SI/PI-Database of PCB-Based Interconnects for Machine Learning Applications

A database is presented that allows the investigation of machine learning (ML) tools and techniques in signal integrity (SI), power (PI), electromagnetic compatibility (EMC) domains. The contains different types printed circuit board (PCB)-based interconnects corresponding frequency domain data from a physics-based (PB) tool represent multiple (EM) aspects to SI PI optimization. have been used past by authors investigate ML PI. However, many more can be developed applied these structures. setup database, its sets, examples on how apply will discussed detail. Overall 78961 variations are presented. By making this available we invite other researchers customize their using our results. This provides possibility accelerate research EMC engineering without need generate expensive data.