基于小波包与改进BP神经网络的变压器励磁涌流识别方法.docVIP

基于小波包和改进BP神经网络的变压器励磁涌流识别方法* 公茂法，李美蓉，殷凡姣，王中刚，刘丙乾，邵群，李杰 （山东科技大学 电气与自动化工程学院，山东 青岛 266590） 摘要：根据励磁涌流和内部故障电流的波形特征存在巨大差异，提出一种基于小波包和改进BP网络的识别励磁涌流的新算法。利用小波包对励磁涌流和故障电流信号进行分解和重构，提取小波包重构系数，计算各频段的能量并进行归一化处理，构造能量特征向量，作为BP网络的输入样本，进行训练和测试，提出保护判据。经过PSCAD/EMTDC和MATLAB软件对大量样本进行仿真验证，证明该方案能够快速准确地识别励磁涌流和内部故障电流。 关键词：小波包；改进BP神经网络；励磁涌流；变压器 中图分类号: TM93 文献标识码：A 文章编号：1001-1390（2015）00-0000-00 Transformer inrush current identification method based on wavelet packet and improved BP neural network Gong Maofa, Li Meirong, Yin Fanjiao, Wang Zhonggang, Liu Bingqian, Shao Qun, Li Jie (College of Electrical Engineering and Automation,Shandong University of Science and Technology,Qingdao 266590,Shandong,China) Abstract：According to the greathuge difference in the waveform characteristics between inrush current and internal fault current, the paper proposed a new method to identify inrush current based on wavelet packet and improved BP network. Decompose and reconstruct The inrush current and fault current signal are decomposed and reconstructed by using wavelet packet to , extracted wavelet packet reconstruction coefficients, calculate the energy of each band and normalize the processd and to construct energy feature vectors as ainput sample for BP network training and testing, and finally propose the protection criterion. Through a large number of samples simulation using by PSCAD / EMTDC and MATLAB software, it proves that the program can quickly and accurately identify inrush current and internal fault current. Keywords：wavelet packet, improved BP neural network, inrush current, transformer 0 引 言 *基金项目：国家级大学生创新创业训练计划资助项目(201210424046);山东省自然科学基金资助项目（ZR2012EEM021）;山东科技大学研究生科技创新基金资助项目(YC140338)目前，随着电力系统的发展，变压器的广泛应用和大容量变压器的日益增加对变压器保护装置的可靠性和速动性要求也就越来越高[1-2]。当变压器空载合闸或者切除外部故障时，将出现励磁涌流，有可能使变压器保护发生误动。正确可靠地识别励磁涌流，防止变压器保护误动，仍然是当前变压器保护的关键问题[3]。本文提出了基于小波包和改进BP神经网络的励磁涌流识别算法。利用小波包算法对励磁涌流和内部故障电流进行分析并提取能量特征，作为 *基金项目：国家级大学生创新创业训练计划资助项目(201210424046); 山东省自然科学基金资助项目（ZR2012EEM021）; 山东科技大学研