Neural Network-Based Optimization of VLSI Wafer Fabrication
基于神经网络方法的半导体生产工艺优化

A neural\|based manufacturing process control system for semiconductor factories is presented. Wafer fabrication is a dynamic, nonlinear,multivariable and complex industrial process.A model based on feedforward neural networks(FNN) is proposed to simulate the wafer manufacturing process. Learning from the historical technological records with a special dynamic learning method, the neural\|based model can approximate the function relationship between the technological parameters and the wafer yield precisely. A gradientdescent method to search a set of optimal technological parameters is used in order to lead to the maximum yield by simulation. The wafer yield increases by 7\^63% after the optimal parameters were applied in the wafer fabrication assembly.