中文摘要：

配电网运行状态复杂多变,迅速甄别配电网的正常、异常以及故障状态,有助于快速排除配电网故障并恢复供电。基于模糊C均值（FCM）和自适应模糊推理系统（ANFIS）,提出一种配电网运行状态分类识别策略,其基于ANFIS构建一种递阶模糊推理系统分类器,并采用FCM分类方法对递阶模糊推理系统参数进行初始优化。定义小波包时间熵对配电网运行状态信号数据进行处理,将构造的分类特征向量作为递阶模糊推理系统分类器的输入,实现对配电网运行状态的智能分类识别。基于PSCAD-EMTDC搭建典型配电网模型,仿真计算配电网各运行状态,测试结果表明,提出的分类识别策略可以得到较高准确性的分类结果,并且对故障点位置的变化和配电网络拓扑结构的改变具有较好的适应性。

英文摘要：

The fast recognition of operational status,i.e. normal,abnormal or faulty,is helpful for the quick fault elimination and power-supply recovery of distribution network. A strategy of operational status recognition based on FCM（Fuzzy C-Mean） and ANFIS（Adaptive Network Fuzzy Inference System） is proposed,which constructs a kind of classifier based on ANFIS for the hierarchical fuzzy inference system and applies the FCM classification method to optimally initialize its parameters. The wavelet-packet time entropy is defined,the operational status data of distribution network are processed,and the constructed vectors of classification feature are taken as the inputs of the classifier to intelligently recognize the operational status of distribution network. A typical distribution network model is built based on PSCAD-EMTDC,each operational status is simulated,and the simulative results show that,the proposed strategy has higher recognition accuracy and better adaptability to the changes of fault location and grid topology.