The internal structure of wind turbines is complex, and the intricate coupling effects between components during gearbox faults can introduce significant interference into the collected signals, greatly increasing the difficulty of fault diagnosis. To address the issue of low diagnostic accuracy caused by traditional methods relying on single sensors, this article proposes a multisource information fusion method for gearbox fault diagnosis in wind turbines. First, a DualStream-FuseNet (DSFN) model is designed, where the dual-branch structure enables fault feature extraction from vibration signals and stator current signals of the doubly fed induction generator. Subsequently, a weighted fusion strategy and attention mechanism are introduced to enhance the fault feature information. Experimental results show that the proposed method exhibits significant superiority in diagnostic accuracy, efficiency, and robustness. Finally, by analyzing the interpretability of the DSFN model, the article visually demonstrates the model’s ability to learn and represent fault features, revealing its feature extraction mechanism, and providing theoretical support for the application of multisource information fusion methods in industrial fault diagnosis.
XuXHuangXBianH, et al. Total process of fault diagnosis for wind turbine gearbox, from the perspective of combination with feature extraction and machine learning: a review. Energy AI2024; 15; 100318.
2.
InturiVBalajiSVGyanamP, et al. An integrated condition monitoring scheme for health state identification of a multi-stage gearbox through Hurst exponent estimates. Struct Health Monit2023; 22(1); 730–745.
3.
GuoZDuWLiuZ, et al. Few-shot sample multi-class incremental fault diagnosis for gearbox based on convolutional-attention fusion network. Expert Syst Appl2025; 264; 125918.
4.
GuBZhangHYueS, et al. Fault warning study of gearbox based on SOM-ASTGCN-BiLSTM and mutual diagnosis of same clustered wind turbines. Renew Energ2025; 251: 123442.
5.
JiangGJiaCNieS, et al. Multiview enhanced fault diagnosis for wind turbine gearbox bearings with fusion of vibration and current signals. Measurement2022; 196: 111159.
6.
YangHJiangXZhaoH, et al. Autocorrelation-based time synchronous averaging for condition monitoring of gearboxes in wind turbines. Measurement2025; 249: 116998.
7.
XiaoYShaoHFengM, et al. Towards trustworthy rotating machinery fault diagnosis via attention uncertainty in transformer. J Manuf Syst2023; 70: 186–201.
8.
ZhuYXieBWangA, et al. Fault diagnosis of wind turbine gearbox under limited labeled data through temporal predictive and similarity contrast learning embedded with self-attention mechanism. Expert Syst Appl2024; 245: 123080.
9.
ZhaoDHuangXWangT, et al. Generalized reassigning transform: algorithm and applications. Reliab Eng Syst Safe2025; 255: 110677.
10.
SanterPReinhardJSchindlerA, et al. Detection of localized bearing faults in PMSMs by means of envelope analysis and wavelet packet transform using motor speed and current signals. Mechatronics2025; 106: 103294.
11.
WanSZhaoXWangY, et al. A fault diagnosis method for variable speed gearbox bearing based on SET improved multi-source ridge line. Measurement2023; 214: 112758.
12.
ShiXLiSGuoH, et al. Stator current signatures diagnosis method of planetary gearbox. J Vib Meas Diagn2022; 42: 671–676.
13.
TongSFuZTongZ, et al. Fault diagnosis for gearboxes based on Fourier decomposition method and resonance demodulation. J Zhejiang Univ Sci A2023; 24: 404–418.
14.
WeiSHouBWangD, et al. Generalized difference mode decomposition for adaptively extracting fault components of rotating machinery under non-stationary conditions. J Sound Vib2025; 609: 119089.
15.
ImpraimakisM.Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification. Struct Health Monit2025; 24(3): 1752–1782.
16.
ZhaoDCaiWCuiL.Multi-perception graph convolutional tree-embedded network for aero-engine bearing health monitoring with unbalanced data. Reliab Eng Syst Safe2025; 257: 110888.
17.
FengLDingZYinY, et al. Scraper conveyor gearbox fault diagnosis based on multi-source heterogeneous data fusion. Measurement2025; 247: 116797.
18.
YangHWangZXuM, et al. Improved deep transfer learning and transmission error based method for gearbox fault diagnosis with limited test samples. Mech Syst Signal Process2025; 230: 112593.
19.
ShaoZJiangHZhangX, et al. PLL-WCAN: pseudo-label progressive learning guided wavelet class-aware adaptive network for gearbox cross-domain fault diagnosis. Mech Syst Signal Process2025; 230: 112624.
20.
YuYKarimiHRGelmanL, et al. MSIFT: a novel end-to-end mechanical fault diagnosis framework under limited & imbalanced data using multi-source information fusion. Expert Syst Appl2025; 274: 126947.
21.
ChoudharyAMishraRKFatimaS, et al. Multi-input CNN based vibro-acoustic fusion for accurate fault diagnosis of induction motor. Eng Appl Artif Intel2023; 120: 105872.
22.
TongJLiuCZhengJ, et al. Multi-sensor information fusion and coordinate attention-based fault diagnosis method and its interpretability research. Eng Appl Artif Intel2023; 124: 106614.
23.
SaleemNElmannaiHBourouisS, et al. Squeeze-and-excitation 3D convolutional attention recurrent network for end-to-end speech emotion recognition. Appl Soft Comput2024; 161: 111735.
24.
AhmadzadehMZahraiSMBitarafM.An integrated deep neural network model combining 1D CNN and LSTM for structural health monitoring utilizing multisensor time-series data. Struct Health Monit2025; 24(1): 447–465.
25.
SongYDuJLiS, et al. Multi-scale feature fusion convolutional neural networks for fault diagnosis of electromechanical actuator. Appl Sci2023; 13: 8689.
26.
KangJZhuXShenL, et al. Fault diagnosis of a wave energy converter gearbox based on an Adam optimized CNN-LSTM algorithm. Renew Energy2024; 231: 121022.
27.
CaoLGuoWLiJ, et al. 2024. Transformer and cross-attention-based multi-sensor in-situ monitoring of molten pool stability and part quality in laser powder bed fusion. Opt Laser Eng2024; 183: 108522.
28.
CaiCXuTRenJ, et al. Bearing fault diagnosis based on the Markov transition field and SE-IShufflenetV2 model. Struct Durab Health Monit2025; 19: 125–144.
29.
WangZShenJZhangX, et al. Gear fault diagnosis research based on GAF-TFR-2DCV with small sample size. Ain Shams Eng J2025; 16: 103344.
30.
WangSTianJLiangP, et al. Single and simultaneous fault diagnosis of gearbox via wavelet transform and improved deep residual network under imbalanced data. Eng Appl Artif Intel2024; 133: 108146.
31.
HaoYZhangCLuY, et al. A novel autoencoder modeling method for intelligent assessment of bearing health based on Short-Time Fourier Transform and ensemble strategy. Precis Eng2024; 85: 89–101.
32.
WuTGuoY. An end-to-end fault diagnosis method: dual-branch network feature fusion model combined with MSACNN and Bi-LSTM. In: 2024 IEEE international conference on automatic control and intelligent systems (I2CACIS), 29 June 2024, New Jersey, USA. pp. 53–58. IEEE.
33.
YeMYanXJiangD, et al. MIFDELN: a multi-sensor information fusion deep ensemble learning network for diagnosing bearing faults in noisy scenarios. Knowl Based Syst2024; 284: 111294.
34.
WangXMaoDLiX.Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement2021; 173: 108518.
35.
PanQBaoYLiH.Transfer learning-based data anomaly detection for structural health monitoring. Struct Health Monit2023; 22(5): 3077–3091.
