Fraunhofer Institute for Wind Energy Systems
Fordatis - Forschungsdaten-Repositorium der Fraunhofer-GesellschaftNot a member yet
228 research outputs found
Sort by
Simulation Decision Matrix_Analytical Hierarchy Process_raw data_expert survey
No full textRaw data of the six decision-makers of the analytical hierarchy process (AHP) expert survey. The expert survey was conducted for prioritising sub-criteria of the Simulation Decision Matrix (SDM). The SDM is primarily used for prioritising quality-critical product parameters of hydrogen technologies for simulation applications in their production process.Co-funding from the European Union and the “Ministry of Food, Rural Areas, and Consumer Protection Baden-Württemberg” (German: Ministerium für Ernährung, Ländlichen Raum und Verbraucherschutz Baden-Württemberg
SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection
No full textVisual surface inspection images of aluminum test objects with different manufacturing surface textures and defects. The textures were produced by sandblasting, paralel milling and spiral milling. The dataset was used to support study of influence of surface texture on defect recognition. It contains real images, synthetic images and segmentation masks for both. Objects were inspected using a ring light and grayscale matrix camera monted on a robotic manipulator.Dataset is a collection of PNG images and text files easily readable by any software
VIADUCT: Multisector data set for Visual Industrial Anomaly Detection
Get PDFVIADUCT data set provides 49 categories of industrial objects with corresponding 135 defect categories.The data set consists exclusively of PNG files. Each category is divided into the sub-followers train, val, test and ground truth. Only defect-free images are in the train and val directory. In the test directory are the sub-folders for each defect category and the category "good" (defect-free). The annotations (also called ground truth or labels) for the images in the defect category directories are located in the ground truth directory mentioned above. The so-called anomaly maps are binary and mark with white on black pixels where the defect is in the image
Vorgehensmodell und Referenzrahmen für strategisches Handeln - ein Handlungsleitfaden für die kommunale Praxis
No full textAbbildungen zu und Arbeithilfen für die Entwicklung kommunaler Datenkompeten
Sequential PatchCore: Anomaly Detection for Surface Inspection using Synthetic Impurities
No full textVisual surface inspection images of aluminum plates with defects and impurities present. Dataset was used to support study of influence of impurities on defect detection. Plates were inspected using a ring light and grayscale camera monted on a robotic manipulator.Dataset is a collection of PNG image files easily readable by any software
HairWidthCracks dataset
Get PDFThis repository contains a dataset of images featuring concrete panels, designed to support research and development in image-based analysis and defect detection. The dataset is divided into two main categories: crack images with corresponding masks, and crack images without masks, which include both crack and no-crack images.The dataset consists of concrete images originally captured at approximately 16,000 × 32,000 pixels. These images depict large concrete panels, each with dimensions of 1200 × 2000 millimeters. To facilitate the identification and extraction of specific regions containing cracks, the software ToolIP [1], especially ToolImA was utilized. The tool enabled the scanning of these large images and the selection of 224 × 224 pixel regions where cracks are present.
In total, a curated subset of 1,500 images was extracted, 1,000 of them with cracks and 500 without. Each extracted image measures 224 × 224 pixels and is presented in an 8-bit grayscale format, with the .pgm extension used for storage.
As part of the second step in the data preparation process, ToolImA was again used to perform binary pixel-wise annotations (crack pixel or background) on the selected regions. The annotations include detailed crack information, with an average crack thickness of 1–2 pixels, providing a high level of granularity for analysis and training of machine learning models. The final dataset, therefore, consists of accurately annotated 224 × 224 pixel images, formatted in 8-bit grayscale with the corresponding masks, ready for use in deep learning and other computational applications.
[1] “ToolIP – Tool for Image Processing.” Fraunhofer-Institut für Techno- und Wirtschaftsmathematik ITWM, https://www.itwm.fraunhofer.de/toolip. Accessed 20 Dec. 2024
Ontologies for FAIR Data in Additive Manufacturing
No full textIt uses Basic Formal Ontology as a Top- and Common Core Ontologies as Mid-Level-Ontologies. Fraunhofer IGCV Manufacturing Application Ontology is used as direct import."^^xsd:string , "This ontology, created for use at Fraunhofer IGCV, includes essential classes specifically relevant to Project ODE_AM within the domain of Additive Manufacturing. It is designed with the capability for successive expansions to accommodate future developments and additional requirements in this field."^^xsd:string , "This ontology, designed for use in data management within the Fraunhofer IGCV's project-specific web-app, includes only those classes that are directly relevant to the project's needs. It primarily integrates existing classes from the Basic Formal Ontology (BFO) and the Common Core Ontologies (CCO), selectively chosen to fit the considered use cases in our project. This focused approach ensures efficient and relevant data categorization and retrieval tailored to our specific project requirements.TTL files (format used to express RDF data) which can be read in a web browser or text editor
Automatic Deduction of the Impact of Context Variability on System Safety Goals - Supplementary Material for EDCC 2024 Paper
No full textSupplementary material for the evaluation section of a publication at EDCC 2024. The data consists of four images: "1-taxonomy.png" shows a taxonomy of variability in the railway domain. "2-contextual-SCT.png" shows a contextual safety concept tree to argue the fulfillment of the safety goal "No train derailments". The sub-tree that is used in the earlier parts of the paper is marked in grey. "3-context-assumption-formulas.png" shows the refinements of the contextual assumptions used in the contextual safety concept tree, based on elements from the taxonomy of variability. "4-odd_definition.png" shows the mathematical definition of three Operational Design Domains for an Automated Train Operation System, again referencing the taxonomy of variability.This work has been funded by the European Union and the German Federal Ministry for Economic Affairs and Climate Action as part of the safe.trAIn project
A cross-domain physical testbed environment for cybersecurity performance evaluations
No full textPCAPs of the paper "CrossTest: A cross-domain physical testbed environment for cybersecurity performance evaluations"