Automated Porosity Characterization for Aluminum Die Casting Materials Using X-ray Radiography, Synthetic X-ray Data Augmentation by Simulation, and Machine Learning
Sensors · 05.05.2024 · 24 (9) · 2933
DOI: 10.3390/s24092933 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.05.2024. Verfasst von Stefan Bosse und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics & Computer Science, University of Bremen, 28359 Bremen, Germany. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German Research Foundation (Deutsche Forschungsgemeinschaft (DFG)).
Themen: Künstliche Intelligenz in der Pflege, Simulation in der Pflegeausbildung
Abstract (Originalsprache)
Detection and characterization of hidden defects, impurities, and damages in homogeneous materials like aluminum die casting materials, as well as composite materials like Fiber–Metal Laminates (FML), is still a challenge. This work discusses methods and challenges in data-driven modeling of automated damage and defect detectors using measured X-ray single- and multi-projection images. Three main issues are identified: Data and feature variance, data feature labeling (for supervised machine learning), and the missing ground truth. It will be shown that simulation of synthetic measuring data can deliver a ground truth dataset and accurate labeling for data-driven modeling, but it cannot be used directly to predict defects in manufacturing processes. Noise has a significant impact on the feature detection and will be discussed. Data-driven feature detectors are implemented with semantic pixel Convolutional Neural Networks. Experimental data are measured with different devices: A low-quality and low-cost (Low-Q) X-ray radiography, a typical industrial mid-quality X-ray radiography and Computed Tomography (CT) system, and a state-of-the-art high-quality μ-CT device. The goals of this work are the training of robust and generalized data-driven ML feature detectors with synthetic data only and the transition from CT to single-projection radiography imaging and analysis. Although, as the title implies, the primary task is pore characterization in aluminum high-pressure die-cast materials, but the methods and results are not limited to this use case.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics & Computer Science, University of Bremen, 28359 Bremen, Germany.
- Fraunhofer Institute for Manufacturing Technology and Advanced Materials, 28359 Bremen, Germany.
- Department of Mechanical Engineering, University of Bremen, 28359 Bremen, Germany.
ORCID-Profile: Stefan Bosse, Dirk Lehmhus
Förderung
- German Research Foundation (Deutsche Forschungsgemeinschaft (DFG))
Zitieren
APA
Bosse, S., Lehmhus, D., & Kumar, S. (2024). Automated Porosity Characterization for Aluminum Die Casting Materials Using X-ray Radiography, Synthetic X-ray Data Augmentation by Simulation, and Machine Learning. Sensors, 24(9), 2933. https://doi.org/10.3390/s24092933
Vancouver
Bosse S, Lehmhus D, Kumar S. Automated Porosity Characterization for Aluminum Die Casting Materials Using X-ray Radiography, Synthetic X-ray Data Augmentation by Simulation, and Machine Learning. Sensors. 2024;24(9):2933. doi:10.3390/s24092933
BibTeX
@article{Bosse2024,
author = {Bosse, Stefan and Lehmhus, Dirk and Kumar, Sanjeev},
title = {Automated Porosity Characterization for Aluminum Die Casting Materials Using X-ray Radiography, Synthetic X-ray Data Augmentation by Simulation, and Machine Learning},
journal = {Sensors},
year = {2024},
volume = {24},
number = {9},
pages = {2933},
doi = {10.3390/s24092933}
}
EUVIMED