A Floating Normalization Scheme for Deep Learning-Based Custom-Range Parameter Extraction in BSIM-CMG Compact Models

TL;DR

This paper presents a deep learning method with a floating normalization scheme for flexible, accurate extraction of BSIM-CMG model parameters from experimental measurements, adaptable to user-defined ranges.

Contribution

It introduces a dynamic normalization approach within a neural network architecture, enabling customizable parameter extraction ranges unlike fixed-range methods.

Findings

High accuracy in parameter extraction validated on 14 nm FinFET data.

Enhanced flexibility allows application to various compact models.

Demonstrates superiority over conventional fixed-normalization techniques.

Abstract

A deep-learning (DL) based methodology for automated extraction of BSIM-CMG compact model parameters from experimental gate capacitance vs gate voltage (Cgg-Vg) and drain current vs gate voltage (Id-Vg) measurements is proposed in this paper. The proposed method introduces a floating normalization scheme within a cascaded forward and inverse ANN architecture enabling user-defined parameter extraction ranges. Unlike conventional DL-based extraction techniques, which are often constrained by fixed normalization ranges, the floating normalization approach adapts dynamically to user-specified ranges, allowing for fine-tuned control over the extracted parameters. Experimental validation, using a TCAD calibrated 14 nm FinFET process, demonstrates high accuracy for both Cgg-Vg and Id-Vg parameter extraction. The proposed framework offers enhanced flexibility, making it applicable to various compact models beyond BSIM-CMG.