Application of neural networks to heat transfer calculation in a round billet continuous casting mould

Based on the measured data of mould temperature during continuous casting of round billets, the feasibility of using neural networks to solve the inverse problem of heat transfer of a continuous casting mould was discussed. The combination of neural networks with numerical simulation was proposed to calculate the heat transfer of the mould. The results show that the temperature and heat flux field calculated are in agreement with the experimental ones, which could correctly reveal the characteristics of non-uniform heat transfer around the mould circumference.