Hydraulic accumulator fault diagnosis using LSTM neural networks

“Hydraulic accumulator fault diagnosis using LSTM neural networks”

Authors: Patryk Olszewski, Kacper F. Pajuro, Lasse B. Hansen, Lígia S. Ramos, Michael K. Odena and Jesper Liniger,
Affiliation: Aalborg University
Reference: 2025, Vol 46, No 3, pp. 101-109.

Keywords: fluid power, hydraulic accumulator, fault detection and diagnosis, gas leakage, LSTM, offshore wind

Abstract: The maintenance costs associated with offshore wind turbines, particularly those related to logistics and system downtimes, are significantly influenced by the reliability of hydraulic components, especially the pitch control system. Accumulator failures, which constitute a notable percentage of system faults, often result from gas leakage and pressure drops, highlighting the need for efficient fault detection and diagnosis (FDD) methods. This paper presents a novel approach utilizing Long Short-Term Memory (LSTM) neural networks for detecting faults in hydraulic accumulators. Two LSTM models were developed: a regression model that estimates the exact pre-charge pressure and a classification model that predicts pressure ranges. The models were trained and validated using both experimental and simulation data from a hydraulic test setup. Results demonstrated that the regression network achieved a root mean square error (RMSE) of approximately 4.2 bar, while the classification network reached 78.75% accuracy. The findings show that LSTM networks provide precision similar to prior art but for a larger variation of load cases. Thus, the proposed non-invasive method is promising for early fault detection in offshore wind turbine accumulators, potentially reducing operational costs and enhancing maintenance strategies.

PDF

PDF (4575 Kb)        DOI: 10.4173/mic.2025.3.1

References:
[1] Asmussen, M.F., Liniger, J., Sepehri, N., and Pedersen, H.C. (2022). Pre-charge pressure estimation of a hydraulic accumulator using surface temperature measurements, Wind. 2(4):784--800. doi:10.3390/wind2040041
[2] Carroll, J., McDonald, A., and McMillan, D. (2016). Failure rate, repair time and unscheduled O&M cost analysis of offshore wind turbines, Wind Energy. 19(6):1107--1119. doi:10.1002/we.1887
[3] Chen, H., Liu, H., Chu, X., Liu, Q., and Xue, D. (2021). Anomaly detection and critical scada parameters identification for wind turbines based on lstm-ae neural network, Renewable Energy. 172:829--840. doi:10.1016/j.renene.2021.03.078
[4] Chen, Y., Rao, M., Feng, K., and Zuo, M.J. (2022). Physics-informed lstm hyperparameters selection for gearbox fault detection, Mechanical Systems and Signal Processing. 171:108907. doi:10.1016/j.ymssp.2022.108907
[5] Elorza, I., Arrizabalaga, I., Zubizarreta, A., Martín-Aguilar, H., Pujana-Arrese, A., and Calleja, C. (2022). A Sensor Data Processing Algorithm for Wind Turbine Hydraulic Pitch System Diagnosis, Energies. 15(1):33. doi:10.3390/en15010033
[6] Goldfrank, J.C. and Cooper, H.W. (1967). Benedict-Webb-Rubin constants and new correlations, Hydrocarbon Processing. 46(12).
[7] He, Y., Liu, J., Wu, S., and Wang, X. (2023). Condition monitoring and fault detection of wind turbine driveline with the implementation of deep residual long short-term memory network, IEEE Sensors Journal. 23(12):13360--13371. doi:10.1109/JSEN.2023.3273279
[8] Helwig, N., Pignanelli, E., and Schütze, A. (2015). Condition monitoring of a complex hydraulic system using multivariate statistics, In 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings. pages 210--215. doi:10.1109/I2MTC.2015.7151267
[9] Lei, J., Liu, C., and Jiang, D. (2019). Fault diagnosis of wind turbine based on long short-term memory networks, Renewable Energy. 133:422--432. doi:10.1016/j.renene.2018.10.031
[10] Liniger, J., Pedersen, H.C., and Soltani, M. (2017). Model-Based Estimation of Gas Leakage for Fluid Power Accumulators in Wind Turbines, American Society of Mechanical Engineers Digital Collection, 2017. doi:10.1115/FPMC2017-4253
[11] Liniger, J., Sepehri, N., Soltani, M., and Pedersen, H. (2017). Signal-Based Gas Leakage Detection for Fluid Power Accumulators in Wind Turbines, Energies, 2017. 10(3):331. doi:10.3390/en10030331
[12] Liniger, J., Soltani, M., Pedersen, H.C., Carroll, J., and Sepehri, N. (2017). Reliability based design of fluid power pitch systems for wind turbines, Wind Energy, 2017. 20(6):1097--1110. doi:10.1002/we.2082
[13] Pfeffer, A., Glück, T., Kemmetmüller, W., and Kugi, A. (2016). Mathematical modelling of a hydraulic accumulator for hydraulic hybrid drives, Mathematical and Computer Modelling of Dynamical Systems, 2016. 22(5):397--411. doi:10.1080/13873954.2016.1174716
[14] Xiang, L., Wang, P., Yang, X., Hu, A., and Su, H. (2021). Fault detection of wind turbine based on scada data analysis using cnn and lstm with attention mechanism, Measurement. 175:109094. doi:10.1016/j.measurement.2021.109094
[15] Zhu, Y., Zhu, C., Tan, J., Tan, Y., and Rao, L. (2022). Anomaly detection and condition monitoring of wind turbine gearbox based on lstm-fs and transfer learning, Renewable Energy. 189:90--103. doi:10.1016/j.renene.2022.02.061

BibTeX:
@article{MIC-2025-3-1,
  title={{Hydraulic accumulator fault diagnosis using LSTM neural networks}},
  author={Olszewski, Patryk and Pajuro, Kacper F. and Hansen, Lasse B. and Ramos, Lígia S. and Odena, Michael K. and Liniger, Jesper},
  journal={Modeling, Identification and Control},
  volume={46},
  number={3},
  pages={101--109},
  year={2025},
  doi={10.4173/mic.2025.3.1},
  publisher={Norwegian Society of Automatic Control}
};

Article

“Hydraulic accumulator fault diagnosis using LSTM neural networks”