Investigation into Surface Defects Arising in Hot-Rolled SUP 11A Grade Spring Billets

It is important to accurately classify the defects in hot rolled steel strip since the detection of defects in hot rolled steel strip is closely related to the quality of the final product. The lack of actual hot-rolled strip defect data sets currently limits further research on the classification of hot-rolled strip defects to some extent. In real production, the convolutional neural network (CNN)-based algorithm has some difficulties, for example, the algorithm is not particularly accurate in classifying some uncommon defects. Therefore, further research is needed on how to apply deep learning to the actual detection of defects on the surface of hot rolled steel strip. In this paper, we proposed a hot rolled steel strip defect dataset called Xsteel surface defect dataset (X-SDD) which contains seven typical types of hot rolled strip defects with a total of 1360 defect images. Compared with the six defect types of the commonly used NEU surface defect database (NEU-CLS), our proposed X-SDD contains more types. Then, we adopt the newly proposed RepVGG algorithm and combine it with the spatial attention (SA) mechanism to verify the effect on the X-SDD. Finally, we apply multiple algorithms to test on our proposed X-SDD to provide the corresponding benchmarks. The test results show that our algorithm achieves an accuracy of 95.10% on the testset, which exceeds other comparable algorithms by a large margin. Meanwhile, our algorithm achieves the best results in Macro-Precision, Macro-Recall and Macro-F1-score metrics.

Download Full-text

An improved Vision Transformer-based method for classifying surface defects in hot-rolled strip steel

Journal of Physics Conference Series ◽

10.1088/1742-6596/2082/1/012016 ◽

2021 ◽

Vol 2082 (1) ◽

pp. 012016

Author(s):

Xinglong Feng ◽

Xianwen Gao ◽

Ling Luo

Keyword(s):

Surface Defect ◽

Surface Defects ◽

Steel Strip ◽

Learning Ability ◽

Rolled Strip ◽

Strip Surface ◽

Strip Steel ◽

Hot Rolled Strip ◽

Hot Rolled ◽

Improved Algorithm

Abstract A new Vision Transformer(ViT) model is proposed for the classification of surface defects in hot rolled strip, optimizing the poor learning ability of the original Vision Transformer model on smaller datasets. Firstly, each module of ViT and its characteristics are analyzed; Secondly, inspired by the deep learning model VGGNet, the multilayer fully connected layer in VGGNet is introduced into the ViT model to increase its learning capability; Finally, by performing on the X-SDD hot-rolled steel strip surface defect dataset. The effect of the improved algorithm is verified by comparison experiments on the X-SDD hot-rolled strip steel surface defect dataset. The test results show that the improved algorithm achieves better results than the original model in terms of accuracy, recall, F1 score, etc. Among them, the accuracy of the improved algorithm on the test set is 5.64% higher than ViT-Base and 2.64% higher than ViT-Huge; the accuracy is 4.68% and 1.36% higher than both of them, respectively.

Download Full-text

Texture Descriptors for Automatic Classification of Surface Defects of the Hot-Rolled Steel Strip

10.1007/978-3-030-87869-6_24 ◽

2021 ◽

pp. 251-260

Author(s):

Virginia Riego del Castillo ◽

Lidia Sánchez-González ◽

Alexis Gutiérrez-Fernández

Keyword(s):

Surface Defects ◽

Steel Strip ◽

Automatic Classification ◽

Rolled Steel ◽

Hot Rolled ◽

Hot Rolled Steel

Download Full-text

Fast Position and Accurate Segmentation Algorithms for Detecting Surface Defects of the Thermal-State Heavy Rail Based on Machine Vision

International Journal of Software Science and Computational Intelligence ◽

10.4018/ijssci.2013100104 ◽

2013 ◽

Vol 5 (4) ◽

pp. 40-60

Author(s):

Xue Wang ◽

Yiran Chen ◽

Tao Cheng ◽

Zhijiang Xie

Keyword(s):

Nearest Neighbor ◽

Surface Defects ◽

Thermal State ◽

Mean Shift ◽

Sampling Point ◽

Positioning Method ◽

Rolled Condition ◽

Novel Algorithms ◽

Hot Rolled ◽

Heavy Rail

Color imaging in the hot rolled condition provides the better reaction of heavy rail on surface defects. In this paper, it proposes a series of novel algorithms of accurate position and segmentation of surface defects of heavy rail. An image acquisition device is designed on the adjustable camera bracket with the linear array CCD, and based on the correlation among pixels at the image level, a fast positioning method is developed for searching the Region Of Interesting (ROI) of the surface defects. Using the Mean-Shift image filtering algorithm which features multi-parameter kernel function, amendments to the sampling point weights and regional search with the nearest neighbor sampling points, accurate segmentation of the identification character is easily achieved by K-means clustering. Experiments show that this algorithm for the identification of the heavy rail surface defects is proven to be more rapid in testing the inclusions, cracks and oxide skin defects with a good promotional value.

Download Full-text

Resource-saving preparation of the 38KHGNM steel surface for heading of automobile components

E3S Web of Conferences ◽

10.1051/e3sconf/202015701006 ◽

2020 ◽

Vol 157 ◽

pp. 01006

Author(s):

Aleksey Filippov ◽

German Pachurin ◽

Diana Goncharova ◽

Gor Gevorgyan ◽

Mariia Mukhina ◽

...

Keyword(s):

Surface Defects ◽

Metal Flow ◽

Steel Grade ◽

Metallographic Analysis ◽

Rolled Stock ◽

Resource Saving ◽

Cold Upsetting ◽

Automobile Components ◽

Hot Rolled ◽

Decarburized Layer

To produce high-quality fasteners for motor group components of automobiles it is necessary to follow the increased requirements to calibrated rolled stock in terms of surface defects. Therefore, the goal of this paper is to study the reasons, types and depth of the surface defects on the calibrated rolled stock from steel 38KHGNM Ø 12.0 mm on the basis of the metallographic analysis. Before cold upsetting, the hot-rolled products are subjected to metal flow and removal of unacceptable surface defects by means of expensive turning operation during which the screw cuts and cracks might appear. It has been defined, that the hot-rolled stock from steel, grade 38KHGNM, diameter 12.0 мм has nonuniform mechanical properties, grooves, laps and partial decarburization on the surface. The heat treatment of the rolled stock with a decarburized layer on the surface contributes to its further decarburization. Poor alignment of calibrated stock during its turning at the turning machine does not enable to completely remove the decarburized layer with minimum skinning of rolled stock. It has been shown that the use of rolled stock from steel 38KHGNM with surface defects and unreasonably high decarburized layer on the surface increases its rejection by 8% and raises the consumption of rolled stock for manufacturing of important fasteners for the motor group of automobiles.

Download Full-text

Automated Visual Inspection of Surface Defects on Hot-Rolled Plate

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.201-203.1619 ◽

2011 ◽

Vol 201-203 ◽

pp. 1619-1622

Author(s):

Qiang Song

Keyword(s):

Visual Inspection ◽

Surface Defects ◽

Digital Camera ◽

Structural Defects ◽

Rolled Plate ◽

Inspection System ◽

Automated Visual Inspection ◽

Accurate Identification ◽

Surface Defect Detection ◽

Hot Rolled

This paper is concerned with the problem of automatic inspection of hot-rolled plate surface using machine vision. An automated visual inspection (AVI) system has been developed to take images of external hot-rolled plate surfaces and the detailed characteristics of the sensor system which include the illumination and digital camera are described. An intelligent surface defect detection paradigm based on morphology is proposed to detect structural defects on plate surfaces. The proposed method has been implemented and tested on a number of hot-rolled plate surfaces. The results suggest that the method can provide an accurate identification to the defects and can be developed into a commercial visual inspection system.

Download Full-text

Numerical Simulation and Analysis for Surface Defect Prediction in the Hot Bar Rolling Process

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.474-476.325 ◽

2011 ◽

Vol 474-476 ◽

pp. 325-329 ◽

Cited By ~ 1

Author(s):

Jie Jin ◽

Gang Huang

Keyword(s):

Numerical Simulation ◽

Surface Defects ◽

Simulation Analysis ◽

Equivalent Stress ◽

Rolling Process ◽

Processing Parameters ◽

Equivalent Strain ◽

Practical Significance ◽

Bar Rolling ◽

Hot Rolled

Establishment of numerical model for hot rolled bar and analysis the changes from the discrete points on surface during the hot bar rolling process (includes velocity, displacement, equivalent stress, equivalent strain). And the position of surface defects can be effectively predicted form this. Compared with the actual hot rolling bar production, numerical simulation was in good agreement with it. So that the numerical simulation analysis has practical significance for optimizing processing parameters and process design to ensure product quality.

Download Full-text

Content-Based Image Retrieval for Surface Defects of Hot Rolled Steel Strip Using Wavelet-Based LBP

10.1007/978-3-030-89691-1_39 ◽

2021 ◽

pp. 404-413

Author(s):

Fatma Zohra Boudani ◽

Nafaa Nacereddine ◽

Nacera Laiche

Keyword(s):

Image Retrieval ◽

Surface Defects ◽

Steel Strip ◽

Content Based Image Retrieval ◽

Rolled Steel ◽

Hot Rolled ◽

Hot Rolled Steel

Download Full-text

Recognition of surface defects of rolled steel in sheets by application micro-X-ray spectral analysis

Ferrous Metallurgy Bulletin of Scientific Technical and Economic Information ◽

10.32339/0135-5910-2021-11-1168-1176 ◽

2021 ◽

Vol 77 (11) ◽

pp. 1168-1176

Author(s):

A. B. Sychkov ◽

N. V. Koptseva ◽

Yu. Yu. Efimova ◽

G. Ya. Atangulova (Kamalova)

Keyword(s):

Spectral Analysis ◽

Surface Defects ◽

Economic Effect ◽

Sheet Steel ◽

Rolled Sheet ◽

Accurate Identification ◽

Sheet Rolling ◽

X Ray ◽

Rolling Production ◽

Hot Rolled

Surface defects of sheet rolled products have a significant impact on its quality, performance and further processing of products, for example, on application of a protective anticorrosive coating. Therefore, the elimination of such defects and their accurate identification is an important aspect of sheet rolling production. Reducing the rejection of metal for surface defects enables to get a significant technical and economic effect. Investigation of the causes of defectiveness of the surface of sheet rolled products will make it possible to determine the source of the appearance of the defects and methods to prevent them. Determination of the nature and morphology of surface defects, the sources of which being metallic and non-metallic inclusions, as well as remnants of slag surface layer, scales from metallurgical and rolling stages, rolled into the surface of a hot-rolled sheet, is often difficult, since the appearance of the defects is very similar. It was shown that application of a scanning electron microscope (SEM) with micro-X-ray spectral analysis (MXSA), thermodynamic analysis makes it possible to determine the chemical composition of micro-areas and associate it with the end-to-end technology of sheet production. The article presents the results of identifying surface defects of cold-rolled sheet steel.

Download Full-text