Title :
3D finite element computation combined with neural networks prediction of eddy current and temperature distribution in TFIH equipments
Author :
Yang, Xiaoguang ; Wang, Youhua ; Liu, Fugui ; Yan, Weili
Author_Institution :
Hebei Univ. of Technol., Tianjin, China
Abstract :
In this paper it describes a method of prediction of eddy current and temperature distribution on the continuously moving thin conducting strips in transverse flux induction heating (TFIH) equipments with the aid of two neural networks. One is used for the eddy current field and the other for the temperature field. The prediction results can be used as initial solutions for the finite element calculation of this nonlinear coupled electromagnetic-thermal problem, which reduce the optimisation time of TFIH inductor structure for improving the temperature distribution on the surface of the continuously moving thin strips.
Keywords :
eddy currents; electromagnetic coupling; finite element analysis; induction heating; inductors; neural nets; power engineering computing; temperature distribution; eddy current distribution; finite element calculation; neural network; nonlinear coupled electromagnetic-thermal problem; optimisation time; temperature distribution; temperature field; thin conducting strip; transverse flux induction heating; Coils; Computer networks; Distributed computing; Eddy currents; Finite element methods; Intelligent networks; Neural networks; Strips; Temperature distribution; Thermal pollution;
Conference_Titel :
Electrical Machines and Systems, 2003. ICEMS 2003. Sixth International Conference on
Conference_Location :
Beijing, China
Print_ISBN :
7-5062-6210-X
