Akademik Veri Yönetim Sistemi
Erzincan University Journal of Science and Technology , cilt.19, sa.1, ss.315-330, 2026 (TRDizin)
In this study, the noises, temperatures and loads of 8 transformers in Istanbul İkitelli Organized Industrial Zone, as well as ambient conditions, were monitored at different moments over a period of 4 months and their data were recorded. It has been observed that the noise levels give different results according to the changing environmental conditions. The received data were determined as inputs and desired targets in MATLAB environment. The data were modeled with feed forward artificial neural network and recurrent artificial neural network types and different training percentages. The estimation results closest to the target were tried to be obtained. As a result of the study, it was seen that the recurrent neural network model was better and it gave better results when the training percentage needed for the network kept high.