This paper presents the development of an artificial neural network (ANN) model for the prediction of heating-line or heating-triangle positions and their parameters in induction heating process to form a desired shape of plate, especially a concave curved surface. This model of ANN can help manufacturers to determine the positions of induction heating lines or triangles and their parameters to form a desired shape of plate. The vertical displacements and transverse shrinkage of nodes on the plate are used as inputs to the network and the selected induction heating positions and the parameters are the output of the models. The training data for the ANN model are obtained using an analytical solution based on laminated plate theory combined with Finite Element Method (FEM) solutions. A feed-forward ANN with 242-400-490 arrangement was developed for predicting the induction heating conditions. The developed neural network model is tested to show its feasibility to determine the heating positions on the surface of a flat steel plate in the induction heating process for forming a desired concave curved surface.