高压直流换流阀零部件故障智能诊断方法研究  

Research on intelligent diagnosis method of high voltage DC converter valve parts

作　　者：黄松 梁凯 王晓丽 魏卓[3] Huang Song;Liang Kai;Wang Xiaoli;Wei Zhuo(School of Mechanical Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Guangxi Power Grid Limited Liability Company Nanning Power Supply Bureau,Nanning 530000,China;XUJI Group Corporation,Xuchang 461000,China)

机构地区：[1]上海理工大学公共实验中心,上海200093 [2]广西电网有限责任公司南宁供电局,南宁530000 [3]许继集团有限公司,许昌461000

出　　处：《电子测量技术》2019年第18期158-162,共5页Electronic Measurement Technology

基　　金：国家重点研发计划资助(2018YFB0106300);国网上海市电力公司科研项目(No.52094016000R)资助

摘　　要：高压直流换流阀是特高压直流输电的核心,换流阀的可靠工作是特高压直流输电系统安全稳定运行的必要保证。高压直流换流阀关键零部件故障智能诊断技术是目前国内换流阀巡检研究中相对空白的领域,尚没有完整的检测诊断体系。在上述背景下,提出了一组利用换流阀可见光图像中各零部件的关键特征进行故障智能诊断的算法,并设计了相应的验证实验。实验表明,所设计的算法能有效识别出TCE板接线脱落、螺母松动、器件老化等阀组件故障。该组算法可以应用在高压直流换流阀关键零部件的智能故障诊断、在线故障预警中,具有较高的工程应用价值。The high-voltage DC converter valve is the core of UHV DC transmission.The reliable operation of the converter valve is a necessary guarantee for the safety and stability of the UHV DC transmission system.The intelligent diagnosis technology for the key components of the high-voltage DC converter valve assembly is a relatively blank field of domestic converter valve inspection research,and there is no complete inspection and diagnosis system.Under the above background,this paper proposes a set of algorithms for intelligent fault diagnosis using the key features of each component in the visible light image of the converter valve,and designs the corresponding verification experiment.Experiments show that the designed algorithm can effectively identify valve component failures such as TCE board disconnection,nut looseness,and device aging.The algorithm can be applied to intelligent fault diagnosis and online fault warning of key components of high-voltage DC converter valve,and has high engineering application value.

关 键 词：高压直流换流阀 智能诊断算法 接线脱落 螺母松动 

分 类 号：TM930[电气工程—电力电子与电力传动]