.::. Learning-Based Fault Detection and Diagnosis for District Heating .::.

This project's main objectives are to:

  • Leverage advanced machine learning for handling time series data.
  • Focus on scalable models, cross-domain adaptability, and robust performance even when fault data is scarce or imbalanced.

About

Our project (in collaboration with VITO -Belgium-) is all about building data-driven solutions for automatic fault detection and diagnosis (FDD) in district heating (DH) substations, built to handle real-world challenges.


View my other profiles »

Senaste publikationer

  1. van Dreven, J., Cheddad, A., Alawadi, S., Nauman, A.G, Al Koussa, J., Vanhoudt, D. “From Bearings to Substations: Transfer Learning for Fault Detection in District Heating,” Energy, vol. 335, 138016, 2025, Elsevier. https://doi.org/10.1016/j.energy.2025.138016
  2. van Dreven, J., Cheddad, A., Ghazi, A.N., Alawadi, S., Al Koussa, J., & Vanhoudt, D. “HEAT: Hierarchical-constrained Encoder-Assisted Time Series Clustering for Fault Detection in District Heating Substations,” Energy and AI, vol. 21, 100548, (2025), Elsevier. https://doi.org/10.1016/j.egyai.2025.100548
  3. Jonne van Dreven, Abbas Cheddad, Sadi Alawadi, Ahmad Nauman, Ghazi, Jad Al Koussa and Dirk Vanhoudt (2025). “From Data Scarcity to Diagnostic Precision: A Novel Data Augmentation and Fault Diagnosis Framework for District Heating Substations,” In Engineering Applications of Artificial Intelligence (Vol. 151). Elsevier BV. https://doi.org/10.1016/j.engappai.2025.110662
  4. Van Dreven, A. Cheddad, S. Alawadi, A. N. Ghazi, J. Al Koussa and D. Vanhoudt, “SHEDAD: SNN-Enhanced District Heating Anomaly Detection for Urban Substations,” 2024 9th International Conference on Fog and Mobile Edge Computing (FMEC), Malmö, Sweden, 2024, pp. 130-137, https://doi.org/10.1109/FMEC62297.2024.10710205