Next Article in Journal
Scaling Concepts in Serpin Polymer Physics
Next Article in Special Issue
Effect of Direct Powder Forging Process on the Mechanical Properties and Microstructural of Ti-6Al-4V ELI
Previous Article in Journal
Strength Properties of Structural Glulam Elements from Pine (Pinus sylvestris L.) Timber Reinforced in the Tensile Zone with Steel and Basalt Rods
Previous Article in Special Issue
Comparison on Tensile Characteristics of Plain C–Mn Steel with Ultrafine Grained Ferrite/Cementite Microstructure and Coarse Grained Ferrite/Pearlite Microstructure
Article

The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts

by 1, 2 and 1,*
1
Department of Mechanical and Industrial Engineering, Louisiana State University, Baton Rouge, LA 70803, USA
2
Department of Civil and Environmental Engineering, Louisiana State University, Baton Rouge, LA 70803, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Kotiba Hamad
Materials 2021, 14(10), 2575; https://doi.org/10.3390/ma14102575
Received: 10 April 2021 / Revised: 5 May 2021 / Accepted: 11 May 2021 / Published: 15 May 2021
(This article belongs to the Special Issue Microstructure and Mechanical Properties of Alloys and Steels)
Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks and pores in the testing images. In addition to the application of static image analysis, defect detection is also successfully applied on a video which mimics the AM process control images. The trained Detectron2 model can identify almost all the pores and cracks that exist in the original video. This study lays a foundation for future in situ process monitoring of the 3D printing process. View Full-Text
Keywords: defect classification; defect detection; image segmentation; CNNs; YOLOv4; Detectron2; additive manufacturing; process control defect classification; defect detection; image segmentation; CNNs; YOLOv4; Detectron2; additive manufacturing; process control
Show Figures

Figure 1

MDPI and ACS Style

Wen, H.; Huang, C.; Guo, S. The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts. Materials 2021, 14, 2575. https://doi.org/10.3390/ma14102575

AMA Style

Wen H, Huang C, Guo S. The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts. Materials. 2021; 14(10):2575. https://doi.org/10.3390/ma14102575

Chicago/Turabian Style

Wen, Hao, Chang Huang, and Shengmin Guo. 2021. "The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts" Materials 14, no. 10: 2575. https://doi.org/10.3390/ma14102575

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
Back to TopTop