Neural Network Based Analysis Of Isolated Asynchronous Generator

This paper deals with the use of Artificial Neural Network (ANN) for performance analysis of Isolated Asynchronous Generator (IAG) feeding star-connected lamp load. Graph theory and loop impedance method have been used for the analysis of IAG, which leads to two higher order equations where the per unit magnetizing reactance "Xm" and per unit generated frequency "a" are considered as the unknown variables. The two non-linear equations are solved using NewtonRaphson technique and the data is fed to the neural network for training. The results obtained from ANN technique have been weighted against the experimental results. It is found that the simulated and the experimental results are very close to each other which indicates the efficacy of the proposed neural network model.