Prediction of Device Characteristics of Feedback Field-Effect Transistors Using TCAD-Augmented Machine Learning

In this study, the device characteristics of silicon nanowire feedback field-effect transistors were predicted using technology computer-aided design (TCAD)-augmented machine learning (TCAD-ML). The full current-voltage ( ) curves in forward and reverse voltage sweeps were predicted well, with high...

Full description

Saved in:
Bibliographic Details
Published in:Micromachines (Basel) 2023-02, Vol.14 (3), p.504
Main Authors: Woo, Sola, Jeon, Juhee, Kim, Sangsig
Format: Article
Language:English
Subjects:
Accuracy
CAD
CAD-CAM systems
Circuit components
Computer aided design
Computer programs
Computing time
Datasets
Decision trees
Electric potential
Feedback
feedback field-effect transistors
Field effect transistors
Latch-up
Machine learning
Nanowires
Neural networks
Physics
random forest regression
Regression analysis
Regression models
Semiconductor devices
Simulation
Simulation methods
TCAD-augmented machine learning
Technology application
technology computer-aided design (TCAD)
Transistors
Voltage
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, the device characteristics of silicon nanowire feedback field-effect transistors were predicted using technology computer-aided design (TCAD)-augmented machine learning (TCAD-ML). The full current-voltage ( ) curves in forward and reverse voltage sweeps were predicted well, with high R-squared values of 0.9938 and 0.9953, respectively, by using random forest regression. Moreover, the TCAD-ML model provided high prediction accuracy not only for the full curves but also for the important device features, such as the latch-up and latch-down voltages, saturation drain current, and memory window. Therefore, this study demonstrated that the TCAD-ML model can substantially reduce the computational time for device development compared with conventional simulation methods.
ISSN:2072-666X
2072-666X
DOI:10.3390/mi14030504