Neuro fuzzy schemes for fault detection in power transformer

This paper proposes fuzzy system and neural network approaches to identify the incipient faults in the power transformer using dissolved gas analysis (DGA) method. Using the IEC/IEEE DGA criteria and the gas concentration values as references the fuzzy diagnosis system and neural network are built. The proposed systems are verified using practical data collected from Electricity Board. The fuzzy system is tested with triangular, trapezoidal and Gaussian membership functions and its effectiveness is analyzed through simulation in terms of accuracy in identifying the transformer faults. The proposed Back propagation network is verified to overcome the drawbacks of conventional methods. The proposed schemes are simulated and tested in the software environment. The simulation results are presented.