Development of a machine learning-based framework for predicting failures in heat supply networks
Darkenbayev D. Balakayeva G. Zhapbasbayev U. Zhanuzakov M.
December 2025Institute of Advanced Engineering and Science
Bulletin of Electrical Engineering and Informatics
2025#14Issue 64678 - 4685 pp.
The increasing complexity and scale of heat supply systems leads to a higher risk of failures, which may cause significant economic and environmental consequences. This study develops a predictive mathematical framework for the early detection of emergency conditions in heat supply networks (HSNs) using machine learning (ML). The proposed approach is based on the LightGBM gradient boosting (GB) algorithm, chosen for its high accuracy and efficiency in handling large datasets. Real operational data (temperature, pressure, flow, and vibration) were considered. Data preprocessing, feature engineering (including SHAP analysis), and hyperparameter tuning with grid search and 5-fold cross-validation improved prediction quality. The model achieved accuracy of 85%, F1-score of 0.82, and receiver operating characteristic (ROC)-area under the curve (AUC) of 0.96, outperforming logistic regression (LR) and decision trees. The framework may be integrated into monitoring systems for predictive maintenance, reducing downtime and optimizing costs.
Anomaly detection , Ensemble learning , Heat supply , Predictive maintenance , Real-time monitoring
Text of the article Перейти на текст статьи
Department of Computational Sciences and Statistics, Faculty of Mechanics and Mathematics, Al-Farabi Kazakh National University, Almaty, Kazakhstan
Department of Computer Science, Faculty of Information Technologies, Al-Farabi Kazakh National University, Almaty, Kazakhstan
Laboratory “Modeling in Energy Sector”, Satbayev University, Almaty, Kazakhstan
Department of Computer Science, Institute of Physics, Mathematics and Digital Technologies, Kazakh National Womens Teacher Training University, Almaty, Kazakhstan
Department of Computational Sciences and Statistics
Department of Computer Science
Laboratory “Modeling in Energy Sector”
Department of Computer Science
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026