Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Autoren

  • Hannes Wagner-Mohnsen
  • Sascha Esefelder
  • Bernhard Kloter
  • Bernhard Mitchell
  • Carsten Schinke
  • Dennis Bredemeier
  • Philip Jager
  • Rolf Brendel

Organisationseinheiten

Externe Organisationen

  • Wavelabs Solar Metrology Systems GmbH
  • Institut für Solarenergieforschung GmbH (ISFH)
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des Sammelwerks2021 IEEE 48th Photovoltaic Specialists Conference
UntertitelPVSC 2021
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten528-531
Seitenumfang4
ISBN (elektronisch)9781665419222
PublikationsstatusVeröffentlicht - 2021
Veranstaltung48th IEEE Photovoltaic Specialists Conference, PVSC 2021 - Fort Lauderdale, USA / Vereinigte Staaten
Dauer: 20 Juni 2021 → 25 Juni 2021

Publikationsreihe

NameConference Record of the IEEE Photovoltaic Specialists Conference
ISSN (Print)0160-8371

Abstract

Advanced mathematical methods, like machine learning or genetic algorithms, have the potential to further accelerate the computer-aided optimization of processes. In this paper we combine the power of sophisticated numerical simulations with these modern concepts. The goal is to combine the strength of both approaches, high predictive quality from numerical models and fast prediction power of machine learning and genetic algorithms. We demonstrate this on a POCl3 diffusion process and optimize an industry relevant PERC solar cell up to 23.4%. This approach is not limited to POCl3 or PECR cells and can be applied to other cell architectures or processes.

ASJC Scopus Sachgebiete

Zitieren

Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process. / Wagner-Mohnsen, Hannes; Esefelder, Sascha; Kloter, Bernhard et al.
2021 IEEE 48th Photovoltaic Specialists Conference: PVSC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. S. 528-531 (Conference Record of the IEEE Photovoltaic Specialists Conference).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review

Wagner-Mohnsen, H, Esefelder, S, Kloter, B, Mitchell, B, Schinke, C, Bredemeier, D, Jager, P & Brendel, R 2021, Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process. in 2021 IEEE 48th Photovoltaic Specialists Conference: PVSC 2021. Conference Record of the IEEE Photovoltaic Specialists Conference, Institute of Electrical and Electronics Engineers Inc., S. 528-531, 48th IEEE Photovoltaic Specialists Conference, PVSC 2021, Fort Lauderdale, USA / Vereinigte Staaten, 20 Juni 2021. https://doi.org/10.1109/PVSC43889.2021.9518450
Wagner-Mohnsen, H., Esefelder, S., Kloter, B., Mitchell, B., Schinke, C., Bredemeier, D., Jager, P., & Brendel, R. (2021). Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process. In 2021 IEEE 48th Photovoltaic Specialists Conference: PVSC 2021 (S. 528-531). (Conference Record of the IEEE Photovoltaic Specialists Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PVSC43889.2021.9518450
Wagner-Mohnsen H, Esefelder S, Kloter B, Mitchell B, Schinke C, Bredemeier D et al. Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process. in 2021 IEEE 48th Photovoltaic Specialists Conference: PVSC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. S. 528-531. (Conference Record of the IEEE Photovoltaic Specialists Conference). doi: 10.1109/PVSC43889.2021.9518450
Wagner-Mohnsen, Hannes ; Esefelder, Sascha ; Kloter, Bernhard et al. / Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process. 2021 IEEE 48th Photovoltaic Specialists Conference: PVSC 2021. Institute of Electrical and Electronics Engineers Inc., 2021. S. 528-531 (Conference Record of the IEEE Photovoltaic Specialists Conference).
Download
@inproceedings{ef990699fd48403b9af2dda3c1ac356c,
title = "Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process",
abstract = "Advanced mathematical methods, like machine learning or genetic algorithms, have the potential to further accelerate the computer-aided optimization of processes. In this paper we combine the power of sophisticated numerical simulations with these modern concepts. The goal is to combine the strength of both approaches, high predictive quality from numerical models and fast prediction power of machine learning and genetic algorithms. We demonstrate this on a POCl3 diffusion process and optimize an industry relevant PERC solar cell up to 23.4%. This approach is not limited to POCl3 or PECR cells and can be applied to other cell architectures or processes.",
keywords = "genetic algorithm, machine learning, PERC, POCl3, TCAD",
author = "Hannes Wagner-Mohnsen and Sascha Esefelder and Bernhard Kloter and Bernhard Mitchell and Carsten Schinke and Dennis Bredemeier and Philip Jager and Rolf Brendel",
note = "Funding Information: Funded by the German Federal Ministry for Economic Affairs and Energy, Project GENESIS (0324274B) ; 48th IEEE Photovoltaic Specialists Conference, PVSC 2021 ; Conference date: 20-06-2021 Through 25-06-2021",
year = "2021",
doi = "10.1109/PVSC43889.2021.9518450",
language = "English",
series = "Conference Record of the IEEE Photovoltaic Specialists Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "528--531",
booktitle = "2021 IEEE 48th Photovoltaic Specialists Conference",
address = "United States",

}

Download

TY - GEN

T1 - Combining Numerical Simulations, Machine Learning and Genetic Algorithms for Optimizing a POCl3Diffusion Process

AU - Wagner-Mohnsen, Hannes

AU - Esefelder, Sascha

AU - Kloter, Bernhard

AU - Mitchell, Bernhard

AU - Schinke, Carsten

AU - Bredemeier, Dennis

AU - Jager, Philip

AU - Brendel, Rolf

N1 - Funding Information: Funded by the German Federal Ministry for Economic Affairs and Energy, Project GENESIS (0324274B)

PY - 2021

Y1 - 2021

N2 - Advanced mathematical methods, like machine learning or genetic algorithms, have the potential to further accelerate the computer-aided optimization of processes. In this paper we combine the power of sophisticated numerical simulations with these modern concepts. The goal is to combine the strength of both approaches, high predictive quality from numerical models and fast prediction power of machine learning and genetic algorithms. We demonstrate this on a POCl3 diffusion process and optimize an industry relevant PERC solar cell up to 23.4%. This approach is not limited to POCl3 or PECR cells and can be applied to other cell architectures or processes.

AB - Advanced mathematical methods, like machine learning or genetic algorithms, have the potential to further accelerate the computer-aided optimization of processes. In this paper we combine the power of sophisticated numerical simulations with these modern concepts. The goal is to combine the strength of both approaches, high predictive quality from numerical models and fast prediction power of machine learning and genetic algorithms. We demonstrate this on a POCl3 diffusion process and optimize an industry relevant PERC solar cell up to 23.4%. This approach is not limited to POCl3 or PECR cells and can be applied to other cell architectures or processes.

KW - genetic algorithm

KW - machine learning

KW - PERC

KW - POCl3

KW - TCAD

UR - http://www.scopus.com/inward/record.url?scp=85115928824&partnerID=8YFLogxK

U2 - 10.1109/PVSC43889.2021.9518450

DO - 10.1109/PVSC43889.2021.9518450

M3 - Conference contribution

AN - SCOPUS:85115928824

T3 - Conference Record of the IEEE Photovoltaic Specialists Conference

SP - 528

EP - 531

BT - 2021 IEEE 48th Photovoltaic Specialists Conference

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 48th IEEE Photovoltaic Specialists Conference, PVSC 2021

Y2 - 20 June 2021 through 25 June 2021

ER -