A Novel Neural Network-Based Transistor Compact Model Including Self-Heating
- 3 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Electron Device Letters
- Vol. 45 (8) , 1512-1515
Abstract
We develop a SPICE-compatible neural network-based compact model to accurately capture the temperature dependence and self-heating effects in Field Effect Transistors (FETs). The model is based on artificial neural networks with no semi-empirical temperature equations. The transfer and activation functions are optimized to improve the accuracy of the model. A new temperature relaxation model is proposed, which allows training the model using ambient temperature data without iteratively extracting the self-heating parameters. The proposed method can simply generate the ambient and dynamic self-heating characteristics for circuit simulations. The model can accurately reproduce the current-voltage (IV), capacitance-voltage (CV), and transient characteristics of FETs across a broad temperature range with a speed advantage of up to 12X versus BSIM-CMG.Keywords
Funding Information
- Berkeley Device Modeling Center, University of California at Berkeley, Berkeley, CA, USA
This publication has 14 references indexed in Scilit:
- Neural Network-Based BSIM Transistor Model Framework: Currents, Charges, Variability, and Circuit SimulationIEEE Transactions on Electron Devices, 2023
- Neural Network-Based and Modeling With High Accuracy and Potential Model Speed IEEE Transactions on Electron Devices, 2022
- Impact of Self-Heating on Negative-Capacitance FinFET: Device-Circuit InteractionIEEE Transactions on Electron Devices, 2021
- BSIM-HV: High-Voltage MOSFET Model Including Quasi-Saturation and Self-Heating EffectIEEE Transactions on Electron Devices, 2019
- BSIM-BULK: Accurate Compact Model for Analog and RF Circuit Design2019
- On the Formulation of Self-Heating Models for Circuit SimulationIEEE Journal of the Electron Devices Society, 2018
- A new framework of physics-based compact model predicts reliability of self-heated modern ICs: FinFET, NWFET, NSHFET comparison2017
- Dynamic FET model - DynaFET - for GaN transistors from NVNA active source injection measurements2014
- Adaptive Neural Network Model for SOI-MOSFET I-V Characteristic Including Self-Heating Effect2006
- Combinational profiles of sequential benchmark circuits2003