A Novel Cardiff Model Coefficients Extraction Process Based on Artificial Neural Network | IEEE Conference Publication | IEEE Xplore

A Novel Cardiff Model Coefficients Extraction Process Based on Artificial Neural Network


Abstract:

This paper presents a novel way to extract the Cardiff model coefficients. Analysis shows that the Cardiff model is easier for implementation in commercial RF design rela...Show More

Abstract:

This paper presents a novel way to extract the Cardiff model coefficients. Analysis shows that the Cardiff model is easier for implementation in commercial RF design related software, while the Artificial Neural Network (ANN) based behavioral model provides more flexibility for extracting the coefficients of a model, the two methods have been combined. The load-pull setup, implemented in Keysight Advanced Design System (ADS), is used to acquire the pseudo-wave data of the Cree 10W transistor. By using the feedforward ANN structure together with a novel Cardiff model related backpropagation algorithm, a set of accurate coefficients can be extracted, whose Normalized Mean Squared Error (NMSE) is -54.73 dB as shown in this paper.
Date of Conference: 22-25 January 2023
Date Added to IEEE Xplore: 21 February 2023
ISBN Information:

ISSN Information:

Conference Location: Las Vegas, NV, USA

I. Introduction

Extracting an accurate nonlinear behavioral model provides an efficient way to design RF power components and systems in a computer-aided design (CAD) environment. There are several kinds of mathematical formulation based non-linear models that have been developed over the past decades to model RF transistors, e.g., the Poly-Harmonic Distortion (PHD) Model [1], X-parameters [2], the Cardiff Behavioral model [3], and the ANN based model [6], [7].

References

References is not available for this document.