A machine learning based sensitivity analysis of the GTN damage parameters for dynamic fracture propagation in X70 pipeline steel

The Gurson–Tvergaard–Needleman (GTN) damage model is widely used to predict ductile failure initiation and propagation. However, the material-dependent parameters can show a significant spread when determined for same steel grade material. Different calibration procedures optimisation processes cause variation in obtained parameter values. Furthermore, there no clear consensus on which require calibration. In this study, influence of dynamic fracture behaviour X70 pipeline investigated. A sensitivity analysis performed finite element Charpy V-Notch (CVN) specimen. Seven GTN are considered total 70 simulations. feedforward back-propagating artificial neural network (ANN) constructed trained using data through numerical connected weights (CW) algorithm allows determine relative each energy. It was observed that void growth acceleration factor plays an important role with respect influences. Remarkably, mean nucleation strain, $$ \varepsilon_{N} has highest importance whilst critical volume fraction, f_{c} —which as crucial parameter—showed smallest low. On contrary, considering high factor, becomes most influential parameter. Based parameter, it suggested f_{0} , f_{F} f_{N} should be selected individual application. Finally, applied machine learning approach energy given set steel. able provide satisfactory approximation CVN