Use Case II
Application and Chances of Machine Learning Methods in the Electromagnetic Compatibility
Date:
Duration:
Location:
Abstract
Electromagnetic Compatibility (EMC) is about the suppression of unwanted electromagnetic interference between electronic devices, systems and components. Increasing demands in the EMC domain – e.g. wireless communication with increasing frequency – require a continuous development of engineering methods to make early, efficient, and cost effective decisions during the development process. In this workshop machine learning methods for EMC-Applications are presented. Own research topics of printed circuit board based power delivery networks (PDNs) are discussed with respect to the application of artificial neural networks. Classifications of PDN impedances against a target impedance are shown in a practical example using jupyter notebooks.
Hamburg University of Technology,Institute of Electromagnetic Theory (TET)
Hamburg University of Technology,Institute of Electromagnetic Theory (TET)
Literature
A. Sánchez-Masís, ANN Hyperparameter Optimization by Genetic Algorithms for Via Interconnect Classification. In 2021 IEEE 25th Workshop on Signal and Power Integrity (SPI), Siegen, Germany, May 2021
M. Schierholz et al., SI/PI-Database of PCB-Based Interconnects for Machine Learning Applications. IEEE Access, vol. 9, pp. 34423–34432, 2021. K. Scharff, C. M. Schierholz, C. Yang, and C. Schuster, ANN Performance for the Prediction of High-Speed Digital Interconnects over Multiple PCBs. In 2020 IEEE 29th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS), San Jose, CA, USA, Oct. 2020.
C. M. Schierholz, K. Scharff, and C. Schuster, Evaluation of Neural Networks to Predict Target Impedance Violations of Power Delivery Networks. In 2019 IEEE 28th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS), Montreal, QC, Canada, Oct. 2019.
M. Schierholz, C. Yang, K. Roy, M. Swaminathan, and C. Schuster, Comparison of Collaborative versus Extended Artificial Neural Networks for PDN Design. In 2020 IEEE 24th Workshop on Signal and Power Integrity (SPI), Cologne, Germany, May 2020.
K. Scharff, H. M. Torun, C. Yang, M. Swaminathan, and C. Schuster, Bayesian Optimization for Signal Transmission Including Crosstalk in a Via Array. In 2020 International Symposium on Electromagnetic Compatibility - EMC EUROPE, Rome, Italy, Sep. 2020