Purpose/Aim
With the continuous expansion of the scale of the smart grid system, the transformer monitoring data presents the characteristics of multiple, huge and rapid growth. Carrying out portrait research on operating condition of power transformers can fully mine the effective information of the data, avoid the subjectivity in the current transformer state evaluation methods, and better carry out equipment health management.
Experimental/Modeling methods
By sorting out the relationship between state quantity and equipment operation, a portrait method of power transformer based on multi-dimensional capabilities and components is proposed. Firstly, an equipment evaluation system with six capabilities, five components and equipment state quantities is constructed. Secondly, the weight of each state quantity is determined by the entropy weight method, and the state of each capability of the equipment is scored by the TOPSIS method. Thirdly, using the membership function of fuzzy mathematics method to integrate various capabilities in order to obtain the overall state of the equipment. Finally, the effectiveness of the proposed method is verified by the actual situation of more than 500 transformers.
Results/discussion
It is verified that the proposed method has good accuracy and applicability through actual cases.
Conclusions
The proposed method can avoid the subjectivity of the threshold setting in the traditional method to a certain extent, and can accurately reflect the real state of the equipment, which provides a new idea for transformer state evaluation.
 

fuzzy membership function,equipment portrait,Power transformers,TOPSIS