摘要
针对电压暂降扰动事件发生频繁、扰动种类多样,难以有效识别扰动源的实际情况,结合电压暂降扰动信号的时-频特性、灰狼优化算法(GWO)和支持向量机(SVM)分类模型,提出了一种电压暂降扰动源识别新方法。通过S变换对电压暂降扰动信号进行多分辨率时-频分析,从S变换结果矩阵中提取出信号的特征曲线,建立6类电压暂降混合扰动信号的8个特征量。构建GWO-SVM一对余(OVR)分类器,以提取出的特征量作为输入,对扰动源进行分类识别。基于MATLAB/Simulink构建电压暂降模型,经仿真验证分析,该方法可以有效识别电压暂降扰动源,也为电压暂降扰动治理提供必要的技术支撑。
n view of the actual situation that voltage sags occur frequently with diverse disturbance categories,which makes it difficult to identify the disturbance sources.A novel identification approach of voltage sag disturbance sources is proposed by combing the time-frequency characteristics of voltage sag disturbance signals,the grey wolf optimization(GWO)algorithm and support vector machine(SVM)in this paper.Multi-resolution time-frequency analysis is applied to voltage sag disturbance signals by S transform,and the feature curves of signals are extracted from S transform result matrix,and then,8 features calculated from 6 kinds of voltage sag complex disturbance signals are established.A one versus rest(OVR)GWO-SVM classifier is established whose inputs are fed with the extracted features to identify disturbance sources.The effectiveness of the proposed method is validated to identify the voltage sag disturbance sources by the analysis result of voltage sag simulation model based on MATLAB/Simulink,which could also be a necessary technical support for voltage sag disturbance governance.
作者
赵洛印
李忠诚
王丹
朱江
李静
张闯
Zhao Luoyin;Li Zhongcheng;Wang Dan;Zhu Jiang;Li Jing;Zhang Chuang(Harbin Research Institute of Electrical Instruments Co.,Ltd.,Harbin 150028,China;Center of Metrology,State Grid Liaoning Electric Power Supply Co.,Ltd.,Shenyang 110168,China;Fushun Power Supply Company,State Grid Liaoning Electric Power Supply Co.,Ltd.,Fushun 113000,Liaoning,China)
出处
《电测与仪表》
北大核心
2019年第23期76-85,共10页
Electrical Measurement & Instrumentation