Prediction of electrical properties of FDSOI devices based on deep learning

被引：4

作者：

Zhao, Rong ^{[1
]}

Wang, Shulong ^{[1
]}

Duan, Xiaoling ^{[1
]}

Liu, Chenyu ^{[1
]}

Ma, Lan ^{[1
]}

Chen, Shupeng ^{[1
]}

Liu, Hongxia ^{[1
]}

机构：

[1] Xidian Univ, Sch Microelect, Xian 710071, Peoples R China

来源：

NANOTECHNOLOGY | 2022年 / 33卷 / 33期

基金：

中国国家自然科学基金;

关键词：

deep learning; neural networks; FDSOI devices; electrical properties; transfer characteristic;

D O I：

10.1088/1361-6528/ac6c95

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

Fully depleted Silicon on insulator technology (FDSOI) is proposed to solve the various non-ideal effects when the process size of integrated circuits is reduced to 45 nm. The research of traditional FDSOI devices is mostly based on simulation software, which requires a lot of calculation and takes a long time. In this paper, a deep learning (DL) based electrical characteristic prediction method for FDSOI devices is proposed. DL algorithm is used to train the simulation data and establish the relationship between the physical parameters and electrical characteristics of the device. The network structure used in the experiment has high prediction accuracy. The mean square error of electrical parameters and transfer characteristic curve is only 4.34 x 10(-4) and 2.44 x 10(-3) respectively. This method can quickly and accurately predict the electrical characteristics of FDSOI devices without microelectronic expertise. In addition, this method can be extended to study the effects of various physical variables on device performance, which provides a new research method for the field of microelectronics.

引用

页数：8

共 31 条

[11]

Haifeng Tong, 2021, Journal of Physics: Conference Series, V1915, DOI 10.1088/1742-6596/1915/2/022065

[12] Deep neural networks for the evaluation and design of photonic devices [J].

Jiang, Jiaqi ;

Chen, Mingkun ;

Fan, Jonathan A. .

NATURE REVIEWS MATERIALS, 2021, 6 (08) :679-700

[13] Resistive Bridging Defect Detection in Bulk, FDSOI and FinFET Technologies [J].

Karel, Amit ;

Comte, Mariane ;

Galliere, Jean-Marc ;

Azais, Florence ;

Renovell, Michel .

JOURNAL OF ELECTRONIC TESTING-THEORY AND APPLICATIONS, 2017, 33 (04) :515-527

[14] Impact of VT and Body-Biasing on Resistive short detection in 28nm UTBB FDSOI - LVT and RVT configurations [J].

Karel, Amit ;

Comte, Mariane ;

Galliere, Jean-Marc ;

Azais, Florence ;

Renovell, Michel .

2016 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI), 2016, :164-169

[15]

Kuang Q, 2021, Journal of Physics: Conference Series, V1852, DOI 10.1088/1742-6596/1852/3/032040

[16]

Lin TY., 2015, P IEEE COMPUT SOC C

[17] Deep learning for the design of photonic structures [J].

Ma, Wei ;

Liu, Zhaocheng ;

Kudyshev, Zhaxylyk A. ;

Boltasseva, Alexandra ;

Cai, Wenshan ;

Liu, Yongmin .

NATURE PHOTONICS, 2021, 15 (02) :77-90

[18] Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials [J].

Ma, Wei ;

Cheng, Feng ;

Liu, Yongmin .

ACS NANO, 2018, 12 (06) :6326-6334

[19] Plasmonic nanostructure design and characterization via Deep Learning [J].

Malkiel, Itzik ;

Mrejen, Michael ;

Nagler, Achiya ;

Arieli, Uri ;

Wolf, Lior ;

Suchowski, Haim .

LIGHT-SCIENCE & APPLICATIONS, 2018, 7

[20] Deep learning for accelerated all-dielectric metasurface design [J].

Nadell, Christian C. ;

Huang, Bohao ;

Malof, Jordan M. ;

Padilla, Willie J. .

OPTICS EXPRESS, 2019, 27 (20) :27523-27535

← 1 2 3 4 →