98%
921
2 minutes
20
Steel defect detection is a crucial aspect of steel production and quality control. Therefore, focusing on small-scale defects in complex production environments remains a critical challenge. To address this issue, we propose an innovative perception-efficient network designed for the fast and accurate detection of multi-scale surface defects. First, we introduce the Defect Capture Path Aggregation Network, which enhances the feature fusion network's ability to learn multi-scale representations. Second, we design a Perception-Efficient Head (PEHead) to effectively mitigate local aliasing issues, thereby reducing the occurrence of missed detections. Finally, we propose the Receptive Field Extension Module (RFEM) to strengthen the backbone network's ability to capture global features and address extreme aspect ratio variations. These three modules can be seamlessly integrated into the YOLO framework. The proposed method is evaluated on three public steel defect datasets: NEU-DET, GC10-DET, and Severstal. Compared to the original YOLOv8n model, PEYOLO achieves mAP50 improvements of 3.5%, 9.1%, and 3.3% on these datasets, respectively. While maintaining similar detection accuracy, PEYOLO retains a high inference speed, making it suitable for real-time applications. Experimental results demonstrate that the proposed PEYOLO can be effectively applied to real-time steel defect detection.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12328634 | PMC |
http://dx.doi.org/10.1038/s41598-025-05574-0 | DOI Listing |
HeartRhythm Case Rep
August 2025
Cardiovascular Centre, Social Medical Corporation Steel Memorial Yawata Hospital, Kitakyushu.
Sci Rep
August 2025
Smart Micro/Nanoelectromechanical Systems (SMNEMS) Lab, School of Advanced Technologies, PhD Student of Nanomaterials, Iran University of Science and Technology, Tehran, Iran.
Corrosion can severely degrade surfaces and materials, impacting both functionality and safety. Laser-induced graphene (LIG) offers substantial corrosion resistance, making it an ideal material for protecting metals, such as carbon steel. This study developed adhesive, corrosion-resistant LIG patches on polyimide (PI) layers, enhanced with an alkyd resin coating, and applied to pretreated aluminum surfaces.
View Article and Find Full Text PDFMicromachines (Basel)
August 2025
School of Mechanical, Materials, Mechatronic and Biomedical Engineering, University of Wollongong, Wollongong, NSW 2522, Australia.
Stainless steel is essential in high-performance industries due to its strength, corrosion resistance, and biocompatibility. However, conventional manufacturing methods limit material efficiency, design complexity, and customization. Additive manufacturing (AM) has emerged as a powerful alternative, enabling the production of stainless-steel components with complex geometries, tailored microstructures, and integrated functionalities.
View Article and Find Full Text PDFSensors (Basel)
August 2025
State Key Laboratory for Strength and Vibration of Mechanical Structures, Shaanxi Engineering Research Center of NDT and Structural Integrity Evaluation, School of Aerospace Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
Three-layer polyethylene (3LPE) coated steel pipelines are currently the preferred solution for global oil and gas transmission. However, external corrosion beneath the 3LPE coating poses a serious threat to pipeline operations. The pressing concern for pipeline safety and integrity involves non-destructive evaluation techniques for the non-invasive and quantitative interrogation of such defects.
View Article and Find Full Text PDFSensors (Basel)
August 2025
Christian Doppler Laboratory for Measurement Systems for Harsh Operating Conditions, Institute of Electrical Measurement and Sensor System, Graz University of Technology, Inffeldgasse 33, 8010 Graz, Austria.
Acoustic sound-based condition monitoring (ASCM) systems, which typically utilize machine learning algorithms on established audio features, have demonstrated effectiveness under controlled conditions. However, their application in real-world industrial environments presents significant challenges due to complex and variable soundscapes with high noise and limited fault data. The presence of random interfering sounds and variability in operating conditions can lead to lower performance and high false-positive rates.
View Article and Find Full Text PDF