Effect of Cold Rolling before Hydrogen Reduction on Reduction Behavior and Morphologies of Oxide Scale on Hot-rolled Low-carbon Steel

Li, Zhifeng; Cao, Guangming; Lin, Fei; Sun, Xianzhen; He, Yu; Liu, Zhenyu

doi:10.2355/isijinternational.isijint-2017-266

Cited by 7 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because the strip material in the rolling production process is affected by various aspects of the production process and equipment, the material surface is susceptible to inclusions, rolled-in scales, crazing, patches, scratches, creases, and other defects. These defects impair the corrosion resistance, wear resistance, and fatigue limit of the manufactured article, as well as other performance-related properties, potentially reducing the service life of the strip and leading to safety accidents [3]. Therefore, efficient detection of strip defects in industrial production is imperative.…”

Section: Introductionmentioning

confidence: 99%

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

Cheng,

Gao,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Defect detection is extensively utilized within the metal industry, particularly for identifying surface imperfections on steel strips. However, the current methods still face challenges in detecting small and elongated defects on steel strips. Such defects occupy a relatively small pixel percentage within the entire image. The repeated downsampling in convolutional networks, coupled with the dynamic changes in the receptive field, can result in the potential loss of these minute defects. To mitigate the problem, our paper proposes EC-YOLO, a real-time defect detection network for steel strips of the above peculiar defects. Firstly, the 1D convolution in the efficient channel attention bottleneck (EB) module enhances the feature extraction ability of the backbone for small and elongated defects, while also facilitating the attentional mechanism for modeling channel features. Secondly, Context Transformation Networks integrate cross-stage localized blocks, referred to as CC modules, to enhance the understanding of feature semantic contextual information. Thirdly, a self-constructed dataset containing both small and elongated defects is used for understanding where such defects are more relevant in feature fusion and extraction. On the public datasets GC10-DET and NEU-DET, the improved model achieves mean Average Precision (mAP) scores of 71% and 83%, respectively, surpassing the performance of other mainstream models. The mAP of the enhanced model on the SLD-DET dataset reaches 87.5%, demonstrating its superiority in detecting both small and elongated defects.INDEX TERMS Defect detection, small and elongated defects, attention, steel strips.

show abstract

Section: Introductionmentioning

confidence: 99%

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

Cheng,

Gao,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Given such a large amount of data and complex parameter systems, traditional analysis methods have shown relatively low performance or extensibility. [1][2][3][4][5][6] Therefore, it is necessary to establish a universal computational analysis system for the efficient and accurate mining of industrial big data to make full use of those resources.…”

Section: Introductionmentioning

confidence: 99%

Physical Metallurgy Guided Industrial Big Data Analysis System with Data Classification and Property Prediction

Huang

et al. 2022

steel research int.

View full text Add to dashboard Cite

show abstract

Reduction Behavior of Oxide Scales Containing Different Structures on the Surface of Hot‐Rolled Steel Strip in Gas Mixture H₂/Ar at 400–625 °C

Wang

Gao

et al. 2019

steel research int.

View full text Add to dashboard Cite

The reduction behavior of the oxide scales with two different microstructures in the gas of H2:Ar = 1:2 at 400–625 °C is investigated in detail. The mass change in the scale is measured by thermogravimetric analysis, and a function between reduction degree, reduction temperature, and reaction time is established. The experiment results show that the increase in temperature has an accelerating influence on the reduction reaction of the scale with eutectoid (Fe3O4/α‐Fe) until reaching 550 °C, and then the further increase in temperature decelerates the reduction. For the scale without eutectoid, the reduction rate at 450 °C is extremely high, and then the rate decreases with the increase in temperatures. Additionally, the reduction rate in the scale with eutectoid is faster than that without eutectoid at the temperature range of this study. At 400–550 °C, a large number of phase interfaces appear within the scale with eutectoid, which can provide diffusion channels for hydrogen atoms and water molecules within the Fe oxides. When the temperature reaches 575–625 °C, the phase transformation in the scale (Fe3O4 + α‐Fe → FeO) is accompanied by the reduction reaction, which is believed to be responsible for the lower reaction rate.

show abstract

Effect of Cold Rolling before Hydrogen Reduction on Reduction Behavior and Morphologies of Oxide Scale on Hot-rolled Low-carbon Steel

Cited by 7 publications

References 19 publications

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

Physical Metallurgy Guided Industrial Big Data Analysis System with Data Classification and Property Prediction

Reduction Behavior of Oxide Scales Containing Different Structures on the Surface of Hot‐Rolled Steel Strip in Gas Mixture H₂/Ar at 400–625 °C

Contact Info

Product

Resources

About

Effect of Cold Rolling before Hydrogen Reduction on Reduction Behavior and Morphologies of Oxide Scale on Hot-rolled Low-carbon Steel

Cited by 7 publications

References 19 publications

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

EC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5

Physical Metallurgy Guided Industrial Big Data Analysis System with Data Classification and Property Prediction

Reduction Behavior of Oxide Scales Containing Different Structures on the Surface of Hot‐Rolled Steel Strip in Gas Mixture H2/Ar at 400–625 °C

Contact Info

Product

Resources

About

Reduction Behavior of Oxide Scales Containing Different Structures on the Surface of Hot‐Rolled Steel Strip in Gas Mixture H₂/Ar at 400–625 °C