Konvolutionales Neuronales Netzwerk

Maschinelles Lernen für Werkstoffe

Konvolutionales Neuronales Netzwerk

Konvolutionale Neuronale Netzwerke sind tiefenlernende Modelle, die durch Faltungs- und Pooling-Operationen lokale Muster in Daten erfassen. In der Werkstoffwissenschaft werden sie zur automatisierten Analyse von Mikrostrukturaufnahmen, Phasenerkennung, Defektklassifikation und Eigenschaftsvorhersage eingesetzt. Ihre hierarchische Merkmalsextraktion ermöglicht robuste, skalierbare Auswertung großer Bilddatensätze aus Mikroskopie oder Tomografie.

Verwandte Tags

Neue Inhalte

Automated AI-based grain boundary detection of a single-phase ceramic microstructure

Klein, J. (V)¹

MaterialsWeek 2021

Deep learning image segmentation enabling automated quantitative microstructure analysis for manufacturing environments

Pham, G.-K. (Speaker)¹; Lampenscherf, S.²

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

Deep Learning-based automated defect classification for Powder Bed Fusion

Kunkel, N. (Speaker)¹; Thölken, D.¹; Behler, K.¹

FEMS EUROMAT 2023

Semantic Segmentation of Steel Microstructures Using U-Net: Identifying Phases and Addressing Patch Border Artifacts

Menon, P.-M. (Speaker)¹; Krauledat, M.¹; Sicking, R.¹

MaterialsWeek 2025

Opportunities for peptide and protein-based materials in non-conventional solvents

Esteves, C.¹; Palma, S.¹; Roque, A. (Speaker)²

8th BioMAT 2025 - Symposium on Biomaterials and Related Areas

AI Based Lifetime Prediction of LEDs using Convolutional Neural Network

Akhtar, M.Z. (Speaker)¹

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

NeuraCell: a neural-network-based tool for the structural characterization of polymeric porous materials

Torre, J. (Speaker)¹; Barroso-Solares, S.²; Pinto, J.²; Rodríguez-Pérez, M.Á.²

8th International Conference on Cellular Materials - CellMAT 2024

Image Characterization and Analysis By Machine Learning Algorithms

Wissel, S. (Speaker)¹; Dextre, A.¹; Helbrecht, C.¹; Schabel, S.¹; Scheunert, J.²; Volz, K.²; Xu, B.-X.¹

Convolutional neural networks for grain boundary segmentation and completion for a wide range of materials

Jansche, A. (V)¹; Rathod, K.¹; Choudhary, A.K.²; Bernthaler, T.¹; Schneider, G.¹

58. Metallographie-Tagung 2024 - Materialographie

Digital Image Analysis of Different Graphite Forms in Spheroidal Graphite Iron

Steingräber, T. (Speaker)¹; Niewiadomski, J.¹; Pittel, C.¹

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

Beliebte Inhalte

Computer Vision and Machine Learning for a Wide Breadth of Microstructure Analyses

Kitahara, A. (V)¹; Holm, E.¹

55. Metallographie-Tagung 2021 - Materialographie

Automated AI-based grain boundary detection of a single-phase ceramic microstructure

Klein, J. (V)¹

MaterialsWeek 2021

Deep learning image segmentation enabling automated quantitative microstructure analysis for manufacturing environments

Pham, G.-K. (Speaker)¹; Lampenscherf, S.²

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

Methods from machine learning for the structural analysis of Li-ion electrode particles

Furat, O. (Speaker)¹; Finegan, D.²; Schmidt, V.¹; Smith, K.²

Uncovering process-structure relationships in inert gas atomization of high-alloy tool steels using a convolutional neural network embedded in a quantitative metallography and stereology workflow

Benito, S.M. (Speaker)¹; Weber, S.¹

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

Deep Learning Predicts Elasticity Tensors and their Bounds in Homogenization by Links to the Microstructure

Eidel, B. (Speaker)¹

Deep Learning-based automated defect classification for Powder Bed Fusion

Kunkel, N. (Speaker)¹; Thölken, D.¹; Behler, K.¹

FEMS EUROMAT 2023

Convolutional neural networks for grain boundary segmentation and completion for a wide range of materials

Jansche, A. (V)¹; Rathod, K.¹; Choudhary, A.K.²; Bernthaler, T.¹; Schneider, G.¹

58. Metallographie-Tagung 2024 - Materialographie

ConvNeXt adaptions in convolutional neural networks for defect detection in Li-ion batteries

Jansche, A. (Speaker)¹; Kopp, A.¹; Bernthaler, T.¹; Schneider, G.¹

FEMS EUROMAT 2023

Digital Image Analysis of Different Graphite Forms in Spheroidal Graphite Iron

Steingräber, T. (Speaker)¹; Niewiadomski, J.¹; Pittel, C.¹

Conference on Artificial Intelligence in Materials Science and Engineering - AI MSE 2023

Semantic Segmentation of Steel Microstructures Using U-Net: Identifying Phases and Addressing Patch Border Artifacts

Menon, P.-M. (Speaker)¹; Krauledat, M.¹; Sicking, R.¹

MaterialsWeek 2025

Neural Cellular Automata for Solidification Microstructure Modeling

Tang, J. (Speaker)¹; De Lorenzis, L.²; Hosseini, E.¹; Kumar, S.³

Oral-Poster-Präsentation

Korngrößenbestimmung an Werkstoffen mit kubischflächenzentriertem Gitter – traditionelle und modernste Methoden im Vergleich

Ketzer-Raichle, G. (V)¹; Reiter, E.¹; Jansche, A.¹; Schiele, T.¹; Choudhary, A.¹; Banholzer, A.¹; Bernthaler, T.¹; Schneider, G.¹

55. Metallographie-Tagung 2021 - Materialographie

Maschinelles Lernen statt energiedisperser Röntgenspektroskopie: Vorhersage der chemischen Zusammensetzung von Stahl-Einschlüssen nur über Bildinformationen

Britz, D. (V)¹; Müller, M. (V)²; Mücklich, F.²; Scholl, S.³; Staudt, T.³

55. Metallographie-Tagung 2021 - Materialographie

Image Characterization and Analysis By Machine Learning Algorithms

Wissel, S. (Speaker)¹; Dextre, A.¹; Helbrecht, C.¹; Schabel, S.¹; Scheunert, J.²; Volz, K.²; Xu, B.-X.¹

Opportunities for peptide and protein-based materials in non-conventional solvents

Esteves, C.¹; Palma, S.¹; Roque, A. (Speaker)²

8th BioMAT 2025 - Symposium on Biomaterials and Related Areas

NeuraCell: a neural-network-based tool for the structural characterization of polymeric porous materials

Torre, J. (Speaker)¹; Barroso-Solares, S.²; Pinto, J.²; Rodríguez-Pérez, M.Á.²

8th International Conference on Cellular Materials - CellMAT 2024

© 2026