EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Physics Monotone Score Transport for Unsupervised Domain Adaptation of Continuous Tool Wear Prediction

Enhao Cui, Runshan Hu, Weina Zhang, Zihan Fei, Chenyang Zhu iD

Sensors · 18.06.2026 · 26 (12) · 3873

DOI: 10.3390/s26123873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 18.06.2026. Verfasst von Enhao Cui und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou 213164, China. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intelligent Manufacturing Longcheng Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-material continuous tool wear prediction is difficult because a model must preserve the physical wear scale, not only align high-dimensional sensor features. This limitation is critical in milling, where the target variable is the continuous flank wear width (VB) and material shift can distort the mapping from sensor response to wear magnitude. We address this problem by recasting cross-domain tool wear prediction as monotone wear-scale adaptation. We propose Multi-Physics Monotone Score Transport (MPMST), a monotone score transport framework that constructs a tool-wear-oriented score from sensor-derived candidate cues, transports the target-domain score onto the source-domain wear scale, and then predicts wear through isotonic regression. We also evaluate One-Physics Monotone Score Transport (OPMST), a force-only variant that uses the same score-transport pipeline with a restricted cue family. On Mondragon Unibertsitatea–Tool Condition Monitoring (MU-TCM) with two cross-material transfer tasks, the validation-driven MPMST configuration reduces mean absolute error by approximately 63% relative to Correlation Alignment (CORAL) and by approximately 31% relative to a physics-informed Gaussian process baseline. The results support monotone score construction and score transport as practical mechanisms for continuous tool wear prediction under domain shift, while also showing that MU-TCM is strongly force dominated.

Schlagwörter

Stichwörter der Autor:innen

intelligent manufacturingregression adaptationtool wear predictionunsupervised domain adaptation

Autor:innen und Institutionen

  • School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou 213164, China.
  • School of Computer Engineering, Jimei University, Xiamen 361021, China.
  • Department of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, UK.

ORCID-Profile: Chenyang Zhu

Förderung

  • Intelligent Manufacturing Longcheng Laboratory

Zitieren

APA

Cui, E., Hu, R., Zhang, W., Fei, Z., & Zhu, C. (2026). Multi-Physics Monotone Score Transport for Unsupervised Domain Adaptation of Continuous Tool Wear Prediction. Sensors, 26(12), 3873. https://doi.org/10.3390/s26123873

Vancouver

Cui E, Hu R, Zhang W, Fei Z, Zhu C. Multi-Physics Monotone Score Transport for Unsupervised Domain Adaptation of Continuous Tool Wear Prediction. Sensors. 2026;26(12):3873. doi:10.3390/s26123873

BibTeX
@article{Cui2026,
  author = {Cui, Enhao and Hu, Runshan and Zhang, Weina and Fei, Zihan and Zhu, Chenyang},
  title = {Multi-Physics Monotone Score Transport for Unsupervised Domain Adaptation of Continuous Tool Wear Prediction},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3873},
  doi = {10.3390/s26123873}
}
Kostenlos starten →