EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism

Changjian Wen iD, Xiaoyu Li, Haipeng Su, Zhipeng Sun, Jian Miao, Juan Lu iD

Sensors · 29.10.2026 · 26 (21) · 6829

DOI: 10.3390/s26216829 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.10.2026. Verfasst von Changjian Wen und 5 weiteren Autor:innen. Beteiligte Einrichtung: Guangxi Key Laboratory of Ocean Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, China. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangxi, China, Guangxi Graduate Education Innovation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable tool condition monitoring under high-noise and different milling conditions requires robust signal preprocessing and adaptive feature extraction. This study proposes a tool wear prediction framework that integrates Adaptive Variational Mode Decomposition (AVMD) with a two-stage Convolutional Block Attention Module (CBAM). AVMD uses signal spectral features to guide a directed search for decomposition parameters, reducing reliance on manually specified settings. The reference architecture processes reconstructed multi-sensor signals through multiscale convolution and a DenseNet–BiLSTM network, with two CBAM stages for feature recalibration. The first CBAM follows multiscale convolution and precedes DenseNet, while the second follows BiLSTM. Using the selected configurations, within-tool evaluations achieve R2 values of 0.9399–0.9573 on TC18 titanium-alloy milling data and 0.9907–0.9929 on the public PHM 2010 dataset. Exploratory cross-tool evaluations on PHM 2010 yield R2 values of 0.8954–0.9599 under fixed cutting conditions. t-distributed stochastic neighbor embedding and Shapley additive explanations are used to visualize feature representations and assess feature contributions to model predictions. The results demonstrate the potential of the framework for multi-sensor tool wear estimation in the evaluated machining scenarios.

Schlagwörter

Stichwörter der Autor:innen

adaptive variational mode decompositionattention mechanismmulti-sensor data fusiontool condition monitoringtool wear prediction

Autor:innen und Institutionen

  • Guangxi Key Laboratory of Ocean Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, China.

ORCID-Profile: Changjian Wen, Juan Lu

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangxi, China
  • Guangxi Graduate Education Innovation Project

Zitieren

APA

Wen, C., Li, X., Su, H., Sun, Z., Miao, J., & Lu, J. (2026). A Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism. Sensors, 26(21), 6829. https://doi.org/10.3390/s26216829

Vancouver

Wen C, Li X, Su H, Sun Z, Miao J, Lu J. A Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism. Sensors. 2026;26(21):6829. doi:10.3390/s26216829

BibTeX
@article{Wen2026,
  author = {Wen, Changjian and Li, Xiaoyu and Su, Haipeng and Sun, Zhipeng and Miao, Jian and Lu, Juan},
  title = {A Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6829},
  doi = {10.3390/s26216829}
}
Kostenlos starten →