In this study, we have presented Neuro-Fuzzy model for fault diagnosis of power transformer based on dissolved gas analysis (DGA). DGA is a very efficient tool for monitoring transformers in-service behavior to avoid catastrophic failures, costly outages and losses of production. Determination of the fault type with few key gases is a convenience for on-line gas-in-oil monitoring systems, used for detecting incipient faults. Three key gases Methane (CH4), Ethylene (C2H4) and Acetylene (C2H2) were chosen for this study. Neuro-Fuzzy is a reliable classification technique based on fuzzy and Artificial Neural Networks (ANN). Total accumulated amount of these gases were calculated and 100 percents (%) of each gas used as inputs of Neuro-Fuzzy. The output is one of the fault types PD, D1, D2, T1, T2, and T3. Classification accuracy has reached up to 76.0 %.