Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Simultaneous Optimization of Efficiency and Degradation in Tunable HTL-Free Perovskite Solar Cells with MWCNT-Integrated Back Contact Using a Machine Learning-Derived Polynomial Regressor

Ihtesham Ibn Malek, Hafiz Imtiaz, Samia Subrina

TL;DR

The paper tackles the challenge of simultaneously boosting efficiency and stability in HTL-free perovskite solar cells. It couples SCAPS-1D simulations with a fourth-degree polynomial regressor (PR-4) to model $\eta$ and degradation $\Delta$ as functions of four fabrication parameters, then uses an L-BFGS-B optimizer with a weighted objective to maximize $\eta$ while minimizing $\Delta$. Experimental validation confirms accurate simulation predictions, and a 1650-sample dataset enables high-performance ML regressors and a 100% accurate MLP-based stability classifier. The work delivers a data-driven, interpretable design framework for CNT-backed HTL-free PSCs, achieving a notable efficiency increase to $16.84\%$ and degradation reduction to $2.39\%$ after 1000 h, with strong implications for scalable, cost-effective solar devices.

Abstract

Perovskite solar cells (PSCs) without a hole transport layer (HTL) offer a cost-effective and stable alternative to conventional architectures, utilizing only an absorber layer and an electron transport layer (ETL). This study presents a machine learning (ML)-driven framework to optimize the efficiency and stability of HTL-free PSCs by integrating experimental validation with numerical simulations. Excellent agreement is achieved between a fabricated device and its simulated counterpart at a molar fraction \( x = 68.7\% \) in \(\mathrm{MAPb}_{1-x}\mathrm{Sb}_{2x/3}\mathrm{I}_3\), where MA is methylammonium. A dataset of 1650 samples is generated by varying molar fraction, absorber defect density, thickness, and ETL doping, with corresponding efficiency and 50-hour degradation as targets. A fourth-degree polynomial regressor (PR-4) shows the best performance, achieving RMSEs of 0.0179 and 0.0117, and \( R^2 \) scores of 1 and 0.999 for efficiency and degradation, respectively. The derived model generalizes beyond the training range and is used in an L-BFGS-B optimization algorithm with a weighted objective function to maximize efficiency and minimize degradation. This improves device efficiency from 13.7\% to 16.84\% and reduces degradation from 6.61\% to 2.39\% over 1000 hours. Finally, the dataset is labeled into superior and inferior classes, and a multilayer perceptron (MLP) classifier achieves 100\% accuracy, successfully identifying optimal configurations.

Simultaneous Optimization of Efficiency and Degradation in Tunable HTL-Free Perovskite Solar Cells with MWCNT-Integrated Back Contact Using a Machine Learning-Derived Polynomial Regressor

TL;DR

The paper tackles the challenge of simultaneously boosting efficiency and stability in HTL-free perovskite solar cells. It couples SCAPS-1D simulations with a fourth-degree polynomial regressor (PR-4) to model and degradation as functions of four fabrication parameters, then uses an L-BFGS-B optimizer with a weighted objective to maximize while minimizing . Experimental validation confirms accurate simulation predictions, and a 1650-sample dataset enables high-performance ML regressors and a 100% accurate MLP-based stability classifier. The work delivers a data-driven, interpretable design framework for CNT-backed HTL-free PSCs, achieving a notable efficiency increase to and degradation reduction to after 1000 h, with strong implications for scalable, cost-effective solar devices.

Abstract

Perovskite solar cells (PSCs) without a hole transport layer (HTL) offer a cost-effective and stable alternative to conventional architectures, utilizing only an absorber layer and an electron transport layer (ETL). This study presents a machine learning (ML)-driven framework to optimize the efficiency and stability of HTL-free PSCs by integrating experimental validation with numerical simulations. Excellent agreement is achieved between a fabricated device and its simulated counterpart at a molar fraction in , where MA is methylammonium. A dataset of 1650 samples is generated by varying molar fraction, absorber defect density, thickness, and ETL doping, with corresponding efficiency and 50-hour degradation as targets. A fourth-degree polynomial regressor (PR-4) shows the best performance, achieving RMSEs of 0.0179 and 0.0117, and scores of 1 and 0.999 for efficiency and degradation, respectively. The derived model generalizes beyond the training range and is used in an L-BFGS-B optimization algorithm with a weighted objective function to maximize efficiency and minimize degradation. This improves device efficiency from 13.7\% to 16.84\% and reduces degradation from 6.61\% to 2.39\% over 1000 hours. Finally, the dataset is labeled into superior and inferior classes, and a multilayer perceptron (MLP) classifier achieves 100\% accuracy, successfully identifying optimal configurations.

Paper Structure

This paper contains 22 sections, 20 equations, 20 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Simulation Model in SCAPS
  4. Characteristic Curves and Performance Parameters
  5. Polynomial Regression in ML
  6. L-BFGS-B Optimization Method
  7. Results and Discussions
  8. Experimental Validation of Simulation
  9. Dataset
  10. Variation in Characteristic Curves
  11. Variation in Degradation Curves
  12. Data Clustering, Labelling and Sampling
  13. Exploratory Data Evaluation
  14. ML Regressor Performance
  15. ML Predicted Characteristic Curves
  16. ...and 7 more sections

Figures (20)

  • Figure 1: Perovskite solar cell structure used in this study.
  • Figure 2: Energy band structure of different layers.
  • Figure 3: J-V and P-V characteristic curves
  • Figure 4: Polynomial regression fits with varying degrees.
  • Figure 5: The process of L-BFGS-B optimization
  • ...and 15 more figures