纵横交叉算法及模糊聚类相结合的变压器故障诊断.doc

纵横交叉算法与模糊聚类相结合的变压器故障诊断* 孟安波，，（，） 摘要： 关键词： 中图分类号：TM 文献标识码：B 文章编号：1001-1390（201）00-0000-00 diagnosis method of transformer based on crisscross optimization algorithm and fuzzy clustering Meng Anbo, Lu Haiming, Guo Zhuangzhi (College of Automation, Guangdong University of Technology, Guangzhou 510006, China) Abstract：Optimized FCM clustering by the proposed CSO (CSO-FCM) is introduced to diagnose the fault of transformer in order to conquer the shortages of FCM clustering. The combination of dissolved gas analysis and FCM clustering is effective on improving the accuracy rate of power transformer fault diagnosis, but the result of FCM clustering is unstable and easy getting stuck in a local optimum. The CSO algorithm includes horizon cross as well as vertical cross, whose combining can enhance the global convergent ability while the introduction of competitive mechanism drives the potential solutions approximate the global optima in an accelerating fashion without sacrificing the convergence speed. This novel method effectively compensates the demerits of single intelligent algorithm, which not only has the ability to dispose the unstable information of fuzzy theory, also has an advantage of global convergence of CSO. Simulation and case analysis indicate that, compared with the traditional FCM clustering, the CSO-FCM clustering can obtain high performance clustering center and effectively raise the accuracy and diagnosis speed of power transformer fault diagnosis. Keywords：crisscross optimization fuzzy clustering, fault diagnosis 0　引 言 1　 纵横交叉算法受儒家中庸思想和遗传算法中交叉操作的启发，其有哪些信誉好的足球投注网站行为由横向交叉和纵向交叉两种方式组成，每次迭代这两种行为将交替进行，交叉后得出的解称为中庸解（，）。通过结合一个简单的竞争机制，使得横向交叉和纵向交叉完美的结合起来：交叉后产生的子代，与其父代进行竞争，只有比父代适应度更好的子代才会被保留下来，竞争后得出的解称为占优解（，），类似于PSO中的个体极值。 1.1　横向交叉是在种群中两个粒子相同维之间的算数交叉。首先对所有粒子进行随机两两配对，假设父代粒子和的第维进行横向交叉，则它们根据式（1）、（2）产生子代。。 1.　　 FCM聚类是通过求取所有样本点与聚类中心距离加权和的目标函数极值点而得到聚类中心迭代公式，其权值是隶属度函数的指数[9-10]。 CSO-FCM聚类算法采用基于聚类中心的编码方式，也就是每个粒子是由个聚类中心组成。设样本向量维数为，则粒子的维数是，粒子的编码结构为：。