Saved in:
Bibliographic Details
Main Authors: Padhy, Rahul Kumar, Chandrasekhar, Aaditya
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.00845
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909235257802752
author Padhy, Rahul Kumar
Chandrasekhar, Aaditya
author_facet Padhy, Rahul Kumar
Chandrasekhar, Aaditya
contents Topology Optimization (TO) holds the promise of designing next-generation compact and efficient photonic components. However, ensuring the optimized designs comply with fabrication constraints imposed by semiconductor foundries remains a challenge. This work presents a TO framework that guarantees designs satisfy fabrication criteria, particularly minimum feature size and separation. Leveraging recent advancements in machine learning and feature mapping methods, our approach constructs components by transforming shapes from a predefined library, simplifying constraint enforcement. Specifically, we introduce a Convo-implicit Variational Autoencoder to encode the discrete shape library into a differentiable space, enabling gradient-based optimization. The efficacy of our framework is demonstrated through the design of several common photonic components.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00845
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PhoTOS: Topology Optimization of Photonic Components using a Shape Library
Padhy, Rahul Kumar
Chandrasekhar, Aaditya
Numerical Analysis
Optics
Topology Optimization (TO) holds the promise of designing next-generation compact and efficient photonic components. However, ensuring the optimized designs comply with fabrication constraints imposed by semiconductor foundries remains a challenge. This work presents a TO framework that guarantees designs satisfy fabrication criteria, particularly minimum feature size and separation. Leveraging recent advancements in machine learning and feature mapping methods, our approach constructs components by transforming shapes from a predefined library, simplifying constraint enforcement. Specifically, we introduce a Convo-implicit Variational Autoencoder to encode the discrete shape library into a differentiable space, enabling gradient-based optimization. The efficacy of our framework is demonstrated through the design of several common photonic components.
title PhoTOS: Topology Optimization of Photonic Components using a Shape Library
topic Numerical Analysis
Optics
url https://arxiv.org/abs/2407.00845