Filtern
Dokumenttyp
Sprache
- Englisch (21)
Referierte Publikation
- ja (21) (entfernen)
Schlagworte
- Additive manufacturing (8)
- Selective laser melting (SLM) (6)
- AISI 316L (4)
- Additive Manufacturing (4)
- Heat accumulation (4)
- Infrared thermography (4)
- Laser powder bed fusion (4)
- Laser powder bed fusion (L-PBF) (4)
- Thermography (4)
- Additive manufacturing (AM) (3)
- In situ monitoring (3)
- Laser Powder Bed Fusion (3)
- Laser beam melting (LBM) (3)
- Process monitoring (3)
- AGIL (2)
- Computed Tomography (2)
- Representative specimens (2)
- Residual Stress (2)
- Selective Laser Melting (SLM) (2)
- Thermal history (2)
- 316L (1)
- 3D printing (1)
- Adaptive remeshing (1)
- Additive Manufacturing (AM) (1)
- Cellular substructure (1)
- Computed tomography (1)
- Computed tomography (CT) (1)
- Convolutional neural networks (CNN) (1)
- Creep (1)
- Creep behavior (1)
- Crystal plasticity (1)
- Data fusion (1)
- Defect detection (1)
- Diffraction (1)
- Dwell-time (1)
- Elastic modulus (1)
- Electron backscatter diffraction (1)
- Emisssivity (1)
- Fatigue damage (1)
- Finite element method (1)
- Flaw detection (1)
- Heat treatment (1)
- IN 718 (1)
- Image registration (1)
- In-situ monitoring (1)
- In-situ process monitoring (1)
- Inconel 718 (1)
- Inter layer time (1)
- Inter-layer time (1)
- LPBF (1)
- Lack-of-fusion (1)
- Laser Powder Bed Fusion (L-PBF) (1)
- Laser Powder Bed Fusion (LPBF) (1)
- Laser Powder Bed Fusion (PBF-LB/M, L-PBF) (1)
- Laser beam melting (1)
- Low-cycle fatigue (1)
- Machine learning (1)
- Mechanical anisotropy (1)
- Melt pool defects (1)
- Microstructure (1)
- Neutron Diffraction (1)
- Online Process Monitoring (1)
- Online monitoring (1)
- Optical Tomography (1)
- Optical tomography (1)
- PBF-LB/M/316L (1)
- Parabolic flight (1)
- Pool dimensions (1)
- Process simulation (1)
- Reference data (1)
- Residual stress (1)
- SS316L alloy (1)
- SWIR camera (1)
- SWIR thermography (1)
- Shear modulus (1)
- Stainless Steel (1)
- Temperature dependence (1)
- Tensile strength (1)
- Tensile testing (1)
- Ti-6Al-4V (1)
- X-ray Diffraction (1)
- X-ray and Neutron Diffraction (1)
- X-ray computed tomography (XCT) (1)
- Young's modulus (1)
- infrared Thermography (1)
- µ-gravity (1)
Organisationseinheit der BAM
- 9 Komponentensicherheit (21) (entfernen)
The prediction of porosity is a crucial task for metal based additive manufacturing techniques such as laser powder bed fusion. Short wave infrared thermography as an in-situ monitoring tool enables the measurement of the surface radiosity during the laser exposure. Based on the thermogram data, the thermal history of the component can be reconstructed which is closely related to the resulting mechanical properties and to the formation of porosity in the part. In this study, we present a novel framework for the local prediction of porosity based on extracted features from thermogram data. The framework consists of a data pre-processing workflow and a supervised deep learning classifier architecture. The data pre-processing
workflow generates samples from thermogram feature data by including feature information from multiple subsequent layers.
Thereby, the prediction of the occurrence of complex process phenomena such as keyhole pores is enabled. A custom convolutional neural network model is used for classification. Themodel is trained and tested on a dataset from thermographic in-situ monitoring of the manufacturing of an AISI 316L stainless steel test component. The impact of the pre-processing parameters and the local void distribution on the classification performance is studied in detail. The presented model achieves an accuracy of 0.96 and an f1-Score of 0.86 for predicting keyhole porosity in small sub-volumes with a dimension of (700 × 700 × 50) μm3. Furthermore, we show that pre-processing parameters such as the porosity threshold for sample
labeling and the number of included subsequent layers are influential for the model performance. Moreover, the model prediction is shown to be sensitive to local porosity changes although it is trained on binary labeled data that disregards the actual sample porosity.