сотрудник с 01.01.2019 по 01.01.2021
Воронежская область, Россия
Воронежская область, Россия
Россия
АО "Научно-исследовательский институт электронной техники"
Россия
В статье говорится о создании поведенческой модели металлооксидных латеральных транзисторов (LDMOS), базирующихся на нейронной сети типа многослойный персептрон. Модель идентифицируется с использованием алгоритма обратного распространения. Продемонстрирован процесс создания модели ИНС с использованием Pytorch, фреймворка машинного обучения для языка Python, с последующим переносом на стандартный язык моделирования аналоговых схем Verilog-A.
LDMOS, ИНС, Verilog-A, Pytorch, поведенческая модель
1. Tsividis, Y. Operation and Modeling of the MOS Transistor / Y. Tsividis. - McGraw-Hill, New York,1999. - 723 p.
2. Khakifirooz, A. A simple semiempirical short-channel MOSFET current-voltage model continuous across all regions of operation and employing only physical parameters / A. Khakifirooz, O.M. Nayfeh, D. Antoniadis // IEEE Transactions on Electron Devices. - 2009. - Т. 56, № 8. - Pp. 1674-1680.
3. Root, D.E. The large-signal model: Theoretical foundations, practical considerations, and recent trends / D.E. Root [et al.] //Nonlinear Transistor Model Parameter Extraction Technique. - 2011. - Pp. 123-170.
4. Zhang, Q.J. Artificial neural networks for RF and microwave design-from theory to practice / Q.J. Zhang, K.C. Gupta, V.K. Devabhaktuni // IEEE transactions on microwave theory and techniques. - 2003. - Т. 51, № 4. - Pp. 1339-1350.
5. Feng, F. Multifeature-assisted neuro-transfer function surrogate-based EM optimization exploiting trust-region algorithms for microwave filter design / F. Feng [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2019. - Т. 68, № 2. - Pp. 531-542.
6. Na, W. Advanced extrapolation technique for neural-based microwave modeling and design / W. Na [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2018. - Т. 66, № 10. - Pp. 4397-4418.
7. Kabir, H. Automatic parametric model development technique for RFIC inductors with large modeling space / H. Kabir, L. Zhang, K. Kim // 2017 IEEE MTT-S International Microwave Symposium (IMS). - IEEE, 2017. - Pp. 551-554.
8. Jin, J. Deep neural network technique for high-dimensional microwave modeling and applications to parameter extraction of microwave filters / J. Jin [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2019. - Т. 67, № 10. - Pp. 4140-4155.
9. Du, X. ANN-based large-signal model of AlGaN/GaN HEMTs with accurate buffer-related trapping effects characterization / X. Du // IEEE Transactions on Microwave Theory and Techniques. - 2020. - Т. 68, № 7. - Pp. 3090-3099.
10. Zhao, P. Homotopy optimization of microwave and millimeter-wave filters based on neural network model / P. Zhao, K. Wu // IEEE Transactions on Microwave Theory and Techniques. - 2020. - Т. 68, № 4. - Pp. 1390-1400.
11. Xiao, L.Y. Semisupervised radial basis function neural network with an effective sampling strategy / L.Y. Xiao [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2019. - Т. 68, № 4. - Pp. 1260-1269.
12. Li, S.Q. Efficient modeling of Ku-band high power dielectric resonator filter with applications of neural networks / S.Q. Li [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2019. - Т. 67, № 8. - Pp. 3427-3435.
13. Feng, F. Parametric modeling of microwave components using adjoint neural networks and pole-residue transfer functions with EM sensitivity analysis / F. Feng [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2017. - Т. 65, № 6. - Pp. 1955-1975.
14. Zhang, W. Space mapping approach to electromagnetic centric multiphysics parametric modeling of microwave components / W. Zhang [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2018. - Т. 66, № 7. - Pp. 3169-3185.
15. Feng, F. Parallel gradient-based EM optimization for microwave components using adjoint-sensitivity-based neuro-transfer function surrogate / F. Feng [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2020. - Т. 68, № 9. - Pp. 3606-3620.
16. Zhang, C. Cognition-driven formulation of space mapping for equal-ripple optimization of microwave filters / C. Zhang [et al.] // IEEE transactions on microwave theory and techniques. - 2015. - Т. 63, № 7. - Pp. 2154-2165.
17. Zhang, J. Polynomial chaos-based approach to yield-driven EM optimization / J. Zhang [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2018. - Т. 66, № 7. - Pp. 3186-3199.
18. Sen, P. Neural-network-based parasitic modeling and extraction verification for RF/millimeter-wave integrated circuit design / P. Sen [et al.] // IEEE Transactions on Microwave theory and Techniques. - 2006. - Т. 54, № 6. - Pp. 2604-2614.
19. Root, D.E. Future device modeling trends / D.E. Root // IEEE Microwave Magazine. - 2012. - Т. 13, № 7. - Pp. 45-59.
20. Liu, W. A time delay neural network based technique for nonlinear microwave device modeling / W. Liu [et al.] // Micromachines. - 2020. - Т. 11, № 9. - Pp. 831.
21. Zhao, Z. Space mapping technique using decomposed mappings for GaN HEMT modeling / Z. Zhao [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2020. - Т. 68, № 8. - Pp. 3318-3341.
22. Rizzoli, V. Computer-aided optimization of nonlinear microwave circuits with the aid of electromagnetic simulation / V. Rizzoli [et al.] // IEEE transactions on microwave theory and techniques. - 2004. - Т. 52, № 1. - Pp. 362-377.
23. Xu, J. Neural-based dynamic modeling of nonlinear microwave circuits / J. Xu [et al.] // IEEE Transactions on Microwave Theory and Techniques. - 2002. - Т. 50, № 12. - Pp. 2769-2780.
24. Liu, T. Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks / T. Liu, S. Boumaiza, F.M. Ghannouchi // IEEE Transactions on Microwave Theory and Techniques. - 2004. - Т. 52, № 3. - Pp. 1025-1033.
25. Cao, Y. A new training approach for robust recurrent neural-network modeling of nonlinear circuits / Y. Cao, Q.J. Zhang // IEEE Transactions on Microwave Theory and Techniques. - 2009. - Т. 57, № 6. - Pp. 1539-1553.
26. Yan, S. Recurrent neural network technique for behavioral modeling of power amplifier with memory effects / S. Yan, C. Zhang, Q.J. Zhang // International Journal of RF and Microwave Computer-Aided Engineering. - 2015. - Т. 25, № 4. - Pp. 289-298.
27. Mkadem F., Boumaiza S. Physically inspired neural network model for RF power amplifier behavioral modeling and digital predistortion //IEEE Transactions on Microwave Theory and Techniques. - 2011. - Т. 59, № 4. - Pp. 913-923.
28. White, H. Artificial neural networks / H. White [et al.]. - Cambridge, Mass. Blackwell, 1992.
29. Wang, F. Neural network structures and training algorithms for RF and microwave applications / F. Wang [et al.] // International Journal of RF and Microwave Computer-Aided Engineering. - 1999. - Т. 9, №. 3. - Pp. 216-240.
30. Ruder, S. An overview of gradient descent optimization algorithms / S. Ruder // arXiv preprint arXiv:1609.04747. - 2016.
