Abstract The correct evaluation of transformer operation state can greatly improve the reliability of power supply. In order to improve the accuracy of transformer condition assessment, considering the deficiency of single parameter selection in traditional transformer condition assessment method, a transformer condition parameter evaluation method based on improved evidence theory is proposed to realize multi-dimensional information fusion. In this method, the parameters of common transformer type test are selected as on-line monitoring indexes, and then the indexes are normalized. The improved D-S evidence theory is used to fuse the state indexes and build the evaluation model of transformer state parameters. The improved D-S evidence theory modifies the combination rules and effectively avoids the conflict evidence. The method can fully integrate a variety of information. The experimental results show that the accuracy of transformer condition assessment is greatly improved by this method.
YUAN Yue,CHEN Shi,LIU Luyao等. Multi-dimensional information fusion and state assessment of transformer based on improved D-S theory[J]. Electrical Engineering, 2021, 22(6): 66-72.
2021, Vol. 22 
