Abstract: The internal insulation condition of capacitor voltage transformer（CVT） is a key factor to ensure its measurement accuracy and operation stability. However, during the long-term operation, the internal insulation condition of CVT would be degraded by electrical aging, thermal aging and system overvoltage. Aiming at this problem, a data-driven CVT internal insulation condition evolution method is proposed in this paper. This method constructs the feature parameters of error condition based on the electrical connection relationship between the high-voltage CVT groups, and the fuzzy analysis is utilized to match the internal insulation condition and error condition of CVTs according to their correlations, therefore, the degree and type of CVT abnormal internal insulation could be evaluated online.