基于神经网络的集成电路生产过程建模与优化

NEURAL NETWORK-BASED OPTIMIZATION OF VLSI WAFER FABRICATION

以提高半导体生产线的成品率为目标 ,利用神经网络对半导体芯片生产过程进行了建模和优化 .首先使用神经网络方法建立模型 ,确定生产线上工艺参数和成品率之间的映射关系 ,构造多维映射函数曲面 ;随后对多维映射函数曲面进行搜索 ,搜索成品率最高的最优点 ,据此确定工艺参数的规范值 ;最后 ,根据优化后的工艺参数规范进行实际生产 .采用这种优化建议 ,半导体生产线的平均成品率由 51 .7%提高到了 57.5% .

A neural-based manufacturing process control system is presented to improve the lot yield of wafer fabrication. A model based on feedforward neural networks 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 describe the function relationship between the technological parameters and the wafer yield. Then a gradient-descent method is used to search a set of optimal technological parameters that lead to the maximum yield. Finally the specifications of the wafer fabrication are determined according to the optimal parameters. The wafer yield increases by 11.2% after the optimized specifications are applied to the wafer fabrication assembly.