Optimisation of submerged arc welding process parameters in hardfacing

In this paper, a feedforward neural network is used to model submerged arc welding (SAW) processes in hardfacing. The relationships between process parameters (arc current, arc voltage, welding speed, electrode protrusion, and preheat temperature) and welding performance (deposition rate, hardness, and dilution) are established, based on the neural network. A simulated annealing (SA) optimisation algorithm with a performance index is then applied to the neural network for searching the optimal process parameters. Experimental results have shown that welding performance can be enhanced by using this new approach.