APPLICATION OF COMBINED GRAY NEURAL NETWORK (GMNN) FOR THE BTP IN SINTERING PROCESS.

Gray theory is a truly multidisciplinary and generic theory that deals with systems that are characterized by poor information and/or for which information is lacking, so it was very important to expand the current gray theory and find out an appropriate model building method. In this paper, an improved gray GM (1, 1) model, using a technique that combines gray residual modification with artificial neural network. The fluctuation of data sequence is weakened by the gray theory and the neural network is capable of processing nonlinear adaptable information, and the GMNN is a combination of those advantages. Therefore, the paper constructs a model base of burn-through point and the simulation proves that the model base has a good performance and can improve the prediction accuracy. [ABSTRACT FROM AUTHOR]