A TCAD-DNN-Based Total-Ionizing-Dose Effect Model for FinFET Devices

ZHOU Ying; LIU Xiaonian; LIU Yansen; CAO Peng

doi:10.12263/DZXB.20241033

您当前的位置：

首页 >

文章列表页 >

A TCAD-DNN-Based Total-Ionizing-Dose Effect Model for FinFET Devices

PAPERS | 更新时间：2026-05-11

- A TCAD-DNN-Based Total-Ionizing-Dose Effect Model for FinFET Devices
- ACTA ELECTRONICA SINICA Vol. 54, Issue 2, Pages: 634-645(2026)
- 作者机构：
  
  1.湖南师范大学物理与电子科学学院，湖南长沙 410081
  2.后摩尔时代物理与器件湖南省普通高等学校重点实验室，湖南长沙 410081
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62204083);Natural Science Foundation of Hunan Province(2024JJ6322)
- DOI：10.12263/DZXB.20241033
  CLC： TN386.1;
- Received：14 November 2024，
  
  Accepted：27 January 2026，
  
  Published：25 February 2026
- 稿件说明：
移动端阅览
周颖, 刘小年, 刘焱森, 等. 基于TCAD与DNN的FinFET器件辐射总剂量效应模型[J]. 电子学报, 2026, 54(02): 634-645.

ZHOU Ying, LIU Xiaonian, LIU Yansen, et al. A TCAD-DNN-Based Total-Ionizing-Dose Effect Model for FinFET Devices[J]. Acta Electronica Sinica, 2026, 54(02): 634-645.
周颖, 刘小年, 刘焱森, 等. 基于TCAD与DNN的FinFET器件辐射总剂量效应模型[J]. 电子学报, 2026, 54(02): 634-645. DOI：10.12263/DZXB.20241033

ZHOU Ying, LIU Xiaonian, LIU Yansen, et al. A TCAD-DNN-Based Total-Ionizing-Dose Effect Model for FinFET Devices[J]. Acta Electronica Sinica, 2026, 54(02): 634-645. DOI：10.12263/DZXB.20241033

摘要

先进鳍式场效应晶体管（Fin Field-Effect Transistor，FinFET）因其高集成度、强栅极控制能力、高驱动电流、高开关速度、低泄漏电流等优势，在先进集成电路中成为主要的晶体管器件。为得到器件物理层面的FinFET工艺下不同器件尺寸的辐射总剂量（Total-Ionizing-Dose，TID）效应模型，本文结合TCAD（Technology Computer Aided Design）技术与深度神经网络（Deep Neural Networks，DNN）技术提出并建立了一个辐射总剂量效应模型（TCAD-DNN模型）预测器件的TID效应的电学响应。本文采用Synopsys Sentaurus TCAD软件对SMIC 14 nm CMOS工艺下的FinFET进行三维（3D）器件建模并进行实测数据校准，后利用Sentaurus软件内置的Gamma射线总剂量辐射模型对器件进行辐射总剂量效应模拟仿真，相比于添加固定电荷以模拟总剂量辐射效应的做法，Gamma射线总剂量辐射模型可以得到更为真实的总剂量效应陷阱电荷分布。通过对器件在辐照前后进行实际电学特性测试，将得到的辐照前后实测数据用于TCAD模型校准，对此工艺节点下不同器件尺寸进行仿真产生数据集，其中32 928个器件数据点作为训练集对该模型进行训练，另外8 232个器件数据点作为测试集，对FinFET器件在开态（ON）辐照偏置下的总剂量效应进行预测。训练后的最终模型所得曲线与测试集数据的平均相对误差为2.98‰。此外，模型所得预测曲线与辐照后的实测数据也有极佳的吻合度，进一步验证了模型在实际工程应用中的巨大潜力。本文结合TCAD仿真技术和深度学习技术构建的TCAD-DNN模型仅需提供特定尺寸范围内的若干器件尺寸的电学特性曲线作为训练集对TCAD-DNN模型进行训练，训练完成后的模型能够在毫秒量级的调用时间内得到一定尺寸和总剂量范围内所有器件可靠的电学性能。此模型有效避免了TCAD仿真中的耗时过长和收敛性不稳定问题，成功预测了器件总剂量效应的电学响应对辐射剂量和器件几何参数方面的依赖性，该模型较高的预测精度和较好的灵活性使其能够应用在FinFET器件设计优化和器件与集成电路抗辐射加固等领域。

Abstract

The fin field-effect transistor (FinFET) has become the primary transistor device in advanced integrated circuits due to its advantages such as high integration

strong gate control capability

high drive current

high switching speed

and low leakage current. To obtain a physical-level total-ionizing-dose (TID) effect model for different device sizes under FinFET technology in advanced integrated circuits

this paper proposes and establishes a technology computer aided design-deep neural networks (TCAD-DNN) model to predict the electrical response of TID effects in devices. This paper uses Synopsys Sentaurus TCAD software to perform three-dimensional (3D) device modeling and actual measurement data calibration for FinFETs in the SMIC 14 nm CMOS process. Subsequently

the built-in Gamma-ray total dose irradiation model in Sentaurus software is utilized to simulate the total dose irradiation effects of the devices. Compared to the method of adding fixed charges to simulate total dose irradiation effects

the Gamma-ray total dose radiation model can obtain a more realistic distribution of trap charges due to total dose effects. By conducting actual electrical characteristic tests on the devices before and after irradiation

the obtained measured data before and after irradiation are used for TCAD model calibration. Simulations are performed on different device sizes under this process node to generate a dataset

where 32 928 device data points serve as the training set to train the model

and another 8 232 device data points serve as the test set to predict the total dose effects of FinFET devices under ON-state irradiation bias. The average relative error between the final model curve obtained after training and the test set data is 2.98‰. Furthermore

the predicted curve obtained from the model also has excellent agreement with the measured data after irradiation

which further verifies the great potential of the model in practical engineering applications. The TCAD-DNN model constructed in this paper

combining TCAD simulation technology and deep learning technology

only requires the provision of electrical characteristic curves for a certain range of device sizes as the training set for training the TCAD-DNN model. The trained model can obtain reliable electrical performance for all devices within a certain size and total dose range within a millisecond-scale call time. This model effectively avoids the issues of excessive simulation time and unstable convergence in TCAD simulations

successfully predicting the dependence of the electrical response of total dose effects on radiation dose and device geometric parameters. The high prediction accuracy and good flexibility of this model make it applicable in fields such as FinFET device design optimization and radiation hardening of devices and integrated circuits.

关键词

Keywords

references

Wu H W , Cui J W , Li Y D , et al . Comparison of total ionizing dose effects in 16-nm core and I/O n-FinFETs [J ] . IEEE Transactions on Nuclear Science , 2024 , 71 ( 2 ): 167 - 175 . DOI: 10.1109/tns.2024.3353189 http://dx.doi.org/10.1109/tns.2024.3353189

殷华湘 , 徐秋霞 . 体硅CMOS FinFET结构与特性研究 [J ] . 电子学报 , 2005 , 33 ( 8 ): 1484 - 1486 .

Yin Huaxiang , Xu Qiuxia . Bulk silicon CMOS FinFET’s structure and characteristics [J ] . Acta Electronica Sinica , 2005 , 33 ( 8 ): 1484 - 1486 . (in Chinese)

Wei X W , Cui J W , Luo D , et al . Enhanced total ionizing dose response of 16 nm n-FinFETs with a single fin [J ] . IEEE Electron Device Letters , 2023 , 44 ( 12 ): 1931 - 1934 . DOI: 10.1109/led.2023.3323315 http://dx.doi.org/10.1109/led.2023.3323315

Zhang Q Z , Zhang Y K , Luo Y N , et al . New structure transistors for advanced technology node CMOS ICs [J ] . National Science Review , 2024 , 11 ( 3 ): nwae008 .

黄云波 , 李博 , 杨玲 , 等 . 体硅nFinFET总剂量效应三维TCAD仿真研究 [J ] . 微电子学与计算机 , 2018 , 35 ( 8 ): 42 - 47 .

Huang Yunbo , Li Bo , Yangling , et al . Three-dimensional TCAD simulation study of the total ionizing dose effect on bulk nFinFET [J ] . Microelectronics & Computer , 2018 , 35 ( 8 ): 42 - 47 . (in Chinese)

崔旭 , 崔江维 , 郑齐文 , 等 . 22 nm体硅nFinFET总剂量辐射效应研究 [J ] . 微电子学 , 2022 , 52 ( 6 ): 1076 - 1080 .

Cui Xu , Cui Jiangwei , Zheng Qiwen , et al . Study on total ionizing dose effect of 22 nm bulk silicon nFinFET [J ] . Microelectronics , 2022 , 52 ( 6 ): 1076 - 1080 . (in Chinese)

Fleetwood D M , Winokur P S , Dodd P E . An overview of radiation effects on electronics in the space telecommunications environment [J ] . Microelectronics Reliability , 2000 , 40 ( 1 ): 17 - 26 . DOI: 10.1016/s0026-2714(99)00225-5 http://dx.doi.org/10.1016/s0026-2714(99)00225-5

彭超 , 雷志锋 , 张战刚 , 等 . 基于TCAD的绝缘体上硅器件总剂量效应仿真技术研究 [J ] . 电子学报 , 2019 , 47 ( 8 ): 1755 - 1761 .

Peng Chao , Lei Zhifeng , Zhang Zhangang , et al . Research on total ionizing dose effect simulation technology of silicon-on-insulator device based on TCAD [J ] . Acta Electronica Sinica , 2019 , 47 ( 8 ): 1755 - 1761 . (in Chinese)

陶伟 , 魏轶聃 , 刘国柱 , 等 . FinFET工艺器件总剂量和单粒子效应研究进展 [J ] . 中国电子科学研究院学报 , 2022 , 17 ( 3 ): 270 - 281 .

Tao Wei , Wei Yidan , Liu Guozhu , et al . Research progress of total ionizing dose and single event effect of devices based on FinFET process [J ] . Journal of China Academy of Electronics and Information Technology , 2022 , 17 ( 3 ): 270 - 281 . (in Chinese)

张峰源 , 李博 , 刘凡宇 , 等 . FinFET器件总剂量效应研究进展 [J ] . 微电子学 , 2020 , 50 ( 6 ): 875 - 884 .

Zhang Fengyuan , Li Bo , Liu Fanyu , et al . A review of total ionizing dose effects in FinFETs [J ] . Microelectronics , 2020 , 50 ( 6 ): 875 - 884 . (in Chinese)

Brewer R M , Zhang E X , Gorchichko M , et al . Total ionizing dose responses of 22-nm FDSOI and 14-nm bulk FinFET charge-trap transistors [J ] . IEEE Transactions on Nuclear Science , 2021 , 68 ( 5 ): 677 - 686 . DOI: 10.1109/tns.2021.3059594 http://dx.doi.org/10.1109/tns.2021.3059594

王保顺 , 崔江维 , 郑齐文 , 等 . 22 nm体硅FinFET热载流子及总剂量效应研究 [J ] . 固体电子学研究与进展 , 2020 , 40 ( 5 ): 384 - 388 .

Wang Baoshun , Cui Jiangwei , Zheng Qiwen , et al . Investigations on hot carrier injection and total ionizing dose effect of 22 nm bulk FinFET [J ] . Research & Progress of SSE , 2020 , 40 ( 5 ): 384 - 388 . (in Chinese)

Wang S H , Pei Y P , Huang R , et al . A model for radiation-induced off-state leakage current in N-channel metal-oxide-semiconductor transistors with shallow trench isolation [J ] . Journal of Applied Physics , 2010 , 107 ( 2 ): 024515 . DOI: 10.1063/1.3277017 http://dx.doi.org/10.1063/1.3277017

Liu Z L , Hu Z Y , Zhang Z X , et al . Total ionizing dose enhanced DIBL effect for deep submicron NMOSFET [J ] . IEEE Transactions on Nuclear Science , 2011 , 58 ( 3 ): 1324 - 1331 .

Oldham T R , McLean F B . Total ionizing dose effects in MOS oxides and devices [J ] . IEEE Transactions on Nuclear Science , 2003 , 50 ( 3 ): 483 - 499 . DOI: 10.1109/tns.2003.812927 http://dx.doi.org/10.1109/tns.2003.812927

Aditya K , Singh R , Kumar M , et al . Impact of gamma-ray radiation on DC and RF performance of 10-nm bulk N-channel FinFETs [J ] . IEEE Transactions on Device and Materials Reliability , 2020 , 20 ( 4 ): 760 - 766 . DOI: 10.1109/tdmr.2020.3033880 http://dx.doi.org/10.1109/tdmr.2020.3033880

Duzellier S . Radiation effects on electronic devices in space [J ] . Aerospace Science and Technology , 2005 , 9 ( 1 ): 93 - 99 . DOI: 10.1016/j.ast.2004.08.006 http://dx.doi.org/10.1016/j.ast.2004.08.006

Huang Y , Li B H , Cristoloveanu S , et al . TCAD simulation of total ionizing dose response on DSOI nMOSFET [C ] // 2019 Joint International EUROSOI Workshop and International Conference on Ultimate Integration on Silicon . Piscataway : IEEE , 2019 : 1 - 5 . DOI: 10.1109/eurosoi-ulis45800.2019.9041900 http://dx.doi.org/10.1109/eurosoi-ulis45800.2019.9041900

Chatterjee I , Zhang E X , Bhuva B L , et al . Bias dependence of total-dose effects in bulk FinFETs [J ] . IEEE Transactions on Nuclear Science , 2013 , 60 ( 6 ): 4476 - 4482 . DOI: 10.1109/tns.2013.2287872 http://dx.doi.org/10.1109/tns.2013.2287872

Liu X N , Dai L H , Ning B X , et al . Total-ionizing-dose-induced body current lowering in the 130 nm PDSOI I/O NMOSFETs [J ] . Chinese Physics Letters , 2017 , 34 ( 1 ): 016103 . DOI: 10.1088/0256-307x/34/1/016103 http://dx.doi.org/10.1088/0256-307x/34/1/016103

Seraphim B I , Palit S , Srivastava K , et al . A survey on machine learning techniques in network intrusion detection system [C ] // 2018 4th International Conference on Computing Communication and Automation . Piscataway : IEEE , 2018 : 1 - 5 . DOI: 10.1109/ccaa.2018.8777596 http://dx.doi.org/10.1109/ccaa.2018.8777596

雷文太 , 隋浩 , 姜和俊 , 等 . DABP: 一种基于深度学习的探地雷达自聚焦后向投影成像方法 [J ] . 电子学报 , 2024 , 52 ( 12 ): 4023 - 4036 .

Lei Wentai , Sui Hao , Jiang Hejun , et al . DABP: A deep learning based auto focusing back projection imaging method for ground penetrating radar [J ] . Acta Electronica Sinica , 2024 , 52 ( 12 ): 4023 - 4036 . (in Chinese)

王伟 , 张静宜 , 温玉辉 , 等 . 基于神经网络的图像风格迁移算法综述 [J ] . 电子学报 , 2025 , 53 ( 5 ): 1692 - 1712 .

Wang Wei , Zhang Jingyi , Wen Yuhui , et al . Neural network based image style transfer: A survey [J ] . Acta Electronica Sinica , 2025 , 53 ( 5 ): 1692 - 1712 . (in Chinese)

Memon Q U , Munir U , Ahmed U F , et al . An efficient technique to predict DC characteristics of nano-FinFETs using a deep neural network [J ] . Journal of Computational Electronics , 2022 , 22 : 230 - 241 . DOI: 10.1007/s10825-022-01978-7 http://dx.doi.org/10.1007/s10825-022-01978-7

Kao M Y , Kam H , Hu C M . Deep-learning-assisted physics-driven MOSFET current-voltage modeling [J ] . IEEE Electron Device Letters , 2022 , 43 ( 6 ): 974 - 977 . DOI: 10.1109/led.2022.3168243 http://dx.doi.org/10.1109/led.2022.3168243

Mittal S , Gupta H , Srivastava S . A survey on hardware security of DNN models and accelerators [J ] . Journal of Systems Architecture , 2021 , 117 : 102163 .

El Mamouni F , Zhang E X , Schrimpf R D , et al . Fin-width dependence of ionizing radiation-induced subthreshold-swing degradation in 100-nm-gate-length FinFETs [J ] . IEEE Transactions on Nuclear Science , 2009 , 56 ( 6 ): 3250 - 3255 . DOI: 10.1109/tns.2009.2034155 http://dx.doi.org/10.1109/tns.2009.2034155

Gaynor B D , Hassoun S . Fin shape impact on FinFET leakage with application to multithreshold and ultralow-leakage FinFET design [J ] . IEEE Transactions on Electron Devices , 2014 , 61 ( 8 ): 2738 - 2744 . DOI: 10.1109/ted.2014.2331190 http://dx.doi.org/10.1109/ted.2014.2331190

Chatterjee I , Zhang E X , Bhuva B L , et al . Geometry dependence of total-dose effects in bulk FinFETs [J ] . IEEE Transactions on Nuclear Science , 2014 , 61 ( 6 ): 2951 - 2958 . DOI: 10.1109/tns.2014.2367157 http://dx.doi.org/10.1109/tns.2014.2367157

Chatterjee I , Zhang E X , Bhuva B L , et al . Length and fin number dependence of ionizing radiation-induced degradation in bulk FinFETs [C ] // 2013 IEEE International Reliability Physics Symposium . Piscataway : IEEE , 2013 : SE.8. 1-SE . 8 . 6 .

Somra N , Mishra K , Singh R . Optimizing current characteristics of 32 nm FinFET by controlling fin width [J ] . Communications on Applied Electronics , 2015 , 2 ( 7 ): 1 - 5 .

Sentaurus Device User Guide [M ] . CA, USA : Synopsys , 2018 . DOI: 10.1007/978-981-10-3066-6_1 http://dx.doi.org/10.1007/978-981-10-3066-6_1

Yadav D S , Rahi S B , Tirkey S . Introduction to the Synopsys Sentaurus TCAD Suite and Device Simulation [M ] // Advanced Field-Effect Transistors: Theory and Applications . Hoboken : Wiley-IEEE Press , 2023 : 232 - 250 . DOI: 10.1201/9781003393542 http://dx.doi.org/10.1201/9781003393542

陈治西 , 刘强 , 任青华 , 等 . 基于FDSOI的TFET和MOSFET总剂量效应仿真 [J ] . 半导体技术 , 2019 , 44 ( 6 ): 464 - 470, 487 .

Chen Zhixi , Liu Qiang , Ren Qinghua , et al . Simulation of total ionizing dose effect in tunneling-FET and MOSFET based on FDSOI [J ] . Semiconductor Technology , 2019 , 44 ( 6 ): 464 - 470, 487 . (in Chinese)

Paillet P , Herve D , Leray J L , et al . Evidence of negative charge trapping in high temperature annealed thermal oxide [J ] . IEEE Transactions on Nuclear Science , 1994 , 41 ( 3 ): 473 - 478 . DOI: 10.1109/23.299787 http://dx.doi.org/10.1109/23.299787

刘文平 . 硅半导体器件辐射效应及加固技术 [M ] . 北京 : 科学出版社 , 2013 .

Liu Wenping . Radiation Effect and Reinforcement Technology of Silicon Semiconductor Devices [M ] . Beijing : Science Press , 2013 . (in Chinese)

Krantz R J , Aukerman L W , Zietlow T C . Applied field and total dose dependence of trapped charge buildup in MOS devices [J ] . IEEE Transactions on Nuclear Science , 1987 , 34 ( 6 ): 1196 - 1201 .

雷涛 . 基于UTBB-FDSOI器件的单粒子和总剂量效应及耦合机理研究 [D ] . 西安 : 西安电子科技大学 , 2021 .

Lei Tao . Research on Single Event and Total Dose Effects and Coupling Effects Based on UTBB-FDSOI Devices [D ] . Xi’an : Xidian University , 2021 . (in Chinese)

Milanowski R J , Pagey M P , Massengill L W , et al . TCAD-assisted analysis of back-channel leakage in irradiated mesa SOI nMOSFETs [J ] . IEEE Transactions on Nuclear Science , 1998 , 45 ( 6 ): 2593 - 2599 . DOI: 10.1109/23.736502 http://dx.doi.org/10.1109/23.736502

Borghello G , Faccio F , Lerario E , et al . Dose-rate sensitivity of 65-nm MOSFETs exposed to ultrahigh doses [J ] . IEEE Transactions on Nuclear Science , 2018 , 65 ( 8 ): 1482 - 1487 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Multi-Sound Source Separation Method Based on Multi-Resolution Parallel Feature Extraction

Adversarial Learning and Enhanced Optimization Based Restoration Method for VC-Generated Speeches

Binary Code Similarity Detection Method Based on Cross-Modal Coordinated Representation Learning

A Hierarchical Automatic Sleep Staging Model Based on Transformer Architecture

Related Author

JIA Maoshen

GAO Shang

LIAN Chen-si

ZHANG Guo-fu

ZHOU Xiao-lin

SU Zhao-pin

WANG Nian-song

YUE Feng

Related Institution

School of Information Science and Technology, Beijing University of Technology

Joint Laboratory of Intelligent Prevention and Recognition of Audio and Video

Intelligent Interconnected Systems Laboratory of Anhui Province (Hefei University of Technology)

Department of Physical Evidence Identification, Anhui Public Security Department

School of Computer and Information Technology, Hefei University of Technology

⁰