EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An IG-LSTM-Based Tool Wear Prediction Method for Cross-Operating-Condition Forecasting

Bo Sun, Jian Zhang, Xiangqin Wu, Lixin Zhang, Lanbo Wang, Chaoran Liu, Yuntao Wei

Sensors · 12.11.2026 · 26 (22) · 7158

DOI: 10.3390/s26227158 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.11.2026. Verfasst von Bo Sun und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Changchun University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tool wear directly affects the accuracy and reliability of machined workpieces; accurately predicting wear trends is crucial for developing reasonable tool-change strategies and avoiding sudden tool failure. Traditional parametric Inverse Gaussian (IG) processes can effectively characterize the non-negativity and stochastic fluctuations of incremental tool wear; however, the mean functions in such models often adopt an analytically defined power-law form that is arbitrarily preset, making it difficult to adapt to the nonlinear evolution patterns of tools at different stages. Consequently, their generalization capabilities are limited in cross-tool prediction scenarios. To address this, this paper proposes an IG-LSTM tool wear prediction method designed for cross-tool forecasting. First, Variational Mode Decomposition (VMD) is employed to extract the degradation trend of wear, and a Long Short-Term Memory (LSTM) neural network is trained based on this. Next, the trend predicted by the LSTM is used as the cumulative degradation function of the IG process to construct a degradation model for wear increment; simultaneously, the model parameters of the IG process are estimated via maximum likelihood estimation based on the training data. Finally, two sets of experiments—single-tool prediction and cross-tool prediction—were designed using the PHM2010 dataset. The experimental results show that, in both scenarios, the proposed method significantly outperforms traditional parametric inverse Gaussian models and purely data-driven LSTM models, achieving an organic integration of data-driven adaptive trend extraction and physics-driven stochastic degradation modeling.

Förderung

  • Changchun University

Zitieren

APA

Sun, B., Zhang, J., Wu, X., Zhang, L., Wang, L., Liu, C., & Wei, Y. (2026). An IG-LSTM-Based Tool Wear Prediction Method for Cross-Operating-Condition Forecasting. Sensors, 26(22), 7158. https://doi.org/10.3390/s26227158

Vancouver

Sun B, Zhang J, Wu X, Zhang L, Wang L, Liu C, et al. An IG-LSTM-Based Tool Wear Prediction Method for Cross-Operating-Condition Forecasting. Sensors. 2026;26(22):7158. doi:10.3390/s26227158

BibTeX
@article{Sun2026,
  author = {Sun, Bo and Zhang, Jian and Wu, Xiangqin and Zhang, Lixin and Wang, Lanbo and Liu, Chaoran and Wei, Yuntao},
  title = {An IG-LSTM-Based Tool Wear Prediction Method for Cross-Operating-Condition Forecasting},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {22},
  pages = {7158},
  doi = {10.3390/s26227158}
}
Kostenlos starten →