The representation of minority-class samples is enhanced by a multichannel fusion framework, where discriminative features are extracted from multidimensional signals to mitigate class imbalance in bearing fault diagnosis. However, the application of multichannel feature fusion in real-world engineering systems is hindered by two factors: temporal-spatial misalignment between heterogeneous sensor data streams and feature space deterioration due to overlapping channel information of minority-class samples. To overcome these challenges, an entropy-guided spatial pyramid Kolmogorov–Arnold residual network (ESPKARN) is proposed. Initially, the application of spatial pyramid pooling (SPP) is innovatively broadened to capture the physical spatial relationships within multichannel data, resolving the problem of spatial semantics loss in time-series data. Subsequently, a novel residual module, augmented with the Kolmogorov–Arnold Network, is introduced to refine feature fusion further. The fused features are then subjected to residual learning and nonlinear mapping mechanisms to optimize the overall feature representation. Finally, a uniquely multichannel framework is proposed, complexity analysis using multiscale sample entropy, multiscale spatial fusion via SPP, and nonlinear optimization within Kolmogorov–Arnold enhanced Residual. ESPKARN is extensively evaluated using two sets of multichannel bearing data featuring varying imbalance ratios. In a severe class-imbalance scenario where healthy data samples are 35 times more numerous than each fault class, the proposed method achieves accuracy rates of 99.80% and 88.62%, respectively, outperforming other fault diagnosis approaches.
LiaoWWuLXuS, et al. A novel approach for intelligent fault diagnosis in bearing with imbalanced data based on cycle-consistent GAN. IEEE Trans Instrum Meas2024; 73: 1–16.
2.
ZhaoDShaoDWangT, et al. Time-frequency self-similarity enhancement network and its application in wind turbines fault analysis. Adv Eng Inform2025; 65: 103322
3.
HeDZhangZJinZ, et al. RTSMFFDE-HKRR: a fault diagnosis method for train bearing in noise environment. Measurement2025; 239: 115417.
4.
WangZYuXGuoY, et al. A noise-enhanced feature extraction method combined with tunable Q-factor wavelet transform and its application to planet-bearing fault diagnosis. Appl Acoust2025; 239: 110845.
5.
ZhaoDShaoDCuiL. CTNet: a data-driven time-frequency technique for wind turbines fault diagnosis under time-varying speeds. ISA Trans2024; 154: 335–351
ZhuZLeiYQiG, et al. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement2023; 206: 112346.
8.
HeDWuJJinZ, et al. AGFCN: a bearing fault diagnosis method for high-speed train bogie under complex working conditions. Reliab Eng Syst Safety2025; 258: 110907.
ChenZWuJDengC, et al. Residual deep subdomain adaptation network: a new method for intelligent fault diagnosis of bearings across multiple domains. Mech Machine Theory2022; 169: 104635.
11.
LeiYJiaFKongD, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era. J Mech Eng2018; 54(5): 94.
12.
ZhangTChenJLiF, et al. Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Trans2022; 119: 152–171.
13.
RenZLinTFengK, et al. A systematic review on imbalanced learning methods in intelligent fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1.
14.
TianJJiangYZhangJ, et al. A novel data augmentation approach to fault diagnosis with class-imbalance problem. Reliab Eng Syst Safety2024; 243: 109832.
15.
ChenHLiCYangW, et al. Deep balanced cascade forest: an novel fault diagnosis method for data imbalance. ISA Trans2022; 126: 428–439.
16.
LiuDZhongSLinL, et al. Feature-level SMOTE: augmenting fault samples in learnable feature space for imbalanced fault diagnosis of gas turbines. Expert Syst Appl2024; 238: 122023.
17.
ZhouPWuDXuJ, et al. Fault diagnosis method for rolling bearing based on probabilistic diffusion models under imbalanced data. IEEE Sens J2024; 24(23): 40059–40068.
18.
WangQWangKLiQ, et al. MBNN: a multi-branch neural network capable of utilizing industrial sample unbalance for fast inference. IEEE Sens J2021; 21(2): 1809–1819.
19.
QianMLiY-F.A weakly supervised learning-based oversampling framework for class-imbalanced fault diagnosis. IEEE Trans Rel2022; 71(1): 429–442.
20.
ZhaoYYangXHuangJ, et al. Improved weighted extreme learning machine with adaptive cost-sensitive strategy for imbalanced fault diagnosis of rotating machinery. Mech Syst Signal Process2024; 217: 111526.
21.
YuYGuoLGaoH, et al. PCWGAN-GP: a new method for imbalanced fault diagnosis of machines. IEEE Trans Instrum Meas2022; 71: 1–11
22.
YuHLiuWGuY, et al. TEM-SDRF: a novel approach for machinery fault diagnosis amid dual imbalances in fault and noise samples. IEEE Sens J2024; 24(14): 22259–22270.
23.
CuiLDongZXuH, et al. Triplet attention-enhanced residual tree-inspired decision network: a hierarchical fault diagnosis model for unbalanced bearing datasets. Adv Eng Inform2024; 59: 102322.
24.
DongZJiangYJiaoW, et al. Double attention-guided tree-inspired grade decision network: a method for bearing fault diagnosis of unbalanced samples under strong noise conditions. Adv Eng Inform2025; 64: 103004.
25.
YaoPWangJZhangF, et al. Intelligent rolling bearing imbalanced fault diagnosis based on Mel-frequency cepstrum coefficient and convolutional neural networks. Measurement2022; 205: 112143.
26.
PrawinJ.Deep learning neural networks with input processing for vibration-based bearing fault diagnosis under imbalanced data conditions. Struct Health Monit2025; 24(2): 883–908.
27.
XuKLiSMiaoX, et al. Interpretable Siamese dual attention enhancement transfer compound diagnostic model for unbalanced samples. Struct Health Monit2025; 24(1): 54–74.
28.
WangJZhangWZhouJ.Fault detection with data imbalance conditions based on the improved bilayer convolutional neural network. Ind Eng Chem Res2020; 59(13): 5891–5904.
29.
HuangFZhangKZhangY, et al. A rolling bearing fault diagnosis method based on interactive generative feature space oversampling-based autoencoder under imbalanced data. Struct Health Monit2024; 24: 979–997.
30.
WangBQiuWHuX, et al. A rolling bearing fault diagnosis technique based on fined-grained multi-scale symbolic entropy and whale optimization algorithm-MSVM. Nonlinear Dyn2024; 112(6): 4209–4225.
31.
WangZChenHYaoL, et al. An effective multi-channel fault diagnosis approach for rotating machinery based on multivariate generalized refined composite multi-scale sample entropy. Nonlinear Dyn2021; 106(3): 2107–2130.
32.
CostaMGoldbergerALPengC-K.Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett2002; 89(6): 068102.
33.
WuCLouYWangL, et al. SPP-CNN: an efficient framework for network robustness prediction. IEEE Trans Circuits Syst I2023; 70(10): 4067–4079.
34.
LinDJiaoWDongZ, et al. SPRout-DBN: a cross domain bearing fault diagnosis method based on spatial pyramid pooling residual network-DBN. Meas Sci Technol2024; 35(2): 125020.
35.
GirosiFPoggioT.Representation properties of networks: Kolmogorov’s theorem is irrelevant. Neural Comput1989; 1(4): 465–469.
ShaoSBaldiP.Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inform2019; 15(4): 2446–2455.
38.
DagaAPFasanaAMarchesielloS, et al. The Politecnico di Torino rolling bearing test rig: description and analysis of open access data. Mech Syst Signal Process2019; 120: 252–273.
39.
MaXWangYQinJ, et al. A bearing fault diagnosis model with convolutional cross transformer and ResNet18. Meas Sci Technol2024; 6(1): 016132.
40.
ZhaoZLiTWuJ, et al. Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study. ISA Trans2020; 107: 224–255.
41.
LiTZhaoZSunC, et al. Multireceptive field graph convolutional networks for machine fault diagnosis. IEEE Trans Ind Electron2021; 68(12): 12739–12749.
