Ensemble Machine Learning Algorithms for Remaining Useful Life Prediction

DOI

10.2991/978-94-6239-813-9_21How to use a DOI?

Keywords

Predictive Maintenance; Remaining Useful Life; Ensemble Learning; Explainable AI; Wavelet Packet Decomposition

ABSTRACT

Accurate cutting-tool degradation prediction is essential for predictive maintenance in Industry 4.0. This paper presents an explainable ensemble framework for direct Remaining Useful Life (RUL) prediction using the NASA Milling Dataset. Wavelet Packet Decomposition (WPD), training-only feature selection and grouped cross-validation were combined to support robust model evaluation. Extra Trees, Gradient Boosting, XGBoost, LightGBM and CatBoost were evaluated alongside ensemble methods. The stacking ensemble achieved the best performance (R² = 0.898, mean absolute error (MAE) = 3.790 min, root mean square error (RMSE) = 5.443 min). SHapley Additive exPlanations (SHAP) analysis identified influential machining and wavelet-derived sensor features, improving model interpretability.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Richard Duffy
AU  - Sagar Nikam
PY  - 2026
DA  - 2026/10/29
TI  - Ensemble Machine Learning Algorithms for Remaining Useful Life Prediction
BT  - Proceedings of the  Global Symposium on Adaptive Manufacturing (GSAM 2026)
PB  - Atlantis Press
SP  - 61
EP  - 63
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-813-9_21
DO  - 10.2991/978-94-6239-813-9_21
ID  - Duffy2026
ER  -