A Neural Network Approach to the Modeling of Heterojunction Bipolar Transistors from S-Parameter Data

Devabhaktuni, V.K.; Xi, Changgeng; Zhang, Q.J.

doi:10.1109/euma.1998.338005

Cited by 27 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These neural models can be used in place of computationally intensive physics/EM models of active/passive devices to speed up microwave design. Neural network modeling techniques have been used for a wide variety of microwave applications such as microstrip interconnects [1,2], vias [3,4], spiral inductors [5], FET devices [1,6], and HBT devices [7]. Neural networks have also been used in circuit simulation and optimization [8], filter design [9], impedance matching [10], and synthesis [11].…”

Section: Introductionmentioning

confidence: 99%

Robust training of microwave neural models

Devabhaktuni

Wang

et al. 2001

Int J RF and Microwave Comp Aid Eng

Self Cite

View full text Add to dashboard Cite

Neural networks recently gained attention as a fast and flexible vehicle to microwave modeling and design. Neural network models can be developed by learning from microwave data, through a process called training. The trained models can be used during microwave design to provide instant answers to the task they learnt. This article addresses certain key challenges in developing RF/microwave neural models. An iterative multistage (IMS) approach including a macro-level process and a stage-level process is proposed. At the macro-level, the IMS decomposes the complicated original task into several simpler subtasks or stages and at the stage-level, the IMS utilizes a variety of neural network structures and effective training techniques, including several existing techniques and a new Huber quasiNewton (HQN) technique. The proposed HQN allows for the IMS approach to model only smooth portion of the problem behavior in one of the training stages, ignoring sharp/sudden variations. The advantages of the proposed microwave-oriented modeling techniques are demonstrated through examples.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust training of microwave neural models

Devabhaktuni

Wang

et al. 2001

Int J RF and Microwave Comp Aid Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…The universal approximation property of ANN [9][10] provides them the ability to learn any arbitrarily nonlinear input-output relationships [11 -14] from corresponding measured or simulated data. Moreover, researches started investigating NN approaches to model transistor DC [15][16][17][18][19] , small signal [20][21] , and large-signal [22][23][24][25][26][27] behaviors. Xiuping et al [28] have proposed an improved microwave active device modeling technique based on the combination of the equivalent circuit and ANN approaches.…”

Section: Introductionmentioning

confidence: 99%

Neural-Based Models of Semiconductor Devices for SPICE Simulator

Hammouda¹,

Gafsi²,

Besbes³

2008

American J. of Applied Sciences

View full text Add to dashboard Cite

The paper addresses a simple and fast new approach to implement Artificial Neural Networks (ANN) models for the MOS transistor into SPICE. The proposed approach involves two steps, the modeling phase of the device by NN providing its input/output patterns, and the SPICE implementation process of the resulting model. Using the Taylor series expansion, a neural based small-signal model is derived. The reliability of our approach is validated through simulations of some circuits in DC and small-signal analyses

show abstract

“…Neural network techniques have been used for a wide variety of microwave applications such as transmission line components [5], [8], vias [31], bends [32], coplanar waveguide (CPW) components [33], spiral inductors [7], field effect transistor (FET) devices [25], [34], heterojuction bipolar transistor (HBT) devices [35], high electron mobility transistor (HEMT) devices [36], [37], filters [38]- [41], amplifiers [42]- [45], mixers [46], antennas [47], embedded passives [4], [26], [27], packaging and interconnects [48], etc. Neural networks have also been used in circuit simulation and optimization [3], [25], [49], signal integrity analysis and optimization of very-large-scale-integration (VLSI) interconnects [48], [50], microstrip circuit design [51], process design [52], microwave impedance matching [53], inverse modeling [54], measurements [55], synthesis [25], [56] and behavioral modeling of nonlinear RF/microwave subsystems [57].…”

Section: Outline Of the Thesismentioning

confidence: 99%

Advanced Neural-Based Model Generation and Extrapolation Techniques for Microwave Applications

Na¹

View full text Add to dashboard Cite

Neural-based modeling techniques have been recognized as important vehicles in the microwave computer-aided design (CAD) area in addressing the growing challenges of designing next generation microwave device, circuits and systems. Artificial neural network models can be trained to learn electromagnetic (EM) and physics behavior. The trained neural network models can be used in high-level circuit and system design allowing faster simulation and optimization including EM and physics effects in components. The purpose of this thesis is to develop advanced neural-based model generation and extrapolation techniques for microwave applications. The proposed techniques take advantage of the high-efficiency of automated model generation algorithm, the cost-effective concept of knowledge-based neural network and the generalization capability of extrapolation techniques, to achieve First of all, I would like to express my sincere appreciation to my supervisor, Prof. Q. J. Zhang, for his professional guidance, invaluable inspiration and continuous support throughout the research work and the preparation of this thesis. This thesis would not have been completed without his patience, assistance, encouragement and faith of this study. It was my great honor to work under his supervision and guidance. Special appreciation to my co-supervisor, Prof. Jianguo Ma for the invaluable counsel and knowledgeable instruction. His invaluable counsel provided a great help for me on my way pursuing my Ph.D degree.

show abstract

A Neural Network Approach to the Modeling of Heterojunction Bipolar Transistors from S-Parameter Data

Cited by 27 publications

References 5 publications

Robust training of microwave neural models

Robust training of microwave neural models

Neural-Based Models of Semiconductor Devices for SPICE Simulator

Advanced Neural-Based Model Generation and Extrapolation Techniques for Microwave Applications

Contact Info

Product

Resources

About