摘要
本研究通过引入证据理论对多个模型结果进行融合,探讨了2种基本概率分配(BPA)的赋值方法,同时给出了模型结果为区间时的融合方案。通过一个真实案例的演示表明,选用第一种BPA赋值方法进行融合时本质上是对模型结果取均值,第二种赋值方法则因引入了专家意见而使融合结果更客观;当结果为区间时融合后的结果虽复杂但可获得更多信息。本研究为科学描述多模型结果提供了解决方案,可为进一步提升再现结果的客观性提供支持。
The evidence theory is introduced in this paper for the fusion of multi-models’results,two methods for evaluating the value of basic probability assignment(BPA)are explored and the fusion scheme when model’s results are intervals is given.The demonstration of a real case indicates that when the first value evaluation method for BPA is chosen,the essence of fusion is to average multi-models’results,while the second method can get more objective results of fusion due to the introduction of experts’opinions.When the models’results are intervals,though the results of fusion are complicated but they contain more information.This study provides a solution for the scientific description of multi-models’results,and gives supports for further enhancing the objectivity of reconstruction results.
作者
邹铁方
刘勇
何枫林
李华
Zou Tiefang;Liu Yong;He Fenglin;Li Hua(School of Automobile and Mechanical Engineering,Changsha University of Science and Technology,Changsha 410114;Mechanical & Manuf. Eng,Trinity College Dublin,Ireland 999015;Key Laboratory of Safety Design and Reliability Technology for Engineering Vehicle,Changsha 410114)
出处
《汽车工程》
EI
CSCD
北大核心
2019年第4期462-467,共6页
Automotive Engineering
基金
国家自然科学基金(51775056)
湖南省自然科学基金(2018JJ3544)
国家留学基金资助
关键词
事故再现
证据理论
融合
基本概率分配
不确定性
accident reconstruction
evidence theory
fusion
basic probability assignment
uncertainty
