Optimal etch time control design using neuro-dynamic programming

Author

Yang, Lei ; Si, Jennie

Author_Institution

Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ, USA

fYear

2001

fDate

2001

Firstpage

75

Lastpage

78

Abstract

This paper focuses on using a new learning algorithm, namely neural dynamic programming (NDP), to design the optimal etch time control system for a reactive ion etch process. First a predictive neural network model is built. This model represents the relation between some state variables and the resulting thickness remain. The NDP is employed to determine the optimal etch time based on the predictive film thickness remain model. Simulation results show that NDP is a viable learning optimization tool. The controlled film thickness remains have smaller variances in a few tested lots of wafers than those measured from 89 wafers during production

Keywords

dynamic programming; feedforward neural nets; learning (artificial intelligence); optimal control; optimisation; process control; semiconductor process modelling; sputter etching; thickness control; action networks; adaptive learning; control system design; controlled film thickness; critic networks; end point detection; goal attainment programming; hidden neurons; learning algorithm; learning optimization tool; neural dynamic programming; nonlinear multilayer feedforward network; nonlinear prediction model; optimal etch time control; predictive film thickness remain model; predictive neural network model; reactive ion etch process; state variables; Algorithm design and analysis; Control design; Control systems; Dynamic programming; Etching; Heuristic algorithms; Neural networks; Optimal control; Predictive models; Semiconductor device modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Semiconductor Manufacturing Symposium, 2001 IEEE International

Conference_Location

San Jose, CA

Print_ISBN

0-7803-6731-6

Type

conf

DOI

10.1109/ISSM.2001.962918

Filename

962918