Evaluation of Starting Current of Induction Motors Using Artificial Neural Network

Induction motors (ims) are widely used in industry including it be an electrical or not. however during starting period, their starting currents are so large that can damage equipment. therefore, this current should be estimated accurately to prevent hazards caused by it. in this paper, the artificial neural network (ann) as an intelligent tool is used to evaluate starting current peak of ims. both multilayer perceptron (mlp) and radial basis function (rbf) structures have been analyzed. six learning algorithms, backpropagation (bp), delta-bar-delta (dbd), extended delta-bar-delta (edbd), directed random search (drs), quick propagation (qp), and levenberg marquardt (lm) were used to train the mlp. the simulation results using matlab show that most developed anns can estimate the starting current peak of ims with good accuracy. however, it is proven that lm and edbd algorithms present better performance for starting current evaluation based on average of relative and absolute errors.