Anomalieerkennung

Algorithmen in der computergestützten Werkstoffforschung

Anomalieerkennung

Anomalieerkennung bezeichnet datengetriebene Methoden zur Identifikation ungewöhnlicher Muster in Prozess- oder Messdaten von Werkstoffen und Fertigung. Mittels statistischer Modelle, maschinellem Lernen und Deep Learning werden Defekte, Prozessabweichungen oder Degradationsphänomene frühzeitig erkannt. Dies ermöglicht zustandsorientierte Instandhaltung, Prozessoptimierung und Qualitätsüberwachung.

Verwandte Tags

Künstliche Intelligenz

Synthetische Datengenerierung

Maschinenlernen

Variational AutoEncoder

Konvolutionale Neuronale Netze

Objekterkennung

Bildrekonstruktion

Datenanreicherung

In situ 2D und 3D Charakterisierung

semantische Segmentierung

Finite-Element-Simulationen

Digitalisierung & Künstliche Intelligenz

Workflow-Integration

Merkmalserfassung

Quantitative Gefügeanalyse

Instanzen-Segmentierung

Lithium-Ionen-Batterien

Prozessüberwachung

Prozessbegleitende Prüfverfahren

Konvolutionales Neuronales Netzwerk

maschinelles Lernen

Mikroskopiebilder

Bildsegmentierung

Materialcharakterisierung & -prüfung

Aufbau- und Verbindungstechnik

Materialinformatik

Defekterkennung

Optische Mikroskopie

Materialwissenschaftsdatenraum

Röntgentomographie

digitale Zwillinge

Datenmanagement

Neue Inhalte

HyMat Lab - Explore Hybrid Materials Processing

Bjarsch, T. (Speaker)¹; Abel, H.²; Bosch, J.³; Drechsler, M.⁴; Hofmann, P.⁵; Meyer, N.⁶

MaterialDigital General Assembly 2025

Unsupervised deep learning approach for structural anomaly detection in 3D CT data of Li-ion battery cylindrical cell

Rathod, K. (Speaker)¹; Malchus, C.¹; Jansche, A.¹; Kopp, A.¹; Bernthaler, T.¹; Schneider, G.¹

Einsatz von VQ-VAE und GPT zur Generierung synthetischer Schliffbilder von Lamellengraphit

Goedecke, M. (V)¹; Pfaff, M.¹

59. Metallographie-Tagung 2025 - Materialographie

Poster-Pitch-Presentation

Efficient Cyberattack Detection in Logs of Cyber-Physical Production Systems

Otto, J. (V)¹; Specht, F. (V)¹

International Conference on System-Integrated Intelligence - SysInt 2025

Real-Time Phase Segmentation for CNC Drilling: A Lightweight Unsupervised Machine Learning Approach for Condition Monitoring and Anomaly Detection

Denkena, B.¹; Buhl, H.¹; Tkachuk, K. (V)¹

International Conference on System-Integrated Intelligence - SysInt 2025

Automated X-ray-based damage detection and characterisation in composite materials by data-driven anomaly predictor models trained by a fusion of real and simulated X-ray data

Bosse, S. (Speaker)¹; Lehmhus, D.²

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

Invited Lecture

Data-mining and Machine Learning for Materials Engineering in Steel Industry

Srivastava, K. (Speaker)¹

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

Overview of deep learning methods for image-based defect detection in Li-ion batteries using destructive and non-destructive microscopy methods

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

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

Deep Learning Anomaly Detection in Directed Energy Deposition using Hyperspectral In-Situ Monitoring Data

Snyers, C. (Speaker)¹; Ertveldt, J.¹; Helsen, J.¹

FEMS EUROMAT 2023

Unsupervised anomaly detection approach for non-destructive quality control in cylindric Li-ion battery cells

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

FEMS EUROMAT 2023

Beliebte Inhalte

Einsatz von VQ-VAE und GPT zur Generierung synthetischer Schliffbilder von Lamellengraphit

Goedecke, M. (V)¹; Pfaff, M.¹

59. Metallographie-Tagung 2025 - Materialographie

HyMat Lab - Explore Hybrid Materials Processing

Bjarsch, T. (Speaker)¹; Abel, H.²; Bosch, J.³; Drechsler, M.⁴; Hofmann, P.⁵; Meyer, N.⁶

MaterialDigital General Assembly 2025

Real-Time Phase Segmentation for CNC Drilling: A Lightweight Unsupervised Machine Learning Approach for Condition Monitoring and Anomaly Detection

Denkena, B.¹; Buhl, H.¹; Tkachuk, K. (V)¹

International Conference on System-Integrated Intelligence - SysInt 2025

Unsupervised deep learning approach for structural anomaly detection in 3D CT data of Li-ion battery cylindrical cell

Rathod, K. (Speaker)¹; Malchus, C.¹; Jansche, A.¹; Kopp, A.¹; Bernthaler, T.¹; Schneider, G.¹

Poster-Pitch-Presentation

Efficient Cyberattack Detection in Logs of Cyber-Physical Production Systems

Otto, J. (V)¹; Specht, F. (V)¹

International Conference on System-Integrated Intelligence - SysInt 2025

Deep learning for defect detection in energy materials

Jansche, A. (Speaker)¹; Badmos, O.¹; Bernthaler, T.¹; Goll, D.¹; Hohs, D.¹; Kopp, A.¹; Schiele, T.¹; Schneider, G.¹; Trier, F.¹

Invited Lecture

Data-mining and Machine Learning for Materials Engineering in Steel Industry

Srivastava, K. (Speaker)¹

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

Non-destructive damage detection of hidden damages in Fibre Metal Laminates composites using X-ray imaging and machine learning algorithms

Shah, C. (Speaker)¹; Bosse, S.²; von Hehl, A.¹

Unsupervised anomaly detection approach for non-destructive quality control in cylindric Li-ion battery cells

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

FEMS EUROMAT 2023

Overview of deep learning methods for image-based defect detection in Li-ion batteries using destructive and non-destructive microscopy methods

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

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

Deep Learning Anomaly Detection in Directed Energy Deposition using Hyperspectral In-Situ Monitoring Data

Snyers, C. (Speaker)¹; Ertveldt, J.¹; Helsen, J.¹

FEMS EUROMAT 2023

Automated X-ray-based damage detection and characterisation in composite materials by data-driven anomaly predictor models trained by a fusion of real and simulated X-ray data

Bosse, S. (Speaker)¹; Lehmhus, D.²

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

© 2026