A new model to predict the critical fracture load of functionally graded steels based on the artificial neural network

The averaged value of the Strain Energy Density (SED) over a well-defined volume is used to evaluate the static and fatigue strength of notched components. In this paper, the SED approach is used to assess the critical fracture load of V-notched components made of functionally graded steels (FGSs) under mixed mode loading. Over 700 finite element models by considering different values of notch radius (0.2 to 1 mm), notch depth (4.5 to 7 mm), notch opening angle (10° to 90°) and the distance of the applied load from the notch bisector line (5 to 15 mm) have been studied. The models have been used to train an Artificial Neural Network (ANN) to obtain a new simple model to predict the critical fracture load of FGS. The output of the ANN model sounds a good agreement with the experimental and finite element data.