不确定条件下考虑相互影响的研发项目组合选择优化  

Multi-objective R&D portfolio selection optimization under uncertainty

作　　者：杜先进[1] 孙树栋[1] 王军强[1] 郝京辉[1] 

机构地区：[1]西北工业大学系统集成与工程管理研究所,陕西西安710072

出　　处：《计算机集成制造系统》2007年第9期1826-1832,1846,共8页Computer Integrated Manufacturing Systems

基　　金：国家863计划资助项目(2002AA414060;2003AA411110);教育部博士点基金资助项目(20040699025)~~

摘　　要：深入分析了研发项目组合选择过程中的项目间收益、技术和资源的相互影响,应用模糊集理论进行研发项目的不确定参数定义。在项目相互独立基本模型的基础上,建立了考虑相互影响的研发项目组合选择优化数学模型;运用定性的可能性原理完成了模糊规划模型的清晰化过程,针对清晰型数学模型,提出利用遗传算法的宏观和微观策略进行求解;最后,应用算例验证了优化方法和算法的有效性。In the process of Research ＆ Development （R＆D） project portfolio selection, interactions among benefit, technology and resources of projects were analyzed. Fuzzy set theory was applied to define the uncertainty parameters of R＆D project. Based on R＆D portfolio selection model of independent projects, a general portfolio selection optimization mathematical model was set up covering the three interactions. To solve the fuzzy model, a crisp transformation was implemented based on qualitative possibility theory. Macroscopic and microcosmic strategies of genetic algorithm were presented to solve clear mathematical model. Effectiveness of optimization model and algorithm were proved by a computational example.

关 键 词：研发项目组合 不确定性 收益相互影响 技术相互影响 资源相互影响 遗传算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] O224[自动化与计算机技术—计算机科学与技术]