Enhanced Defect Detection in Additive Manufacturing via Virtual Polarization Filtering and Deep Learning Optimization

Enhanced Defect Detection in Additive Manufacturing via Virtual Polarization Filtering and Deep Learning Optimization

Additive manufacturing (AM) is widely used in industries such as aerospace, medical, and automotive. Within this domain, defect detection technology has emerged as a critical area of research focus in the quality inspection phase of AM. The main challenge lies in that under extreme lighting conditio...

Full description

Saved in:
Bibliographic Details
Main Authors: Xu Su, Xing Peng, Xingyu Zhou, Hongbing Cao, Chong Shan, Shiqing Li, Shuo Qiao, Feng Shi
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Photonics
Subjects:
polarimetric imaging
defect detection
additive manufacturing
deep learning
Online Access:https://www.mdpi.com/2304-6732/12/6/599
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Additive manufacturing (AM) is widely used in industries such as aerospace, medical, and automotive. Within this domain, defect detection technology has emerged as a critical area of research focus in the quality inspection phase of AM. The main challenge lies in that under extreme lighting conditions, strong reflected light obscures defect feature information, leading to a significant decrease in the defect detection rate. This paper introduces a novel methodology for intelligent defect detection in AM components with reflective surfaces, leveraging virtual polarization filtering (IEVPF) and an improved YOLO V5-W model. The IEVPF algorithm is designed to enhance image quality through the virtual manipulation of light polarization, thereby improving defect visibility. The YOLO V5-W model, integrated with CBAM attention, DenseNet connections, and an EIoU loss function, demonstrates superior performance in defect identification across various lighting conditions. Experiments show a 40.3% reduction in loss, a 10.8% improvement in precision, a 10.3% improvement in recall, and a 13.7% improvement in mAP compared to the original YOLO V5 model. Our findings highlight the potential of combining virtual polarization filtering with advanced deep learning models for enhanced AM surface defect detection.
ISSN:2304-6732

Similar Items