Accurate fault diagnosis of hydraulic systems is essential for ensuring safe and reliable industrial operation. To address challenges such as inconsistent sampling rates of multi-source sensor data, feature redundancy, and inefficient inter-channel fusion, this study proposes a multi-scale temporal modeling and adaptive channel fusion framework. The Spearman correlation coefficient is applied to select sensor signals highly correlated with fault patterns, reducing data redundancy. A multi-branch structure processes signals with different sampling rates, where each branch integrates a temporal convolutional network (TCN) and multi-head self-attention (MHSA) to capture local and global temporal dependencies. An efficient channel attention (ECA) module further adaptively weights and fuses multi-channel features, emphasizing key fault information. Experiments on a public hydraulic dataset show that the proposed method outperforms traditional concatenation and other deep learning models, confirming its effectiveness for multi-rate data fusion and complex fault classification.
MahatoACGhoshalSK. An overview of energy savings approaches on hydraulic drive systems. Int J Fluid Power2020; 21(1): 81–118.
2.
DaiJTangJHuangS, et al. Signal-based intelligent hydraulic fault diagnosis methods: review and prospects. Chin J Mech Eng2019; 32(1): 75.
3.
GunerHErtugrulSTayyarGT. Fault simulation and identification of an electrohydraulic system by using fault emulation. In: 2024 10th International conference on control, decision and information technologies, CODIT, 2024, pp. 229–235. IEEE.
4.
SinghUKTripathiJPKhannaK. Analysis of convergence and stability of PSO for accurate estimation of the incipient faults of hydraulic pump. J Braz Soc Mech Sci Eng2024; 46(3): 158.
5.
WratGRanjanPMishraSK, et al. Neural network-enhanced internal leakage analysis for efficient fault detection in heavy machinery hydraulic actuator cylinders. Proc Inst Mech Eng C J Mech Eng Sci2025; 239(3): 1021–1031.
6.
XuWZhangJLiH. Compound fault diagnosis of hydraulic system based on sample screening and joint analysis with pressure sensors pairs. Adv Eng Inform2025; 68: 103621.
7.
JiangRYuanZWangH, et al. MCFPred: a novel multichannel signal adaptive fusion framework for fault diagnosis in hydraulic systems. IEEE Trans Instrum Meas2025; 74: 1–13.
8.
GuanHRenYTangH, et al. Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects. Meas Sci Technol2024; 35(8): 082001.
9.
ChenSZhengXWuH. A multi-rate sensor fusion and multi-task learning network for concurrent fault diagnosis of hydraulic systems. Digit Signal Process2025; 156: 104796.
10.
FeiSZhangJ. Fault diagnosis of rolling bearings based on variational mode decomposition and fractional synchroextracting transform. Proc Inst Mech Eng C J Mech Eng Sci2025; 239(16): 6677–6693.
11.
JiangRYuanZWangH, et al. Intelligent fault diagnosis of hydraulic systems based on multisensor fusion and deep learning. IEEE Trans Instrum Meas2024; 73: 3526515–15.
12.
LiuQLiM. Research on hydraulic system fault diagnosis method based on machine learning. Eng Res Express2025; 7(1): 015401.
13.
ZhongQXuEShiY, et al. Fault diagnosis of the hydraulic valve using a novel semi-supervised learning method based on multi-sensor information fusion. Mech Syst Signal Process2023; 189: 110795.
14.
GuanXYuHYiX. Optimized methods for basic probability assignments in evidence theory: applications to fault diagnosis. Eng Appl Artif Intell2025; 160: 111737.
15.
VenkatachalamYSubbaiyanT. Intelligent fault diagnosis in power systems: a comparative analysis of machine learning-based algorithms. Expert Syst Appl2025; 265: 125945.
16.
HelwigNPignanelliESchuetzeA. Condition monitoring of a complex hydraulic system using multivariate statistics. In: 2015 IEEE International instrumentation and measurement technology conference(I2MTC)Proceeding, Pisa, Italy, 2015, pp.210–215. IEEE.
17.
FuYCaiLZhengG. Failure diagnosis of electro-hydraulic servo valve based on SA-PSO-SVM. J Mech Sci Technol2022; 36(12): 5971–5976.
18.
YinHWangYSunW, et al. Fault diagnosis of hydraulic system based on D-S evidence theory and SVM. Int J Hydromechatronics2024; 7(1): 1–15.
19.
LeiYYangBJiangX, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
20.
ChenXLiuHNikitasN. Internal pump leakage detection of the hydraulic systems with highly incomplete flow data. Adv Eng Inform2023; 56: 101974.
21.
QiuZLiWTangT, et al. Denoising graph neural network based hydraulic component fault diagnosis method. Mech Syst Signal Process2023; 204: 110828.
22.
FuSZouLWangY, et al. DCSIAN: a novel deep cross-scale interactive attention network for fault diagnosis of aviation hydraulic pumps and generalizable applications. Reliab Eng Syst Saf2024; 249: 110246.
23.
ChaoQLuSLiuC, et al. Unsupervised learning to detect wear faults in axial piston pumps by the similarity of periodic discharge pressure ripples. Proc Inst Mech Eng C J Mech Eng Sci2024; 238(18): 9278–9292.
24.
HanTWangXGuoJ, et al. Health-aware joint learning of scale distribution and compact representation for unsupervised anomaly detection in photovoltaic systems. IEEE Trans Instrum Meas2025; 74: 1–11.
25.
ZhangXYanSWangC, et al. Generalizable fault diagnosis under distribution shifts induced by unseen working conditions via synthetic and adversarial sample learning. IEEE Trans Reliab2025; 74(4): 5517–5530.
26.
ShiJRenYYiJ, et al. A new multisensor information fusion technique using processed images: algorithms and application on hydraulic components. IEEE Trans Instrum Meas2022; 71: 1–12.
27.
DaoFZengYQianJ. Fault diagnosis of hydro-turbine via the incorporation of Bayesian algorithm optimized CNN-LSTM neural network. Energy2024; 290: 130326.
28.
LiTQiaoZKumarA, et al. A hydraulic motor fault diagnosis method based on weighted multi-channel information fusion. Meas Sci Technol2025; 36(1): 015120.
29.
WangJXuHLiuJ, et al. A bagging-strategy based heterogeneous ensemble deep neural networks approach for the multiple components fault diagnosis of hydraulic systems. Meas Sci Technol2023; 34(6): 065007.
30.
LiuYLiWLinS, et al. Hydraulic system fault diagnosis of the chain jacks based on multi-source data fusion. Measurement2023; 217: 113116.
31.
HuangKWuSLiF, et al. Fault diagnosis of hydraulic systems based on deep learning model with multirate data samples. IEEE Trans Neural Netw Learn Syst2022; 33(11): 6789–6801.
32.
LiuHYanSHuangM, et al. A fault diagnosis method for hydraulic system based on multi-branch neural networks. Eng Appl Artif Intell2024; 137: 109188.
33.
LiangNZhangFYuanZ, et al. Fault diagnosis in hydraulic systems via multi-channel multi-modal fusion. Meas Sci Technol2025; 36(5): 055023.
34.
ZhangWYWeiZWWangBH, et al. Measuring mixing patterns in complex networks by Spearman rank correlation coefficient. Physica A2016; 451: 440–450.
35.
LeaCFlynnMDVLidalR, et al. Temporal convolutional networks for action segmentation and detection. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), Honolulu, HI, USA, 2017, pp. 1003–1012.
36.
LiJDingWMaoW, et al. Causal dilated convolution-based residual dense net with channel attention for RUL prediction of rolling bearings. Measurement2024; 235: 115012.
37.
JiaCHeHZhouJ, et al. A performance degradation prediction model for PEMFC based on bi-directional long short-term memory and multi-head self-attention mechanism. Int J Hydrogen Energy2024; 60: 133–146.
38.
WangQWuBZhuP, et al. ECA-Net: efficient channel attention for deep convolutional neural networks. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Seattle, WA, USA, 2020, pp. 11531–11539.
