This thesis presents an investigation and a comparative study of four different approaches namely ANSI/IEEE standard models, Adaptive Neuro-Fuzzy Inference System (ANFIS), Multilayer Feedforward Neural Network (MFNN) and Elman Recurrent Neural Network (ERNN) to modeling and prediction of the top and bottom-oil temperatures for the 8 MVA Oil Air (OA)-cooled and 27 MVA Forced Air (FA)-cooled class of power transformers. The models were derived from real data of temperature measurements obtained from two industrial power installations. A comparison of the proposed techniques is presented for predicting top and bottom-oil temperatures based on the historical data measured over a 35 day period for the first transformer and 4.5 days for the second transformer with either a half or a quarter hour sampling time. Comparisons of the results obtained indicate that the hybrid neuro-fuzzy network is the best candidate for the analysis and prediction of the power transformer top and bottom-oil temperatures. The ANFIS demonstrated the best comparative performance in temperature prediction in terms of Root Mean Square Error (RMSE) and peak error.