In industrial settings, it is important to diagnose new faults from the updated data stream. The model that learns incrementally by taking in new data can meet this requirement. However, the problems of time-consuming iterative updates and catastrophic forgetting in traditional incremental learning methods greatly reduce the diagnostic efficiency. To solve these problems, this paper introduces a replay-free evolutionary classifier (RFEC) architecture. The core of this strategy is to optimize the classification decision process by reconstructing the association between classification weights and feature vectors, with effective constraints on the objective function. Also, a nonparametric prototype classifier is introduced to ensure timely online fault diagnosis. This classifier uses classification prototypes and initial weights to allow quick updates during later incremental phases. The experimental results of the wind turbine simulation experimental platform show that RFEC has better accuracy and real-time update efficiency than other popular incremental learning methods. Specifically, it achieves an average accuracy of 90.57% and a dramatically reduced total training time of approximately 0.06 seconds during the incremental update stage.
LiXWangYYaoJ, et al. Multi-sensor fusion fault diagnosis method of wind turbine bearing based on adaptive convergent viewable neural network. Reliab Eng Syst Saf2024; 245: 109980.
2.
HeZLiuQShaoH, et al. Uncertainty NVAE-SVDD based on monte carlo dropout for trustworthy detection of mechanical failures. IEEE Trans Reliab2025; 74(4): 5544–5553.
3.
JiangFLinWZhangS, et al. Enhanced domain transfer deep fuzzy echo state network for rotating machinery fault diagnosis based on current signal. Appl Soft Comput2024; 165: 112033.
4.
WangCYangJJieH, et al. An uncertainty perception metric network for machinery fault diagnosis under limited noisy source domain and scarce noisy unknown domain. Adv Eng Inform2024; 62: 102682.
5.
TangHTangYSuY, et al. Feature extraction of multi-sensors for early bearing fault diagnosis using deep learning based on minimum unscented Kalman filter. Eng Appl Artif Intell2024; 127: 107138.
6.
HeZShenCChenB, et al. A new feature boosting based continual learning method for bearing fault diagnosis with incremental fault types. Adv Eng Inform2024; 61: 102469.
7.
ZhouZSuZJiangW, et al. Distribution character-guided projection replay network for class-incremental fault diagnosis of rotating machinery. IEEE Sens J2024; 24(8): 13656–13665.
8.
ZhuJWangYHuangCG, et al. A new incremental learning for bearing fault diagnosis under noisy conditions using classification and feature-level information. IEEE Trans Instrum Meas2024; 73: 1–14.
9.
ZhangYHanDShiP.Semi-supervised prototype network based on compact-uniform-sparse representation for rotating machinery few-shot class incremental fault diagnosis. Expert Syst Appl2024; 255: 124660.
10.
YouZChuJLiZ, et al. Adaptive federated class-incremental learning for reducing catastrophic forgetting. Expert Syst Appl2025; 291: 128442.
11.
DoanH-GLuongH-QHaT-O, et al. An efficient strategy for catastrophic forgetting reduction in incremental learning. Electronics2023; 12: 2265.
12.
SingampalliAGufranDPasrichaS.CIELO: class-incremental continual learning for overcoming catastrophic forgetting with smartphone-based indoor localization. IEEE Access2025; 13: 3561103.
13.
CaiQLiPZhaoZ, et al. Dynamic electricity theft behavior analysis based on active learning and incremental learning in new power systems. Int J Electr Power Energy Syst2024; 162: 110309.
14.
YinLXiongY.Incremental learning user profile and deep reinforcement learning for managing building energy in heating water. Energy2024; 313: 133705.
15.
DingAQinYWangB, et al. Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systems. Mech Syst Signal Process2024; 210: 111175.
16.
GharounHMomenifarFChenF, et al. Meta-learning approaches for few-shot learning: a survey of recent advances. ACM Comput Surv2024; 56(12): 1–41.
17.
LiuZPengZ.Few-shot bearing fault diagnosis by semi-supervised meta-learning with graph convolutional neural network under variable working conditions. Measurement2025; 240: 115402.
18.
HeYHeDLaoZ, et al. Few-shot fault diagnosis of turnout switch machine based on flexible semi-supervised meta-learning network. Knowl Based Syst2024; 294: 111746.
19.
WuYChenJLeiX, et al. A novel fault diagnosis method of high-speed train based on few-shot learning. Entropy2024; 26(5): 428.
20.
LinCKongYHanQ, et al. An information fusion-based meta transfer learning method for few-shot fault diagnosis under varying operating conditions. Mech Syst Signal Process2024; 220: 111652.
21.
FanCZhangYMaH, et al. A novel metric-based model with the ability of zero-shot learning for intelligent fault diagnosis. Eng Appl Artif Intell2024; 129: 107605.
22.
ZhouDWCaiZWYeHJ, et al. Revisiting class-incremental learning with pre-trained models: generalizability and adaptivity are all you need. Int J Comput Vis2024; 133(3): 1012–1032.
23.
ZhangYDaiYLiJ.Incremental and sequence learning algorithms for weighted regularized extreme learning machines. Appl Intell2024; 54(7): 5859–5878.
24.
HuangWCChenCFHsuH. OVOR: oneprompt with virtual outlier regularization for rehearsal-free class-incremental learning. In: The Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria, 2024.
25.
LiYLiQWangH, et al. Towards efficient replay in federated incremental learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR 2024), Seattle, USA, 2024, pp. 12820–12829.
26.
ZhuKCaoYZhaiW, et al. Self-promoted prototype refinement for few-shot class-incremental learning. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR 2021), Virtual Conference, 2021, pp. 6801–6810.
27.
AkmelFMengFWuQ, et al. Class similarity weighted knowledge distillation for few shot incremental learning. Neurocomputing2024; 584: 127587.
28.
WenHPanLDaiY, et al. Class incremental learning with multi-teacher distillation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR 2024), Seattle, USA, 2024, pp. 28443–28452.
29.
TianSLiLLiW, et al. A survey on few-shot class-incremental learning. Neural Netw2024; 169: 307–324.
30.
RanHLiWLiL, et al. Learning optimal inter-class margin adaptively for few-shot class-incremental learning via neural collapse-based meta-learning. Inform Process Manag2024; 61(3): 103664.
31.
AlfatemiARahoutiMAminR, et al. Advancing ddos attack detection: a synergistic approach using deep residual neural networks and synthetic oversampling. arXiv:2401.03116, 2024.
