Machine learning approaches for predicting geometric and mechanical characteristics for single P420 laser beads clad onto an AISI 1018 substrate

The final mechanical and physical properties should be predicted in tandem with the bead geometry characteristics for effective additive manufacturing (AM) solutions processes such as directed energy deposition. Experimental approaches to investigate are costly, simulation time-consuming. Alternative artificial intelligent (AI) systems explored they a powerful approach predict properties. In present study, geometrical well (residual stress hardness) single clads investigated. data is used calibrate multi-physics finite element models, both sets seed AI models. adaptive neuro-fuzzy inference system (ANFIS) feed-forward back-propagation neural network (ANN) utilized explore their effectiveness 1D (discrete values), 2D (bead cross-sections), 3D (complete bead) domains. prediction results evaluated using mean relative error measure. ANFIS predictions more precise than those from ANN domains, but had less scenario. These models capable of predicting values very well, including capturing transient regions; however, this research extended multi-bead scenarios before conclusive “best approach” strategy can determined.