Development of an ANN-based generalized model for hardness prediction of SPSed AlCoCrCuFeMnNiW containing high entropy alloys

The present study reports the development of AlCrFeMnNiWx (x = 0, 0.05, 0.1, 0.5 mol) high entropy alloys (HEAs), processed by mechanical alloying (MA) cum spark plasma sintering (SPS) techniques, followed by the evaluation of the mechanical properties. Furthermore, an artificial Neural Network (ANN)-based model has been developed for the prediction of the hardness of a particular class of HEAs by using 36 HEAs available data from the literature, which stimulates the data by utilizing training, validation, and testing methods in a useful way with excellent overall regression coefficient (R) is 97.1 %. A backpropagation ANN model (9-9-1 neuron system) has been used to predict the value of the hardness with an accuracy of 95.9 %, which is based on elemental composition and sintering temperature. The predicted capability of the developed model also provides the freedom to choose the HEA composition with the required hardness of HEA without any experimental trials.