Next Article in Journal
High-Temperature Oxidation Behaviour of AISI H11 Tool Steel
Next Article in Special Issue
Influence of Additive Manufactured Stainless Steel Tool Electrode on Machinability of Beta Titanium Alloy
Previous Article in Journal
Study of the Residual Bond Strength between Corroded Steel Bars and Concrete—A Comparison with the Recommendations of Fib Model Code 2010
Previous Article in Special Issue
Ti Interlayer Mediated Uniform NiGe Formation under Low-Temperature Microwave Annealing
Open AccessArticle

Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys

1
Department of Engineering Mechanics, Faculty of Engineering, University of Rijeka, 51000 Rijeka, Croatia
2
Research and Development Department, CIMOS d.d. Automotive Industry, 6000 Koper, Slovenia
3
CAE Department, Elaphe Propulsion Technologies Ltd., 1000 Ljubljana, Slovenia
4
Department of Computer Engineering, Faculty of Engineering, University of Rijeka, 51000 Rijeka, Croatia
*
Authors to whom correspondence should be addressed.
Academic Editor: Claudio Testani
Metals 2021, 11(5), 756; https://doi.org/10.3390/met11050756
Received: 13 April 2021 / Revised: 28 April 2021 / Accepted: 29 April 2021 / Published: 4 May 2021
This paper investigates the determination of secondary dendrite arm spacing (SDAS) using convolutional neural networks (CNNs). The aim was to build a Deep Learning (DL) model for SDAS prediction that has industrially acceptable prediction accuracy. The model was trained on images of polished samples of high-pressure die-cast alloy EN AC 46000 AlSi9Cu3(Fe), the gravity die cast alloy EN AC 51400 AlMg5(Si) and the alloy cast as ingots EN AC 42000 AlSi7Mg. Color images were converted to grayscale to reduce the number of training parameters. It is shown that a relatively simple CNN structure can predict various SDAS values with very high accuracy, with a R2 value of 91.5%. Additionally, the performance of the model is tested with materials not used during training; gravity die-cast EN AC 42200 AlSi7Mg0.6 alloy and EN AC 43400 AlSi10Mg(Fe) and EN AC 47100 Si12Cu1(Fe) high-pressure die-cast alloys. In this task, CNN performed slightly worse, but still within industrially acceptable standards. Consequently, CNN models can be used to determine SDAS values with industrially acceptable predictive accuracy. View Full-Text
Keywords: secondary dendrite arm spacing; convolutional neural network; casting microstructure inspection; deep learning; aluminum alloys secondary dendrite arm spacing; convolutional neural network; casting microstructure inspection; deep learning; aluminum alloys
Show Figures

Figure 1

MDPI and ACS Style

Nikolić, F.; Štajduhar, I.; Čanađija, M. Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys. Metals 2021, 11, 756. https://doi.org/10.3390/met11050756

AMA Style

Nikolić F, Štajduhar I, Čanađija M. Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys. Metals. 2021; 11(5):756. https://doi.org/10.3390/met11050756

Chicago/Turabian Style

Nikolić, Filip; Štajduhar, Ivan; Čanađija, Marko. 2021. "Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys" Metals 11, no. 5: 756. https://doi.org/10.3390/met11050756

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop