CMAS Lab - Deep Learning-Based Fast BSIM-CMG Parameter Extraction for

Journal article

A. Ashai, Aakash Jadhav, A. Behera, Sourajeet Roy, A. Dasgupta, B. Sarkar
IEEE Transactions on Electron Devices, 2023

Cite

APA Click to copy
Ashai, A., Jadhav, A., Behera, A., Roy, S., Dasgupta, A., & Sarkar, B. (2023). Deep Learning-Based Fast BSIM-CMG Parameter Extraction for General Input Dataset. IEEE Transactions on Electron Devices.

Chicago/Turabian Click to copy
Ashai, A., Aakash Jadhav, A. Behera, Sourajeet Roy, A. Dasgupta, and B. Sarkar. “Deep Learning-Based Fast BSIM-CMG Parameter Extraction for General Input Dataset.” IEEE Transactions on Electron Devices (2023).

MLA Click to copy
Ashai, A., et al. “Deep Learning-Based Fast BSIM-CMG Parameter Extraction for General Input Dataset.” IEEE Transactions on Electron Devices, 2023.

BibTeX Click to copy

@article{a2023a,
  title = {Deep Learning-Based Fast BSIM-CMG Parameter Extraction for General Input Dataset},
  year = {2023},
  journal = {IEEE Transactions on Electron Devices},
  author = {Ashai, A. and Jadhav, Aakash and Behera, A. and Roy, Sourajeet and Dasgupta, A. and Sarkar, B.}
}

Abstract

A deep learning (DL) technique to extract the set of Berkeley short-channel IGFET model-common multigate (BSIM-CMG) compact model parameters directly from experimental capacitance–voltage ( Cgg – Vg) and current–voltage ( Id ,– Vg) measurements is presented in this article. The proposed technique uses a cascade of inverse and forward artificial neural networks (ANNs) to accurately compute an inverse of the compact model while avoiding the problem of non-uniqueness. It also accurately adjusts the BSIM-CMG compact model parameter values for any variation in the geometry, highlighting that the proposed technique successfully captures the uncertainties in device dimensions. The proposed model exhibits good generalizability and scalability with respect to the size of the sampled Cgg – Vg and Id – Vg datasets as well as the number of compact model parameters to be extracted.