基于主元分析与核偏最小二乘的CVT误差在线检测方法  

Online Detection Method of CVT Error Based on Principal Component Analysis and Kernel Partial Least Squares

作　　者：王春雨[1] 于海波[1] 赵晓健 赵进全[2] WANG Chunyu;YU Haibo;ZHAO Xiaojian;ZHAO Jinquan(Electrical Power Research Institute,Beijing 100192,China;School of Electrical Engineering,Xi’an Jiaotong University,Xi’an 710049,China)

机构地区：[1]中国电力科学研究院,北京100192 [2]西安交通大学电气工程学院,西安710049

出　　处：《电力电容器与无功补偿》2020年第6期57-62,共6页Power Capacitor & Reactive Power Compensation

基　　金：国家电网公司总部科技项目(JL71-18-002)。

摘　　要：针对CVT定期离线检测方式难于及时发现其误差变化的情况,本文提出一种基于PCAKPLS的CVT误差在线检测方法。该方法首先利用主元分析将电网波动与CVT的状态进行分离,将CVT的状态映射在残差子空间中并建立Q统计量,根据Q统计量判断CVT的状态。然后对正常运行的CVT采用核偏最小二乘法实时检测其误差。最后通过仿真,结果表明该方法能够准确地进行CVT误差检测及故障检测,是CVT误差在线检测的一种有效方法。In view of such situation that error variation of CVT is difficult to be found by the periodical offline detection method,a kind of online detection method of CVT error based on PCA⁃KPLS is proposed in this paper.The method firstly uses the principal component analysis to separate the grid fluctuation from the state of the CVT,maps the state of the CVT in the residual subspace and establishes a Q statistic and judges the state of the CVT according to the Q statistic.Then,the kernel partial least squares method in real time is used to detect the error of CVT which is in normal operation.Finally,it is shown by the simulation result that the method can perform accurately both error and fault detection of CVT and is an effective method for online detection of CVT error.

关 键 词：CVT误差在线检测 主元分析 核偏最小二乘 

分 类 号：TM451[电气工程—电器]