A Lightweight Class-Incremental Learning Framework with Feature Calibration for Bearing Fault Diagnosis
Electronics · 22.07.2026 · 15 (14) · 3225
DOI: 10.3390/electronics15143225 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 22.07.2026. Verfasst von Hanbo Zhang und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
With the rapid development of the Industrial Internet of Things, data-driven deep learning has achieved remarkable success in bearing fault diagnosis. However, traditional static models suffer from catastrophic forgetting when facing continuously emerging fault categories and limited edge storage. Existing class-incremental learning frameworks expose critical limitations when applied to 1D vibration signals on micro edge devices, including feature space oscillation, difficulty in anchoring lightweight classifiers, and prototype drift over long incremental cycles. To address these challenges, this paper proposes a novel end-to-end class-incremental fault diagnosis method based on lightweighting and feature calibration tailored for severe memory-constrained conditions. Specifically, a lightweight feature extraction mechanism based on an L2 constraint is introduced to replace computationally expensive similarity distillation, effectively suppressing feature space oscillations and providing stable spatial coordinates for old knowledge. Moreover, a mandatory balanced center–margin hybrid replay (CAHM) strategy is designed to balance class representation while proportionally retaining class center prototypes and marginal hard examples, balancing the anchor accuracy of the Nearest Class Mean (NCM) classifier and the discriminability of the decision boundary. Furthermore, an ultra-low-cost linear prototype calibration module is constructed using a learnable affine transformation to actively redirect shifted old class prototypes with negligible inference latency. Extensive long-tail incremental experiments on the CWRU bearing dataset demonstrate that the proposed method forms a highly synergistic anti-forgetting closed loop. Under an extremely limited memory budget (K=40), the proposed framework achieves an outstanding final average accuracy of 98.92% after five incremental stages, significantly outperforming mainstream baselines such as iCaRL, PRIL, and SCKD and exhibiting exceptional robustness for continuous online monitoring on industrial edge devices.
Zitieren
APA
Zhang, H., & Huang, J. (2026). A Lightweight Class-Incremental Learning Framework with Feature Calibration for Bearing Fault Diagnosis. Electronics, 15(14), 3225. https://doi.org/10.3390/electronics15143225
Vancouver
Zhang H, Huang J. A Lightweight Class-Incremental Learning Framework with Feature Calibration for Bearing Fault Diagnosis. Electronics. 2026;15(14):3225. doi:10.3390/electronics15143225
BibTeX
@article{Zhang2026,
author = {Zhang, Hanbo and Huang, Jing},
title = {A Lightweight Class-Incremental Learning Framework with Feature Calibration for Bearing Fault Diagnosis},
journal = {Electronics},
year = {2026},
volume = {15},
number = {14},
pages = {3225},
doi = {10.3390/electronics15143225}
}
EUVIMED