Résumé
Largement utilisés dans la conception de modules multipuces micro-ondes, les modèles de composants passifs font l’objet de recherches intensives. Cet article introduit le concept de génération automatisée de modèles de composants passifs et d’interconnexions par réseaux de neurones. Précis et rapides, ces modèles intègrent efficacement les effets électromagnétiques présents aux hyperfréquences. En optimisant les performances d’un circuit, notre approche peut déterminer automatiquement non seulement la structure géométrique finale des différents composants passifs et de leurs interconnexions respectives mais également, pour la première fois, leur localisation optimale dans le circuit. Des applications utilisant des modèles de composants passifs implémentés dans des simulateurs de circuits sont présentées.
Abstract
Widely used in microwave multichip module design, passive device models are subject to intensive researches. This paper introduces the concept of automate generation of neural models for passives and interconnects. Accurate and fast, these models efficiently integrate electromagnetic effects present at microwave frequencies. By optimizing the circuit performance, the proposed approach can automatically predict not only the final geometrical structure of the different passive components and their respective interconnects but also, for the fist time, their optimum location in the circuit. Applications using passive models implemented in circuit simulators are presented.
Bibliographie
cads v.2003,Agilent Technologies, Palo Alto,ca, usa.
Ansofthfss v.8.0, 2002,Ansoft Corporation, Pittsburg,pa, usa.
Antonini (G.),Orlandi (A.), Gradient evaluation for neural-network-based electromagnetic procedures,ieee Trans. Microwave Theory Tech.,48, pp. 874–876, 2000.
Bandler (J.),Ismail (M.),Rayas-Sanchez (J.),Zhang (Q.J.), New directions in model development forrf/microwave components utilizing artificial neural networks and space mapping,ieee aps Int. Symp., 1999, pp. 2572–2575.
Baudrand (H.), Electromagnetic study of coupling between active and passive circuits,ieee mit Int. Microwave and Optoelectronics Conf., 1997, pp. 143–152.
Bhattacharya (S.K.),Young (W.K.),Chahal (P.),Allen (M.G.),Tummala (R.R.),Hubbard (R.L.),mcm-l compatible integrated resistors and capacitors,4th Int. Symp. on Advanced Packaging Materials, 1998, pp. 295–299.
Centeno (A.), A comparison of numerical dispersion infdtd andtlm algorithms,Asia-Pacific Conf. on Applied Electromagnetics, 2003, pp. 128–131.
Chahal (P.),Tummala (R.R.),Allen (M.G.),Swaminathan (M.), A novel integrated decoupling capacitor formcm-L technology,46th Electronic Components and Technology Conf., 1996, pp. 125–132.
Chang (T.N.),Chang Sze (Y.), Flexibility in the choice of Green’s function for the boundary element method,ieee Trans. Microwave Theory Tech.,42, pp. 1973–1977, 1994.
Chattaraj (B.),Yagoub (M.C.E.),Ding (X.),Zhang (Q.J.),em Based optimization of microwave circuits by neural models and their application to power distribution and decoupling optimization,31stEuropean Microwave Conf., 2001, pp. 125–128.
Cho (C.),Gupta (K.),em-ann modeling of overlapping open-ends in multiplayer microstrip lines for design of bandpass filter,ieee aps Int. Symp., 1999, pp. 2592–2595.
Coates (K.L.),Chien (C.P.),Hsiao (Y.-Y.R.),Kovach (D.J.),Tanielian (M.H.), Highly reliable embedded thin film resistors in Cu/PI MCM-Ds for aerospace applications,9thElectronic Components and Technology Conf., 1999, pp. 93–98.
Cornett (K.D.), A wirelessr&d perspective onrf/if passives integration,Bipolar/BiCMOS Circuits and Technology Meeting, 2000, pp. 187–190.
Creech (G.L.),Paul (B.J.),Lesniak (C.D.),Jenkins (T.J.),Calcatera (M.C.), Artificial neural networks for fast and accurateem-cad of microwave circuits,ieee Trans. Microwave Theory Tech.,45, pp. 794–802, 1997.
Creech (G.L.),Zurada (J.M.), Neural network modeling of GaAsic material andmesfet device characteristics,Int. J. RF and Microwave cae,9, pp. 241–253, 1999.
Del Mar Hershenson (M.),Mohan (S.S.),Boyd (S.P.),Lee (T.H.), Optimization of inductor circuits via geometric programming,36th Design Automation Conf., 1999, pp. 994–998.
Devabhaktuni (V.K.),Chattaraj (B.),Yagoub (M.C.E.),Zhang (Q.J.), Advanced microwave modeling framework exploiting automatic model generation, knowledge neural networks and space mapping,ieee mtt Int. Microwave Symp., 2002, pp. 1098–1100.
Devabhaktuni (V.K.),Yagoub (M.C.E.),Fang (Y.),Xu (J.J.),Zhang (Q.J.), Neural networks for microwave modeling: model development issues and nonlinear techniques,Int. J. rf Microwave cae, 11, pp. 4–21, 2001.
Ding (X.),Devabhaktuni (V.K.),Chattaraj (B.),Yagoub (M.C.E.),Deo (M.),Xu (J.),Zhang (Q.J.), Neural-Network approaches to electromagnetic-based modeling of passive components and their applications to high-frequency and high-speed nonlinear circuit optimization,ieee Trans. Microwave Theory Tech.,52, pp. 436–449, 2004.
Edwards (T.), Countdown to the microwave millenium,Microwave J.,41, pp. 70–81, 1998.
Filicori (F.),Ghione (G.),Naldi (C.U.), Physics-based electron device modeling and computer-aided mmic design,ieee Trans. Microwave Theory Tech.,40, pp. 1333–1352, 1992.
Friday (D.), Microwave technology: directions and measurement requirements for the 21th century,Microwave J.,41, pp. 110–114, 1998.
Garcia (J.A.),Puente (A.T.),Sanchez (A.M.),Santamaria (I.),Lazaro (M.),Pantaleon (C.J.),Pedro (J.C.), Modelingmesfets andhemts intermodulation distortion behavior using generalized radial basis function network,Int. J. rf and Microwave cae,9, pp. 261–276, 1999.
Ge (Y.),Esselle (K.P.), New closed-form Green’s functions for microstrip structures — theory and results,ieee Trans. Microwave Theory Tech.,50, pp. 1556–1560, 2002.
Gentili (G.G.),Macchiarella (G.), Quasi-static analysis of shielded planar transmission lines with finite metallization thickness by a mixed spectral-space domain method,ieee Trans. Microwave Theory Tech.,42, pp. 249–255, 1994.
Golonka (L.J.),Wolter (K.-J.),Dziedzic (A.),Kita (J.),Rebenklau (L.), Embedded passive components formcm,24th Int. Spring Seminar on Concurrent Engineering in Electronic Packagin, 2001, pp. 73–77.
Gupta (K.C.), Emerging trends in millimeter wavecad,ieee Trans. Microwave Theory Tech.,46, pp. 747–755, 1998.
Halchin (D.),Golio (M.), Trends for portable wireless applications,Microwave J.,40, pp. 62–78, 1997.
Harkouss (Y.),Rousset (J.),Chehade (H.),Ngoya (E.),Barataud (D.),Teyssier (J.P.), Modeling microwave devices and circuits for telecommunications system design,ieee Int. Conf. Neural Networks, 1998, pp. 128–133.
Hartung (J.), Integrated passive components inmcm-Si technology and their applications inrf-systems,Int. Conf. on Multichip modules and High Density Packaging, 1998, pp. 256–261.
Haykin (S.),Neural Networks: A Comprehensive Foundation, Upper Saddle River,nj: Prentice Hall, 1994
Ju (C.-W.),Lee (S.-P.),Lee (Y.-M.),Hyun (S.-B.),Park (S.-S.),Sonmg (M.-K.), Embedded passive components inmcm-d forrf applications,Electronic Components and Technology Conf., 2000, pp. 211–214.
Kythakyapuzha (S.R.),Kuhn (W.B.), Modeling of inductors and transformers,ieee mtt Int. Symp., 2001, pp. 587–590.
Lenihan (T.),Schaper (L.),Morcan (G.),Fairchild (K.),Parkerson (J.), Embedded thin film resistors, capacitors and inductors in flexible polyimide films,Int. J. Microcircuits and Electronic Packaging,20, pp. 474–481, 1997.
Mahajan (R.L.), Design and optimization through physical/neural network models,ieee mtt Int. Microwave Symp. Workshop on Appl. of ann to Microwave Design, 1997, pp. 1–16.
Martini (E.),Pelosi (G.),Selleri (S.), A hybrid finite-element-modal-expansion method with a new type of curvilinear mapping for the analysis of microwave passive devices,IEEE Trans. Microwave Theory Tech.,51, pp. 1712–1717, 2003.
Mccullogh (W.S.),Pitts (W.), A logical calculus of the ideas immanent in nervous activity,Bulletin of Math. Biophysics,5, pp. 115, 1943.
Mohan (S.S.),Hershenson (M.),Boyd (S.P.),Lee (T.H.), Simple accurate expressions for planar spiral inductances,ieee J. of Solid-State Circuits,34, pp. 1419–1424, 1999.
Nakhla (M.), Application of Neural networks to simulation and optimization of high speed interconnects,ieee mtt Int. Microwave Symp. Workshop on Appl. of ann to Microwave Design, 1997, pp. 49–66.
NeuroModeler v. 1.2, 2000, Q.J. Zhang,Carleton University, Ottawa, Canada.
Niknejad (A.M.),Meyer (R.G.), Analysis, design, and optimization of spiral inductors and transformers for Sirf ic’s,ieee J. of Solid-State Circuits,33, pp. 1470–1481, 1998.
Patnaik (A.),Mishra (R.K.),ann techniques in microwave engineering,ieee Microwave Magazine,1, pp. 55–60, 2000.
Piernas (B.),Nishikawa (K.),Kamogawa (K.),Nakagawa (T.),Araki (K.), Improved three-dimensional GaAs inductors,ieee mtt Int. Microwave Symp., 2001, pp. 189–192.
Pieters, (P.),Vaesen, (K.),Carchon, (G.),Brebels, (S.),De Raedt, (W.),Beyne, (E.), Integration of passive components in thin film multilayermcm-d technology for wireless front-end applications,Asia-Pacific Microwave Conf., 2000, pp. 221–224.
Purviance (J.),Meehan (M.),cad for statistical analysis and design of microwave circuits,Int. J. Microwave and Millimeter-Wave cae,1, pp. 59–76, 1991.
Rizzoli (V.),Costanzo (A.),Masotti (D.),Lipparini (A.),Mastri (F.), Computer-Aided optimization of nonlinear microwave circuits with the aid of electromagnetic simulation,ieee Trans. Microwave Theory Tech.,52, pp. 362–377, 2004.
Rousset (J.),Harkouss (Y.),Collantes (J.M.),Campovecchio (M.), An accurate neural network model offet intermodulation and power analysis,European Microwave Conf., 1996, pp. 16–19.
Shirakawa (K.),Shimiz (M.),Okubo (N.),Daido (Y.), A large-signal characterization of anhemt using a multilayered network,ieee Trans. Microwave Theory Tech.,45, pp. 1630–1633, 1997.
Sonnet v.9.51,Sonnet Software Inc., Liverpool,ny, usa.
Tatinian (W.),Pannier (P.),Gillon (R.), A new T circuit topology for the broadband modelling of symmetric inductors fabricated incmos technology,ieee mtt Int. Microwave Symp., 2001, pp. 583–586.
Tounsi (M.L.),Halheit (H.),Yagoub (M.C.E.),Khodja (A.), Analysis of shielded planar circuits by a mixed variational-spectral method,ieee cas Int. Circuit Syst. Symp., 2003, pp. 65–68.
Vai (M.),Prasad (S.), Neural networks in microwave circuit design — beyond black box models,Int. J. of rf and Microwave cae,9, pp. 187–197, 1999.
Vuong (T.P.),Garcia (R.),Raveu (N.),Zeid (A.),Baudrand (H.),Peuch (J.C.),fwcip method forpgb planar structures,Int. J. rf Microwave Computer-Aided Eng., 12, pp. 236–246, 2002.
Wang (S.),Wang (F.),Devabhaktuni (V.K.),Zhang (Q.J.), A Hybrid neural and circuit-based model structure for microwave modeling,European Microwave Conf., 1999, pp. 174–177.
Watson (P.M.),Gupta (K.C.), Design and optimization ofcpw circuits usingem-ann models forcpw components,ieee Trans. Microwave Theory Tech.,45, pp. 2515–2523, 1997.
Yagoub (M.C.E.), Optimisation des performances de modules multipuces à base de modèles neuronaux de composants passifs et d’interconnexions,4eConf. Européenne sur les Méthodes Numériques en Électromagnétisme, 2003, pp. S42_1–S42_2.
Yamaguchi (M.),Baba (M.),Arai (K.I.), Sandwich type ferromagneticrf integrated inductor,ieee mtt Int. Microwave Symp., 2001, pp. 185–188.
Yamashita (E.),Mittra (R.), Variational method for the analysis of microstrip lines,IEEE Trans. Microwave Theory Tech.,16, pp. 251–256, 1968.
Zaabab (A.H.),Zhang (Q.J.),Nakhla (M.S.), A neural network models approach to circuit optimization and statistical design,ieee Trans. Microwave Theory Tech.,43, pp. 1349–1358, 1995.
Zeid (A.),Baudrand (H.), Electromagnetic scattering by metallic holes and its applications in microwave circuits design,ieee Trans. Microwave Theory Tech.,50, pp. 1198–1206, 2002.
Zhang (Q.J.),Gupta (K.C.),Neural Networks for rf and Microwave Design, Norwood,ma: Artech House, 2000.
Zhang (Q.J.),Wang (F.),Nakhla (M.S.), Optimization of high-speedvlsi interconnects: A review,Int. J. Microwave Millimeter-Wave cae, 7, pp. 83–107, 1997.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yagoub, M.C.E. Optimisation des performances de modules multipuces Modélisation par réseaux de neurones. Ann. Télécommun. 59, 1092–1117 (2004). https://doi.org/10.1007/BF03179712
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF03179712
Mots clés
- Circuit intégré hyperfréquence
- Circuit intégré hybride
- Composant passif
- Interconnexion
- Réseau neuronal
- Optimisation
- Automatisation
- Simulateur
- Boîtier métallique