不确定条件下多目标R&D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] 司书宾[1] 蔡志强[1] 

机构地区：[1]西北工业大学系统集成与工程管理研究所,西安710072

出　　处：《系统工程理论与实践》2008年第2期98-104,共7页Systems Engineering-Theory & Practice

基　　金：国家863计划基金(2002AA414060;2003AA411110);教育部博士点基金(20040699025)

摘　　要：应用模糊集理论描述R&D项目过程的模糊不确定性,建立了以模糊实物期权度量收益,模糊熵度量风险,模糊净现值度量费用的多目标R&D项目组合选择优化数学模型;运用定性可能性原理将模糊模型清晰化,并针对清晰型数学模型提出了一种改进的多目标遗传算法进行求解;仿真实验证明,实现的多目标遗传算法可以有效求解清晰型多目标R&D项目组合选择优化问题.To solve the R＆D portfolio selection under uncertainty, fuzzy set theory is applied to deal with project＇s uncertainty parameters. A multi-objective mathematical model is constructed, which simultaneously optimizes benefit with fuzzy real option, risk with fuzzy entropy, and cost with fuzzy net present value. A crisp transformation is implemented with the fuzzy model based on qualitative possibility theory and an improved multi-objective Pareto genetic algorithm is presented. Finally, a simulation experiment is carried out to illustrate that the proposed method could solve multi-objective R＆D portfolio selection effectively.

关 键 词：R&D项目组合 不确定性 多目标优化 模糊实物期权 模糊熵 遗传算法 

分 类 号：F224.3[经济管理—国民经济] O224[理学—运筹学与控制论]