基于HHM-RFRM理论的智能船舶航行风险识别与筛选

Intelligent ship navigation risk identification and screening based on HHM-RFRM method

针对智能船舶航行过程中航行关键风险因素的有效识别和筛选问题,提出了基于等级全息建模(Hierarchical Holographic Modeling, HHM)框架和风险过滤、评级与管理(Risk Filter, Ranking and Management, RFRM)思想的智能船舶航行风险识别与筛选理论。首先,构建智能船舶航行风险识别HHM模型,以全面而准确地选取和反映智能船舶航行风险来源;其次,通过RFRM模型对风险因素进行过滤、排序和筛选,结合贝叶斯方法的多判据评估模型,识别出智能船舶航行过程中可能存在的关键风险因素。结果可以为相关海事机构和船舶公司进行动态管理提供理论依据,同时为保障智能船舶航行安全提供一种手段。

Aiming at the effective identification and screening of key risk factors in intelligent ship navigation, this paper proposes an intelligent ship navigation risk identification and screening theory based on Hierarchical Holographic Modeling(HHM) framework and Risk Filter, Ranking and Management(RFRM) framework. Firstly, the HHM model of intelligent ship navigation risk identification is constructed, focusing on four basic elements of ship safe navigation at sea: person, ship, environment, and management. The intelligent ship navigation risk identification and evaluation index is created according to the classification principles of these four elements. Secondly, the risk factors are sorted and screened by using the RFRM model, and the key risk factors that may exist in the navigation process of intelligent ships are identified by combining the multi-criteria evaluation model of Bayesian method. Combined with the survey opinions of experts, this study filters the identified main risk scenarios to reduce the number of risks entering the next step. The risk matrix is used to further filter the risk factors and sort the risks preliminarily to improve the accuracy of the next analysis: multi-criteria assessment. For the risk factors screened in the previous step, in addition to the two influencing factors of possibility and risk consequence, we should also consider the reducibility, redundancy, and other factors of each scenario. Eleven criteria for intelligent ship navigation risk assessment are given and divided into three levels: “high(H)”, “medium(M)” and “low(L)”. Each level is described according to multiple criteria for intelligent ship navigation risk assessment. Quantify and rank the filtered risks, determine the importance of each risk by using quantitative criteria, screen out small risks and small risks, and then filter out important risks. The results can not only provide a theoretical basis for the dynamic management of relevant maritime institutions and shipping companies but also provide an important means to ensure the navigation safety of intelligent ships.