A multi-source data fusion anomaly detection method for new energy vehicle bearings based on electric drive-adaptive heterogeneous feature collaborative learning
Restricted accessResearch articleFirst published online 2026
A multi-source data fusion anomaly detection method for new energy vehicle bearings based on electric drive-adaptive heterogeneous feature collaborative learning
Bearings in new energy vehicles (NEVs) are critical components in drive systems, directly affecting vehicle safety, energy efficiency, and operational reliability. To address the challenges of incomplete single-source data and heterogeneous data fusion in NEV bearing health monitoring, this paper presents an Electric Drive-Adaptive Heterogeneous Feature Collaborative Learning Framework (ED-HFCLF). This framework is designed for NEV operating conditions, including electromagnetic interference, regenerative braking impacts, and wide-range speed variations. The framework employs a dual-stream architecture to separately process time-frequency spectrograms and multivariate time series. The image stream incorporates a ResNeXt-based multi-scale spatial feature extractor with electromagnetic noise suppression and a pyramid feature fusion module. The time-series stream utilizes a hierarchical LSTM encoder-decoder with a drive-cycle-aware mechanism. A cross-modal alignment mechanism with torque-compensation bridges semantic features across streams. A multi-task learning strategy jointly optimizes fault classification, severity estimation, and remaining useful life prediction. Experiments on the CWRU dataset and real vehicle data demonstrate 95.8% fault detection accuracy and 86.7% early fault detection rate, achieving better performance than existing deep models by 3.1% and 8.5%, respectively.
AcikgozHKorkmazDBudakU (2023) Photovoltaic cell defect classification based on integration of residual-inception network and spatial pyramid pooling in electroluminescence images. Expert Systems with Applications229: 120546. https://doi.org/10.1016/j.eswa.2023.120546
2.
AndrewGAroraRBilmesJ, et al. (2013) Deep canonical correlation analysis. In: Proceedings of the 30th International Conference on Machine Learning (ICML 2013), 16–21 June 2013, Atlanta, Georgia, USA. PMLR, pp. 1247–1255.
3.
AntoniJ (2007) Fast computation of the kurtogram for the detection of transient faults. Mechanical Systems and Signal Processing21(1): 108–124. https://doi.org/10.1016/j.ymssp.2005.12.002
BaltrušaitisTAhujaCMorencyLP (2018) Multimodal machine learning: a survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence41(2): 423–443.
6.
ChenZLiW (2017) Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network. IEEE Transactions on Instrumentation and Measurement66(7): 1693–1702. https://doi.org/10.1109/tim.2017.2669947
7.
ChenGLiuMChenJ (2020) Frequency-temporal-logic-based bearing fault diagnosis and fault interpretation using Bayesian optimization with Bayesian neural networks. Mechanical Systems and Signal Processing145: 106951. https://doi.org/10.1016/j.ymssp.2020.106951
8.
ChenLChenDShangZ, et al. (2023) Multi-scale adaptive graph neural network for multivariate time series forecasting. IEEE Transactions on Knowledge and Data Engineering35(10): 10748–10761. https://doi.org/10.1109/tkde.2023.3268199
9.
ChengLAnZGuoY, et al. (2023) MMFSL: a novel multimodal few-shot learning framework for fault diagnosis of industrial bearings. IEEE Transactions on Instrumentation and Measurement72: 1–13. https://doi.org/10.1109/tim.2023.3289549
10.
ChungJGulcehreCChoK, et al. (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. arXiv. https://arxiv.org/abs/1412.3555
11.
DingSHuSLiX, et al. (2021) Leveraging multimodal semantic fusion for gastric cancer screening via hierarchical attention mechanism. IEEE Transactions on Systems, Man, and Cybernetics: Systems52(7): 4286–4299. https://doi.org/10.1109/tsmc.2021.3096974
12.
FeichtenhoferZChengJLiuL, et al. (2022) Dual-stream cross-modality fusion transformer for RGB-D action recognition. Knowledge-Based Systems255: 109741. https://doi.org/10.1016/j.knosys.2022.109741
13.
FengZLiangMChuF (2013) Recent advances in time–frequency analysis methods for machinery fault diagnosis: a review with application examples. Mechanical Systems and Signal Processing38(1): 165–205. https://doi.org/10.1016/j.ymssp.2013.01.017
14.
FengFYangXYangR, et al. (2025) An insulator defect detection network combining bidirectional feature pyramid network and attention mechanism in unmanned aerial vehicle images. Engineering Applications of Artificial Intelligence152: 110745. https://doi.org/10.1016/j.engappai.2025.110745
15.
FuCZhengGHuangC, et al. (2023) Multiplex heterogeneous graph neural network with behavior pattern modeling. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), 6–10 August 2023, Long Beach, California, USA, pp. 482–494.
16.
HaoJLvYLiuJ, et al. (2025) Dynamic weighted multimodal fusion for fault diagnosis of marine rotating machinery under noisy and low-sample conditions. Ocean Engineering339: 122082. https://doi.org/10.1016/j.oceaneng.2025.122082
17.
HouBWangDWangY, et al. (2020) Adaptive weighted signal preprocessing technique for machine health monitoring. IEEE Transactions on Instrumentation and Measurement70: 1–11. https://doi.org/10.1109/tim.2020.3033471
18.
HouYWangJChenZ, et al. (2023) Diagnosisformer: an efficient rolling bearing fault diagnosis method based on improved Transformer. Engineering Applications of Artificial Intelligence124: 106507. https://doi.org/10.1016/j.engappai.2023.106507
19.
JiangZLiJ (2022) Recommendation models based on heterogeneous information networks and multi-task learning. Journal of Beijing University of Technology48(12): 1289–1297.
20.
JiangXWangJShiJ, et al. (2019) A coarse-to-fine decomposing strategy of VMD for extraction of weak repetitive transients in fault diagnosis of rotating machines. Mechanical Systems and Signal Processing116: 668–692. https://doi.org/10.1016/j.ymssp.2018.07.014
21.
LeiYYangBJiangX, et al. (2020) Applications of machine learning to machine fault diagnosis: a review and roadmap. Mechanical Systems and Signal Processing138: 106587. https://doi.org/10.1016/j.ymssp.2019.106587
22.
LiXZhangWDingQ (2018) A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning. Neurocomputing310: 77–95. https://doi.org/10.1016/j.neucom.2018.05.021
23.
LiFWangLWangD, et al. (2023) An adaptive multiscale fully convolutional network for bearing fault diagnosis under noisy environments. Measurement216: 112993. https://doi.org/10.1016/j.measurement.2023.112993
24.
LiYLuoXXieY, et al. (2023) Multi-head spatio-temporal attention based parallel GRU architecture: a novel multi-sensor fusion method for mechanical fault diagnosis. Measurement Science and Technology35(1): 015111. https://doi.org/10.1088/1361-6501/acfe29
25.
LiSJiJCXuY, et al. (2024) Dconformer: a denoising convolutional transformer with joint learning strategy for intelligent diagnosis of bearing faults. Mechanical Systems and Signal Processing210: 111142. https://doi.org/10.1016/j.ymssp.2024.111142
26.
LinTYDollarPGirshickR, et al. (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 21–26 July 2017, Honolulu, Hawaii, USA, pp. 2117–2125.
27.
LiuRYangBZioE, et al. (2018) Artificial intelligence for fault diagnosis of rotating machinery: a review. Mechanical Systems and Signal Processing108: 33–47. https://doi.org/10.1016/j.ymssp.2018.02.016
28.
LiuRHuPZhaoS, et al. (2024) Out-of-distribution fault diagnosis of industrial cyber-physical systems based on orthogonal anchor clustering with adaptive balance. IEEE Transactions on Industrial Cyber-PhysicalSystems. Epub ahead of print. https://doi.org/10.1109/TICPS.2024.10767395
29.
LyuJZhangYLuX, et al. (2024) Task diversity in Bayesian federated learning: simultaneous processing of classification and regression. arXiv preprint arXiv:2412.10897. arXiv. https://arxiv.org/abs/2412.10897
30.
MallatSG (2002) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence11(7): 674–693. https://doi.org/10.1109/34.192463
31.
MisraIShrivastavaAGuptaA, et al. (2016) Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 27–30 June 2016, Las Vegas, Nevada, USA, pp. 3994–4003.
32.
NathAShuklaSGuptaP (2025) MTMedFormer: Multi-task vision transformer for medical imaging with federated learning. Medical, & Biological Engineering & Computing63: 1–14. https://doi.org/10.1007/s11517-025-03404-z
33.
OtarbayZKyzyrkanovA (2025) SVM-enhanced attention mechanisms for motor imagery EEG classification in brain-computer interfaces. Frontiers in Neuroscience19: 1622847. https://doi.org/10.3389/fnins.2025.1622847
34.
PengYXiaFZhangC, et al. (2024) Deformation feature extraction and double attention feature pyramid network for bearing surface defects detection. IEEE Transactions on Industrial Informatics20(6): 9048–9058. https://doi.org/10.1109/tii.2024.3370330
35.
RahmanMMWatanobeYShirafujiA, et al. (2023) Exploring automated code evaluation systems and resources for code analysis: a comprehensive survey. arXiv preprint arXiv:2307.08705. arXiv. https://arxiv.org/abs/2307.08705
36.
SafizadehMSLatifiSK (2014) Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell. Information Fusion18: 1–8. https://doi.org/10.1016/j.inffus.2013.10.002
37.
ShangZChenLWuB, et al. (2024) Ada-MSHyper: adaptive multi-scale hypergraph transformer for time series forecasting. Advances in Neural Information Processing Systems37: 33310–33337.
38.
ShaoHJiangHZhangX, et al. (2015) Rolling bearing fault diagnosis using an optimization deep belief network. Measurement Science and Technology26(11): 115002. https://doi.org/10.1088/0957-0233/26/11/115002
39.
ShiLZhangYChengJ, et al. (2019) Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019), 16–20 June 2019, Long Beach, California, USA, pp. 12026–12035.
40.
SimonyanKZissermanA (2014) Two-stream convolutional networks for action recognition in videos. Advances in Neural Information Processing Systems27: 568–576.
41.
SongZJiaCYangL, et al. (2023) GraphAlign++: an accurate feature alignment by graph matching for multi-modal 3D object detection. IEEE Transactions on Circuits and Systems for Video Technology34(4): 2619–2632. https://doi.org/10.1109/tcsvt.2023.3306361
42.
SunJZhouFHuX, et al. (2025) Personalized federated learning for remaining useful life prediction under scenarios of fragmented out-of-distribution data. Reliability Engineering & System Safety261: 111094. Available at: https://doi.org/10.1016/j.ress.2025.111094
43.
TianRCuiMChenG (2024) A neural-symbolic network for interpretable fault diagnosis of rolling element bearings based on temporal logic. IEEE Transactions on Instrumentation and Measurement73: 1–14. https://doi.org/10.1109/tim.2024.3373103
44.
TongSHanYZhangX, et al. (2024) Uncertainty-weighted domain generalization for remaining useful life prediction of rolling bearings under unseen conditions. IEEE Sensors Journal24(7): 10933–10943. https://doi.org/10.1109/jsen.2024.3366689
45.
VaswaniAShazeerNParmarN, et al. (2017) Attention is all you need. Advances in Neural Information Processing Systems30: 1.
46.
WangBLeiYLiN, et al. (2018) A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Transactions on Reliability69(1): 401–412. https://doi.org/10.1109/tr.2018.2882682
47.
WangBZhangXWangS, et al. (2025a) Topology optimization of random memristors for input-aware dynamic SNN. Science Advances11(16): eads5340. Available at: https://doi.org/10.1126/sciadv.ads5340
48.
WangSYuanGLiJ (2025b) RTDU: interpretable region-aware transformer-based deep unfolding network for pan-sharpening. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. Epub ahead of print. https://doi.org/10.1109/JSTARS.2025.3567769
49.
WenLLiXGaoL, et al. (2017) A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics65(7): 5990–5998. https://doi.org/10.1109/tie.2017.2774777
50.
XiaMLiTXuL, et al. (2017) Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE23(1): 101–110. https://doi.org/10.1109/tmech.2017.2728371
51.
XiangCQinmingLJiaruiHU (2024) Bearing fault diagnosis and life prediction based on attention mechanism and long short-term memory network under multi-source sensor data. Information and Control53(2): 211–225.
52.
XuYFengKYanX, et al. (2023) Cross-modal fusion convolutional neural networks with online soft-label training strategy for mechanical fault diagnosis. IEEE Transactions on Industrial Informatics20(1): 73–84. https://doi.org/10.1109/tii.2023.3256400
53.
XuWTuJXuN, et al. (2024) Predicting daily heating energy consumption in residential buildings through integration of random forest model and meta-heuristic algorithms. Energy301: 131726. https://doi.org/10.1016/j.energy.2024.131726
54.
ZhangWPengGLiC, et al. (2017) A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors17(2): 425. https://doi.org/10.3390/s17020425
55.
ZhangWLiCPengG, et al. (2018) A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical Systems and Signal Processing100: 439–453.
56.
ZhaoRWangJYanR, et al. (2016) Machine health monitoring with LSTM networks. In: 2016 10th International Conference on Sensing Technology (ICST), 11–13 November 2016, Nanjing, China. IEEE, pp. 1–6.
57.
ZhaoRYanRWangJ, et al. (2017) Learning to monitor machine health with convolutional bi-directional LSTM networks. Sensors17(2): 273. https://doi.org/10.3390/s17020273
58.
ZhaoRYanRChenZ, et al. (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing115: 213–237. https://doi.org/10.1016/j.ymssp.2018.05.050
ZhouWHongJYanW, et al. (2023) Modal evaluation network via knowledge distillation for no-service rail surface defect detection. IEEE Transactions on Circuits and Systems for Video Technology34(5): 3930–3942.
