Abstract: Aiming at the defect that the important factor of trust was not considered in partner selection research of virtual enterprise,the index system with three dimensions of ability,motivation and persistence was proposed by combining with the features of virtual enterprise.Based on fuzzy cognitive maps theory,the real-coded genetic algorithm and nonlinear Hebbian learning algorithm were designed to construct trust-aware partner selection model.Simulation and experimental results demonstrated that the method was effective and feasible,and could better fit to history data.

Key words: virtual enterprise, partner selection, fuzzy cognitive maps, trust

摘要： 针对现有虚拟企业伙伴选择研究以时间、成本、风险等定量指标为准则,优化伙伴选择过程,但未考虑信任这一重要协作因素的缺陷,结合虚拟企业特征,给出能力、动机、持续性三个维度的指标体系;采用模糊认知图理论,设计了实时编码遗传算法和非线性Hebbian学习算法,构建了基于信任的虚拟企业伙伴选择模型;对模型及算法进行了仿真实验。实验表明,模型结果与历史数据拟合较好,具有较好的有效性和可行性。

关键词: 虚拟企业, 伙伴选择, 模糊认识图, 信任