Transformation of fault trees into bayesian networks:
Optimization of maintenance in engineering systems
DOI:
https://doi.org/10.51896/rilcods.v6i52.445Keywords:
Maintenance, Fault tree, Bayesian networks, Failure diagnosis and prognosisAbstract
Failure diagnosis and prognosis in industry is crucial to avoid unplanned outages, optimize efficiency and reduce maintenance costs. The use of Bayesian based networks allows an accurate and probabilistic evaluation, improving decision making and strategic maintenance planning. The objective of this research lies in the presentation of a detailed methodology for the accurate and systematic transformation of a fault tree into a Bayesian network, with the aim of improving the ability to diagnose and forecast failures. To achieve this objective, the fault tree of a wind turbine was constructed using historical data and expert consultation and transformed into a Bayesian network using the proposed method. As results, the main advantages of the Bayesian network with respect to the fault tree are presented and the most critical sets and combinations of faults for the system are obtained. The research concludes that the transformation allows a more accurate and detailed evaluation of the failures in the wind turbine. The Bayesian network considers the probabilistic relationships between events and allows obtaining a more accurate estimation of the failure probability, which facilitates the diagnosis. As future research, the integration of the Bayesian network in intelligent maintenance systems and decision support systems is proposed. This will allow the automation of maintenance planning and the optimization of resources in a more effective way.
References
Bobbio, A., Portinale, L., Minichino, M., & Ciancamerla, E. (2001). Improving the analysis of dependable systems by mapping fault trees into Bayesian networks. Reliability Engineering & System Safety, 71(3), 249-260. https://doi.org/https://doi.org/10.1016/S0951-8320(00)00077-6
Jin, H., & Liu, C. (2017, 28-30 May 2017). Reliability analysis of wind turbine gear box based on fault tree and Bayesian network. 2017 29th Chinese Control And Decision Conference (CCDC),
Kabir, S., & Papadopoulos, Y. (2019). Applications of Bayesian networks and Petri nets in safety, reliability, and risk assessments: A review. Safety Science, 115, 154-175. https://doi.org/10.1016/j.ssci.2019.02.009
Li, H., Guedes Soares, C., & Huang, H.-Z. (2020). Reliability Analysis of a Floating Offshore Wind Turbine using Bayesian Networks. Ocean Engineering, 217, 107827. https://doi.org/10.1016/j.oceaneng.2020.107827
Liu, W. (2019). Intelligent fault diagnosis of wind turbines using multi-dimensional kernel domain spectrum technique [Article]. Measurement: Journal of the International Measurement Confederation, 133, 303-309. https://doi.org/10.1016/j.measurement.2018.10.027
Rodríguez-López, M. Á. (2015). Metodología para sistemas inteligentes de detección de mal funcionamiento en equipos Universidad de La Rioja]. España. https://dialnet.unirioja.es/servlet/tesis?codigo=46488
Torres Valle, A., & Martínez Martín, E. (2016). Evaluación de confiabilidad tecnológica del parque aerogenerador de Gibara 2 %J Ingeniería Energética. 37, 25-34. http://scielo.sld.cu/scielo.php?script=sci_arttext&pid=S1815-59012016000100004&nrm=iso
Vachtsevanos, G., & Zahiri, F. (2022). Prognosis: Challenges, Precepts, Myths and Applications. IEEE Aerospace Conference Proceedings,
Villar Ledo, L., Díaz Concepción, A., Infante Abreu, M. B., Vilalta Alonso, J. A., Alfonso Álvarez, A., & Rodríguez Soto, Á. A. (2022). ANALYSIS OF TOOLS FOR THE DIAGNOSIS OF MAINTENANCE MANAGEMENT [Article]. Universidad y Sociedad, 14(1), 493-510. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85126333566&partnerID=40&md5=c2fa336146a2130db8f410adffaaa786
Wang, K. S. (2014). Key Techniques in Intelligent Predictive Maintenance (IPdM) – A Framework of Intelligent Faults Diagnosis and Prognosis System (IFDaPS). Advanced Materials Research, 1039, 490-505. https://doi.org/10.4028/www.scientific.net/AMR.1039.490
Zhou, H., Chen, W., Shen, C., Cheng, L., & Xia, M. (2022). Intelligent machine fault diagnosis with effective denoising using EEMD-ICA- FuzzyEn and CNN [Article]. International Journal of Production Research. https://doi.org/10.1080/00207543.2022.2122621
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Usted es libre de:
- Compartir — copiar y redistribuir el material en cualquier medio o formato
- Adaptar — remezclar, transformar y construir a partir del material
Bajo los siguientes términos:
- Atribución — Usted debe dar crédito de manera adecuada, brindar un enlace a la licencia, e indicar si se han realizado cambios. Puede hacerlo en cualquier forma razonable, pero no de forma tal que sugiera que usted o su uso tienen el apoyo de la licenciante.
- NoComercial — Usted no puede hacer uso del material con propósitos comerciales.
