Neuro-genetic design centering of millimeter wave oscillators

Author

Sen, P. ; Pratap, R.J. ; Mukhopadhyay, R. ; Sarkar, S. ; Lee, C.-H. ; Pinel, S. ; May, G.S. ; Laskar, J.

Author_Institution

Sch. of ECE, Georgia Inst. of Technol., Atlanta, GA

fYear

2006

fDate

18-20 Jan. 2006

Abstract

In this paper, a new technique for design centering and the yield enhancement of millimeter-wave (MMW) circuits is presented using neural networks for circuit modeling and genetic algorithms for parametric yield optimization. A Monte Carlo based method is developed for the yield estimation utilizing the neural network models. The neuro-genetic methodology has been used for the design centering of 30 GHz cross-coupled VCO as well as a fixed-frequency 60 GHz oscillator. The results display significant yield enhancement i.e. 8% to 91% for 30 GHz VCO and 7% to 70% for the 60 GHz oscillator

Keywords

Monte Carlo methods; circuit CAD; circuit optimisation; genetic algorithms; integrated circuit design; millimetre wave oscillators; neural nets; voltage-controlled oscillators; 30 GHz; 60 GHz; Monte Carlo based method; circuit modeling; cross-coupled VCO; fixed-frequency oscillator; genetic algorithms; millimeter wave oscillators; millimeter-wave circuits; neural networks; neuro-genetic design centering; parametric yield optimization; voltage controlled oscillator; yield enhancement; Algorithm design and analysis; Design optimization; Displays; Genetic algorithms; Millimeter wave circuits; Millimeter wave technology; Monte Carlo methods; Neural networks; Voltage-controlled oscillators; Yield estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Silicon Monolithic Integrated Circuits in RF Systems, 2006. Digest of Papers. 2006 Topical Meeting on

Conference_Location

San Diego, CA

Print_ISBN

0-7803-9472-0

Type

conf

DOI

10.1109/SMIC.2005.1587929

Filename

1587929