Comparison and optimization of machine learning methods for fault detection in district heating and cooling systems

• Autorzy: Çinar Mehmet , Aslan Emrah , Özüpak Yıldırım

Identyfikatory

DOI

10.24425/bpasts.2025.154063

• Języki publikacji: EN

Abstrakty

EN

In this study, the methods used for the detection of sub-station pollution failures in district heating and cooling (DHC) systems are analyzed. In the study, high, medium, and low-level pollution situations are considered and machine learning methods are applied for the detection of these failures. Random forest, decision tree, logistic regression, and CatBoost regression algorithms are compared within the scope of the analysis. The models are trained to perform fault detection at different pollution levels. To improve the model performance, hyperparameter optimization was performed with random search optimization, and the most appropriate values were selected. The results show that the CatBoost regression algorithm provides the highest accuracy and overall performance compared to other methods. The CatBoost model stood out with an accuracy of 0.9832 and a superior performance. These findings reveal that CatBoost-based approaches provide an effective solution in situations requiring high accuracy, such as contamination detection in DHC systems. The study makes an important contribution as a reliable fault detection solution in industrial applications.

Słowa kluczowe

EN

pollution detection; grid search; machine learning; DHC

PL

wykrywanie zanieczyszczeń; przeszukiwanie siatki; uczenie maszynowe; DHC

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2025
• Tom: Vol. 73, nr 3
• Strony: art. no. e154063
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wykr.

Twórcy

autor

Çinar Mehmet

• Bitlis Eren University, Organized Industrial Zone Vocational School, Electrical Department, Bitlis, Türkiye

autor

Aslan Emrah

• Mardin Artuklu University, Faculty of Engineering and Architecture, Department of Computer Engineering, Mardin, Türkiye

• https://orcid.org/0000-0002-0181-3658

autor

Özüpak Yıldırım

• Dicle University, Silvan Vocational School, Electrical Department, Diyarbakır, Türkiye

• https://orcid.org/0000-0001-8461-8702

Bibliografia

• [1] F. Zhang, N. Saeed, and P. Sadeghian, “Deep learning in fault detection and diagnosis of building HVAC systems: A systematic review with meta-analysis,” Energy AI, vol. 12, p. 100235, 2023, doi: 10.1016/j.egyai.2023.100235.
• [2] M. Vallee, T. Wissocq, Y. Gaoua, and N. Lamaison, “Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems,” Energy, vol. 283, p. 128387, 2023, doi: 10.1016/j.energy.2023.128387.
• [3] A. Rafati and H.R. Shaker, “Predictive maintenance of district heating networks: A comprehensive review of methods and challenges,” Therm. Sci. Eng. Progress, vol. 53, p. 102722, 2024, doi: 10.1016/j.tsep.2024.102722.
• [4] C. Hermans, J. Al Koussa, T. Van Oevelen, and D. Vanhoudt, “Fault detection for district heating substations: Beyond threesigma approaches,” Smart Energy, vol. 16, p. 100159, 2024, doi: 10.1016/j.segy.2024.100159.
• [5] Q. Shi, M. Liu, S. Zhang, R. Zheng, and X. Lan, “Multi-Agent Path Finding Method Based on Evolutionary Reinforcement Learning,” 2024 43rd Chinese Control Conference (CCC), Kunming, China, 2024, pp. 5728–5733, doi: 10.23919/CCC63176.2024.10661475.
• [6] F.L.O. Martins et al., “Multiple Fault Diagnosis in a Wind Turbine Gearbox with Autoencoder Data Augmentation and KPCA Dimension Reduction,” J. Nondestruct. Eval., vol. 43, p. 114, 2024, doi: 10.1007/s10921-024-01131-3.
• [7] F. Alpsalaz and M.S. Mamiş, “Detection of Arc Faults in Transformer Windings via Transient Signal Analysis,” Appl. Sci., vol. 14, p. 9335, 2024, doi: 10.3390/app14209335.
• [8] Y. Zhou, S. Zheng, and J.L.M. Hensen, “Machine learning-based digital district heating/cooling with renewable integrations and advanced low-carbon transition,” Renew. Sustain. Energy Rev., vol. 199, p. 114466, 2024, doi: 10.1016/j.rser.2024.114466.
• [9] M. Vallee, T. Wissocq, Y. Gaoua, and N. Lamaison, “Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems,” Energy, vol. 283, p. 128387, 2023, doi: 10.1016/j.energy.2023.128387.
• [10] X. Yang, Q. Zhao, Y. Wang, and K. Cheng, “Fault signal reconstruction for multi-sensors in gas turbine control systems based on prior knowledge from time series representation,” Energy, vol. 262, p. 124996, 2023, doi: 10.1016/j.energy.2022.124996.
• [11] R. Panday, N. Indrawan, L.J. Shadle, and R.W. Vesel, “Leak detection in a subcritical boiler,” Appl. Therm. Eng., vol. 185, p. 116371, 2021, doi: 10.1016/j.applthermaleng.2020.116371.
• [12] P. Hundi and R. Shahsavari, “Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants,” Appl. Energy, vol. 265, p. 114775, 2020, doi: 10.1016/j.apenergy.2020.114775.
• [13] H. Gadd and S. Werner, “Fault detection in district heating substations,” Appl. Energy, vol. 157, pp. 51–59, 2015, doi: 10.1016/j.apenergy.2015.07.061.
• [14] S. Buffa et al., “Advanced control and fault detection strategies for district heating and cooling systems—a review,” Appl. Sci., vol. 11, no. 1, p. 455, 2021, doi: 10.3390/app11010455.
• [15] S. Månsson et al., “Faults in district heating customer installations and ways to approach them: Experiences from Swedish utilities,” Energy, vol. 180, pp. 163–174, 2019, doi: 10.1016/j.energy.2019.04.220.
• [16] P. Leoni, R. Geyer, and R.-R. Schmidt, “Developing innovative business models for reducing return temperatures in district heating systems: Approach and first results,” Energy, vol. 195, p. 116963, 2020, doi: 10.1016/j.energy.2020.116963.
• [17] Z. Bilici, D. Özdemir, and H. Temurtaş, “Comparative analysis of metaheuristic algorithms for natural gas demand forecasting based on meteorological indicators,” J. Eng. Res., vol. 11, no. 3, pp. 259–265, 2023. doi: 10.1016/j.jer.2023.100127.
• [18] A.J. Patil, R. Naresh, R.K. Jarial, and H. Malik, “Optimized synthetic data integration with transformer’s DGA data for improved ML-based fault identification,” IEEE Trans. Dielectr. Electr. Insul., vol. 32, no. 1, pp. 598–607, 2025, doi: 10.1109/TDEI.2024.3421915.
• [19] M. Vallee, T. Wissocq, Y. Gaoua, and N. Lamaison, “Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems,” Energy, vol. 283, p. 128387, 2023, doi: 10.1016/j.energy.2023.128387.
• [20] Z. Bilici and D. Özdemir, “Comparative analysis of metaheuristic optimization algorithms for natural gas demand forecasting based on meteorological parameters,” J. Fac. Eng. Archit. Gazi Univ., vol. 38, no. 2, pp. 1153–1168, 2022. doi: 10.17341/gazimmfd.1014788.
• [21] P. Xue et al., “Machine learning-based leakage fault detection for district heating networks,” Energy Build., vol. 223, p. 110161, 2020, doi: 10.1016/j.enbuild.2020.110161.
• [22] S. Månsson et al., “A machine learning approach to fault detection in district heating substations,” Energy Procedia, vol. 149, pp. 226–235, 2018, doi: 10.1016/j.egypro.2018.08.187.
• [23] E. Aslan and Y. Özüpak, “Detection of road extraction from satellite images with deep learning method,” Cluster Comput., vol. 28, p. 72, 2025, doi: 10.1007/s10586-024-04880-y.
• [24] I. De la Cruz and C.E. Ugalde-Loo, “District Heating and Cooling Systems,” in Microgrids and Local Energy Systems, UK: IntechOpen Limited, 2021. doi: 10.5772/intechopen.99740.
• [25] E. Aslan, “Prediction and comparative analysis of emissions from gas turbines using random search optimization and different machine learning-based algorithms,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 72, no. 6, p. e151956, 2024, doi: 10.24425/bpasts.2024.151956.
• [26] B. Ozdemir, E. Aslan, and I. Pacal, “Attention Enhanced InceptionNeXt-Based Hybrid Deep Learning Model for Lung Cancer Detection,” IEEE Access, vol. 13, pp. 27050–27069, 2025, doi: 10.1109/ACCESS.2025.3539122.
• [27] Y. Özüpak, “Machine learning-based fault detection in transmission lines: A comparative study with random search optimization,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 73, no. 2, p. e153229, 2025, doi: 10.24425/bpasts.2025.153229.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).