EUVIMEDEUVIMED entdecken
Crossref

Adaptive Network-Integrated Hierarchical Frozen Transfer Learning for Tool Condition Monitoring

Xing Shui, Yong Lv, Zhang Dang, Rui Yuan, Hongan Wu, Weihang Zhu

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 3515212-3515212

DOI: 10.1109/tim.2026.3697030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Xing Shui und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hubei Province Regional Innovation System Project, China Postdoctoral Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable tool condition monitoring (TCM) is critical to maintaining machining accuracy and operational efficiency in intelligent manufacturing. Yet, conventional methods often fail to capture the time-varying nature of milling signals and to remain robust under limited labeled data and varying operating conditions. Moreover, deep learning (DL)-based TCM models typically incur costly, inefficient hyperparameter tuning. To address these issues, this article proposes a CNN–BiLSTM framework whose hyperparameters are adaptively optimized by the sine–cosine strategy-based sparrow search algorithm (SCSSA) for few-shot TCM. The resulting model learns joint spatial–temporal dependencies directly from raw vibration signals, enabling accurate extraction of wear-related features. In addition, a hierarchical frozen transfer learning (HFTL) strategy is proposed to adapt the pretrained model to new domains with limited labeled data, thereby improving cross-dataset generalization. Experimental results on the PHM2010 dataset and a self-designed experimental dataset show that the proposed method delivers superior accuracy and robustness under few-shot and cross-dataset scenarios.

Förderung

  • National Natural Science Foundation of China
  • Hubei Province Regional Innovation System Project
  • China Postdoctoral Science Foundation
  • Hubei Provincial Natural Science Foundation

Zitieren

APA

Shui, X., Lv, Y., Dang, Z., Yuan, R., Wu, H., & Zhu, W. (2026). Adaptive Network-Integrated Hierarchical Frozen Transfer Learning for Tool Condition Monitoring. IEEE Transactions on Instrumentation and Measurement, 75, 3515212-3515212. https://doi.org/10.1109/tim.2026.3697030

Vancouver

Shui X, Lv Y, Dang Z, Yuan R, Wu H, Zhu W. Adaptive Network-Integrated Hierarchical Frozen Transfer Learning for Tool Condition Monitoring. IEEE Transactions on Instrumentation and Measurement. 2026;75:3515212-3515212. doi:10.1109/tim.2026.3697030

BibTeX
@article{Shui2026,
  author = {Shui, Xing and Lv, Yong and Dang, Zhang and Yuan, Rui and Wu, Hongan and Zhu, Weihang},
  title = {Adaptive Network-Integrated Hierarchical Frozen Transfer Learning for Tool Condition Monitoring},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {3515212--3515212},
  doi = {10.1109/tim.2026.3697030}
}
Kostenlos starten →