首页 | 本学科首页   官方微博 | 高级检索  
     

基于do算子的船舶风险干预及推理方法
引用本文:王学峰,苏高辉,谢旭阳,曾国庆,王劲韬,陈国兵,杨自春. 基于do算子的船舶风险干预及推理方法[J]. 科学技术与工程, 2023, 23(12): 5332-5339
作者姓名:王学峰  苏高辉  谢旭阳  曾国庆  王劲韬  陈国兵  杨自春
作者单位:海军工程大学;青岛装备技术质量监测站
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
摘    要:针对船舶风险侧重于计算发生概率,其管控和干预效果难以评估及推理难题,提出了基于do算子的船舶风险干预及推理方法。首先利用先验知识建立因果关系网络;其次引入Leaky Noisy-Or假设和隐变量节点,建立基于结构性孪生因果网络模型;最后根据do算子干预进行反事实推理,利用引起故障的充分因和必要因来确定干预措施的有效性。实例分析表明,该方法可以有效衡量风险管控措施的有效性,判断干预的行为对危险源排序的影响,具有一定的稳定性和优越性。

关 键 词:船舶风险评估;孪生网络模型;do算子;反事实推理
收稿时间:2022-09-13
修稿时间:2023-02-15

Research on ship risk intervention and reasoning method based on do operator
Wang Xuefeng,Su Gaohui,Xie Xuyang,Zeng Guoqing,Wang Jintao,Chen Guobing,Yang Zichun. Research on ship risk intervention and reasoning method based on do operator[J]. Science Technology and Engineering, 2023, 23(12): 5332-5339
Authors:Wang Xuefeng  Su Gaohui  Xie Xuyang  Zeng Guoqing  Wang Jintao  Chen Guobing  Yang Zichun
Affiliation:Naval University of Engineering
Abstract:Aiming at the ship risk focusing on calculating the occurrence probability, its control and intervention effect is difficult to assess and reasoning difficulties, the do operator-based ship risk intervention and reasoning method is proposed. Firstly, the causal network is established using a priori knowledge; secondly, the Leaky Noisy-Or hypothesis and hidden variable nodes are introduced to establish a structural twin-based causal network model; finally, counterfactual inference is performed based on do operator interventions, and the effectiveness of interventions is determined using sufficient and necessary causes that cause failures. The case analysis shows that the method can effectively measure the effectiveness of risk control measures and determine the impact of the intervention''s behavior on the hazard source ranking, with certain stability and superiority.
Keywords:ship risk assessment    twin network model    do operator    counterfactual reasoning
点击此处可从《科学技术与工程》浏览原始摘要信息
点击此处可从《科学技术与工程》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号