Artificial Intelligence and Data Management

Our work in the "AI and Data management" Research Topic is divided into the fields of data science and data engineering. In the field of data science, we develop artificial intelligence models for the quality inspection of workpieces and production processes along the PV value chain. We integrate our expertise in AI and solar cell physics in equal measure to develop fast, robust and interpretable AI models based on our extensive measurement technology portfolio.

We develop the latest AI methods for our partners in measurement technology and software development as well as solar cell production, such as (a) computer vision models for classifying and segmenting defects and objects in 2D and 3D, (b) methods of theory-based data analysis and semantic data compression for analyzing and efficiently storing high-dimensional data in the form of a digital twin and (c) generative models for developing accelerated and high-resolution measurement processes, e.g. for high-throughput production. 

In the field of data engineering, we develop metadata models, interfaces and software systems for monitoring complex production processes, for the automated acquisition and structuring of data and their provision in modern database networks and test the concepts and systems in the laboratory at Fraunhofer ISE. Current technologies and concepts of software development are used, such as micro-service architectures, container concepts, virtualization platforms and DevOps strategies.

The data science and data engineering competencies originate from PV cell production, but are technology-independent and can therefore be used in a variety of application fields.

Fields of Work

In the research topic "Artfifcial Intelligence and Data Management" we focus on the following fields of work:

Deep Learning Processes for Rapid Quality Control from Wafer to Solar Cell

Generative AI Models and Transfer Learning for Data and Measurement Technology Optimization

Physics-Informed AI Models for Interpretable Data Analysis

Video Analysis for Digitalizing Inventory

Process Control and Predictive Maintenance Methods

Data Management in Database Networks with Metadata Models

Modular Digitalization Concepts for Multi-Variant Production

R&D-Infrastructure

For our research and development activities ...

... the following range of methods is used and continuously developed at Fraunhofer ISE:

  • Toolbox with AI models for unsupervised and supervised learning methods
  • Tools for rapid deployment of the developed AI methods
  • Powerful NoSQL database technologies: graph databases for storing metadata and document databases for storing production data
  • Tools for innovative management of context data in the form of dynamically adaptable, »growing« metadata models
  • Software architectures based on micro-services to ensure (a) easy functional extensibility, (b) high scalability and (c) clear separation of responsibilities between the individual software modules
  • Consistent application of the Docker container concept in programming in order to be able to operate the individual services in a virtualization environment
  • Comprehensive quality assurance of the code through (a) a defined and automated Development & Operations (DevOps) strategy using Gitlab, (b) extensive unit tests to validate the functional requirements, (c) the Git Flow release management strategy for structured versioning, (d) automated deployment using the Kubernetes package manager »Helm«

... this infrastructure is available to us at Fraunhofer ISE:

  • Extensive GPU server infrastructure for training the AI models
  • Inline and reference measurement technology for efficient data collection and model training
  • Kubernetes server cluster as a high-performance virtualization platform for (a) fully automated, hardware-independent rollout of software components, (b) efficient support during operation and (c) protection of the production software against hardware failures

Contact

Stefan Rein

Contact Press / Media

Dr. Stefan Rein

Artificial Intelligence and Data Management

Fraunhofer ISE
Heidenhofstr. 2
79110 Freiburg

Phone +49 761 4588-5271

Matthias Demant

Contact Press / Media

Dr.-Ing. Matthias Demant

Computer Vision

Fraunhofer ISE
Heidenhofstr. 2
79110 Freiburg

Phone +49 761 4588-5651

Current Publications on the Topic “Artificial Intelligence and Data Management"

Jahr
Year
Titel/Autor:in
Title/Author
Publikationstyp
Publication Type
2025 Shingle cell IV characterization based on spatially resolved host cell measurements
Kunze, Philipp; Demant, Matthias; Krieg, Alexander; Tummalieh, Ammar; Wöhrle, Nico; Rein, Stefan
Zeitschriftenaufsatz
Journal Article
2025 Physics-Informed Machine Learning for TCO-Layer Thickness Prediction and Process Analysis from Multi-Spectral Images
Wörnhör, Alexandra; Senthil Kumar, Saravana Kumar; Burkhardt, Daniel; Schönauer, Jonas Johannes Felix; Pingel, Sebastian; Voicu Vulcanean, Ioan; Steinmetz, Anamaria; Rein, Stefan; Demant, Matthias
Zeitschriftenaufsatz
Journal Article
2024 Digitale Bestandsaufnahme für die Wärmewende mit Deep Learning
Hain, Antonia; Gölzhäuser, Simon; Meyer, Robert; Ihlenburg, Moritz; Herkel, Sebastian; Réhault, Nicolas; Demant, Matthias
Konferenzbeitrag
Conference Paper
2024 Deep-Learning Based Depth-Tracking of Stacking-Faults in Epitaxially Grown Silicon Wafers
Trötschler, Theresa; Al-Hajjawi, Saed; Raghavendran, Siddharth; Haunschild, Jonas; Demant, Matthias; Haunschild, Jonas; Wörnhör, Alexandra; Rein, Stefan; Demant, Matthias; Rein, Stefan
Konferenzbeitrag
Conference Paper
2024 Integrated Inline Characterisation Techniques for Improved Silicon Heterojunction Solar Cell Production
Diestel, Christian; Senthil Kumar, Saravana Kumar; Wörnhör, Alexandra; Burkhardt, Daniel; Wöhrle, Nico; Pingel, Sebastian; Demant, Matthias; Haunschild, Jonas; Rein, Stefan
Konferenzbeitrag
Conference Paper
2023 Every Cell Needs a Beautiful Image: On-The-Fly Contacting Measurements for High-Throughput Production
Kurumundayil, Leslie Lydia; Ramspeck, Klaus; Rein, Stefan; Demant, Matthias
Zeitschriftenaufsatz
Journal Article
2023 A Self-Consistent Hybrid Model Connects Empirical and Optical Models for Fast, Non-Destructive Inline Characterization of Thin, Porous Silicon Layers
Wörnhör, Alexandra; Vahlman, Henri; Demant, Matthias; Rein, Stefan
Zeitschriftenaufsatz
Journal Article
2023 Next Generation High Throughput Production Processes & Inline Characterization for Si Solar Cells
Clement, Florian; Meßmer, Marius; Höffler, Hannes; Ourinson, Daniel; Goraya, Baljeet Singh; Emanuel, Gernot; Meyer, Fabian; Lorenz, Andreas; Bartsch, Jonas; Demant, Matthias; Nold, Sebastian; Wolf, Andreas; Zimmer, Martin; Greulich, Johannes; Preu, Ralf; Köpge, Ringo; Ramspeck, Klaus; Hemsendorf, Marc; Straub, Benedikt; Ebert , Christian; Drews, Matthias; Jooss, Wolfgang; Schmid, Elina; Schönfelder, Stephan
Vortrag
Presentation
2023 Contactless Inline IV Measurement of Solar Cells Using an Empirical Model
Kunze, Philipp; Greulich, Johannes; Tummalieh, Ammar; Wirtz, Wiebke; Höffler, Hannes; Wöhrle, Nico; Glunz, Stefan; Rein, Stefan; Demant, Matthias
Zeitschriftenaufsatz
Journal Article
2022 Learning an Empirical Digital Twin from Measurement Images for a Comprehensive Quality Inspection of Solar Cells
Kunze, Philipp; Rein, Stefan; Hemsendorf, M.; Ramspeck, K.; Demant, Matthias
Zeitschriftenaufsatz
Journal Article
2021 The Empirical Digital Twin: Representation Learning on Solar Cell Images and Efficient Defect Detection with Human-in-the-Loop
Kunze, Philipp; Rein, Stefan; Mueller, Thomas; Hemsendorf, M.; Ramspeck, K.; Demant, Matthias
Konferenzbeitrag
Conference Paper
2021 The advent of modern solar-powered electric agricultural machinery: A solution for sustainable farm operations
Gorjian, S.; Ebadi, H.; Trommsdorff, Maximilian; Sharon, H.; Demant, Matthias; Schindele, Stephan
Zeitschriftenaufsatz
Journal Article
2020 Verfahren zur Verarbeitung von Abbildungen von Halbleiterstrukturen, sowie zur Prozesscharakterisierung und Prozessoptimierung mittels semantischer Datenkompression
Demant, Matthias; Rein, Stefan; Kovvali, Aditya Sai; Greulich, Johannes; Wöhrle, Nico
Patent
2020 Machine Learning for Advanced Solar Cell Production. Adversarial Denoising, Sub-pixel Alignment and the Digital Twin
Demant, Matthias; Kurumundayil, Leslie Lydia; Kunze, Philipp; Woernhoer, A.; Kovvali, Aditya Sai; Rein, Stefan
Vortrag
Presentation
2020 High-Precision Alignment Procedures for Patterning Processes in Solar Cell Production
Lohmüller, Elmar; Weber, Julian; Demant, Matthias; Lohmüller, Sabrina; Gutscher, Simon; Saint-Cast, Pierre; Wolf, Andreas
Zeitschriftenaufsatz
Journal Article
2020 Early Stage Quality Assesment in Silicon Ingots from MDP Brick Characterization
Kovvali, Aditya Sai; Demant, Matthias; Rebba, B.; Schüler, N.; Haunschild, Jonas; Rein, Stefan
Konferenzbeitrag
Conference Paper
2020 The Crystal Growth Explorer: Real-Time Navigable 3D Visualization of Silicon Grains and Defect Related Data in Cast-Mono and Multicrystalline Bricks
Schönauer, J.; Demant, Matthias; Trötschler, Theresa; Kovvali, Aditya Sai; Schremmer, H.; Krenckel, Patricia; Riepe, Stephan; Rein, Stefan
Konferenzbeitrag
Conference Paper
2020 Efficient Deployment of Deep Neural Networks for Quality Inspection of Solar Cells using Smart Labeling
Kunze, Philipp; Greulich, Johannes M.; Rein, Stefan; Ramspeck, K.; Hemsendorf, M.; Vetter, Andreas; Demant, Matthias
Konferenzbeitrag
Conference Paper
2019 Learning Quality Rating of As-Cut mc-Si Wafers via Convolutional Regression Networks
Demant, Matthias; Virtue, P.; Kovvali, Aditya Sai; Yu, S.X.; Rein, Stefan
Zeitschriftenaufsatz
Journal Article
2019 Visualizing Material Quality and Similarity of mc-Si Wafers Learned by Convolutional Regression Networks
Demant, Matthias; Virtue, P.; Kovvali, Aditya Sai; Yu, S.X.; Rein, Stefan
Zeitschriftenaufsatz
Journal Article
Diese Liste ist ein Auszug aus der Publikationsplattform Fraunhofer-Publica

This list has been generated from the publication platform Fraunhofer-Publica