کاربرد نگاشت فضايي عصبي در مدل‌سازي ادوات نيمه‌هادي
محورهای موضوعی : مهندسی برق و کامپیوتر
مهدی گردی ارمکی
1
(دانشگاه تربیت معلم سبزوار)
سیدابراهیم حسینی
2
(دانشگاه تربیت معلم سبزوار)
محمدکاظم انوري‌فرد
3
(فني و مهندسي شرق گيلان)
کلید واژه: شبکه عصبي RBF نگاشت فضايي عصبي مدل‌سازي نيمه‌هادي معادله بولتزمن,
چکیده مقاله :
در اين مقاله روش جديد و کارآمدي براي مدل‌سازي دقيق افزاره‌هاي نيمه‌هادي با استفاده از مدل تقريبي و به کمک شبکه عصبي ارائه شده است. بر خلاف مدل‌هاي دقيق که داراي پيچيدگي بالا و هزينه زماني و پردازشي زيادي هستند، روش پيشنهادي از پيچيدگي کمتر و سرعت پردازش بيشتري برخوردار است. در اين روش از شبکه عصبي RBF براي محاسبه پارامتر اصلاحي در مدل نفوذ - رانش استفاده شده است. بدين صورت حل مدل تقريبي اصلاح‌شده منجر به جواب دقيق مي‌شود. روش پيشنهادي ابتدا براي ديود n - i - n سيليکوني به صورت يک‌بعدي و سپس براي ترانزيستور اثر ميداني سيليکوني به صورت دوبعدي براي دو حالت درون‌يابي و برون‌يابي در رنج محدود، شبيه‌سازي شده است که نتايج آن براي متغيرهاي اساسي مدل، مثل توزيع الکترون و پتانسيل در طول افزاره در ولتاژهاي مختلف، دقت بالاي روش پيشنهادي را تأييد مي‌کنند.
In this paper an efficient method for modeling semiconductor devices using the drift-diffusion (DD) model and neural network is presented. Unlike HD model which is complicated, time consuming with high processing cost, the proposed method has lower complexity and higher simulate speed. In our method, a RBF neural network is used to modify DD parameters. The modified DD model can generate simulate results of accurate HD model. The proposed method is first applied to a silicon n-i-n diode in one dimension, and then to a silicon thin-film MOSFET in two dimensions, both for interpolation and extrapolation. The obtained results for basic variables, i.e., electron and potential distribution for different voltages, confirm the high efficiency of the proposed method.
[1] A. Khakifirooz and D. Antoniadis, "MOSFET performance scaling, part I: historical trends," IEEE Trans. on Electron Devices, vol. 55, no. 6, pp. 1401-1408, Nov. 2008.
[2] A. Khakifirooz and D. Antoniadis, "MOSFET performance scaling, part II: feture directions," IEEE Trans. on Electron Devices, vol. 55, no. 6, pp. 1391-1400, Nov. 2008.
[3] Q. J. Zhang and K. C. Gupta, Neural Networks for RF and Microwave Design, Norwood, MA: Artech House, 2000.
[4] A. Veluswami, M. S. Nakhla, and Q. J. Zhang, "The application of neural networks to EM-based simulation and optimization of interconnects in high-speed VLSI circuits," IEEE Trans. Microwave Theory Tech., vol. 45, no. 5, pp. 712-723, May 1997.
[5] Y. Harkouss, J. Rousset, H. Chehade, E. Ngoya, D. Barataud, and J. P. Teyssier, "The use of artificial neural networks in nonlinear microwave devices and circuits modeling: an application to telecommunication system design," Int. J. RF and Microwave Computer-Aided Engineering, vol. 9, no. 3, pp. 198-215, May 1999.
[6] M. Lazaro, I. Santamaria, and C. Pantaleon, "NNs for large and small-signal modeling of MESFET/HEMT transistors," IEEE Trans. on Circuits Measure, vol. 50, no. 6, pp. 1587-1593, Dec. 2001.
[7] S. Goasguen and S. M. El-Ghazaly, "A practical large - signal global modeling simulation of a microwave amplifier using artificial neural network," IEEE Microwave and Guided Wave Letters, vol. 10, no. 7, pp. 273-275, Jul. 2000.
[8] P. H. da F. Silva, M. A. B. de Melo, and A. D. D. Neto, "Using neural network models for efficient GaAs MESFET time domain nonlinear circuit analysis," in Proc. IJCNN, vol. 3pp. 2282-2287, 2002.
[9] J. W. Bandler, M. A. Ismail, J. E. Rayas - Sanchez, and Q. J. Zhang, "Neuromodeling of microwave circuits exploiting space - mapping technology," IEEE Trans. Microw. Theory Tech., vol. 47, no. 12, pp. 2417-2427, Dec. 1999.
[10] L. Zhang, J. Xu, M. C. E. Yagoub, R. T. Ding, and Q. J. Zhang, "Efficient analytical formulation and sensitivity analysis of neuro -space mapping for nonlinear microwave device modeling," IEEE Trans. Microw. Theory Tech., vol. 53, no. 9, pp. 2752-2767, Sep. 2005.
[11] M. Lundstrom, Fundamentals of Carrier Transport, 2nd ed., Cambridge University Press, 2000.
[12] S. E. Hosseini and R. Faez, "Novel quantum hydrodynamic equations for semiconductor devices," Jap. J. Appl. Phys., pt. 1, vol. 41, n. 3A, 1300-1304, 15 Mar. 2002.
[13] S. Hatami, M. Y. Azizi, H. R. Bahrami, D. Motavalizadeh, and A. Afzali-Kusha, "Accurate and efficient modeling of SOI MOSFET with technology independent neural networks," IEEE Trans. on Computer Aided Design of Integrated Circuits and Systems, vol. 23, no. 11, pp. 1580-1587, Nov. 2004.
[14] S. Heykin, Neural Networks: A Comprehensive Foundation, Prentice Hall, 2nd Edition, 1998.
[15] C. Christodoulou and M. Georgiopoulos, Applications of Neural Networks in Electromagnetics, Artech House Publishers, 2001.
[16] B. Goffe, G. Ferrier, and J. Rogers, "Global optimization of statistical function with simulated annealing," J. Econometrics, vol. 60, no. 1-2, pp. 65-100, Jan./Feb. 1994.