Collation of Mamdani-Type and Sugeno-Type Fuzzy Inference System for Condition Monitoring of Power Transformer

摘要

The power transformer is one of the main components in a power transmission network. Major faults in these transformers can cause extensive damage which does not only interrupt electricity supply but also results in large revenue losses. Due to the large number of transformers of different makes and capacities, routine maintenance and diagnosis of such transformers are rather difficult as different transformers exhibit different characteristics and problems. Dissolved Gas Analysis (DGA) has got the highest attention and attraction from the researchers. DGA is used in oil filled transformers. The mineral oil in the transformers under the effect of various thermal and electrical stresses decomposes into number of gases compounds such as H_2, O_2, N_2, CO, CO_2, CH_4, C_2H_6, C_2H_4, C_2H_2 and C_2H_8. These gases are further analyzed to investigate presence of the fault in the transformer. The accuracy and diagnosis of condition monitoring of transformers can be increased manifold by combination of conventional DGA interpretation techniques with the artificial intelligence techniques. This paper deals with Fuzzy Logic Model development to monitor the condition of power transformer. Fuzzy inference for condition monitoring using compositional rules have been designed and developed. In this paper, both the models are simulated using MATLAB.