检索结果-内蒙古大学图书馆

IEEE International Workshop on Electromagnetics, Applications and Student Innovation (iWEM)

作者： Shijie Wang MingQing Geng Chao Yu Jialin Cai Key Laboratory of RF Circuit and System Ministry of Education Hangzhou Dianzi University China State Key Laboratory of Millimeter Waves Southeast University China

ISBN: (纸本)9781665418294

In this article, a novel behavioral modeling approach is proposed based on augmented long-short term memory (ALSTM) networks for ultra-broadband mmWave power amplifiers (PAs). The basic theory and modeling procedure of this technique are provided. In order to verify the proposed approach, validation example is given, a 4-carrier 320 MHz modulated signal was used to stimulate a millimeter-wave power amplifier with a 41 GHz center frequency. The results of the experiments show that the proposed ALSTM model has better predictive capability when compared with the traditional and other existing machine learning modeling techniques.

关键词： Technological innovation Power measurement Millimeter wave technology Measurement uncertainty Power amplifiers Predictive models Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

GaN HEMT Modeling versus Bias Point and Gate Width

GaN HEMT Modeling versus Bias Point and Gate Width

引用

Information, Communication and Energy systems and Technologies (ICEST), International Scientific Conference on

作者： Giovanni Crupi Mariangela Latino Giovanni Gugliandolo Zlatica Marinković Jialin Cai Enza Fazio Nicola Donato BIOMORF Department University of Messina Messina Italy Engineering Department University of Messina Messina Italy Faculty of Electronic Engineering University of Niš Niš Serbia Key Laboratory of RF Circuit and System Ministry of Education College of Electronics and Information Hangzhou Dianzi University Hangzhou China MIFT Department University of Messina Messina Italy

This paper focuses on the equivalent-circuit modelling of gallium-nitride (GaN) high electron-mobility transistors (HEMTs) on silicon carbide (SiC) substrate. The model is extracted from scattering (S-) parameters measurements by using the well-known “cold” approach. The extracted model is successfully validated by investigating three devices with different gate widths in a wide range of bias points over a broad frequency range spanning from 45 MHz up to 50 GHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Optimization Based Frequency Piecewise Small Signal Model for GaN HEMT

A New Optimization Based Frequency Piecewise Small Signal Mo...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Mingqiang Geng Chao Yu Jialin Cai Key Laboratory of RF Circuit and System Hangzhou Dianzi University China Southeast University Nanjing China

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

In this paper, a new optimization based frequency piecewise small-signal model for Gallium nitride (GaN) high electron mobility transistor (HEMT) is proposed. Different from the classic modeling technique, which use a single set of model parameters to describe the behavioral of the device across the whole broad frequency band, the new proposed model uses piecewise modeling method. Due to the inner nonlinearity of GaN HEMT at high frequency, the behavior of the device across the band is decomposed into few different pieces, based on the nonlinearity of the device. The model is extracted and optimized with commercial tool at each different piece of frequency band. The verification is carried out on an 8 × 125 μm GaN HEMT with a 0.25 μm gate feature size. The proposed model shows a big improvement in accuracy of S-parameter behavior prediction. The relative error of S 11 and S 22 is greatly reduced and can be controlled under 2%.

关键词： Millimeter wave transistors HEMTs Predictive models Tools Scattering parameters Gallium nitride Optimization

来源：评论

学校读者我要写书评

暂无评论

Piecewise Small Signal Behavioral Model for GaN HEMTs based on Support Vector Regression

Piecewise Small Signal Behavioral Model for GaN HEMTs based ...

引用

International Conference on Numerical Electromagnetic Modeling and Optimization for rf, Microwave, and Terahertz Applications (NEMO)

作者： Mingqiang Geng Jialin Cai Chao Yu Jiangtao Su Jun Liu Key Laboratory of RF Circuit and System Hangzhou Dianzi University China State Key Laboratory of Millimeter Wave Southeast University Nanjing China

ISBN: (数字)9781728169668

ISBN: (纸本)9781728169675

In this paper, a machine learning (ML) technique based, piecewise small-signal behavioral modeling methodology for Gallium nitride (GaN) high electron mobility transistors (HEMTs) is presented. Support vector regression (SVR), as one of the core algorithm of ML technique is employed. Compared with equivalent small-signal circuit model, which extracting the precise parameters of the circuit, the proposed piecewise SVR technique analyze and modeling the measured data by means of mathematical method. The verification is carried out on an 8 × 125 μm GaN HEMT with a 0.25 μm gate feature size. The SVR model shows a big improvement in accuracy of S-parameter behavior prediction when compared with conventional piecewise equivalent circuit model. The relative error of S-parameter prediction is greatly reduced.

关键词： Predictive models HEMTs Numerical models Mathematical model Integrated circuit modeling Gallium nitride MODFETs

来源：评论

学校读者我要写书评

暂无评论

Polynomial-Assisted Neural Network Behavioral Model of Wideband Radio Frequency Power Amplifiers for 5G New Radio

Polynomial-Assisted Neural Network Behavioral Model of Wideb...

引用

International Conference on Numerical Electromagnetic Modeling and Optimization for rf, Microwave, and Terahertz Applications (NEMO)

作者： Yucheng Yu Hang Yin Chao Yu Jialin Cai State Key Laboratory of Millimeter Waves Southeast University Nanjing China Key Laboratory of RF Circuit and System Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9781728169668

ISBN: (纸本)9781728169675

In this paper, a novel polynomial-assisted neural network is proposed for behavioral modeling of wideband radio frequency power amplifiers for 5G new radio. It is achieved by embedding the polynomial basis function of conventional models into the neural network structure to reduce the computation complexity and improve the convergence of the neural network. Experimental results employing a wideband GaN PA using 5G new radio signal shows that the proposed model that integrates memory polynomial (MP) with vector decomposition time delay neural network (VDTDNN) can achieve either better performance or lower complexity compared with the conventional models.

关键词： Computational modeling Neural networks Power amplifiers Radiofrequency amplifiers Numerical models Wideband Optimization

来源：评论

学校读者我要写书评

暂无评论

Large Signal Behavioral Model of rf Transistor Using Least Square Support Vector Machine

Large Signal Behavioral Model of RF Transistor Using Least S...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Jiain Cai Chao Yu Jun Liu Lingling Sun Key Laboratory of RF Circuit and System Ministry of Education Hangzhou Dianzi University China State Key Laboratory of Millimeter Wave Southeast University Nanjing China

ISBN: (数字)9781728157337

ISBN: (纸本)9781728157344

A novel frequency domain, large signal modeling technique using least square support vector regression (LS-SVR), is presented in this paper. The proposed LS-SVR modeling technique give a more efficient way to develop the large signal behavioral model of radio frequency (rf) transistors when compared with the standard SVR technique. The theory and the model implementation procedure of the proposed LS-SVR model is provided. The model is validated through both simulation and experimental test including dc and rf prediction of Gallium Nitride (GaN) transistor, giving that the LS-SVR based model provides a faster prediction compared with standard SVR.

关键词： Radio frequency Support vector machines Millimeter wave transistors Simulation Predictive models Gallium nitride Standards

来源：评论

学校读者我要写书评

暂无评论

A broadband high-efficiency Doherty power amplifier using symmetrical devices

引用

Journal of Semiconductors 2018年第4期39卷 72-76页

作者： Zhiqun Cheng Ming Zhang Jiangzhou Li Guohua Liu Key Laboratory of RF Circuit and System Education Ministry Hangzhou Dianzi University

This paper proposes a method for broadband and high-efficiency amplification of Doherty power amplifier （DPA） using symmetric devices. In order to achieve the perfect load modulation, the carrier amplifier output circuit total power length is designed to odd multiple of 90°, and the peak amplifier output total power length is designed to even multiple of 180°. The proposed method is demonstrated by designing a broadband high-efficiency DPA using identical 10-W packaged GaN HEMT devices. Measurement results show that over 51% drain effi- ciency is achieved at 6-dB back-off power, over the frequency band of 1.9-2.4 GHz.

关键词： Doherty power amplifier broadband high efficiency symmetric devices

来源：评论

学校读者我要写书评

暂无评论

Large Signal Behavioral Modeling of Power Transistor from Active Load-pull systems

Large Signal Behavioral Modeling of Power Transistor from Ac...

引用

IEEE International Workshop on Radio-Frequency Integration Technology (rfIT)

作者： Jialin Cai Jiangtao Su Jun Liu Key Laboratory of RF Circuit and System Hangzhou Dianzi University Hangzhou China

Large signal behavioral modeling for rf power transistor has been developed rapidly in the past decade, this paper compares and contrasts recent nonlinear large-signal behavioral modeling techniques designed for power transistors. These techniques include traditional function based behavioral modeling techniques, e.g. X-parameters, Padé model, Cardiff model, load-pull X-parameters; and artificial neural network (ANN) and machine learning (ML) technique based methods, e.g. real value feed-forward neural network (RVFFNN) model, Bayesian inference model, support vector regression (SVR) based model, in the frequency domains. Besides, approaches to generating the data for modeling from active load-pull measurements are reviewed as well, including closed loop, feed-forward, and open loop active load pull system.

关键词： Load modeling Power transistors Integrated circuit modeling Predictive models Harmonic analysis Microwave measurement Microwave theory and techniques

来源：评论

学校读者我要写书评

暂无评论

Iteration Process Analysis of Real-Valued Time-Delay Neural Network with Different Activation Functions for Power Amplifier Behavioral Modeling

Iteration Process Analysis of Real-Valued Time-Delay Neural ...

引用

IEEE International Workshop on Radio-Frequency Integration Technology (rfIT)

作者： Hang Yin Jialin Cai Chao Yu State Key Laboratory of Millimeter Waves Southeast University Nanjing China Key Laboratory of RF Circuit and System Ministry of Education Hangzhou Dianzi University Hangzhou China

The dynamic iteration process analysis of real-valued time-delay neural network (RVTDNN) for power amplifier (PA) behavioral modeling is provided in this paper. The performance with three activation functions of hyperbolic tangent sigmoid (tansig), logistic sigmoid (logsig) and rectified linear unit (ReLU) are investigated. It is discovered that RVTDNN with ReLU has the fastest convergence speed, and the ones with tansig and logsig have similar modeling accuracy which is higher than ReLU, but slower convergence speed, validated by experiments on a Doherty PA. The iteration process investigation of RVTDNN with different activation functions provides practical considerations for applying the model into different future 5G scenarios.

关键词： Convergence Numerical models Neural networks Analytical models 5G mobile communication Predistortion

来源：评论

学校读者我要写书评

暂无评论

A high-precision sideband suppression model for transmitter leakage compensation

A high-precision sideband suppression model for transmitter ...

引用

2018 IEEE MTT-S International Wireless Symposium, IWS 2018

作者： Yang, Na Yu, Chao Lu, Qianyun Zhai, Jianfeng Cai, Jialin State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China Key Laboratory of RF Circuit and System Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9781538663462

In this paper, a novel high-precision sideband suppression model is proposed for the compensation of transmitter leakage. By further exploiting the merits of dual-band modeling methodology and decomposed vector rotation behavioral model in sideband modeling, this proposed model can achieve significant suppression performance with relatively low computational complexity in model construction. The experimental results have shown a great validation that the unwanted distortion can be suppressed over 50 dB by employing this proposed model. © 2018 IEEE.

关键词： Power amplifiers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：