摘要
针对半潜式平台安装作业风险评估中存在的风险多态性和模糊性问题,构建了一种多态模糊贝叶斯网络风险分析模型。根据行业规范推荐标准定义语言性评价模糊集,描述根节点的事故状态发生概率,克服了传统方法中确定性概率难以获取的困难。利用相似性聚合法结合置信度指标融合专家意见,引入改进的去模糊化转换方法,提高了专家知识经验转化为定量数据的合理性和可靠性。基于贝叶斯网络的双向推理和敏感性分析技术,实现了工程作业全过程的风险评估。通过对陵水17-2项目半潜平台整体吊装过程进行风险分析,验证该模型的合理性与有效性,为半潜平台安装作业风险管理与防控策略制定提供指导。
A polymorphic fuzzy Bayesian network risk analysis model is constructed to deal with the polymorphism and fuzziness in the risk assessment of semi submersible platform installation.According to the industry standard,the linguistic evaluation fuzzy sets are defined to describe the accident probability of the root node,which overcomes the difficulty of obtaining the deterministic probability with traditional methods.The similarity aggregation method combined with confidence level is used to integrate the expert opinions,and an improved defuzzification transformation method is introduced to improve the rationality and reliability of transforming expert knowledge into quantitative data.Based on the bidirectional reasoning and sensitivity analysis technology of Bayesian network,the risk assessment of the whole process of engineering operation is realized.Through the risk analysis of the installation process of Lingshui 17-2 semi submersible platform,the rationality and effectiveness of the model are verified,which provides guidance for the formulation of risk management and prevention strategy.
作者
冯岩
余建星
FENG Yan;YU Jianxing(State Key Laboratory of Hydraulic Engineering Simulation and Safety,Tianjin University,Tianjin 300072,China;China Communications Construction Company Limited,Beijing 100088,China)
出处
《海洋工程》
CSCD
北大核心
2023年第4期12-21,共10页
The Ocean Engineering
基金
国家自然科学基金面上项目(52071234)
高技术船舶科研项目(SSBQ-2020-HN-01-03)。
关键词
半潜平台
多态系统
模糊贝叶斯网络
风险分析
相似性聚合法
semi-submersible platform
multi-state system
fuzzy Bayesian networks
risk analysis
similarity aggregation method
