Neural modeling of an induction furnace using robust learning criteria

Neural models are built to predict the temperature of the steel sheet at th e exit of an induction furnace in a galvanizing line, with respect to the p ower applied and to the operating conditions. The second section briefly de scribes the induction furnace in the galvanizing line and presents the info rmation available for modeling. The third section recalls the structure of the one hidden layer feedforward neural network basically used for system i dentification and describes the Gauss-Newton training rule based on a quite general error criterion. The following section derives different training algorithms from three robust forms of the general criterion. In the last pa rt, the three robust learning rules are employed on the available data. Res ults are compared with those of the standard Levenberg-Marquardt update rul e. The best model obtained is then pruned to improve the generalization abi lity of the network.