Power transformer is a complicated system due to its stochastic, fuzzy and alterable behavior. It is a decision-making problem of engineering system to assess transformer behavior. Qualitative knowledge and quantitative data need to be integrated. Quantitative change and qualitative change all need be reflected in the assessment results of transformer behavior. The behavior of whole transformer system need also be assessed by combination of different items. A method integrating quantitative and qualitative information need be used to assess transformer behavior. Extension theory is used generally to solve the inconsistent problems. A matter element consisted of research object, evaluation index, normalized value. According to rhombic thinking mode and the extension of matter element, the multi-index and hierarchical system of transformer behavior evaluation was built. Matter-element model was constructed to assess transformer behavior by matter-element transform. Three-dimensional evaluation for the behavior of whole transformer system can be implemented by quantitative, qualitative description and their change with time.
[1]
Wen Cai.
Extension theory and its application
,
1999
.
[2]
M. H. Wang,et al.
A Novel Extension Method for Transformer Fault Diagnosis
,
2002,
IEEE Power Engineering Review.
[3]
J. L. Guardado,et al.
A Comparative Study of Neural Network Efficiency in Power Transformers Diagnosis Using Dissolved Gas Analysis
,
2001,
IEEE Power Engineering Review.
[4]
Wei-Song Lin,et al.
CMAC-based fault diagnosis of power transformers
,
2002,
Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).