98%
921
2 minutes
20
Steel surface defect detection constitutes a critical inspection task in industrial production. To address challenges including missed detections and low accuracy for fine defects, this study develops an enhanced Faster R-CNN algorithm. The proposed framework incorporates a feature fusion module and lightweight channel attention mechanism between Feature Pyramid Networks (FPN) and Region Proposal Network (RPN), substantially augmenting subtle feature extraction capabilities. Evaluated on the NEU-DET dataset, the optimized model achieves a mean average precision (mAP) of 80.2%-yielding a 12.6% improvement over the baseline-while increasing detection speed by 40.9%. This approach not only significantly elevates defect recognition accuracy but also establishes a practical framework for automated steel surface inspection systems.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12358517 | PMC |
http://dx.doi.org/10.1038/s41598-025-12740-x | DOI Listing |
J Colloid Interface Sci
September 2025
State Key Laboratory of Hydro Science and Engineering, and Department of Energy and Power Engineering, Tsinghua University, Beijing, 100084, China. Electronic address:
Hypothesis: On highly cleaned planar surfaces submerged in highly cleaned water, flat surface nanobubbles with an angle of attachment of ∼15 are observed - never on engineering surfaces submerged in plain water, though here unidentified cavitation nuclei are always present and cause low tensile strength.
Experiments: In the present study, surface nanobubbles are generated by standard experimental techniques on a polished steel surface, and we find that the shape and the angles of attachment of the bubbles are influenced by the local substrate topography. These observations align with the theory of non-adsorbed liquid zones, which explains a surface nanobubble as a bubble with a skin of contamination molecules, which bond along the bubble rim at a contact angle of ∼14.
Mikrochim Acta
September 2025
Affordable and Sustainable Sample Preparation (AS2P) Research Group, Departamento de Química Analítica, Instituto Químico para la Energía y el Medioambiente IQUEMA, Universidad de Córdoba, Campus Universitario de Rabanales, Edificio Marie Curie, E-14071, Córdoba, Spain.
Stainless-steel substrates have grown in importance in the development of planar sorptive phases. However, the reduced wettability of polished sheets makes difficult their functionalization. This limitation can be solved by using amorphous silica gel microparticles as superficial guides.
View Article and Find Full Text PDFACS Omega
September 2025
Laboratory of Materials, Nanotechnology, and Environment, Faculty of Sciences, Mohammed V University in Rabat, Av. Ibn Battuta, P.O. Box 1014, Rabat 10000, Morocco.
In this study, we describe the synthesis and characterization of the mononuclear complexes [ )], [ ], and [ ], where = (2-((2-hydroxybenzylidene)-amino)-phenol). The structural analysis of these complexes was carried out utilizing mass spectrometry, H NMR, C NMR, P NMR, UV-visible, and FT-IR. All three complexes were investigated as corrosion inhibitors for mild steel in 1 M HCl.
View Article and Find Full Text PDFLangmuir
September 2025
Institute of Technology for Carbon Neutralization, Yangzhou University, Yangzhou 225127, Jiangsu, China.
To expand the application scope of carbon steel, imparting superhydrophobicity to its surface offers an effective strategy to overcome its inherently poor corrosion resistance. However, in marine environments, conventional superhydrophobic coatings often suffer from limited mechanical durability and inadequate long-term corrosion protection. In this study, a durable superhydrophobic bilayer coating composed of PDMS-MWCNTs (top layer) and PDMS (bottom layer) was developed to address these challenges.
View Article and Find Full Text PDFAdv Mater
September 2025
Department of Mechanical and Materials Engineering, University of Western Ontario, London, Ontario, N6A 5B9, Canada.
Anode-free sulfide-based all-solid-state lithium metal batteries (ASSLMBs), which eliminate the need for a lithium metal anode during fabrication, offer superior energy density, enhanced safety, and simplified manufacturing. Their performance is largely influenced by the interfacial properties of the current collectors. Although previous studies have investigated the degradation of sulfide electrolytes on commonly used copper (Cu) and stainless steel (SS) current collectors, the impact of spontaneously formed surface oxides, such as copper oxide (CuO/CuO) and chromium oxide (CrO), on interfacial stability remains underexplored.
View Article and Find Full Text PDF