Penetration depth, defined as the distance from the surface of the base material to the deepest point of the molten zone, is a critical factor influencing the strength and mechanical properties of welds. This study investigates the effects of process parameters in submerged arc welding (SAW) on penetration depth, utilizing a two-hidden-layer artificial neural network (ANN) for modeling. The input parameters include arc voltage, welding current, electrode stick-out, welding speed, and the thickness of a manganese-enriched nanoparticle layer, with penetration depth as the output variable. The results demonstrate that increasing the welding current to 700 amps enhances heat transfer to the molten pool, thereby improving base material melting and penetration depth. Similarly, raising the arc voltage from 24 to 32 volts results in a moderate increase in penetration depth due to higher heat input while maintaining a relatively stable electrode melting rate. These findings highlight the potential of optimizing SAW parameters to achieve consistent weld quality and desirable mechanical prop

Keywords