Investigation of the temperature cycle in effusion treatment of plates using neural network

After rolling, the plates will cool down in a delayed manner either in free piles or stacked in bins. In the case of delayed cooling, hydrogen will have the opportunity for effusion. The efficiency of effusion is thereby controlled by the time evolution of the plate temperatures in the bin. In order to get information on that evolution, the stack-in and stack-out temperatures were measured. As there are different parameters influencing the temperature evolution, a neural network approach was used for quantification of parameter dependencies. By that it was possible to quantify the influence of each parameter separately. The result of that investigation was used for process optimization.