Petri neural network model for the effect of controlled thermomechanical process parameters on the mechanical properties of HSLA steels

The effect of composition and controlled thermomechanical process parameter s on the mechanical properties of HSLA steels is modelled using the Widrow- Hoff's concept of training a neural net with feed-forward topology by apply ing Rumelhart's back propagation type algorithm for supervised learning, us ing a Petri like net structure. The data used are from laboratory experimen ts as well as from the published literature. The results from the neural ne twork are found to be consistent and in good agreement with the experimente d results.