Adaptive NOx Emissions Forecasting for Gas Turbines via Dynamic PCA-Driven Clustering
2025 5th International Conference on AI-ML-Systems (AIMLSystems 2025), Bangalore, India, pages 290-298, IEEE
Presented on
In short
The paper proposes an adaptive framework for predicting NOx emissions from gas turbines that clusters incoming data with dynamic PCA, based on reconstruction error, and pairs the clusters with SVR, MLP and XGBoost regressors. On real turbine data the clustered approach coped with shifts in operating conditions better than baseline models.
Cite
@inproceedings{Zeinalipour_2025,
title={Adaptive NOX Emissions Forecasting for Gas Turbines via Dynamic PCA-Driven Clustering},
url={http://dx.doi.org/10.1109/AIMLSystems67835.2025.11331232},
DOI={10.1109/aimlsystems67835.2025.11331232},
booktitle={2025 5th International Conference on AI-ML-Systems (AIMLSystems)},
publisher={IEEE},
author={Zeinalipour, Kamyar and Barriere, Laure and Ghelardi, David and Gori, Marco},
year={2025},
month=Oct,
pages={290–298}
}