基于改进遗传算法的物流绩效评价方法  

The Evaluation of Logistics Performance Based on Improved Genetic Algorithm

作　　者：陈晓利[1] 

机构地区：[1]佛山职业技术学院,广东佛山528000

出　　处：《物流科技》2011年第2期67-70,共4页Logistics Sci-Tech

摘　　要：在分析物流绩效关键影响因素基础上,提出采用改进的GA遗传算法应用于物流绩效评价测试。以多个主要影响因子为网络的输入信息,建立物流绩效综评遗传神经网络模型,利用GA较强的全局寻优化能力和BP梯度法较强的局部搜索能力,较快同时又较好地综合评价出网络输出信息的物流绩效等级。进行不同综合评价方法对比,结果表明基于改进遗传算法的评价方法计算速度快、精度高、鲁棒性强,可以有效直观地对物流绩效进行综合评价,具有一定实际应用价值。Based on the analysis of key influence factors in logistics performance,an improved genetic algorithm is applied to the logistics performance assessment system.The key influence factors are used as the inputs of proposed network model.The global optimal search of GA is combined to the local optimal search of BP network based on gradient method.The quality evaluation of logistics performance can be identified quickly and accurately.The performances of BP network as well as the improved GA network proposed in this paper are compared.The effectiveness of the proposed approach is demonstrated via experiments by applying it to a realistic enterprise logistics performance.The improved GA has the advantages of fast computation,high classification precision,and better robustness to evaluate the logistics performance.

关 键 词：企业物流绩效评价 遗传算法 梯度法 均方差准则 

分 类 号：F224.0[经济管理—国民经济]