Development of a Predictive Model for Turbine Component Failure in Geothermal Power Plants Using The Integration of Failure Mode and Effects Analysis (FMEA) and Random Forest
Keywords:
Geothermal power plant, turbine failure, FMEA, Random Forest, K-Means clustering, predictive maintenanceAbstract
Turbines in geothermal power plants are subject to various failure modes due to high-temperature, high-pressure operations, and corrosive environments. This research aims to develop a predictive failure model for turbine components by integrating Failure Mode and Effects Analysis (FMEA) and the Random Forest algorithm. Failure data collected from maintenance reports, overhaul logs, and inspection assessments between 2015 and 2024 are clustered to identify dominant failure modes. The identified failure modes are evaluated using FMEA to calculate Risk Priority Numbers (RPN). These RPN scores are used as classification labels to train the Random Forest model using operational parameters. The model's performance is assessed through accuracy, precision, and recall metrics. Furthermore, model predictions are used to dynamically update RPN values, enabling adaptive risk management. Preliminary clustering results suggest nine dominant failure modes, merging low-impact failure categories. This research contributes a dynamic risk-based predictive maintenance framework tailored for geothermal turbine systems.
Downloads
References
Lu, T., Gao, X., Wang, X., & Zhao, Y. (2009). The geothermal power and main technical problems. 2009 International Conference on Sustainable Power Generation and Supply, 1–4. https://doi.org/10.1109/supergen.2009.5348251
Feili, H. R., Akar, N., Lotfizadeh, H., Bairampour, M., & Nasiri, S. (2013). Risk analysis of geothermal power plants using failure modes and effects analysis (FMEA) technique. Energy Conversion and Management, 72, 69–76. 2013. https://doi.org/10.1016/.enconman.2012.10.027.
Sader, S., Husti, I., & Daróczi, M. Enhancing failure mode and effects analysis using Auto Machine Learning: A Case Study of the Agricultural Machinery Industry. Processes, 8(2), 224. 2020. https://doi.org/10.3390/pr8020224.
Akbari, Mohsen., P. Khazee, Failure Modes & Effects Analysis (FMEA) for Power Transformer. 28th International Power System Conference. 2013
Liu, H.-C., Chen, X.-Q., You, J.-X., & Li, Z. A new integrated approach for risk evaluation and classification with dynamic expert weights. IEEE Transactions on Reliability, 70(1), 163–174. 2021. https://doi.org/10.1109/tr.2020.2973403.
Ashfania, G. A., Warsokusumo, T., Prahasto, T., & Widodo, A. Detection and diagnostic with Random Forest Classifier (RFC) to improve the maintenance management system in steam boiler of Power Plant. PHM Society Asia-Pacific Conference, 4(1). 2023. https://doi.org/10.36001/phmap.2023.v4i1.3670.
Cheng, Jiaxing, et al. A Comparative Study of K-Means Clustering and a Novel Ranking Algorithm for Risk Priority Number Analysis in FMECA. Nanyang Technological University, Singapore, 2023.
Mazur, Z., García-Illescas, R., & Porcayo-Calderón, J. (2009). Last stage blades failure analysis of a 28MW geothermal turbine. Engineering Failure Analysis, 16(4), 1020–1032. https://doi.org/10.1016/j.engfailanal.2008.05.012.
Eyuboglu, O. H., Dindar, B., & Gul, O. (2020). Risk assessment by using failure modes and effects analysis (FMEA) based on power transformer aging for maintenance and replacement decision. 2020 2nd Global Power, Energy and Communication Conference (GPECOM), 251–255. https://doi.org/10.1109/gpecom49333.2020.9247887.
Ramere, M. D., & Laseinde, O. T. (2021). Optimization of condition-based maintenance strategy prediction for aging automotive industrial equipment using FMEA. Procedia Computer Science, 180, 229–238. https://doi.org/10.1016/j.procs.2021.01.160
More, A. S., & Rana, D. P. (2017). Review of Random Forest classification techniques to resolve data imbalance. 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM), 72–78. https://doi.org/10.1109/icisim.2017.8122151
Filipe de Lima Munguba, C., Villa Ochoa, A. A., de Novaes Pires Leite, G., Araújo da Costa, A. C., Peixoto da Costa, J. Â., Duarte de Menezes, F., Alves de Mendonça, E. P., de Petribú Brennand, L. J., de Castro Vilela, O., & Guedes de Souza, M. G. (2024). Fault detection framework in wind turbine pitch systems using Machine Learning: Development, validation, and results. Engineering Applications of Artificial Intelligence, 138, 109307. https://doi.org/10.1016/j.engappai.2024.109307.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 ITB Graduate School Conference
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
