Articles | Volume 21
https://doi.org/10.5194/ars-21-25-2023
https://doi.org/10.5194/ars-21-25-2023
01 Dec 2023
 | 01 Dec 2023

Mathematical optimization and machine learning to support PCB topology identification

Ilda Cahani and Marcus Stiemer

Related authors

Iterative Placement of Decoupling Capacitors using Optimization Algorithms and Machine Learning
Zouhair Nezhi, Nima Ghafarian Shoaee, and Marcus Stiemer
Adv. Radio Sci., 21, 123–132, https://doi.org/10.5194/ars-21-123-2024,https://doi.org/10.5194/ars-21-123-2024, 2024
Short summary

Cited articles

Archambeault, B. R. and Drewniak, J.: PCB Design for Real-World EMI Control, vol. 696, Springer Science & Business Media, https://doi.org/10.1007/978-1-4757-3640-3, 2013. a
Arsenovic, A., Hillairet, J., Anderson, J., Forstén, H., Rieß, V., Eller, M., Sauber, N., Weikle, R., Barnhart, W., and Forstmayr, F.: scikit-rf: An Open Source Python Package for Microwave Network Creation, Analysis, and Calibration [Speaker’s Corner], IEEE Microwave Magazine, 23, 98–105, https://doi.org/10.1109/MMM.2021.3117139, 2022. a, b
Bogatin, E.: Signal and Power Integrity: Simplified, Prentice Hall Professional, 2nd edn., https://doi.org/10.1007/978-1-4757-3640-3, 2004. a
Brooks, D.: Signal Integrity Issues and Printed Circuit Board Design, Prentice Hall modern semiconductor design series, Prentice Hall Professional, ISBN 2003046969, 2003. a
Chandrasekar, K., Weis, C., Akesson, B., Wehn, N., and Goossens, K.: System and circuit level power modeling of energy-efficient 3D-stacked wide I/O DRAMs, in: 2013 Design, Automation & Test in Europe Conference & Exhibition, 18–22 March 2013, Grenoble, France, pp. 236–241, IEEE, https://doi.org/10.7873/DATE.2013.061, 2013. a
Download
Short summary
A framework to assist to the modeling, classification, and identification of PCB designs involving different topological approaches is proposed based on the analysis of scattering parameters. The underlying idea is to break down the relevant information hidden in the network topology to a flattened latent space via an encoder-decoder structure. Various machine learning and optimization methods are proposed using the trained encoder or decoder as upstream or downstream component.