An extraction method based on artificial neural network techniques for novel Cardiff model with reasonable extrapolation behavior

Tian, Mengyue, Bell, James J. ORCID: https://orcid.org/0000-0002-4815-2199, Quaglia, Roberto ORCID: https://orcid.org/0000-0003-3228-301X and Tasker, Paul J. ORCID: https://orcid.org/0000-0002-6760-7830 2024. An extraction method based on artificial neural network techniques for novel Cardiff model with reasonable extrapolation behavior. IEEE Microwave and Wireless Components Letters 34 (1) , pp. 5-8. 10.1109/LMWT.2023.3329979

PDF - Accepted Post-Print Version Download (830kB)

Abstract

This letter presents an advanced Cardiff Model (CM) extraction method based on artificial neural network (ANN) techniques that ensures reasonable extrapolation behavior. The nonphysical extrapolation behavior occurring with CMs using a high, user-defined, mixing order, i.e., false output optima point and erroneous efficiency behavior, when extracted using measured load-pull datasets can be avoided with the proposed method. The method proposed maintains the accuracy within the load-pull measurements, design-relevant, impedance space. The method was verified by modeling the measured load-pull data of a Wolfspeed 10-W gallium nitride (GaN) packaged device and a WIN Semiconductors GaN on-wafer device. With both the devices, the extrapolation issues shown when using the high-order CM are removed by the novel extracted CM coefficients.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1558-1764
Date of First Compliant Deposit:	30 October 2023
Date of Acceptance:	29 October 2023
Last Modified:	18 Jan 2024 16:50
URI:	https://orca.cardiff.ac.uk/id/eprint/163567

Actions (repository staff only)

Edit Item