配电系统谐波扰动的定位与识别研究  

Localization and Identification Research of Harmonic Disturbance in Power Distribution System

作　　者：何巨龙[1] 王根平[1,2] 刘丹[1] 唐友明[1] 

机构地区：[1]湘潭大学智能计算与信息处理教育部重点实验室,湖南湘潭411105 [2]深圳职业技术学院,广东深圳518055

出　　处：《电气技术》2016年第12期25-30,共6页Electrical Engineering

基　　金：深圳市科技研发资金(JCYJ20140508155916430)

摘　　要：配电系统谐波扰动具有非平稳性、突变性和短时持续性,给快速、精准地定位与识别谐波扰动带来困难。为了改善配电系统谐波扰动的定位与识别效果,本文提出一种基于提升小波和改进BP神经网络的扰动定位与识别新方法。首先用Euclidean分解算法得到db4小波提升方案,然后对谐波扰动信号进行提升小波分解,结合模极大值对谐波扰动突变点峰值进行定位,再用自适应学习率和增加动量项相结合的方法对传统BP神经网络改进并进行谐波扰动识别训练。仿真结果表明,该方法能更好地获取扰动时刻信息,定位快速精确,对配电系统谐波扰动识别率高。According to the nonstationarity, mutability and short duration of harmonic disturbance in power distribution system, it is difficult to localize and identify harmonic disturbance with high speed and accuracy. In order to improve localization and identification results of harmonic disturbance, a new method is proposed based on lifting wavelet and improved BP neural network. At first, the Euclidean decomposition principle is used to obtain db4 wavelet lifting scheme. Then, harmonic disturbance signal is decomposed through lifting wavelet analysis, and mutation peak of harmonic disturbance is localized using lifting wavelet modulus maxim. At last, traditional BP algorithm is improved by combining increasing momentum method with self-adaption learning rate method, and improved BP neural network is used to identify harmonic disturbance. The simulation results show that the proposed method can better localize the harmonic disturbances＇ time information with high speed and accuracy, and can identify harmonic disturbance with high discrimination ratio.

关 键 词：配电系统 谐波扰动 提升小波 BP神经网络 定位与识别 

分 类 号：TM935[电气工程—电力电子与电力传动]