Application of BP neural network in combination with mathematical models to prediction of plate crown

This paper analyzes a simple plate crown model and gives an on-line model relevant to it. A new method is proposed to optimize plate crown model basis on BP neural networks to improve the control accuracy of crown predicted. The fuzzy cluster analysis was used as the preprocessing to select the sample set, which can increase the speed of study. It is shown that the prediction precision of BP neural networks can be improved greatly according to many on-line data and the optimization model can be adapted to varied techniques and equipment.