Model Parameter Extraction with Back Propagation Algorithms

GAO Bin; YE Zuo-chang; WANG Yan

Chinese

您当前的位置：

首页 >

文章列表页 >

Model Parameter Extraction with Back Propagation Algorithms

更新时间：2026-09-04

- Model Parameter Extraction with Back Propagation Algorithms
- Vol. 36, Issue 1, Pages: 79-84(2019)
- 作者机构：
  
  清华大学微电子学研究所,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2019
- 稿件说明：
移动端阅览
高彬, 叶佐昌, 王燕. 基于反向传播的电路优化与模型参数提取方法[J]. 微电子学与计算机, 2019, 36(1): 79-84.

GAO Bin, YE Zuo-chang, WANG Yan. Model Parameter Extraction with Back Propagation Algorithms[J]. 2019, 36(1): 79-84.
高彬, 叶佐昌, 王燕. 基于反向传播的电路优化与模型参数提取方法[J]. 微电子学与计算机, 2019, 36(1): 79-84. DOI：

GAO Bin, YE Zuo-chang, WANG Yan. Model Parameter Extraction with Back Propagation Algorithms[J]. 2019, 36(1): 79-84. DOI：

摘要

传统的电路优化和模型参数提取方法假定仿真器为黑盒子

通过修改参数或者优化变量得到仿真结果

并用迭代的方式进行优化或模型参数提取.由于仿真器并未提供梯度信息

因此只能采用不依赖于梯度的优化方法

限制了优化和参数提取的性能.本文介绍了一种开源的电路仿真工具

通过在给出仿真结果的同时计算出指定函数对指定参数的梯度

为基于梯度的优化算法在电路参数提取、电路优化等领域的应用提供了便利.使用该工具实现的梯度下降算法在电感模型和变压器模型参数提取问题上的实验表现显著优于模拟退火等非梯度方法和同一算法不使用其梯度的实现的版本.实验结果证明

本文提出的方法在电路优化和模型参数提取问题上的性能有很好的改进作用.

Abstract

This work aimed at pushing forward the application on electronic fields of optimization algorithms which hire gradients. The authors developed an open source electronic simulating tool that gives out gradients of designed functions with respect to customized parameters of interest simultaneously when computing the desired state vectors of a circuit net list. These gradients power most gradient based optimization algorithms efficiently and relieve them from fetching the gradients expensively by secant methods. These optimization algorithms perform much better with the help of it

and also beat some non-gradient algorithms namely simulate anneal.

关键词

Keywords

references

Berlin, Germany Price K, Storn R M, Lampinen J A, Differential evolution. a practical approach to global optimization[M]. Berlin, Germany: Springer, 2005.

Yao J, Ye Z, Wang Y. An automatic parameter extraction and scalable modeling method for transformers in RF circuit[C]// Proc. IEEE RFIC Symp., Seattle, WA, USA, 2013: 57-60.

Gao W, Jiao C, Liu T, et al. Scalable compact circuit model for differential spiral transformers in CMOS RFICs[J]. IEEE Trans. Electron Devices, 2006, 53(9): 2187-2194. DOI: 2187

Guo J, Tan T. A broadband and scalable model for on-chip inductors incorporating substrate and conductor loss effects[J]. IEEE Trans. Electron Devices, 2006, 53(3): 413-421. DOI: 413

Amari Shun Ichi. Natural gradient works efficiently in learning[J]. Neural computation, 1998, 10(2):251-276. DOI: 251

Mandal S, Sural S, Patra A. ANN and PSO based synthesis of on-chip spiral inductors for RF ICs[J]. IEEE Trans. ComputerAided Design Integr. Circuits Syst., 2008, 27(1): 188-192. DOI: 188

Rumelhart D E, Hinton G E, Williams R J. Learn-ingrepre- sentations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. DOI: 533

Yue C, Wong S. Physical modeling of spiral inductors on silicon[J]. IEEE Trans. Electron Devices, 2000, 47(3): 560-568. DOI: 560

Cao Y. Frequency-independent equivalent-circuit model for onchip spiral inductors[J]. IEEE J. Solid-State Circuits, 2003, 38(3): 419-426. DOI: 419

Leite B, Kerherve E, Begueret J B, et al. An analytical broadband model for Millimeter-Wave transformers in silicon technologies[J]. IEEE Trans. Electron Devices, 2012, 59(3): 582-589. DOI: 582

Liu B, Lu J, Wang Y, et al. An effective parameter extraction method based on memetic differential evolution algorithm[J]. Microelectron. J., 2008, 39(12): 1761-1769. DOI: 1761

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Steganography model guided by attention mechanism and improved dense convolution

A feature-oriented context understanding and slice analysis network for tuberculosis detection

A review of large model development: technological evolution from BERT to Deepseek

A high-efficiency charge pump for ultra-low voltage boost systems

Aerial small object detection algorithm based on improved RT-DETR

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰