Next Article in Journal
Selective Photothermal Therapy Using Antioxidant Nanoparticles Encapsulating Novel Near-Infrared-Absorbing Platinum(II) Complexes
Previous Article in Journal
Tunable Plasmonic Bandwidth Broadening via DC Electrical Bias
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Automated Detection of Micro-Scale Porosity Defects in Reflective Metal Parts via Deep Learning and Polarization Imaging

1
College of Intelligent Science and Technology, National University of Defense Technology, Changsha 410073, China
2
National Key Laboratory of Equipment State Sensing and Smart Support, Changsha 410073, China
3
State Key Laboratory of Functional Crystals and Devices, Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai 201899, China
4
College of Physics, Zhejiang University of Technology, Hangzhou 310023, China
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Nanomaterials 2025, 15(11), 795; https://doi.org/10.3390/nano15110795
Submission received: 9 April 2025 / Revised: 19 May 2025 / Accepted: 23 May 2025 / Published: 25 May 2025
(This article belongs to the Section Nanofabrication and Nanomanufacturing)

Abstract

Aiming at the key technology of defect detection in precision additive manufacturing of highly reflective metal materials, this study proposes an enhanced SCK-YOLOV5 framework, which combines polarization imaging and deep learning methods to significantly improve the intelligent identification ability of small metal micro and nano defects. This framework introduces the SNWD (Selective Network with attention for Defect and Weathering Degradation) Loss function, which combines the SIOU Angle Loss with the NWD distribution sensing characteristics. It is specially designed for automatic positioning and identification of micrometer hole defects. At the same time, we employ global space construction with a dual-attention mechanism and multi-scale feature refining technique with selection kernel convolution to extract multi-scale defect information from highly reflective surfaces stably. Combined with the polarization imaging preprocessing and the comparison of enhancement defects under high reflectivity, the experimental results show that the proposed method significantly improves the precision, recall rate, and MAP50 index compared with the YOLOv5 baseline (increased by 0.5%, 1.2%, and 1.8%, respectively). It is the first time that this improvement has been achieved among the existing methods based on the YOLO framework. It creates a new paradigm for intelligent defect detection in additive manufacturing of high-precision metal materials and provides more reliable technical support for quality control in industrial manufacturing.
Keywords: additive manufacturing; deep learning; micro–nano defect; defect detection; polarization imaging additive manufacturing; deep learning; micro–nano defect; defect detection; polarization imaging

Share and Cite

MDPI and ACS Style

Li, H.; Peng, X.; Wang, B.; Shi, F.; Xia, Y.; Li, S.; Shan, C.; Li, S. Automated Detection of Micro-Scale Porosity Defects in Reflective Metal Parts via Deep Learning and Polarization Imaging. Nanomaterials 2025, 15, 795. https://doi.org/10.3390/nano15110795

AMA Style

Li H, Peng X, Wang B, Shi F, Xia Y, Li S, Shan C, Li S. Automated Detection of Micro-Scale Porosity Defects in Reflective Metal Parts via Deep Learning and Polarization Imaging. Nanomaterials. 2025; 15(11):795. https://doi.org/10.3390/nano15110795

Chicago/Turabian Style

Li, Haozhe, Xing Peng, Bo Wang, Feng Shi, Yu Xia, Shucheng Li, Chong Shan, and Shiqing Li. 2025. "Automated Detection of Micro-Scale Porosity Defects in Reflective Metal Parts via Deep Learning and Polarization Imaging" Nanomaterials 15, no. 11: 795. https://doi.org/10.3390/nano15110795

APA Style

Li, H., Peng, X., Wang, B., Shi, F., Xia, Y., Li, S., Shan, C., & Li, S. (2025). Automated Detection of Micro-Scale Porosity Defects in Reflective Metal Parts via Deep Learning and Polarization Imaging. Nanomaterials, 15(11), 795. https://doi.org/10.3390/nano15110795

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop