Inverse identification of interfacial heat transfer coefficient between the casting and metal mold using neural network

Abstract

The effect of the heat transfer coefficient at the casting-mold interface is of prime importance to improve the casting quality, especially for castings in metal molds. However, it is difficult to determine the values of heat transfer coefficient from experiments due to the influence of various factors, such as contacting pressure, oxides on surfaces, roughness of surfaces, coating material, coating thickness and gap formation caused by the deformation of casting and mold, etc. In the present paper, the interfacial heat transfer coefficient (IHTC) between the casting and metal mold is identified by using the method of inverse analysis based on measured temperatures, neural network with back-propagation algorithm and numerical simulation. Then, by applying the identified IHTC in finite element analysis, the comparison between numerical calculated and experimental results is made to verify the correctness of method. The results show that the numerical calculated temperatures are in good agreement with experimental ones. These demonstrate that the method of inverse analysis is a feasible and effective tool for determination of the casting-mold IHTC. In addition, it is found that the identified IHTC varies with time during the casting solidification and varies in the range of about 100–3200 Wm −2K −1. The characteristics of the time-varying IHTC have also been discussed.