Fault Detection and Diagnosis; Support Vector Machine; Random Forest; Organic Rankine Cycles
Abstract :
[en] This study investigates fault detection and diagnosis (FDD) techniques aimed at enhancing the reliability and
operational efficiency of organic Rankine cycle (ORC) systems used for waste heat recovery. By improving fault
management, this approach can significantly reduce maintenance costs and unplanned downtime, contributing to
the broader adoption of ORC technology in sustainable energy applications. The proposed methodology leverages
advanced machine learning algorithms, specifically support vector machines (SVM) and Random Forest (RF), to
identify and classify critical system faults. These faults include evaporator fouling, the presence of non-condensable
gases, and mechanical issues in the expander and pump components. To evaluate the performance of the FDD
framework, simulation-based experiments are conducted to address practical challenges such as data scarcity and
noise, which are common in industrial applications. Results demonstrate the robustness of the SVMand RF models
in accurately detecting and diagnosing faults, highlighting their potential to maintain high system performance
in real-world scenarios. Additionally, the analysis provides insights into selecting appropriate strategies based on
the quantity and quality of data available. Furthermore, the study explores the trade-offs between computational
efficiency and diagnostic accuracy, offering insights into the applicability of these techniques for online monitoring
systems. The findings underscore the critical role of machine learning in predictive maintenance strategies, paving
the way for smarter and more resilient energy recovery solutions.
Disciplines :
Energy
Author, co-author :
Hernandez Naranjo, Jairo Andres ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Systèmes énergétiques
Cendoya, Aitor ; Université de Liège - ULiège > Aérospatiale et Mécanique (A&M)
Chaudoir, Basile ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Systèmes énergétiques
Lemort, Vincent ; Université de Liège - ULiège > Département d'aérospatiale et mécanique > Thermodynamique appliquée
Language :
English
Title :
Performance Comparison of Machine Learning Fault Detection and Diagnosis Algorithms in Organic Rankine Cycle Systems
Publication date :
04 July 2025
Event name :
38th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems
Event organizer :
ECOS and École des Mines Paris – PSL
Event date :
29/06/2025-04/07/2025
Event number :
38
By request :
Yes
Audience :
International
Main work title :
In proceedings of the 38th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems
HE - 101069740 - DECAGONE - DEmonstrator of industrial CArbon-free power Generation from Orc-based waste-heat-to-Energy systems
Name of the research project :
DECAGONE - DEmonstrator of industrial CArbon-free power Generation from Orc-based waste-heat-to-Energy systems
Funders :
European Union
Funding number :
101069740
Funding text :
This projectDECAGONEhas received funding from the EuropeanUnion’s Horizon Europe research and innovation
programme under grant agreement No 101069740. The information presented on this document reflects only the
authors’ view. The Agency is not responsible for any use that may be made of the information it contains.
Amalfi, R. L., Vakili-Farahani, F., & Thome, J. R. (2016a). Flow boiling and frictional pressure gradients in plate heat exchangers. part 1: Review and experimental database. International Journal of Refrigeration, 61, 166–184. https://doi.org/10.1016/j.ijrefrig.2015.07.010
Amalfi, R. L., Vakili-Farahani, F., & Thome, J. R. (2016b). Flow boiling and frictional pressure gradients in plate heat exchangers. part 2: Comparison of literature methods to database and new prediction methods. International Journal of Refrigeration, 61, 185–203. https://doi.org/10.1016/j.ijrefrig.2015.07.009
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13, 281–305.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Cendoya, A., Ransy, F., Dumont, O., Hernandez, A., Guo, B., & Lemort, V. (2025). Developing a control strategy for carnot batteries: Analysing temperature glide effects in organic rankine cycle and heat pump modes. Proceedings of the 37th International Conference on Efficiency, cost, optimization, simulation and environmental impact of energy systems.
Cendoya, A., Ransy, F., Lemort, V., Dumont, O., & Bentao, G. (2024). Numerical modelling of a 50 kwe reversible carnot battery coupled with waste heat. In proceedings 1st Belgian Symposium of Thermodynamics.
Chen, X., Li, H., Patel, S., & Kumar, A. (2022). Computational efficiency in real-time fault diagnosis systems. IEEE Transactions on Industrial Informatics, 18(6), 4123–4135. https://doi.org/10.1109/TII.2022.3141234
Choi, S., & Krumdieck, S. (2016). Dynamic modeling of organic rankine cycle (orc) system for fault diagnosis and control system design. Proceedings 38th New Zealand Geothermal Workshop.
Cioncolini, A., & Thome, J. R. (2012). Void fraction prediction in annular two-phase flow. International Journal of Multiphase Flow, 43, 72–84. https://doi.org/10.1016/j.ijmultiphaseflow.2012.03.003
Cuevas, C., Lebrun, J., Lemort, V., & Ngendakumana, P. (2009). Development and validation of a condenser three zones model. Applied Thermal Engineering, 29(17–18), 3542–3551. https://doi.org/10.1016/j.applthermaleng.2009.06.007
Dickes, R. (2019). Charge-sensitive methods for the off-design performance characterization of organic rankine cycle (orc) power systems [Doctoral dissertation, University of Liege].
Dragan, D. (2011). Fault detection of an industrial heat-exchanger: A model-based approach. Journal of Mechanical Engineering, 57(6), 477–484.
Eck, B. (1973). Fans: Design and operation of centrifugal, axial-flow and cross-flow fans (1st English Edition). Pergamon Press.
Elmouatamid, A., Fricke, B., Sun, J., & Pong, P. (2023). Air conditioning systems fault detection and diagnosis-based sensing and data-driven approaches. Energies, 16, 4721.
García, M., Torres, F., & Smith, R. (2019). Machine learning for industrial iot: Challenges and opportunities. Journal of Process Control, 85, 24–36. https://doi.org/10.1016/j.jprocont.2019.10.002
Hosamo, H., Ragnar, P., Svidt, K., Han, D., & Nielsen, H. (2022). A digital twin predictive maintenance framework of air handling units based on automatic fault detection and diagnostics. Energy and Buildings, 261, 111988.
Kira, K., & Rendell, L. A. (1992). The feature selection problem: Traditional methods and a new algorithm. Proceedings of the Tenth National Conference on Artificial Intelligence (AAAI), 129–134.
Lee, J., Kim, B., & Choi, H. (2020). Edge ai for predictive maintenance: A survey. Engineering Applications of AI, 95, 103861. https://doi.org/10.1016/j.engappai.2020.103861
Lemort, V., Declaye, S., & Quoilin, S. (2012). Experimental characterization of a hermetic scroll expander for use in a micro-scale rankine cycle. Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, 226(1), 126–136. https://doi.org/10.1177/0957650911413840
Longo, G. A. (2010). Heat transfer and pressure drop during hfc refrigerant saturated vapour condensation inside a brazed plate heat exchanger. International Journal of Heat and Mass Transfer, 53(5–6), 1079–1087. https://doi.org/10.1016/j.ijheatmasstransfer.2009.11.003
Markowski, M., Trafczynski, M., & Urbaniec, K. (2013). Identification of the influence of fouling on the heat recovery in a network of shell and tube heat exchangers. Applied Energy, 102, 755–764. https://doi.org/10.1016/j.apenergy.2012.08.020
Martin, H. (2010). N6: Pressure drop and heat transfer in plate heat exchangers. In H. Martin (Ed.), Vdi heat atlas: Chapter. Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-77877-6
Schölkopf, B., & Smola, A. J. (2002). Learning with kernels: Support vector machines, regularization, optimization, and beyond. MIT Press.
Shah, M. M. (2021). Heat transfer during condensation in corrugated plate heat exchangers. International Journal of Refrigeration, 127, 180–193. https://doi.org/10.1016/j.ijrefrig.2021.02.011
van de Sand, R.(2021). A predictive maintenance model for heterogeneous industrial refrigeration systems[Doctoral dissertation, Tor Vergata University of Rome, Italy].
Vapnik, V. (2000). The nature of statistical learning theory. Springer.
Wang, J., Zuo, Q., Liao, G., Luo, F., Zhao, P., Wu, W., He, Z., & Dai, Y. (2021). Machine learning-based fault detection and diagnosis of organic rankine cycle system for waste-heat recovery. Journal of Energy Engineering, 147(4), 04021016.
Wieland, C., Schifflechner, C., Braimakis, K., Kaufmann, F., Dawo, F., Karellas, S., Besagni, G., & Markides, C. (2023). Innovations for organic rankine cycle power systems: Current trends and future perspectives. Applied Thermal Engineering, 225, 120201.
Yan, K., Ji, Z., & Shen, W. (2017). Online fault detection methods for chillers combining extended kalman filter and recursive one-class svm. Neurocomputing, 228, 205–212.
Zhang, Y., & Wang, T. (2021). Efficient machine learning models for smart manufacturing. International Journal of Automation Science, 12(4), 289–305. https://doi.org/10.1109/IJAS.2021.3156789
