Research on Online Assessment Method for Power Transformer Condition Based on Multi-Data Fusion

Aiming at the problems of multiple characteristic indicators and fault types in power transformer condition assessment, an online transformer condition assessment method based on multi-data fusion is proposed. An online transformer condition assessment system is established. Through case analysis, the weights of characteristic indicators are determined by combining the Analytic Hierarchy Process (AHP) and association rules. The thresholds of characteristic indicators are determined using the Weibull model combined with a trapezoidal membership function to evaluate the real-time state of the transformer. Instance verification shows that the evaluation results of this method are consistent with the actual operating state of the transformer, verifying the feasibility of the method.