Dynamic Fault Prediction of Power Transformers Based on Hidden Markov Model of Dissolved Gases Analysis

Dissolved gases analysis (DGA) provides widely recognized practice for oil-immersed power transformers, and it is mainly interpreted for fault diagnosis. In order to accurately estimate the health index state of power transformers and predict the incipient operation failure, a dynamic fault prediction technique based on hidden Markov model (HMM) of DGA is proposed in this paper. Gaussian mixture model, as a soft clustering method, is used to extract the static features of different health states from a DGA dataset of 65 in-service power transformers with 1600 days operation. Especially, a sub-health state is introduced to enrich the health index and aging stages of power transformers. The static features between health states and concentrations of dissolved gases are built, and the effectiveness of clustering is cross validated. Furthermore, taking time sequence into consideration, transition probability of power transformer between different health states based on the HMM model is calculated and analyzed. The effectiveness of dynamic early warning and incipient fault prediction in sub-health status of in-service power transformers has been proved. Moreover, the dynamic fault prediction is able to provide decision-making basis for practical condition-based operation and maintenances.