基于VMD多尺度模糊熵的HVDC输电线路故障识别方法  

Fault Recognition Method for HVDC Transmission Line Based on VMD Multi-scale Fuzzy Entropy

作　　者：王桥梅 吴浩 胡潇涛 顾小平 陈佳豪 WANG Qiaomei;WU Hao;HU Xiaotao;GU Xiaoping;CHEN Jiahao(Automation and Information Engineering,Sichuan University of Science&Engineering,Zigong 643000,China;Artificial Intelligence Key Laboratory of Sichuan Province,Zigong 643000,China;Sichuan Province Key Laboratory of Information Technology and Internet of Things Measurement and Control Technology,Zigong 643000,China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,自贡643000 [2]人工智能四川省重点实验室,自贡643000 [3]企业信息化与物联网测控技术四川省高校重点实验室,自贡643000

出　　处：《电力系统及其自动化学报》2021年第5期134-144,共11页Proceedings of the CSU-EPSA

摘　　要：针对HVDC输电线路故障识别率低、远端高阻故障识别困难等问题,提出一种基于变分模态分解VMD(variational mode decomposition)多尺度模糊熵的HVDC输电线路智能故障识别方法。首先对暂态电流信号进行VMD分解,利用中心频率法则提取合适的IMF分量计算多尺度模糊熵、VMD能量和比值。分别利用VMD多尺度模糊熵和VMD能量和比值表征区内外故障特征和故障极特征,将它们组合成特征向量。将特征向量集分成训练集和测试集,将训练集进行训练得到Softmax分类器模型,利用测试集进行测试。仿真结果表明:基于VMD多尺度模糊熵和Softmax分类器的HVDC输电线路故障识别方法能在不同故障距离和不同过渡电阻情况下有效实现区内外故障识别和故障极选择,且耐受过渡电阻能力强,具有一定的抗干扰能力。Aimed at problems such as the low fault recognition rate of HVDC transmission line and the difficulty in remote high-impedance fault recognition,a smart fault recognition method for HVDC transmission line based on variational mode decomposition(VMD)multi-scale fuzzy entropy is proposed.First,VMD is performed on the transient current signal,and the appropriate IMF component is extracted using the central frequency rule to calculate the multiscale fuzzy entropy and VMD energy sum ratio.The VMD multi-scale fuzzy entropy and VMD energy sum ratio are used to characterize the internal/external fault characteristics and fault pole characteristics,respectively,which are further combined into feature vectors.The feature vector set is divided into a training set and a test set.The former is trained to obtain a Softmax classifier model,while the latter is used for testing.A large number of simulation results show that the fault recognition method for HVDC transmission line based on VMD multi-scale fuzzy entropy and Softmax classifier can effectively realize internal/external fault recognition and fault pole selection under different fault distances and different transition resistances,and it can strongly withstand the transition resistance,with a certain antiinterference capability.

关 键 词：高压直流输电线路 变分模态分解 多尺度模糊熵 Softmax分类器 故障识别 

分 类 号：TM77[电气工程—电力系统及自动化]