ANN Performance for the Prediction of High-Speed Digital Interconnects over Multiple PCBs

Katharina Scharff, Morten Schierholz, Cheng Yang, Christian Schuster
October 2020
Schematic of Procedure including the setup of Backplane and Daughtercard

Abstract

In this paper the performance and the accuracy of artificial neural networks for the prediction of high-speed digital interconnects up to 100 GHz on printed circuit boards are analyzed and evaluated. The prediciton accuracy is evaluated both for scattering parameters in frequency domain as well as weighted power sums thereof. The interconnects considered all contain a backplane connected to a daughtercard, showing two via arrays each. Several parameter variations of the basic setup lead to a wide range of possible transmission and crosstalk parameters. Training data sets are obtained using physics-based via modeling up to 100 GHz. Approximately 7000 data sets were made available in total for this study. Neural networks are able to predict the overall link behavior.

Type
Conference paper
Publication
[EPEPS 2020 - 29th Conference on Electrical Performance of Electronic Packaging and Systems]
Maschinelles Lernen Künstliche Neuronale Netze Signal Integrity High-Speed Links Physics-Based Modeling
Avatar
Morten Schierholz
Doktorand
Avatar
Cheng Yang
Oberingenieur

Computational Electromagnetics, Elektromagnetische Verträglichkeit (EMV), Signal Integrity (SI) und Power Integrity (PI), Mikrowellen-Messtechnik, Maschinelles Lernen für EMV-Engineering

Avatar
Christian Schuster
Professor, MLE-Gründer & -Advisor

Related