By Topic

A feedforward neural networks (FNN) used for semiconductor wafer fabrication parameters optimization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)

Semiconductor wafer fabrication process is a dynamic, very complex and multiphase system. The wafer performance is determined by so many factors in manufacturing process that it is very difficult to model the whole process with a statistical method. In this paper, an effective optimization strategy of the semiconductor manufacturing process is implemented. This method is based on a feedforward neural network (FNN), which uses a Gaussian function as the activation function of its hidden units and sigmoid as that of output unit. By training with samples collected from historical technological record, the static FNN model is built to fit the wafer fabrication process. Then some newer samples collected from the latest manufacturing lots are fed to retrain the network. During this retrain process, some “bad” or noisy samples are replaced by the new ones, a dynamic FNN model is built so that the trained network would fit the actual manufacturing process better and closely

Published in:

Neural Networks, 1999. IJCNN '99. International Joint Conference on  (Volume:6 )

Date of Conference:

Jul 1999