Using neural network models for predicting mechanical properties after hot plate rolling processes

摘要

The neural network model for prediction of mechanical properties of hot rolled plates wasconstructed in the present work. The use of a neural network gives good results in predicting anon-linear relationship between a steel chemical composition, microstructure parameters, coolingrate and final mechanical properties. The model can be used to describe the spread of the ferriticgrain size and the distribution of mechanical properties in the thickness of final plates.