Abstract

In this work we use machine learning to extract actual Cu doping profiles that result from the process of diffusion annealing and cool-down in the fabrication sequence of CdTe solar cells. We use two deep learning neural network models (Artificial Neural Network (ANN) model using a Keras API with TensorFlow backend and a Radial Basis Function Network (RBFN) model) to predict the Cu doping profiles for different temperatures and duration of the annealing process. We find excellent agreement between the simulated results obtained with the PVRD-FASP Solver and predicted values. It takes significant amount of time to generate with the PVRD-FASP Solver the Cu doping profiles given the initial conditions. The generation of the same with machine learning is almost instantaneous and can serve as an excellent simulation tool to guide future fabrication of optimal doping profiles in CdTe solar cells.

Original languageEnglish (US)
Title of host publication2021 IEEE 48th Photovoltaic Specialists Conference, PVSC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages540-543
Number of pages4
ISBN (Electronic)9781665419222
DOIs
StatePublished - Jun 20 2021
Event48th IEEE Photovoltaic Specialists Conference, PVSC 2021 - Fort Lauderdale, United States
Duration: Jun 20 2021Jun 25 2021

Publication series

NameConference Record of the IEEE Photovoltaic Specialists Conference

Conference

Conference48th IEEE Photovoltaic Specialists Conference, PVSC 2021
Country/TerritoryUnited States
CityFort Lauderdale
Period6/20/216/25/21

Keywords

  • CdTe solar cells
  • Cu doping
  • diffusion processes
  • machine learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Machine Learning for Optimal Copper Doping Profile Design in CdTe Solar Cells'. Together they form a unique fingerprint.

Cite this