Machine Learning-Assisted Optimization of Additive Engineering in FAPbI3-Based Perovskite Solar Cells: Achieving High Efficiency and Long-Term Stability
{"title":"Machine Learning-Assisted Optimization of Additive Engineering in FAPbI3-Based Perovskite Solar Cells: Achieving High Efficiency and Long-Term Stability","authors":"Weihua Qu, Qiang Xie, Yufeng Chen","doi":"10.1002/ente.202401684","DOIUrl":null,"url":null,"abstract":"<p>Additive engineering in perovskite solar cells (PSCs) has been proven to enhance device performance, yet comparing the effects of different additives through experimental methods is still a challenge. Herein, machine learning (ML) is used to quantitatively analyze the impact of additive engineering on performance of PSCs, utilizing a dataset with 778 samples and 39 input features. Key features affecting device performance are identified, revealing that alkali metal additives boost short-circuit current, alkylamine additives improve open-circuit voltage, and passivation at A-site defects is more beneficial than at interstitial sites. Using the results gained from the ML approach, the performance of PSCs improves significantly, achieving an efficiency of 23.50%, with <i>V</i><sub>OC</sub> and <i>J</i><sub>SC</sub> values of 1.16 V and 25.35 mA cm<sup>−2</sup>, respectively, markedly higher than those of the control samples.</p>","PeriodicalId":11573,"journal":{"name":"Energy technology","volume":"13 4","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy technology","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/ente.202401684","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Additive engineering in perovskite solar cells (PSCs) has been proven to enhance device performance, yet comparing the effects of different additives through experimental methods is still a challenge. Herein, machine learning (ML) is used to quantitatively analyze the impact of additive engineering on performance of PSCs, utilizing a dataset with 778 samples and 39 input features. Key features affecting device performance are identified, revealing that alkali metal additives boost short-circuit current, alkylamine additives improve open-circuit voltage, and passivation at A-site defects is more beneficial than at interstitial sites. Using the results gained from the ML approach, the performance of PSCs improves significantly, achieving an efficiency of 23.50%, with VOC and JSC values of 1.16 V and 25.35 mA cm−2, respectively, markedly higher than those of the control samples.
期刊介绍：
Energy Technology provides a forum for researchers and engineers from all relevant disciplines concerned with the generation, conversion, storage, and distribution of energy.
This new journal shall publish articles covering all technical aspects of energy process engineering from different perspectives, e.g.,
new concepts of energy generation and conversion;
design, operation, control, and optimization of processes for energy generation (e.g., carbon capture) and conversion of energy carriers;
improvement of existing processes;
combination of single components to systems for energy generation;
design of systems for energy storage;
production processes of fuels, e.g., hydrogen, electricity, petroleum, biobased fuels;
concepts and design of devices for energy distribution.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
