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 −2 K −1 . The characteristics of the time-varying IHTC have also been discussed.

[1]  George-Christopher Vosniakos,et al.  Simulation-based selection of optimum pressure die-casting process parameters using neural nets and genetic algorithms , 2006 .

[2]  Y. Hwang,et al.  Applying neural networks to the solution of forward and inverse heat conduction problems , 2006 .

[3]  Anthony T. Patera,et al.  Inverse identification of thermal parameters using reduced-basis method , 2005 .

[4]  K. Y. Lam,et al.  Material characterization of functionally graded material by means of elastic waves and a progressive-learning neural network , 2001 .

[5]  Xu Han,et al.  A computational inverse technique for material characterization of a functionally graded cylinder using a progressive neural network , 2003, Neurocomputing.

[6]  Xu Han,et al.  Neural identification of rock parameters using fuzzy adaptive learning parameters , 2003 .

[7]  Carlos Alexandre dos Santos,et al.  Determination of transient interfacial heat transfer coefficients in chill mold castings , 2001 .

[8]  Matthew S. Dargusch,et al.  Development of a non intrusive heat transfer coefficient gauge and its application to high pressure die casting , 2005 .

[9]  Abdel Magid Hamouda,et al.  Numerical simulation of casting solidification in permanent metallic molds , 2006 .

[10]  Mariusz Krupiński,et al.  Computer aided classification of flaws occurred during casting of aluminum , 2005 .

[11]  Taegyu Kim,et al.  Time-varying Heat Transfer Coefficients between Tube-Shaped Casting and Metal Mold , 1997 .

[12]  T. Kumar,et al.  Spatial variation of heat flux at the metal–mold interface due to mold filling effects in gravity die-casting , 2008 .

[13]  N. Huber,et al.  A neural network tool for identifying the material parameters of a finite deformation viscoplasticity model with static recovery , 2001 .

[14]  H. Şahin,et al.  Determination of unidirectional heat transfer coefficient during unsteady-state solidification at metal casting-chill interface , 2006 .

[15]  Marcelo de Aquino Martorano,et al.  Heat transfer coefficient at the metal–mould interface in the unidirectional solidification of Cu–8%Sn alloys , 2000 .

[16]  S.M.H. Mirbagheri,et al.  Modeling of metalo-static pressure on the metal–mould interface thermal resistance in the casting process , 2007 .