SOLAR-SKIES: AI optimization of CIGS thin-film PV technology

Challenge: Increasing efficiency and reducing costs through data-driven approaches

Photovoltaic (PV) technologies are a key component of the energy transition, but face challenges in terms of efficiency, costs and environmental compatibility. Flexible CIGS thin-film solar cells offer enormous potential, but require continuous optimization of materials and processes. SOLAR-SKIES addresses these challenges through data-driven approaches and AI-supported modeling.

The SOLAR-SKIES project focuses on three main objectives:

• Increasing PV efficiency: AI-supported modeling and data analysis should significantly increase the conversion efficiency of flexible CIGS PV cells. The target is an efficiency of 18 % for 1 cm² solar cells and 14 % for 10×10 cm² modules.
• Reduction of manufacturing costs: By analyzing extensive process data and automated optimization using AI, the production costs of flexible CIGS PV cells are to be reduced to below €0.9/Wp.
• Sustainability and stability: Data-driven material analysis enables the selection of environmentally friendly, easily recyclable materials. The aim is to ensure performance stability, with less than 10 % performance loss after 1000 hours at 85 % relative humidity and 85 °C.

Technological solution: AI-supported analysis and high-throughput screening

SOLAR-SKIES combines high-throughput screening with AI-supported analysis to accelerate and optimize the development process of thin-film solar cells. Data from combinatorial thin-film depositions and automated measurement processes are collected and analyzed, with AI models identifying the optimal material combinations and process parameters.

Machine learning and Bayesian networks are used to determine correlations between process parameters, material properties and solar cell performance. These data-driven insights enable precise control of manufacturing processes and the prediction of new material combinations and process parameters. This accelerates development and helps to evaluate and scale up innovative materials more quickly.

Identified optimizations are scaled up from laboratory to pilot scale without costly modifications to the production line. This approach enables cost-efficient and sustainable scaling of production.

RISC Software GmbH: Expertise in the field of AI-based methods

As part of the project, RISC Software GmbH will use AI-based methods to contribute to determining the causal dependencies between the process parameters in production, the material properties and the efficiency of the solar cells produced.

The underlying measurement data for these analyses is collected through high-throughput screening. In this context, RISC Software GmbH also supports the collection and efficient management of data, which subsequently enables the upscaling of research results into industrial processes.

This project is funded by the FFG.