Skip to content

SagharShafaati/TriFuse-PdM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

TriFuse-PdM

Related Publication and Citation

The conference paper associated with this code is available at the following DOI: https://doi.org/10.1109/ICCKE68588.2025.11273807

If you find this repository useful for your research or practical work, please cite the paper as follows:

S. Shafaati and J. Mohammadzadeh, “TriFuse-PdM: High-Fidelity Machine Failure Prediction Using Hybrid Resampling and Model Calibration,” in 2025 15th International Conference on Computer and Knowledge Engineering (ICCKE), Mashhad, Iran, 2025, pp. 1–5, doi: 10.1109/ICCKE68588.2025.11273807.

Keywords: Predictive Maintenance (PdM), Machine Failure Prediction, Class Imbalance, Ensemble Learning, Random Forests, Hybrid Resampling (SMOTE–Tomek), Model Calibration, Uncertainty, SHAP Explainability.

A full accessible version of the paper, along with the presentation slides, is also available on my ResearchGate profile.

About

TriFuse-PdM is an interpretable, fusion-based predictive maintenance pipeline combining classical ML, deep learning, and SHAP explainability with advanced resampling and calibration for robust industrial failure prediction.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors