关于深度信息融合的小电流接地故障选线.docVIP

基于深度信息融合的小电流接地故障选线 冯孝宏1，陈博博2，储亚男1，陈奎2，王爱东1 江苏省海安县供电公司，江苏 海安 226600； 2、中国矿业大学 信息与电气工程学院，江苏 徐州 221008） 摘要：基于信息融合技术的小电流接地故障选线方法当信息融合效率低时，将直接影响接地选线的准确性。分别利用傅里叶变换（FFT）和经验模态分解（EMD）对稳态和暂态的零序分量特征进行分析，通过建立故障测度函数，计算出线路故障测度；利用信息增益度，建立各种选线方法的故障测度；利用线路和方法故障测度得到最终的样本故障测度。把样本故障测度作为特征输入量，利用单纯形法(SM)优化参数的最小二乘支持向量机(LSSVM)算法进行深度信息融合选线。仿真结果表明上述方法应用于选线中具有很高的准确率和灵敏度。 关键词：信息增益度；故障选线；最小二乘支持向量机；信息融合 中图分类号：TM 文献标识码：B 文章编号：1001-1390（201）00-0000-00Fault line selection based on depth information fusion for small current grounding system Feng Xiaohong1, Chen Bobo2, Chu Yanan1, Chen Kui2, Wang Aidong1 (1. Haian Power Supply Company of Jiangsu, Haian 226600, Jiangsu, China. 2. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221008, Jiangsu, China) Abstract: When the fusion efficiency is low, the method based on depth information fusion technology will directly affect the accuracy of the grounding line selection for small current. The EEMD and FFT are used respectively to analyze the zero-sequence component of steady-state and transient, this paper sets up faulty measurement function to calculate fault measures of feeders and establishes fault measures of different methods based on information gain. Finally, sample fault measures are founded by fusing the two fault measures. Then, the depth information fusion line selection is conducted by using the least squares support vector machine (LSSVM) of the simplex optimum-seeking algorithm and the information gain degree with the sample fault measures as characteristic input. Simulation results show that the above method is of high accuracy and sensitivity in fault line selection. keywords：information gain, fault line selection, LSSVM, information fusion   0 引言 我国配电网大都采用中性点非有效接地方式运行，且80%以上的故障为单相接地故障。因此，及时准确找出故障线路并进行相应处理，对保证供电系统的安全性和可靠性具有重要意义。 由于中性点非有效接地系统中单相接地故障特征小，因此，普遍存在选线准确度低的问题。因此，国内外学者对其进行了大量研究，提出了多种选线方法。这些方法根据所依据的信号特征大致可以分为基于稳态信号的选线方法[1-2]、基于暂态信号的选线方法[3-9]、基于多种特征信息融合[10-13]的选线方