查询结果:   南敬昌,王梓琦,高明明,王颖.超宽带滤波器的稀疏贝叶斯正则化逆向神经网络建模[J].计算机应用与软件,2018,35(10):232 - 237.
中文标题
超宽带滤波器的稀疏贝叶斯正则化逆向神经网络建模
发表栏目
算法
摘要点击数
726
英文标题
SPARSE BAYESIAN REGULARIZED INVERSE NEURAL NETWORK MODELING OF UWB FILTER
作 者
南敬昌 王梓琦 高明明 王颖 Nan Jingchang Wang Ziqi Gao Mingming Wang Ying
作者单位
辽宁工程技术大学电子与信息工程学院 辽宁 葫芦岛 125105     
英文单位
School of Electronic and Information Engineering,Liaoning Technical University, Huludao 125105, Liaoning, China     
关键词
神经网络 逆向建模 贝叶斯 L1/2范数 超宽带滤波器
Keywords
Neural network Inverse modeling Bayesian L1/2 norm UWB filter
基金项目
国家自然科学基金项目(61372058);辽宁省教育厅重点实验室项目(LJZS007);辽宁省教育厅科学研究一般项目(L2015209)
作者资料
南敬昌,教授,主研领域:射频电路与系统,电路系统,电磁仿真。王梓琦,硕士生。高明明,副教授。王颖,硕士生。 。
文章摘要
针对射频器件建模中使用直接逆向神经网络精度较低,BP逆向神经网络泛化能力较差的问题,提出一种性能函数为贝叶斯L1/2范数的逆向神经网络建模方法。贝叶斯方法调整网络权系数避免过拟合现象,使模型输出更加平滑;增加L1/2范数扩充输入向量,使网络结构稀疏化且泛化能力更强。应用于超宽带滤波器谐振器逆向建模中,根据陷波频率处插入损耗值,求解对应的长度和宽度。结果表明:该方法与BP逆向建模方法相比,求得的长度、宽度和频率相对误差分别减小81.4%、99.8%、48.9%,网络运行时间减少16.3%,不存在多解问题,建模效率更高。
Abstract
In the modeling of radio frequency devices, direct inverse neural network has low precision and BP inverse neural network has poor generalization ability. To solve these problems, we proposed an inverse neural network modeling method with Bayesian L1/2 norm. The Bayesian method adjusted the network weight coefficient to avoid the over-fitting phenomenon so that the model output was much smoother. The input vector was expanded by adding the L1/2 norm so that the network structure was sparse and the generalization ability was much stronger. The method was applied into the inverse modeling of the UWB filter resonator. The value of the loss was inserted according to the notch frequency and the corresponding length and width were solved. The results show that compared with the BP inverse modeling method, the relative errors of length, width, and frequency obtained by this method are respectively reduced by 81.4%, 99.8%, and 48.9%. And the network operation time is decreased by 16.3%. This method does not have multiple solutions and has better modeling efficiency.
下载PDF全文