粒子滤波算法在评标中的应用  

Evaluating projects by particle filter

作　　者：张晓宇[1] 胡士强[1,2] 梁国壮[1] 

机构地区：[1]河北科技大学电气信息学院,河北石家庄050018 [2]上海交通大学信息与控制所,上海200240

出　　处：《河北科技大学学报》2008年第4期341-346,共6页Journal of Hebei University of Science and Technology

基　　金：国家自然科学基金资助项目(60674107);河北省自然科学基金重点基金资助项目(F2006000343);河北省"百名优秀人才计划"联合资助项目

摘　　要：针对现行评标方法中层次分析法易受主观意见影响以及模糊综合评价法隶属函数的选取带有主观随意性的不足,提出了一种基于粒子滤波算法的评标方法。该方法依据粒子滤波思想,选取最优值作为高斯抽样变量,进行粒子滤波迭代,求取某指标下某单位的中标概率密度,解决了其他方法在评定各指标时无法客观准确反映各投标单位真实差距的缺陷,使评标在合理性、公平性等方面都得到了改进。通过对同一投标案例的计算分析,说明了粒子滤波算法的有效性,同时该算法也可以推广到其他类似的评价中。In view of the fact that present evaluation methods such as AHP（the analytic hierarchy process） are vulnerable to the impact of subjective views and that fuzzy comprehensive evaluation＇s membership selection tends to be subjective and arbitrary, a evaluation method based on particle filter algorithm is proposed. This method, based on the principle of particle filter, selects optimal value as a Gaussian random variable and uses particle filter iterative to strike a unit＇s success probability density under a indicator. This method resolves the problem that other methods cannot resolve, the unability aceurately and objectively reflect all tenders＇ real gap under various indicators. This method makes evaluation get improvement in rationality and fairness. The effectiveness of the algorithm is shown by one bidding case＇, whose computing and analysing indicates that the algorithm can be extended to other similar problems in the evaluation as well.

关 键 词：评标 粒子滤波 层次分析法 模糊综合评价法 

分 类 号：C934[经济管理—管理学] TP391[自动化与计算机技术—计算机应用技术]