EUVIMEDEUVIMED entdecken
Crossref

Physics-informed Gaussian process for tool wear prediction

Kunpeng Zhu, Chengyi Huang, Si Li, Xin Lin

ISA Transactions · 2023-12 · 143 · 548-556

DOI: 10.1016/j.isatra.2023.09.007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2023-12. Verfasst von Kunpeng Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Precision Manufacturing, School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan 430081, China; Institute …. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Ministry of Science and Technology of the People's Republic of China, National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The tool wear monitoring (TWM) system plays an increasingly important role to ensure high quality finishing and system safety in advanced CNC machining process. The pure data-based TWM approaches generally needs to develop complex machine learning models and require massive sensory data to learn the models to reach high monitoring accuracy, while the physics-based tool wear models are simple but hard to adapt to varied working conditions. In order to incorporate the benefits of both methods, a novel physics-informed Gaussian process model is developed to predict the tool wear. Different from the traditional approaches, three tool wear physical models are introduced to develop the physics-informed Gaussian process regression (PB-GPR) model. The wear model is applied to constrain the mean function of the Gaussian process, so that the PB-GPR is more in line with the actual tool wear. At the same time, the model can initiate small data training to meet limited tool wear labels in practice, and then update the model with new measurements. Multi-sensor signals are collected and multi-domain features are extracted for the model learning. The proposed approach is validated from high speed milling experiments. The results show a significant performance improvement including tool wear prediction accuracy and robustness in extrapolation compared to the conventional machine learning methods.

Schlagwörter

Stichwörter der Autor:innen

Extrapolation predictionGaussian processPhysical modelTool condition monitoring

Autor:innen und Institutionen

  • Institute of Precision Manufacturing, School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan 430081, China; Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese…
  • Institute of Intelligent Machines, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Changzhou 213164, China. Electronic address: hcy95@mail.ustc.edu.cn.
  • Institute of Precision Manufacturing, School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan 430081, China. Electronic address: sili@wust.edu.cn.
  • Institute of Precision Manufacturing, School of Machinery and Automation, Wuhan University of Science and Technology, Wuhan 430081, China. Electronic address: xinlin@wust.edu.cn.

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Zhu, K., Huang, C., Li, S., & Lin, X. (2023). Physics-informed Gaussian process for tool wear prediction. ISA Transactions, 143, 548-556. https://doi.org/10.1016/j.isatra.2023.09.007

Vancouver

Zhu K, Huang C, Li S, Lin X. Physics-informed Gaussian process for tool wear prediction. ISA Transactions. 2023;143:548-556. doi:10.1016/j.isatra.2023.09.007

BibTeX
@article{Zhu2023,
  author = {Zhu, Kunpeng and Huang, Chengyi and Li, Si and Lin, Xin},
  title = {Physics-informed Gaussian process for tool wear prediction},
  journal = {ISA Transactions},
  year = {2023},
  volume = {143},
  pages = {548--556},
  doi = {10.1016/j.isatra.2023.09.007}
}
Kostenlos starten →