Application of improved BP algorithm to the optimized formulation of ceramics glaze

This paper takes a kind of ceramic glaze as an example, and builds an improved BP neural network model for optimizing the formulation on ceramic glaze. The improved BP neural network adopts Levenberg-Marquardt algorithms. The paper reviews how to build the ceramic formulation optimization model based on BP artificial neural network, including the establishment of neural network, the training, and the inspection of results. Meanwhile, the software Matlab7 has a neural network toolbox. The BP network model of ceramic formulation optimization is simulated by Matlab7. The model has achieved the good effect in the prediction precision and the algorithm convergence speed respects. So, application of improved BP algorithm has an important significance on ceramic formulation optimization research.