A fuzzy neural network approach for die yield prediction of wafer fabrication line

  • Authors:
  • Lihui Wu;Jie Zhang;Gong Zhang

  • Affiliations:
  • CIM Research Institute, Shanghai Jiao Tong Univ., Shanghai, China;CIM Research Institute, Shanghai Jiao Tong Univ., Shanghai, China;CIM Research Institute, Shanghai Jiao Tong Univ., Shanghai, China

  • Venue:
  • FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

To improve prediction accuracy of die yield, a novel fuzzy neural networks (FNN) based yield prediction approach is proposed. The yield prediction model is built, in which the impact factors of yield, including physical parameters, electrical test parameters and wafer defect parameters are considered simultaneously and are taken as independent variables. A back-propagation algorithm is used to train and adjust the weight parameters and variables of fuzzy membership functions. By historical experimental data of wafer fabrication line in shanghai, the comparison experiment shows that the FNN prediction model can get better precision than the Poisson model, the negative binomial model and neural network model.