Modelling and analysis of delta ferrite content in claddings deposited by flux cored arc welding using a neural network
Measurement of delta ferrite in cladding gives important insight into the future mechanical and corrosion resistant behaviour of the cladded structures. The amount of delta ferrite formed during cladding is influenced by process parameters such as welding speed, welding current, and nozzle-to-plate distance. Therefore, it is essential to predict the effect of these parameters on the formation of delta ferrite. This article discusses the development of an artificial neural network model to predict the delta ferrite content in austenitic stainless-steel claddings deposited by the flux cored arc welding process. A novel approach of using the design of experiments to collect data to train the network has been adopted in this investigation. The study revealed that the delta ferrite content can be predicted more accurately using the neural networks with a minimum number of experiments. The results also indicated that welding current and speed have a significant influence on the amount of ferrite and the interaction effects of these parameters play a major role in determining ferrite in the claddings.