一种基于D-S证据理论的复杂产品模块划分评价方法  

Research on Method of Evaluating Module Clustering for Complex Product Based on D-S Evidence Reasoning

作　　者：李军鹏[1] 陈兴玉[2] 赵韩[1] 

机构地区：[1]合肥工业大学机械与汽车工程学院,安徽合肥230009 [2]中国电子科技集团公司第三十八研究所,安徽合肥230031

出　　处：《工程图学学报》2011年第3期105-109,共5页Journal of Engineering Graphics

基　　金：国防科技攻关资助项目(2005BA201A83-01);合肥市重点科研资助项目(2007-2008)

摘　　要：模块划分是复杂产品模块化设计的基础,划分的优劣直接关系到客户定制产品设计、制造和装配的效率。针对现有的研究在模块划分方案形成以后缺乏对模块优劣的合理评价,该文通过引入D-S证据理论,从装配复杂性、可制造性、模块性、稳定性、造型结果与体积紧凑性6个指标对模块创建方案的满意度进行不确定和不完全性的综合评判,提出了一种双层模块化创建方案评价方法。该方法符合人的思维判断过程,具有一定的灵活性、有效性和合理性。Module clustering is foundation of modular design for complex product.Its performance counts for much in efficiency of product design,manufacture and assembly.However,the existing methods lack performance evaluation on modules after module clustering.In this paper,D-S evidence theory is adopted to make uncertain and incomplete evaluation on module satisfaction according to assembly complexity,manufacturability,modularity,stability,sculpt ion and compactness.A two-layered evaluation method on module clustering is proposed,and its evaluation accords with process of human thinking and judgment.The agility,validity and rationality of the method have been illustrated by an instance.

关 键 词：计算机应用 综合评价 D-S证据理论 模块聚类 贡献率 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]