst. Chem. Eng}., vol. 169, no. January, p. 105915, 2025, https://doi.org/10.1016/j.jtice.2024.105915

Downloads

Published

2025-04-01

How to Cite

Diaz, F., Borrás, C., & García Cena, C. E. (2025). Fault detection in axial piston hydraulic pumps: integrating principal component analysis with silhouette-based cluster evaluation. Enfoque UTE, 16(2), 1–9. https://doi.org/10.29019/enfoqueute.1120

Issue

Vol. 16 No. 2 (2025)

Section

Miscellaneous

License

Copyright (c) 2025 The Authors

Creative Commons License

This work is licensed under a Creative Commons Attribution 3.0 Unported License.

The articles and research published by the UTE University are carried out under the Open Access regime in electronic format.  This means that all content is freely available without charge to the user or his/her institution. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, without asking prior permission from the publisher or the author. This is in accordance with the BOAI definition of open access. By submitting an article to any of the scientific journals of the UTE University, the author or authors accept these conditions.

The UTE applies the Creative Commons Attribution (CC-BY) license to articles in its scientific journals. Under this open access license, as an author you agree that anyone may reuse your article in whole or in part for any purpose, free of charge, including commercial purposes. Anyone can copy, distribute or reuse the content as long as the author and original source are correctly cited. This facilitates freedom of reuse and also ensures that content can be extracted without barriers for research needs.

 

This work is licensed under a Creative Commons Attribution 3.0 International (CC BY 3.0).

 

The Enfoque UTE journal guarantees and declares that authors always retain all copyrights and full publishing rights without restrictions [© The Author(s)]. Acknowledgment (BY): Any exploitation of the work is allowed, including a commercial purpose, as well as the creation of derivative works, the distribution of which is also allowed without any restriction.