Doherty功放的贝叶斯正则化神经网络逆向建模研究

计算机工程与科学

Doherty功放的贝叶斯正则化神经网络逆向建模研究

南敬昌，胡婷婷，盛爽爽，高明明

（辽宁工程技术大学电子与信息工程学院，辽宁葫芦岛 125105）

收稿日期:2017-04-11 修回日期:2017-05-11 出版日期:2018-08-25 发布日期:2018-08-25
基金资助:
国家自然科学基金(61372058);辽宁省高校重点实验室项目(LJZS007)

Bayesian regularization neural network inverse

modeling for Doherty power amplifier

NAN Jingchang,HU Tingting,SHENG Shuangshuang,GAO Mingming

(School of Electronic and Information Engineering,Liaoning Technical University,Huludao 125105,China)

Received:2017-04-11 Revised:2017-05-11 Online:2018-08-25 Published:2018-08-25

摘要/Abstract

摘要：

针对直接逆向建模方法精度低、稳定性差等缺点，提出了一种采用规则化函数为L1/2范数的贝叶斯正则化神经网络逆向建模方法，L1/2正则化使得网络结构具有稀疏性，能够缩小网络的规模、加快网络的训练速度，用贝叶斯正则化方法可以使网络的输出更加平滑，提高网络的稳定性和泛化能力。将此方法应用到Doherty功率放大器的设计中，在已知Doherty主功放效率、输出匹配端的S11和S21的情况下，分别仿真得出相对应的输出功率和f,可以简化设计过程。实验结果表明，此逆向模型求得的输出功率、与S11相对的f、与S21相对的f比直接逆向建模方法的均方误差分别减少了8.83%、9.30%和9.00%，运行时间分别减少了99.34%、99.40%和99.23%，解决了设计中的多解问题，可用于设计射频微波器件。

关键词: 针对直接逆向建模方法精度低、稳定性差等缺点, 提出了一种采用规则化函数为L1/2范数的贝叶斯正则化神经网络逆向建模方法, L1/2正则化使得网络结构具有稀疏性, 能够缩小网络的规模、加快网络的训练速度, 用贝叶斯正则化方法可以使网络的输出更加平滑, 提高网络的稳定性和泛化能力。将此方法应用到Doherty功率放大器的设计中, 在已知Doherty主功放效率、输出匹配端的S11和S21的情况下, 分别仿真得出相对应的输出功率和f,可以简化设计过程。实验结果表明, 此逆向模型求得的输出功率、与S11相对的f、与S21相对的f比直接逆向建模方法的均方误差分别减少了8.83%、9.30%和9.00%, 运行时间分别减少了99.34%、99.40%和99.23%, 解决了设计中的多解问题, 可用于设计射频微波器件。

Abstract:

Since direct reverse modeling methods suffer low precision, poor stability and other short comings, we propose a Bayesian regularization neural network reverse modeling method for L1/2 norm regularization. L1/2 norm regularization makes the network structure sparse, so it can reduce network size and accelerate the training speed of the network. When the proportionality coefficient is greater than 0.5, using the Bayesian regularization method can make the output of the network more smooth, and improve the stability and generalization ability of the network. We apply this method to the design of Doherty power amplifier with known Doherty main power amplifier efficiency and output matching terminals S11 and S21. Simulations corresponding to the output power and f can simplify the design process. Experimental results show that the mean square error of the output power, the f related to S11, and the f related to S21 obtained from the proposed model are reduced by 8.83%, 9.30% and 9% respectively in comparison with the direct reverse modeling method, and the running time is reduced by 99.34%, 99.40% and 99.23%. It can also solve the multisolution problem in design and be used in RF microwave devices design.

Key words: neural network;reverse modeling;L1/2 , norm;Bayesian regularization;Doherty power amplifier

南敬昌，胡婷婷，盛爽爽，高明明. Doherty功放的贝叶斯正则化神经网络逆向建模研究[J]. 计算机工程与科学.

NAN Jingchang,HU Tingting,SHENG Shuangshuang,GAO Mingming.

Bayesian regularization neural network inverse

modeling for Doherty power amplifier

[J]. Computer Engineering & Science.