基于主元分析的电容式电压互感器计量性能在线评估方法OA

In view of the incomplete and inaccurate analysis of the measurement features of the capacitive voltage transformer(CVT)measurement evaluation system,a CVT measurement performance online evaluation method based on improved princi-pal component analysis algorithm is proposed.In the data analysis module,the traditional principal component analysis algo-rithm is combined with the sample point update algorithm and the data block update algorithm to improve the efficiency and adaptability of the algorithm.In the fault diagnosis module,the cross wavelet transform technology is introduced,the fault fea-tures are extracted by time-frequency domain analysis,and the dimensionality of the features is reduced by principal component analysis,which effectively reduces the noise interference and improves the accuracy of fault diagnosis.A large number of CVT measurement data are optimized,and the processing efficiency and real-time performance of the system are further improved by means of parallel calculation.The experiment proves that the proposed method takes less time to process large-scale data,the accuracy of anomaly detection is as high as 98％,and the misjudgment rate of a large number of CVT measurement data is low,which can meet the measurement needs in complex power grid environment.