Application of Multi-Objective Genetic Optimization in PCB Component Placement
Name
ngo-ngot-meng-bcs-2024-thesis.pdf
Description
Thesis PDF
Size
7.82 MB
Format
Adobe PDF
Checksum (MD5)
b77d2a8f71644a2166b061dbb0729ccc
Author(s)
Ngô, Thomas
Advisor(s)
Daniel, Luca
Date Issued
February 2024
Publisher
Massachusetts Institute of Technology
Abstract
Designing a printed circuit board (PCB) is a complex process that involves creating a schematic, placing components, ensuring that every component is routable, and performing simulations to predict the behavior of the PCB before it is manufactured. With the rise of technological innovations, the demand for chips will increase, putting pressure on the electronic design automation (EDA) industry to innovate in PCB design. As part of Cadence’s Allegro X AI team, which aims to develop AI technology to automate PCB designers’ tasks, we explored the application of multi-objective genetic optimization in component placements as an alternative method for automating component placement. More specifically, we applied genetic optimization to a two-sided printed circuit board (PCB). We discovered that employing multiple objectives, such as half-perimeter wirelength and routability, produces promising component placements.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
Persistent DSpace Link
