Fast PDN Impedance Prediction Using Deep Learning
This addresses a domain-specific problem for PCB designers by providing a fast and accurate tool for PDN impedance prediction, though it is incremental as it applies deep learning to an existing bottleneck.
The paper tackles the computational inefficiency of modeling power distribution network (PDN) impedance for printed circuit boards (PCBs) with irregular shapes and multi-layer stackups by using deep learning, achieving a prediction time of 0.1 seconds, which is over 100 times faster than boundary element methods and 5000 times faster than full-wave simulations.
Modeling and simulating a power distribution network (PDN) for printed circuit boards (PCBs) with irregular board shapes and multi-layer stackup is computationally inefficient using full-wave simulations. This paper presents a new concept of using deep learning for PDN impedance prediction. A boundary element method (BEM) is applied to efficiently calculate the impedance for arbitrary board shape and stackup. Then over one million boards with different shapes, stackup, IC location, and decap placement are randomly generated to train a deep neural network (DNN). The trained DNN can predict the impedance accurately for new board configurations that have not been used for training. The consumed time using the trained DNN is only 0.1 seconds, which is over 100 times faster than the BEM method and 5000 times faster than full-wave simulations.