Open Access System for Information Sharing

Login Library

 

Article
Cited 18 time in webofscience Cited 18 time in scopus
Metadata Downloads

Deep Q-network to produce polarization-independent perfect solar absorbers: a statistical report SCIE SCOPUS

Title
Deep Q-network to produce polarization-independent perfect solar absorbers: a statistical report
Authors
Sajedian, ImanBadloe, TrevonLee, HeonRho, Junsuk
Date Issued
2020-08
Publisher
SPRINGER
Abstract
Using reinforcement learning, a deep Q-network was used to design polarization-independent, perfect solar absorbers. The deep Q-network selected the geometrical properties and materials of a symmetric three-layer metamaterial made up of circular rods on top of two films. The combination of all the possible permutations gives around 500 billion possible designs. In around 30,000 steps, the deep Q-network was able to produce 1250 structures that have an integrated absorption of higher than 90% in the visible region, with a maximum of 97.6% and an integrated absorption of less than 10% in the 8-13 mu m wavelength region, with a minimum of 1.37%. A statistical analysis of the distribution of materials and geometrical parameters that make up the solar absorbers is presented.
URI
https://oasis.postech.ac.kr/handle/2014.oak/105580
DOI
10.1186/s40580-020-00233-8
ISSN
2196-5404
Article Type
Article
Citation
NANO CONVERGENCE, vol. 7, no. 1, page. 1 - 7, 2020-08
Files in This Item:
There are no files associated with this item.

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

노준석RHO, JUNSUK
Dept of Mechanical Enginrg
Read more

Views & Downloads

Browse