Title :
Modeling of APCVD-doped silicon dioxide deposition process by a modular neural network
Author :
Natale, Corrado Di ; Proietti, Emanuela ; Diamanti, Roberto ; D´Amico, Arnaldo
Author_Institution :
Dept. of Electron. Eng., Univ. of Rome, Italy
fDate :
2/1/1999 12:00:00 AM
Abstract :
This paper describes a methodology based on the combined utilization of both a multisensor system and an optimized artificial neural network that has been applied to equipment utilized for the production of doped silicon dioxide films. The model exhibits an average relative error around 1% in predicting the concentrations of dopants and the thickness of the oxide layer. One of the major benefits of such a predictor is the ability of providing an on-line estimate of the process yield, thus avoiding off-line testing and gaining a significant reduction of risks of wafer loss. The neural model here described is currently utilized as a control tool at the Texas Instruments Avezzano, Italy, plant
Keywords :
chemical vapour deposition; insulating thin films; integrated circuit yield; neural nets; process control; semiconductor process modelling; silicon compounds; APCVD-doped oxide deposition process; SiO2; Texas Instruments; average relative error; control tool; modular neural network; multisensor system; off-line testing; oxide layer thickness; process yield; wafer loss; Artificial neural networks; Multisensor systems; Optimization methods; Predictive models; Production systems; Semiconductor films; Semiconductor process modeling; Silicon compounds; Testing; Yield estimation;
Journal_Title :
Semiconductor Manufacturing, IEEE Transactions on
