Session: DAC-02-01-Artificial Intelligence and Machine Learning for Challenging Real-World Problems in Design Automation

Paper Number: 90046

90046 - Automatic Power Plane Generation With Genetic Optimization and Multilayer Perceptron 

We present an automatic power plane generation method to accelerate the design of printed circuit boards (PCB). In PCB design, while automatic solvers have been developed to predict important indicators such as the IR-drop, power integrity, and signal integrity, the generation of the power plane itself still largely relies on laborious manual methods. Our automatic power plane generation approach is based on genetic optimization combined with a multilayer perceptron and is able to automatically generate power planes across a diverse set of problems with varying levels of difficulty. Our method consists of an outer loop genetic optimizer (GO) and an inner loop multi-layer perceptron (MLP) that generate power planes automatically. The critical elements of our approach include contour detection, feature expansion, and a distance measure to enable island-minimizing complex power plane generation. We compare our approach to a baseline solution based on A*. The A* method consisting of a sequential island generation and merging process which can produce less than ideal solutions. Our experimental results show that our method outperforms A* in 71% of the design problems with varying levels board layout difficulty. We also present ablation studies demonstrating the influence of various algorithmic choices. Finally, we provide insights into how the power planes evolve with our model parameters to form feasible and desirable space partitions.

Presenting Author: Levent Burak Kara Carnegie Mellon Univ

Presenting Author Biography: L. Burak Kara is a professor in the Department of Mechanical Engineering, with a courtesy appointment in the Robotics Institute. His research develops new computational analysis, design, and manufacturing technologies with wide-ranging applications in the space of mechanical CAD, topology optimization, additive manufacturing, electronics design, and bio-engineering. To this end, his research combines principles of machine learning, optimization, and geometric modeling to develop new knowledge and computational software for use in next-generation design systems.

Authors:

Haiguang Liao Carnegie Mellon University
Vinay Patil Carnegie Mellon University
Xuliang Dong Carnegie Mellon University
Devika Shanbhag Carnegie Mellon University
Elias Fallon Cadence Design Systems
Taylor Hogan Cadence Design Systems
Mirko Spasojevic Cadence Design Systems
Levent Burak Kara Carnegie Mellon Univ