AI-supported Degradation Study of Carbon-based Perovskite Solar Cells: Learning the Device Physics of Perovskite Solar Cells: A Drift-Diffusion Guided Autoencoder Approach

TL;DR

This paper employs machine learning to analyze degradation in carbon-based perovskite solar cells, enabling in situ tracking of device physics changes and creating a digital twin for better understanding and prediction of device aging.

Contribution

It introduces a drift-diffusion guided autoencoder approach that combines ML with device physics to monitor and simulate perovskite solar cell degradation in real-time.

Findings

ML accurately estimates charge transport and recombination parameters

Predicted parameters reveal degradation mechanisms during aging

Digital twin simulations match experimental device behavior

Abstract

Carbon-electrode-based PSC devices are stressed under 1 Sun equivalent illumination in a stability setup, and different scan-speed dependent current-voltage (J-V) curves are measured during aging. The collected data is used to estimate several physical parameters that contain information about charge transport and recombination using Machine Learning (ML), which allows for in situ tracking of possible signs of degradation. These results are compared to what can be classically interpreted by analysing changes in J-V curves, and the evolution of the predicted parameters is studied. The predictions are then used to simulate a digital twin of the measured devices, and their physical implications and the differences between measurements and devices are discussed.