Modelling of hysteresis loop and magnetic behaviour of Fe-48Ni alloys using artificial neural network coupled with genetic algorithm

Abstract

In this work, the application of a hybrid artificial neural network and genetic algorithm is proposed for prediction of hysteresis loop and magnetic properties of Fe-48Ni permalloy as an important and widely used soft magnetic material. In this case, thickness of samples, annealing temperature, holding time and field strength are considered as the network inputs and the magnetization as the output. The experiments were performed at thicknesses of 0.4, 0.8, 1.2 and 1.6 mm which are related to 80%, 60%, 40% and 20% rolled samples, annealing temperatures of 600, 700, 800, 900, 1000 and 1100 °C, different holding times of 5, 10, 20 and 60 min and field strength between −10,000 and +10,000 Oe. Using an artificial neural network coupled with genetic algorithm, Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values found as 2.69 and 3.47 (emugr) for the training part and 3.95 and 4.77 (emugr) for the test. Finally, the major conclusions of this research show that ANNs as powerful computational techniques in modeling of nonlinear systems, can be reliably used in the prediction of hysteresis and magnetic properties from the input variables in Fe-48Ni permalloys.