Liu Chao, Zhou Chuankun, Wang Hongyan, Liu Shenyu, Cui Junguo, Zhao Wenbo, Liu Shichao, Tan Liping, Xiao Wensheng, Chen Yaqi
College of Electromechanical Engineering, Qingdao University of Science & Technology, Qingdao, 266061, China.
National Engineering Research Center of Marine Geophysical Prospecting and Exploration and Development Equipment, China University of Petroleum (East China), Qingdao, 266580, China.
Sci Rep. 2025 Apr 4;15(1):11523. doi: 10.1038/s41598-025-92588-3.
Subsea pipeline system faces significant challenges in practical engineering applications, including system complexity, environmental variability, and limited historical data. These factors complicate the accurate estimation of component failure rates, leading to fault polymorphism and inherent uncertainty. To address these challenges, this study proposes a reliability analysis method based on a Fuzzy Polymorphic Bayesian Network (FPBN). The approach utilizes a multi-state fault tree to construct a polymorphic Bayesian Network (BN), integrating traditional BN techniques with the consideration of multiple failure states and fuzzy failure rates. This extension allows the network to handle uncertainties such as imprecise fault data and unclear logical relationships. The method is applied to subsea pipeline risk analysis by developing a system BN model. Through quantitative analysis, the failure probability of the system is calculated. Reverse fault diagnosis is then conducted to determine the posterior probabilities of root nodes and identify system vulnerabilities. The results demonstrate that the FPBN effectively addresses the ambiguity and uncertainty in component failure rates, providing a robust framework with practical engineering applications.
海底管道系统在实际工程应用中面临重大挑战，包括系统复杂性、环境多变性和历史数据有限。这些因素使得准确估计部件故障率变得复杂，导致故障多态性和固有不确定性。为应对这些挑战，本研究提出一种基于模糊多态贝叶斯网络（FPBN）的可靠性分析方法。该方法利用多状态故障树构建多态贝叶斯网络（BN），将传统BN技术与多故障状态和模糊故障率的考虑相结合。这种扩展使网络能够处理诸如不精确故障数据和不清晰逻辑关系等不确定性。通过开发系统BN模型，该方法应用于海底管道风险分析。通过定量分析，计算系统的故障概率。然后进行反向故障诊断，以确定根节点的后验概率并识别系统漏洞。结果表明，FPBN有效解决了部件故障率中的模糊性和不确定性，为实际工程应用提供了一个强大的框架。
