The Development of an Artificial Neural Network Model to Predict Heating-Line Positions for Plate Forming in Induction Heating Process
Authors:
- 12 May 2009
- journal article
- research article
- Published by Taylor & Francis in Mechanics Based Design of Structures and Machines
- Vol. 37 (2) , 201-227
Abstract
An artificial neural network model can help manufacturers determine the positions of induction heating lines and their heating parameters to form a desired shape of plate. The vertical displacements of a deformed plate are considered as the input parameters and the selected induction heating lines as output parameters to develop the model. The training patterns of neural network are obtained using an analytical solution that is derived from the plate theory to predict plate deformations in induction heating process. The plastic region in the analytical solution of the angular deformation of a steel plate is obtained from the thermal analysis of the plate with the heat input calculated from the electro-magnetic analysis of the induction heating process.Keywords
This publication has 13 references indexed in Scilit:
- Derivation of simplified formulas to predict deformations of plate in steel forming process with induction heatingInternational Journal of Machine Tools and Manufacture, 2008
- Designing of suitable construction of high-frequency induction heating coil by using finite-element methodIEEE Transactions on Magnetics, 2005
- Thermal and magnetic field analysis of induction heating problemsJournal of Materials Processing Technology, 2005
- SIMULATIONS AND VERIFICATIONS OF INDUCTION HEATING ON A MOLD PLATEInternational Communications in Heat and Mass Transfer, 2004
- Numerical solution of 2D and 3D induction heating problems with nonlinear material properties taken into accountIEEE Transactions on Magnetics, 2000
- Analysis of a multilayered plate containing a cuboidal inclusion with eigenstrainsMechanics of Materials, 1999
- A computer aided finite element/experimental analysis of induction heating process of steelComputers in Industry, 1996
- Analysis of magneto-thermal coupled problem involving moving eddy-current conductorsIEEE Transactions on Magnetics, 1996
- Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights1990
- Neural computing overviewComputer Physics Communications, 1989