Title :
Neural network control of a plasma gate etch: Early steps in wafer-to-wafer process control
Author :
Rietman, E.A. ; Patel, S.H. ; Lory, E.R.
Author_Institution :
Bell Labs, Murray Hill, NJ, USA
Abstract :
A gate oxide thickness controller for a plasma etch reactor has been developed. This controller is for 0.9-μm technology. By monitoring certain processes, signatures are fed forward into a neural network trained by the backpropagation method. It is possible to predict in real time the correct over-etch time on a wafer-by-wafer basis. Computer simulations indicate that the neural network is equivalent to humans for this task. The uniqueness of this controller is compared with a previous controller for a 1.25-μm technology gate etch process
Keywords :
backpropagation; feedforward neural nets; integrated circuit manufacture; intelligent control; neurocontrollers; process control; sputter etching; thickness control; wafer-scale integration; 0.9 micron; backpropagation; gate oxide thickness controller; neural network control; plasma gate etch; wafer-to-wafer process control; Backpropagation; Computer simulation; Computerized monitoring; Etching; Humans; Inductors; Neural networks; Plasma applications; Plasma simulation; Thickness control;
Conference_Titel :
Electronic Manufacturing Technology Symposium, 1993, Fifteenth IEEE/CHMT International
Conference_Location :
Santa Clara, CA
Print_ISBN :
0-7803-1424-7
DOI :
10.1109/IEMT.1993.398165
