基于BN-AHP的UUV系统效能评估方法  

UUV System Performance Evaluation Method Based on BN-AHP

作　　者：曾静超 黄奇珊[2] 张红英[1] Zeng Jingchao;Huang Qishan;Zhang Hongying(School of Information Engineering,Southwest University of Science and Technology,Mianyang,China;University of Electronic Science and Technology of China,Chengdu,China)

机构地区：[1]西南科技大学信息工程学院,四川绵阳 [2]电子科技大学,四川成都

出　　处：《科学技术创新》2024年第5期74-77,共4页Scientific and Technological Innovation

摘　　要：提出了一种结合层次分析法(Analytic Hierarchy Process,AHP)和贝叶斯网络(Bayesian Networks,BN)的新型效能评估方法。首先,梳理提炼了UUV(Unmanned underwater vehicle,UUV)效能评估的五个维度;其次,利用AHP方法为每个维度建立了指标体系,并将其作为贝叶斯网络的节点输入,从而将不确定性因素纳入评估过程;随后,通过贝叶斯推理得出UUV效能评估值;最后,通过计算机仿真与传统AHP法,信息熵和人工神经网络法进行对比,实验结果表明,所提的方法相较于传统AHP方法和信息熵方法的评估结果更具收敛性和集中度,相较于人工神经网络方法可以在数据缺乏的情况下完成评估,同时在效能影响因子分析和方案优选方面更具区分度。This paper proposes a new performance evaluation method combining Analytic Hierarchy Process(AHP)and Bayesian Networks(BN).Firstly,five dimensions of Unmanned underwater vehicle(UUV)effectiveness evaluation are summarized.Secondly,AHP method is used to establish an index system for each dimension,and it is used as the node input of Bayesian network,so as to bring uncertainty factors into the evaluation process.Then,the evaluation value of UUV efficacy is obtained by Bayesian inference.Finally,the computer simulation is compared with the traditional AHP method,information entropy method and artificial neural network method.The experimental results show that the proposed method has more convergence and concentration compared with the traditional AHP method and information entropy method.Compared with the artificial neural network method,the evaluation can be completed in the case of lack of data.At the same time,it is more distinguishability in efficiency impact factor analysis and scheme optimization.

关 键 词：UUV 效能评估 模糊AHP分析 贝叶斯推理 BAYESIAN网络 

分 类 号：U674.941[交通运输工程—船舶及航道工程] P715[交通运输工程—船舶与海洋工程]