Automated formulation and analysis of perovskite composition
Atinary Technologies aims to deploy its Self-driving Lab platform -SDLabs- to accelerate the formulation, analysis and stability testing of perovskite composition. Atinary will provide the software backbone to integrate various robotics, database, data analytics and proprietary ML algorithms into a closed-loop experimentation system. The overall experiment follows a three-step process -Design, Make and Test- orchestrated and driven by Atinarys SDLabs in the cloud. This allows remote control of the experiments, from anywhere on any devices.
Status: Ongoing
Date of proposal: 01/12/2021
Start date: 03/08/2022
End Date: 07/10/2022
Used Instruments: HI ERN AMANDA infrastructure. Atinary Self-driven Labs platform (SDLabs).
Experimental Technique: Automated formulation and analysis of perovskite composition. Use of machine learning (ML) algorithms for optimization. Photoluminescence measurements (PL, TRPL).
Experiment Description: The project focused on efficient automated perovskite formulation and composition optimization using Atinary SDLabs, which integrated robotics, database data analytics, and proprietary ML algorithms. The project followed a Design-Make-Test process loop to optimize perovskite solar cell (PSC) formulations.
Type Samples: Perovskite compositions developed through SDLabs.
Sample Description: Perovskite formulations created by varying combinations of cations, anions, ratios between ions, and film processing conditions.
Experiment Data Type: Data on semiconducting properties of perovskite films. Photoluminescence full width at half maximum (PL FWHM), time-resolved photoluminescence (TRPL) measurements, and luminescence deviation.
Characterization Technics: Automated analysis of perovskite compositions. Machine learning-driven optimization and analysis.
Characterization Data Type: Perovskite semiconducting properties based on various formulation parameters. Photoluminescence characteristics and deviations.
Analyzed Data: Optimization of perovskite formulations for improved PSC efficiencies. Analysis of perovskite compositions for optimal semiconducting properties.
Main Targets Project: Automated optimization of perovskite formulations for enhanced PSC performance. Use of machine learning to accelerate PSC development and increase efficiency.
Main Achievements Findings: Improved efficiencies in PSCs through automated optimization of formulation and composition. Reduction in costs and increased development speed of PSCs using automated processes combined with ML. Enhanced research capabilities and flexibility using Atinary SDLabs ML for optimization. Improved accuracy and repeatability in perovskite layer deposition and testing through automated processes.