A welding process that combined plasma are welding with laser welding was u
sed to make autogenous head on plate welds on a sheet stock of a carbon ste
el. A wide range of welding parameters (are current, laser power, weld spee
d) was employed. The experimental weld pool shapes were analysed and the da
ta were used to train it neural network to predict weld pool shape as a fun
ction of process conditions. The predictions of the neural network model sh
owed excellent agreement with the experimental results, indicating that a n
eural network model is a viable means for predicting weld pool shape. Using
the model, a parametric study was carried out to examine the influence of
process conditions on the final weld pool profile.