國立虎尾科技大學 |

Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization./
Author:	Jaiswal, Rahul.
Description:	1 online resource (146 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
Subject:	Engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798380606851

Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization.
Jaiswal, Rahul.

Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization. - 1 online resource (146 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--The University of New Mexico, 2023.

Includes bibliographical references

Silicon heterojunction solar cell of Heterojunction with Thin Intrinsic Layer (HIT) structure is a commercially available technology, and its market share will significantly increase by the next decade. With such a significant market share, any minor improvement in the device's overall efficiency can be beneficial three folds - customer return on investment, industry revenue, and the overall carbon footprint (from manufacturing to recycling/ disposing of the device). Conventionally, device optimization for solar cells has been achieved using a hit & trial approach where multiple experiments are done to evaluate the best process conditions and device parameters. This approach has some inherent disadvantages, especially, because it is expensive in terms of resources, time, and manpower required. In the past couple of decades, simulation techniques are also being utilized in addition to the conventional approaches and very recently use of data science-based techniques has become popular in research and is gaining some traction in the photovoltaics industry.In this doctoral research, an innovative approach is presented, where device simulations for solar cells are designed and calibrated to match the performance of an industrially manufactured device using a minimal set of measurement data. Then a digital twin for the numerical simulations is developed by training Machine Learning (ML) models using simulation and measurement data. ML methods are also used for the calibration of simulation models in addition to being used forthe digital twin. The use of machine learning helps significantly reduce computational time to prototype any design changes in the device. In our work, apart from providing mean predictions, we are also providing a measure of uncertainty with every prediction, using Gaussian Process Regression (GPR).

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380606851Subjects--Topical Terms:

561152
Engineering.
Subjects--Index Terms:

CalibrationIndex Terms--Genre/Form:

554714
Electronic books.

Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization.
LDR:03274ntm a22004217 4500 001 1142767
005 20240429063830.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380606851
035 $a (MiAaPQ)AAI30315785
035 $a AAI30315785
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jaiswal, Rahul. $3 1467205
245 1 0 $a Machine Learning Based Prediction Models for Silicon Heterojunction Solar Cell Optimization.
264 0 $c 2023
300 $a 1 online resource (146 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Busani, Tito.
502 $a Thesis (Ph.D.)--The University of New Mexico, 2023.
504 $a Includes bibliographical references
520 $a Silicon heterojunction solar cell of Heterojunction with Thin Intrinsic Layer (HIT) structure is a commercially available technology, and its market share will significantly increase by the next decade. With such a significant market share, any minor improvement in the device's overall efficiency can be beneficial three folds - customer return on investment, industry revenue, and the overall carbon footprint (from manufacturing to recycling/ disposing of the device). Conventionally, device optimization for solar cells has been achieved using a hit & trial approach where multiple experiments are done to evaluate the best process conditions and device parameters. This approach has some inherent disadvantages, especially, because it is expensive in terms of resources, time, and manpower required. In the past couple of decades, simulation techniques are also being utilized in addition to the conventional approaches and very recently use of data science-based techniques has become popular in research and is gaining some traction in the photovoltaics industry.In this doctoral research, an innovative approach is presented, where device simulations for solar cells are designed and calibrated to match the performance of an industrially manufactured device using a minimal set of measurement data. Then a digital twin for the numerical simulations is developed by training Machine Learning (ML) models using simulation and measurement data. ML methods are also used for the calibration of simulation models in addition to being used forthe digital twin. The use of machine learning helps significantly reduce computational time to prototype any design changes in the device. In our work, apart from providing mean predictions, we are also providing a measure of uncertainty with every prediction, using Gaussian Process Regression (GPR).
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Engineering. $3 561152
650 4 $a Computer science. $3 573171
650 4 $a Energy. $3 784773
650 4 $a Alternative energy. $3 1241221
650 4 $a Materials science. $3 557839
653 $a Calibration
653 $a Digital twin
653 $a Machine learning
653 $a Silicon photovoltaics
653 $a Solar cells
655 7 $a Electronic books. $2 local $3 554714
690 $a 0537
690 $a 0984
690 $a 0791
690 $a 0363
690 $a 0794
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of New Mexico. $b Electrical Engineering. $3 1148490
773 0 $t Dissertations Abstracts International $g 85-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30315785 $z click for full text (PQDT)