An electro-hydraulic drive system is essential for the stable operation of tunnel drilling rigs in underground coal mines. However, components such as pumps, valves, and controllers inevitably experience gradual degradation under long-term and high-load conditions. Conventional monitoring approaches often rely on labeled fault data or suffer from limited interpretability, restricting their applicability in real engineering environments. To overcome these limitations, this study proposes an unsupervised degradation trend analysis method that does not use labeled samples. A sliding-window strategy was adopted to extract key statistical features. Principal component analysis was then employed to construct a unified health index, and Z-score normalization enabled the interpretable detection of abnormal tendencies in individual features. Validation on real drilling data revealed clear degradation behaviors, such as main pump leakage and control current drift, demonstrating that the proposed method offered a lightweight and interpretable solution for trend-based condition monitoring and provided practical support for the intelligent maintenance of electro-hydraulic drive systems.

1. [1] S. Tang, Y. Zhu, and S. Yuan, “An improved convolutional neural network with an adaptable learning rate towards multi-signal fault diagnosis of hydraulic piston pump,” Adv. Eng. Inform., Vol.50, Article No.101406, 2021. https://doi.org/10.1016/j.aei.2021.101406
2. [2] N. Liang et al., “A multi-output fault diagnosis framework for hydraulic system using a CNN-SVM hierarchical learning strategy,” Meas. Sci. Technol., Vol.35, No.7, Article No.076212, 2024. https://doi.org/10.1088/1361-6501/ad3f3b
3. [3] J. Shi et al., “Fault diagnosis in a hydraulic directional valve using a two-stage multi-sensor information fusion,” Measurement, Vol.179, Article No.109460, 2021. https://doi.org/10.1016/j.measurement.2021.109460
4. [4] W.-T. Yang, M. S. Reis, V. Borodin, M. Juge, and A. Roussy, “An interpretable unsupervised Bayesian network model for fault detection and diagnosis,” Control Eng. Pract., Vol.127, Article No.105304, 2022. https://doi.org/10.1016/j.conengprac.2022.105304
5. [5] K. Huang, S. Wu, F. Li, C. Yang, and W. Gui, “Fault diagnosis of hydraulic systems based on deep learning model with multirate data samples,” IEEE Trans. Neural Netw. Learn. Syst., Vol.33, No.11, pp. 6789-6801, 2022. https://doi.org/10.1109/TNNLS.2021.3083401
6. [6] C. Lu, S. Tian, M. Wu, N. Yao, and H. Song, “Generalized incremental dissipative control of drill-string system based on equivalent input-disturbance approach with stubborn state observer,” Automatica, Vol.181, Article No.112501, 2025. https://doi.org/10.1016/j.automatica.2025.112501
7. [7] A. Melo, M. M. Câmara, N. Clavijo, and J. C. Pinto, “Open benchmarks for assessment of process monitoring and fault diagnosis techniques: A review and critical analysis,” Comput. Chem. Eng., Vol.165, Article No.107964, 2022. https://doi.org/10.1016/j.compchemeng.2022.107964
8. [8] C. Zhao, H. Sun, and F. Tian, “Total variable decomposition based on sparse cointegration analysis for distributed monitoring of nonstationary industrial processes,” IEEE Trans. Control Syst. Technol., Vol.28, No.4, pp. 1542-1549, 2020. https://doi.org/10.1109/TCST.2019.2908339
9. [9] W. Yu, C. Zhao, and B. Huang, “MoniNet with concurrent analytics of temporal and spatial information for fault detection in industrial processes,” IEEE Trans. Cybern., Vol.52, No.8, pp. 8340-8351, 2022. https://doi.org/10.1109/TCYB.2021.3050398
10. [10] H. Fan et al., “Adaptive monitoring for geological drilling process using neighborhood preserving embedding and Jensen–Shannon divergence,” Control Eng. Pract., Vol.134, Article No.105476, 2023. https://doi.org/10.1016/j.conengprac.2023.105476
11. [11] A. Mallak and M. Fathi, “Sensor and component fault detection and diagnosis for hydraulic machinery integrating LSTM autoencoder detector and diagnostic classifiers,” Sensors, Vol.21, No.2, Article No.433, 2021. https://doi.org/10.3390/s21020433
12. [12] C. Ji, F. Ma, J. Wang, and W. Sun, “Orthogonal projection based statistical feature extraction for continuous process monitoring,” Comput. Chem. Eng., Vol.183, Article No.108600, 2024. https://doi.org/10.1016/j.compchemeng.2024.108600
13. [13] S. Yin, S. X. Ding, X. Xie, and H. Luo, “A review on basic data-driven approaches for industrial process monitoring,” IEEE Trans. Ind. Electron., Vol.61, No.11, pp. 6418-6428, 2014. https://doi.org/10.1109/TIE.2014.2301773
14. [14] A. Yang, M. Wu, C. Lu, J. Hu, and Y. Nakanishi, “Full condition monitoring of geological drilling process based on just-in-time learning-aided slow feature analysis,” J. Process Control, Vol.142, Article No.103284, 2024. https://doi.org/10.1016/j.jprocont.2024.103284
15. [15] Q. Chao, Y. Shao, C. Liu, and X. Yang, “Health evaluation of axial piston pumps based on density weighted support vector data description,” Reliab. Eng. Syst. Saf., Vol.237, Article No.109354, 2023. https://doi.org/10.1016/j.ress.2023.109354
16. [16] Y. Wen, M. F. Rahman, H. Xu, and T.-L. B. Tseng, “Recent advances and trends of predictive maintenance from data-driven machine prognostics perspective,” Measurement, Vol.187, Article No.110276, 2022. https://doi.org/10.1016/j.measurement.2021.110276
17. [17] F. L. Gewers et al., “Principal component analysis: A natural approach to data exploration,” ACM Comput. Surv., Vol.54, No.4, Article No.70, 2021. https://doi.org/10.1145/3447755
18. [18] A. Yang et al., “Data augmentation considering distribution discrepancy for fault diagnosis of drilling process with limited samples,” IEEE Trans. Ind. Electron., Vol.70, No.11, pp. 11774-11783, 2023. https://doi.org/10.1109/TIE.2022.3229274
19. [19] H. Fan et al., “An operating performance assessment strategy with multiple modes based on least squares support vector machines for drilling process,” Comput. Ind. Eng., Vol.159, Article No.107492, 2021. https://doi.org/10.1016/j.cie.2021.107492
20. [20] C. Zhang, Z.-H. Xu, Y.-Y. Lao, and Y. Li, “Dynamic process fault detection and diagnosis method based on factor analysis: Application on the three-tank system process,” J. Chemom., Vol.38, No.12, Article No.e3627, 2024. https://doi.org/10.1002/cem.3627
21. [21] H. Fan et al., “A decentralized operating performance assessment for geological drilling process via multi-block total projection to latent structures and Bayesian inference,” J. of Process Control, Vol.117, pp. 26-39, 2022. https://doi.org/10.1016/j.jprocont.2022.07.005
22. [22] S. Du, C. Huang, X. Ma, and H. Fan, “A review of data-driven intelligent monitoring for geological drilling processes,” Processes, Vol.12, No.11, Article No.2478, 2024. https://doi.org/10.3390/pr12112478
23. [23] A. Yang et al., “Discrimination and correction of abnormal data for condition monitoring of drilling process,” Neurocomputing, Vol.433, pp. 275-286, 2021. https://doi.org/10.1016/j.neucom.2020.11.064
24. [24] J. Liu, H. Xu, X. Peng, J. Wang, and C. He, “Reliable composite fault diagnosis of hydraulic systems based on linear discriminant analysis and multi-output hybrid kernel extreme learning machine,” Reliab. Eng. Syst. Saf., Vol.234, Article No.109178, 2023. https://doi.org/10.1016/j.ress.2023.109178
25. [25] H. Fan et al., “Distributed monitoring with integrated probability PCA and mRMR for drilling processes,” IEEE Trans. Instrum. Meas., Vol.71, Article No.3516213, 2022. https://doi.org/10.1109/TIM.2022.3186081