A Fast and Accurate Method for Bond Wires Inductances Extraction Based on Machine Learning Strategy

Liu, Qi; Shao, Zijian; Zhang, Yueping; Mao, Jun‐Fa

doi:10.1109/imws-amp49156.2020.9199770

Cited by 3 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As power module layouts are normally constrained by the fixed packaging dimensions, such as two-layer ceramic with copper traces on one side only, and can be approximately treated as 2.5D structures, makes them a good candidate for a fundamentally different approach to parasitic inductance extraction with the help of machine learning. Machine learning has been applied to some well-defined inductance estimation tasks, such as microstrips [6], coils [7] or parametrized bondwires [8]. However, it has not been yet applied to inductance estimation problems where geometry can significantly vary and is not easy to describe with a few simple parameters.…”

Section: Introductionmentioning

confidence: 99%

Ultra-Fast Power Module Inductance Estimation using Convolutional Neural Networks

Kubulus,

Michal Beczkowski,

Munk-Nielsen

et al. 2023

2023 IEEE Energy Conversion Congress and Exposition (ECCE)

View full text Add to dashboard Cite

The widespread usage of wide bandgap (WBG) semiconductors forces extra emphasis on the early estimation of the layout parasitic elements. Be it a printed circuit board or a power module, layout optimization is necessary to minimize the negative effects of present inductances. Unfortunately, multiple invocations of inductance extraction software can be timeconsuming. In this work, state-of-the-art convolutional neural networks (CNN) are applied in order to lower the time consumption of inductance estimation without compromising the accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%