基于模糊聚类的构件耐久性评估  

THE APPLICATION OF FUZZY CLUSTER ANALYSIS IN THE EVALUATION OF DURABILITY OF COMPONENTS

作　　者：夏宁[1] 任青文[1] 朱正华 

机构地区：[1]河海大学土木工程学院,南京210098 [2]南通市规划设计院有限公司,南通226006

出　　处：《工业建筑》2005年第5期72-74,共3页Industrial Construction

基　　金：重大水利工程病变机理与健康诊断方法研究基金项目(SCX2 0 0 0 -5 6)。

摘　　要：基于模糊划分的聚类方法,提出了一种构件耐久性评估方法。该方法依据各构件与其所属类的聚类中心的耐久性指标加权广义欧式距离平方之总和最小的原则,采用迭代算法对构件耐久性模糊划分矩阵进行不断修正,直至最优。通过对算例的分析比较,证明该方法是合理的,并且避免了传统方法评估的不合理性,易于实现编程。Based on the fuzzy partition clustering, an evaluation method of components durability is proposed. According to the principle that the sum of squares of generalized Euclid distance of durability indexes between components and their clustering center should be the least, the durability fuzzy partition matrix is modified by use of iteration until the optimum result is obtained. The method proves to be correct. It avoids the irrationality in the conventional method and can be easily realized by programming.

关 键 词：模糊聚类 混凝土构件 耐久性 迭代算法 

分 类 号：TU317[建筑科学—结构工程]