On the Surface Micromorphology and Structure of Stainless Steel Obtained via Selective Laser Melting

Afanasieva, L. E.; Ratkevich, G. V.; Иванова, А. И.; Новоселова, М. В.; Zorenko, D. A.

doi:10.1134/s1027451018050385

Cited by 5 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The surface quality of the steel strip is of paramount importance to the final product, therefore surface defects in the steel strip must be strictly controlled. The surface quality of strip steel can be affected by several factors [3][4][5], although the number of strip surface defects generated can be reduced to some extent by a variety of reasonable control methods, until now the surface of the steel strip inevitably exit different types of defects, e.g., slag inclusion, red iron and surface scratches. These various surface defects of hot rolled steel strip have different effects on the production quality, therefore, it is necessary to classify the surface defects of hot rolled steel strip in order to better reduce their adverse effects.…”

Section: Introductionmentioning

confidence: 99%

X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection

2021

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection

2021

View full text Add to dashboard Cite

show abstract

“…Hot-rolled strip steel has good processing performance and strong coverage ability, which is widely used in automobile manufacturing, home appliance manufacturing, shipbuilding and chemical industry, etc. In the manufacturing process of strip steel, for various reasons [1][2][3], surface defects will inevitably arise, and these defects cannot be completely overcome by improving the process. Therefore, the detection of surface defects in hot rolled strip is an important part of hot rolled strip production and is closely related to the surface quality of the strip.…”

Section: Introductionmentioning

confidence: 99%

“…"Gradient disappearance" and "gradient explosion" can lead to the following shortcomings: (1) Long training time but network convergence becomes very difficult or even non-convergent. (2) The network performance will gradually saturate and even begin to degrade, known as the degradation problem of deep networks. To solve such problems, He et al [23] proposed the ResNet network, which makes it possible to obtain a good performance and efficiency of the network even when the number of network layers is very deep (even over 1000 layers).…”

Section: Introduction Of Resnetmentioning

confidence: 99%

A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel

Feng

Gao

Luo³

2021

Mathematics

View full text Add to dashboard Cite

Hot-rolled strip steel is widely used in automotive manufacturing, chemical and home appliance industries, and its surface quality has a great impact on the quality of the final product. In the manufacturing process of strip steel, due to the rolling process and many other reasons, the surface of hot rolled strip steel will inevitably produce slag, scratches and other surface defects. These defects not only affect the quality of the product, but may even lead to broken strips in the subsequent process, seriously affecting the continuation of production. Therefore, it is important to study the surface defects of strip steel and identify the types of defects in strip steel. In this paper, a scheme based on ResNet50 with the addition of FcaNet and Convolutional Block Attention Module (CBAM) is proposed for strip defect classification and validated on the X-SDD strip defect dataset. Our solution achieves a classification accuracy of 94.11%, higher than more than a dozen other compared deep learning models. Moreover, to adress the problem of low accuracy of the algorithm in classifying individual defects, we use ensemble learning to optimize. By integrating the original solution with VGG16 and SqueezeNet, the recognition rate of oxide scale of plate system defects improved by 21.05 percentage points, and the overall defect classification accuracy improved to 94.85%.

show abstract

Numerical simulation and experimental study of aluminum heat exchanger based on Comsol Multiphysics

Liu,

Peng,

Jiang

et al. 2024

Trans. Can. Soc. Mech. Eng.

View full text Add to dashboard Cite

Controlling the temperature of the air flow during printing can greatly improve the data measurement of air flow and the printing effect of selective laser melting equipment. In this study, an aluminum-welded heat exchanger was designed and manufactured combined with an engineering application example. The thermal performances of heat exchanger were carried out by experiment and numerical simulation in Comsol Multiphysics. Results show that the model has high accuracy (the relative error is less than 12% in most cases and the absolute error is less than 16 Pa below the flow rate of 350 m3/h), and the overall pipeline resistance loss is small. The temperature difference between outlet and inlet is always lower than 6.5 °C during actual working conditions, which meets the requirements for use. The research can provide good theoretical guidance for the design and application of aluminum heat exchangers.

show abstract

On the Surface Micromorphology and Structure of Stainless Steel Obtained via Selective Laser Melting

Cited by 5 publications

References 4 publications

X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection

X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection

A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel

Numerical simulation and experimental study of aluminum heat exchanger based on Comsol Multiphysics

Contact Info

Product

Resources

About