Class labels are usually utilized as constraint information of class relationships between two samples, and diagnostic accuracy of rotating machinery faults can be improved with the assistance of class-relationship constraints. However, it is difficult to fully embed the discriminative information of class labels into fault features via the indirect use of labels in fault diagnosis, which limits further improvement in diagnostic accuracy. To solve the issue, we propose a multi-view rotating machinery fault diagnosis method called cross-view label-unified correlation space learning. In the method, we reconstruct feature attributes of the class labels as a view data, and the label view data possess essential discriminative information. By one label view and multiple fault views, we construct a cross-view label-unified correlation space optimization model, and the model maximizes the correlation between the label view and the other fault views, which can effectively embed the discriminative information of the label view into the other fault views in learned cross-view label-unified correlation space. Besides, we further derive the analytical solutions of the model in theory, and then the fault features with strong discriminative power can be directly obtained by space projection. Extensive experiment results on the Paderborn bearing dataset, the Case Western Reserve University bearing dataset, and our experimental platform show the effectiveness of our method.
YouKGuYShaoH, et al. A liquid-impulse neural network model based on heterogeneous fusion of multimodal information for interpretable rotating machinery fault diagnosis. Mech Syst Signal Process2026; 246: 113923. https://doi.org/10.1016/j.ymssp.2026.113923
2.
MianTKunduP. A comprehensive review on generative artificial intelligence models for fault diagnostics and prognostics of rotating machineries. Eng Appl Artif Intell2026; 166: 113594. https://doi.org/10.1016/j.engappai.2025.113594
3.
GuJYuanXLiX, et al. Bridging the subpopulation gap: a new paradigm for robust fault diagnosis in rotating machinery. IEEE Trans Ind Inform2026; 22: 3388–3399. https://doi.org/10.1109/TII.2025.3575130
4.
YangMZhangKTangH, et al. An adaptive feature extraction technique via bispectrum-driving graph domain for bearing fault diagnosis. ISA Trans2025; 167: 1828–1840. https://doi.org/10.1016/j.isatra.2025.09.020
5.
ZhouHZhengJPanH, et al. Step robust mode decomposition method and its application in rolling bearing fault diagnosis. ISA Trans2026; 173: 522–538. https://doi.org/10.1016/j.isatra.2026.02.014
6.
ZhengLZhaoXXuS, et al. Learning discriminative representations by a Canonical Correlation Analysis-based Siamese Network for offline signature verification. Eng Appl Artif Intell2025; 139: 109640. https://doi.org/10.1016/j.engappai.2024.109640
7.
WangCZhaoZLiL, et al. A distributed alternating optimization approach to canonical correlation analysis based fault detection for dynamic systems. ISA Trans2025. https://doi.org/10.1016/j.isatra.2025.12.030
8.
ZhangHZhaoHFuY, et al. The class labels and spatial information based fault diagnosis of air handling unit via combining kernel Fischer discriminant analysis with an improved graph convolutional neural network. Measurement2026; 257: 118622. https://doi.org/10.1016/j.measurement.2025.118622
9.
LinCKongYHanQ, et al. IF-EDAAN: an information fusion-enhanced domain adaptation attention network for unsupervised transfer fault diagnosis. Mech Syst Signal Process2025; 224: 112180. https://doi.org/10.1016/j.ymssp.2024.112180
10.
LiZWangF. A method of kernel principal component analysis and machine learning algorithms for fault diagnosis of power transformers. IEEE Trans Dielectr Electr Insul2025; 32(5): 3068–3077. https://doi.org/10.1109/TDEI.2025.3543337
11.
YuTJiangZRenZ, et al. A convolutional multisensor fusion fault diagnosis framework based on multidimensional distance matrix for rotating machinery. Struct Health Monit2026; 25(1): 468–483. https://doi.org/10.1177/14759217241296804
12.
LiuZWuYQuanH, et al. A non-Euclidean method for open-circuit fault diagnosis in back-to-back converters leveraging SPD manifold and mathematical morphological filtering. IEEE Trans Power Electron2026; 41: 11268–11283. https://doi.org/10.1109/TPEL.2026.3658883
13.
DongXDingHGaoD, et al. Multi-source fault data fusion diagnosis method based on hyper-feature space graph collaborative embedding. Adv Eng Inform2025; 64: 103092. https://doi.org/10.1016/j.aei.2024.103092
14.
ZhangYZhangYZhangY, et al. Multi-class data augmentation and fault diagnosis of wind turbine blades based on ISOMAP-CGAN under high-dimensional imbalanced samples. Renew Energy2025; 243: 122609. https://doi.org/10.1016/j.renene.2025.122609
15.
UllahAMengY. Finding influential nodes via graph embedding and hybrid centrality in complex networks. Chaos Soliton Fract2025; 194: 116151. https://doi.org/10.1016/j.chaos.2025.116151
PanHXuHZhengJ, et al. A semi-supervised matrixized graph embedding machine for roller bearing fault diagnosis under few-labeled samples. IEEE Trans Ind Inform2023; 20(1): 854–863. https://doi.org/10.1109/TII.2023.3265525
19.
XuHLvRZiB. MAFN: a multi-view adaptive fusion network with image and time-series signal aggregation for additive manufacturing fault diagnosis. Mech Syst Signal Process2026; 242: 113680. https://doi.org/10.1016/j.ymssp.2025.113680
20.
YuYKarimiHRGelmanL, et al. A novel multi-source sensor correlation adaptive fusion framework with uncertainty quantification for intelligent fault diagnosis. Reliab Eng Syst Saf2025; 267: 111812. https://doi.org/10.1016/j.ress.2025.111812
21.
SongBGuXShiH, et al. Quality-related fault detection based on reversible instance normalization temporal auto-encoder canonical correlation analysis. IEEE Trans Ind Inform2026; 22(4): 3517–3526. https://doi.org/10.1109/TII.2025.3645117
22.
ChenYLiangHYueL, et al. Elastic-Net regularized two-dimensional canonical correlation analysis for robust underwater sonar image classification. Signal Process2025; 239: 110272. https://doi.org/10.1016/j.sigpro.2025.110272
23.
DongLShaoHZhangL, et al. STCCA: spatial–temporal coupled cross-attention through hierarchical network for EEG-based speech recognition. Sensors2025; 25(21): 6541. https://doi.org/10.3390/s25216541
24.
DaiSZhangCGuoC, et al. Hierarchical fuzzy stochastic configuration network based on canonical correlation analysis for multi-view pulse signal fusion. IEEE Trans Fuzzy Syst2025; 33(8): 2779–2791. https://doi.org/10.1109/TFUZZ.2025.3576112
25.
PillalamarriRShanmugamU. A review on EEG-based multimodal learning for emotion recognition. Artif Intell Rev2025; 58(5): 131. https://doi.org/10.1007/s10462-025-11126-9
26.
WangAWangGJiaoJ, et al. Self-attention sliding window enhanced canonical correlation analysis for incipient fault detection in dynamic industrial processes. IEEE Trans Ind Inf2025; 21(10): 7412–7423. https://doi.org/10.1109/TII.2025.3575115
27.
YuanYHLiYShenXB, et al. Laplacian multiset canonical correlations for multiview feature extraction and image recognition. Multimed Tools Appl2017; 76(1): 731–755. https://doi.org/10.1007/s11042-015-3070-y
28.
TongZLiWZhangB, et al. Bearing fault diagnosis based on discriminant analysis using multi-view learning. Mathematics2022; 10(20): 3889. https://doi.org/10.3390/math10203889
29.
JiangGJiaCNieS, et al. Multiview enhanced fault diagnosis for wind turbine gearbox bearings with fusion of vibration and current signals. Measurement2022; 196: 111159. https://doi.org/10.1016/j.measurement.2022.111159.
30.
MastealiSHBayatMBettingerP, et al. Uncertainty analysis of linear and non-linear regression models in the modeling of water quality in the Caspian Sea basin: application of Monte-Carlo method. Ecol Indic2025; 170: 112979. https://doi.org/10.1016/j.ecolind.2024.112979
31.
DingF. Least squares parameter estimation and multi-innovation least squares methods for linear fitting problems from noisy data. J Comput Appl Math2023; 426: 115107. https://doi.org/10.1016/j.cam.2023.115107
32.
LiTSunCZhaoZ, et al. A Kolmogorov–Arnold-informed interpretable graph wavelet activation network for machine fault diagnosis. IEEE Trans Syst Man CY-S2026; 56(3): 1693–1705. https://doi.org/10.1109/TSMC.2025.3647102
