Parametric identification of fuzzy model for power transformer based on real operation data
Eugen Bardyk, Nickolai P. Bolotnyi · Eastern-European Journal of Enterprise Technologies · 2017
The research is devoted to the development of a fuzzy model for assessing the technical condition of power oil transformers based on the DGA. The parametric identification of optimal values of membership functions of fuzzy terms for linguistic variables is carried out to increase the reliability and objectivity of fault identification. For this purpose, it is proposed to use the theory of fuzzy sets, the nonlinear optimization method. A comparative analysis of the fuzzy simulation results for the technical condition with the fault diagnostic results on existing power transformers has confirmed high efficiency. The diagnostic accuracy of the adapted fuzzy model for the technical condition assessment of power transformers is 97 %, which is acceptable in the power transformers diagnostic. The developed model will be used for further research on the development of an algorithm for making effective decisions regarding the operation strategy of power transformers and preventive control of the subsystem operation of electric power systems. The obtained results of the fuzzy simulation for the technical condition assessment of power transformers give grounds to assert regarding the possibility of implementation in software of operation risk analysis of electric power systems for power supply companies