High-Voltage CVT Fault Diagnosis Based on Effective Data Recognition and Multi-dimensional Information Fusion

In view of the poor identification of the effective data in online monitoring of high-voltage capacitor voltage transformer (CVT), this paper proposes a method for effective data identification based on the analysis of data correlation coefficients, with utilization of the data characteristics that multiple online monitoring data sources exhibit linear correlation. To address the prevalent problem in current high-voltage CVT fault diagnosis, such as limited information sources, poor accuracy, and significant interference in partial discharge devices leading to compromised fault signal detection and accuracy, a fault diagnosis method based on multi-dimensional information fusion is proposed. Firstly, factor analysis is employed to perform data-level information fusion on the diagnostic indicators of CVT by extracting the variance contribution values of common factors corresponding to each fault type as eigenvalues that reflect the differences among fault types. Subsequently, fuzzy theory is utilized for feature-level information fusion, and the variance contribution values of common factors are taken as input parameters for the membership function to identify the fault types of CVT, thus achieving the accurate diagnosis of high-voltage CVT faults. The validity of the proposed method is demonstrated through case studies, which can provide a theoretical reference and practical experience for CVT fault diagnosis。