Multi-source information fusion for power transformer condition assessment

This paper presents a multi-source data and information fusion framework for power transformer condition assessment. The proposed method adopts Bayesian Network (BN), which can integrate every piece of data and information obtained from different transformer diagnostic measurements. Within the Bayesian Network, Monte Carlo and Bootstrap methods are employed to extract the most informative characteristics regarding transformer condition from different diagnostic measurements. Reliability metrics are computed to evaluate the effectiveness of combinations of different type diagnostic measurements and subsequently facilitate determining optimal diagnostic strategies involved in transformer condition assessment. Theories, implementations, and results of the proposed method are presented using case studies in this paper.