Bayesian network-based evaluation of a novel fault detection system for preventing catastrophic condenser failures in offshore facilities

Ertan, F, Uğurlu, Ö, Tonoğlu, F, Sivri, F, Yıldız, S and Wang, J ORCID: 0000-0003-4646-9106 (2026) Bayesian network-based evaluation of a novel fault detection system for preventing catastrophic condenser failures in offshore facilities. Safety Science, 201. ISSN 0925-7535

Preview

Text Bayesian network-based evaluation of a novel fault detection system for preventing catastrophic condenser failures in offshore facilities.pdf - Accepted Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

This study investigates the causes and consequences of condenser failures in seawater-cooled combined cycle systems on offshore platforms, using a real-life accident scenario as a case study. A Bayesian Network (BN) integrated with fuzzy logic was employed to model the failure pathways and assess the impact of contributing factors, such as operator errors and alarm deficiencies. The resulting network enabled the development and evaluation of targeted system improvements, including the integration of additional analyzers and a shutdown command mechanism. These enhancements demonstrated a significant reduction in the probability of catastrophic failure. Expert evaluations supported the effectiveness of the proposed measures in enhancing operational safety and reducing human error. The study emphasizes the critical role of timely intervention, robust control systems, and preventive maintenance in mitigating failure risks. The study results also highlight the need for continuous risk analysis, improved component/system or part selection, and training programs to support resilient operations in high-risk offshore environments. The findings offer practical recommendations for industry stakeholders and contribute to the development of safer and more reliable offshore energy systems.

Item Type:	Article
Uncontrolled Keywords:	Condenser failure; Combined cycle systems; Bayesian Network (BN); Fuzzy logic; System reliability; 40 Engineering; Prevention; 7 Affordable and Clean Energy; 09 Engineering; 11 Medical and Health Sciences; 17 Psychology and Cognitive Sciences; Human Factors; 40 Engineering; 42 Health sciences; 52 Psychology
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Engineering and Built Environment
Publisher:	Elsevier
Date of acceptance:	29 April 2026
Date of first compliant Open Access:	2 September 2026
Date Deposited:	01 Sep 2026 09:51
Last Modified:	02 Sep 2026 00:50
DOI or ID number:	10.1016/j.ssci.2026.107272
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29231

View Item