Modeling the effect of chemical Composition on the Ultimate tensile strength of weld metal obtained from E۷۰۱۸ electrode using artificial neural networks

Optimal metallurgical properties of E۷۰۱۸ weld metal introduce this electrode as a useful industrial electrode. Chemical composition of E۷۰۱۸ weld metal affect the mechanical and chemical properties of weld metal significantly. Due to the relatively wide range of E۷۰۱۸ standard chemical composition tolerance, in this study, the relationship between the chemical composition and the ultimate tensile strength of deposited weld metal of E۷۰۱۸ electrode was investigated by using artificial neural networks (ANN). Studies on network hyperparameters illustrated that the best ANN for modeling the correlation between chemical composition and ultimate tensile strength of E۷۰۱۸ weld metal is perceptron neural network with two hidden layers with ۲ and ۵ neurons. The goodharmony between the predicted tensile strength of E۷۰۱۸ weld metal by trained neural network and experimental results indicated to the accuracy and capability of ANN for prediction the mechanical property of weld metal

کلیدواژه ها:

Artificial Neural Network ، Regression ، Perceptron ، E۷۰۱۸ Electrode ، ultimate tensile strength