Application of artificial neural network for accelerated optimization of ultra thin organic solar cells

Mine Kaya, Shima Hajimirza

Research output: Contribution to journalArticlepeer-review

29 Scopus citations

Abstract

In this study, we show that design optimization of solar cells can be accelerated using neural networks (NN) effectively. We consider an organic thin film solar cell consisting of a poly(3-hexylthiophene):(6,6)-phenyl-C61-butyric-acid-methyl ester (P3HT:PCBM) absorber, an antireflective indium tin oxide (ITO) layer and an aluminum back reflector layer. Zinc oxide (ZnO) and molybdenum trioxide (MoO3) interlayers are also used as electron and hole transfer layers. Silver nanotextures are embedded within absorber layer to create near field effects thus enhancing optical absorption. Optical properties of structures at sub-wavelength scales are measured by numerically solving first principle electromagnetic equations, e.g., by means of finite difference time domain and finite element methods. These methods are time-consuming, and therefore limit the possibility of exhaustive optimization. Surrogate modeling can be used to overcome this challenge. In the present work, we design a two-layer NN surrogate model to estimate the optical absorptivity of the cell for any given geometry vector as well as any radiation wavelength. After the preliminary optimization which utilizes NN, the result of optimization is obtained within narrowed optimization bounds obtained from the results of surrogate based optimization. A 325% of enhancement in absorption is obtained as a result of optimization.

Original languageEnglish
Pages (from-to)159-166
Number of pages8
JournalSolar Energy
Volume165
DOIs
StatePublished - 1 May 2018

Keywords

  • Artificial neural network
  • Optimization
  • Organic solar cells
  • Plasmonics
  • Surrogate based analysis

Fingerprint

Dive into the research topics of 'Application of artificial neural network for accelerated optimization of ultra thin organic solar cells'. Together they form a unique fingerprint.

Cite this