Unraveling pore evolution in post-processing of binder jetting materials: X-ray computed tomography, computer vision, and machine learning

Zhu, Yunhui; Wu, Ziling; Hartley, W. Douglas; Sietins, Jennifer M.; Williams, Christopher B.; Yu, Hang

doi:10.1016/j.addma.2020.101183

Cited by 43 publications

(36 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 11d compares the pore orientation distribution in the sintered body, the sintered feedstock, and the sintered body at high resolution. Each pore orientation is defined as the direction along the ellipsoid's longest axis [41]. The 3D orientation is represented by the angle of altitude (the angle of the orientation vector relative to the vertical axis or direction of the printing).…”

Section: Sinteringmentioning

confidence: 99%

Copper additive manufacturing using MIM feedstock: adjustment of printing, debinding, and sintering parameters for processing dense and defectless parts

Singh

Missiaen

Bouvard

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

In the present study, an additive manufacturing process of copper using extrusion 3D printing, solvent and thermal debinding, and sintering was explored. Extrusion 3D printing of metal injection moulding (MIM) feedstock was used to fabricate green body samples. The printing process was performed with optimized parameters to achieve high green density and low surface roughness. To remove water-soluble polymer, the green body was immersed in water for solvent debinding. The interconnected voids formed during solvent debinding were favorable for removing the backbone polymer from the brown body during thermal debinding. Thermal debinding was performed up to 500 °C, and ~ 6.5% total weight loss of the green sample was estimated. Finally, sintering of the thermally debinded samples was performed at 950, 1000, 1030, and 1050°C. The highest sintering temperature provided the highest relative density (94.5%) and isotropic shrinkage. Micro-computed tomography (μCT) examination was performed on green samples and sintered samples, and qualitative and quantitative analysis of the porosity confirmed the benefits of optimized printing conditions for the final microstructure. This work opens up the opportunity for 3D printing and sintering to produce pure copper components with complicated shapes and high density, utilizing raw MIM feedstock as the starting material.

show abstract

Section: Sinteringmentioning

confidence: 99%

Copper additive manufacturing using MIM feedstock: adjustment of printing, debinding, and sintering parameters for processing dense and defectless parts

Singh

Missiaen

Bouvard

et al. 2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…Enikeev et al suggest a step by step algorithm for processing chemical corrosion data that combines image processing, image binarization, and identification of object contours and analysis of object characterization. Their algorithm is based on fractal analysis for corrosion of cracking specimens, giving thus, a more complete analysis and representation of the failure the metallic surface is subjected to [16][17].…”

Section: Computer Vision Techniques Used In Metal Failure Detectionmentioning

confidence: 99%

A Review of Computer Vision Techniques in the Detection of Metal Failures

Fitzgerald

Fragoudakis

2021

MATEC Web Conf.

View full text Add to dashboard Cite

This paper considers and contrasts several computer vision techniques used to detect defects in metallic components during manufacturing or in service. Methodologies include statistical analysis, weighted entropy modification, Fourier transformations, neural networks, and deep learning. Such systems are used by manufacturers to perform non-destructive testing and inspection of components at high speeds [1]; providing better error detection than traditional human visual inspection, and lower costs [2]. This is a review of the computer vision system comparing different mathematical analysis in order to illustrate the strengths and weaknesses relative to the nature of the defect. It includes exemplar that histograms and statistical analysis operate best with significant contrast between the defect and background, that co-occurrence matrix and Gabor filtering are computationally expensive, that structural analysis is useful when there are repeated patterns, that Fourier transforms, applied to spatial data, need windowing to capture localized issues, and that neural networks can be utilized after training.

show abstract

“…More recently, Ibragimova et al [24] employed an ensemble of ANNs to predict the non-monotonic behavior and texture evolution of face-centered cubic (FCC) polycrystalline materials. Machine learning approaches such as feed forward neural network (FFNN), convolutional neural network (CNN), deep belief network (DBN), k-means clustering, support vector machine (SVM), and random forest (RF) have been applied in additive manufacturing to design new materials [25][26][27], to optimize topology [28,29], to predict porosity [30][31][32], to monitor printing process for quality assurance [33][34][35], to predict thermal history during printing [36,37], to construct process maps [38,39], to predict melt pool dimensions [40], to classify melting states [41], and to detect process-induced defects [42][43][44]. Recently, Muhammad et al [45] proposed a machine learning framework to model the evolution of local strains, plastic anisotropy, and fracture in AlSi10Mg alloy produced by SLM.…”

Section: Introductionmentioning

confidence: 99%

Experimental investigation and development of a deep learning framework to predict process-induced surface roughness in additively manufactured aluminum alloys

Muhammad

Kang²,

Ibragimova

et al. 2022

Weld World

View full text Add to dashboard Cite

A deep learning framework is developed to predict the process-induced surface roughness of AlSi10Mg aluminum alloy fabricated using laser powder bed fusion (LPBF). The framework involves the fabrication of round bar AlSi10Mg specimens, surface topography measurement using 3D laser scanning profilometry, extraction, coupling, and streamlining of roughness and LPBF processing data, feature engineering to select the relevant feature set and the development, validation, and evaluation of a deep neural network model. A mix of core and contour-border scanning strategies are employed to fabricate four sets of specimens with different surface roughness conditions. The effects of different scanning strategies, linear energy density (LED), and specimen location on the build plate on the resulting surface roughness are discussed. The inputs to the deep neural network model are the AM process parameters (i.e., laser power, scanning speed, layer thickness, specimen location on the build plate, and the x,y grid location for surface topography measurements), and the output is the surface profile height measurements. The proposed deep learning framework successfully predicts the surface topography and related surface roughness parameters for all printed specimens. The predicted surface roughness ($${S}_{a}$$ S a ) measurements are well within 5% of experimental error for the majority of the cases. Moreover, the intensity and location of the surface peaks and valleys as well as their shapes are well predicted, as demonstrated by comparing roughness line scan results with corresponding experimental data. The successful implementation of the current framework encourages further applications of such machine learning-based methods toward AM material development and process optimization.

show abstract

Unraveling pore evolution in post-processing of binder jetting materials: X-ray computed tomography, computer vision, and machine learning

Cited by 43 publications

References 51 publications

Copper additive manufacturing using MIM feedstock: adjustment of printing, debinding, and sintering parameters for processing dense and defectless parts

Copper additive manufacturing using MIM feedstock: adjustment of printing, debinding, and sintering parameters for processing dense and defectless parts

A Review of Computer Vision Techniques in the Detection of Metal Failures

Experimental investigation and development of a deep learning framework to predict process-induced surface roughness in additively manufactured aluminum alloys

Contact Info

Product

Resources

About