Condition assessment of power transformer using fuzzy and evidential theory

To meet the needs of risk assessment of power transformer in power system, a condition assessment model of power transformer based on fuzzy evaluation method and information fusion technology is proposed in this paper. Typical parameters from preventative test and on-line monitoring are selected to evaluate operational condition of power transformer. The selected condition parameters are normalized at first and then membership to different condition level are calculated. Assessment model with multi-information fusion method based on Dempster-Shafer evidential theory is employed. Moreover, data from routine tests and on-line monitoring of a 220kV power transformer are analyzed and the results verified the validity of the proposed model. It is indicated that the proposed model is helpful to improving the accuracy and timeliness of transformer condition evaluation by combining on-line monitoring parameters.