Investigation of a surface defect and its elimination in automotive grade galvannealed steels

Chakraborty, Anindita; Mondal, Avik; Agnihotri, Soham; Pais, R.; Dutta, Moumita

doi:10.1016/j.engfailanal.2016.05.010

Cited by 16 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RD [70], (200 total defects) De nition: Rolling dust is a surface defect that appears as dark, irregularly shaped patches or lines on the surface of the steel.…”

Section: Sc [67] (773 Total Defects)mentioning

confidence: 99%

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Shahin¹,

Chen

Hosseinzadeh³

et al. 2023

Preprint

View full text Add to dashboard Cite

The global steel demand continues to increase, with steel being used in various industries, including construction, automobile, national defense, and machinery. However, steel production is a delicate process that can result in different defects on the steel surface, negatively affecting the quality of the steel products. Therefore, recognizing metal surface defects is critical in the metal production industry. Manual detection of these defects is the standard method, but it is time-consuming, labor-intensive, and prone to subjective factors, leading to low accuracy and unreliable results. Automated defect detection using computer vision methods can replace or supplement manual detection. In recent years, machine learning algorithms, particularly Convolutional Neural Networks (CNNs), have shown great promise in achieving high accuracy rates in this task. In addition, image classification algorithms can contribute to Lean metal production by identifying defects or anomalies in the manufacturing process, which can be used to reduce waste and increase efficiency. However, the performance and cost of different CNN architectures can vary widely, making it challenging for decision-makers to select the most suitable model. This paper analyzes various CNN-based image classification algorithms, including MobileNet, ShuffleNet, DenseNet, RegNet, and NasNet, in classifying steel surface defects in the NEU-CLS-64 dataset. We evaluate their performance using metrics such as accuracy, precision, sensitivity, specificity, F1 score, and G-mean, and benchmark these models against each other. Our findings revealed that RegNet achieved the highest accuracy, precision, sensitivity, specificity, F1 score, and G-mean performance but at a higher cost than other models. Meanwhile, MobileNet had the lowest performance. The results provide decision-makers with valuable insights into selecting the most suitable CNN model for steel surface defect detection based on their performance.

show abstract

“…RD [70], (200 total defects) De nition: Rolling dust is a surface defect that appears as dark, irregularly shaped patches or lines on the surface of the steel.…”

Section: Sc [67] (773 Total Defects)mentioning

confidence: 99%

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Shahin¹,

Chen

Hosseinzadeh³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The presence of defects hampers average surface roughness and deteriorates the paintability and thereby the aesthetics [7]. Investigation of patch-type defects has been reported by researchers in the past.…”

Section: Automotive Steel-common Surface Defectsmentioning

confidence: 99%

Study of White Patch Defect in Automotive Grade Interstitial Free Steel

Pawar

Chakraborty

Jugade

et al. 2020

J Fail. Anal. and Preven.

View full text Add to dashboard Cite

Surface of cold-rolled steel intended for automotive body panel applications is expected to be defect free. The presence of surface defects hampers the aesthetics and average surface roughness and thereby deteriorates the paintability of the steel sheet. This study aims to investigate the source of white patch defect in cold-rolled and skin-passed interstitial free steel sheets. Macroscopic observations of as-received white patch sample revealed the presence of blackish deposit having cracks inside the deposits, suggesting that these deposits were heated up possibly during annealing process. Further during macroscopic observation, it was revealed that the black deposits were of near round shape. If deposit is present before rolling, then it is expected that it will elongate during rolling and will not retain round shape. Round shape of the deposits under investigation suggested that it is not before rolling. Electrolytic cleaning line (ECL) is the only inbetween process. Surface characterization techniques such as SEM-EDS, Raman spectroscopy, Fourier transform infrared spectroscopy were used to analyze the defect and good region of the steel sheet. Overall analysis indicated grease contamination on cold-rolled steel sheet at the entry of ECL caused generation of white patch defect. Regular cleaning and preventive maintenance of plant machinery were recommended to avoid such leakages to arrest the defect generation in the future.

show abstract

“…Such coatings are employed, for example, in applications such as automobiles, sun-power plants and offshore platforms and, in general, in all the applications where time to mission is much more significant than life of coatings. Their large diffusion is due to both low production costs and high resistance to corrosion in many aggressive environments, also in presence of zones notwell galvanized (uncoated zones or black spot defects) [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Novel zinc-based alloys used to improve the corrosion protection of metallic substrates

Vantadori

Cocco

Fortese

et al. 2017

Engineering Failure Analysis

View full text Add to dashboard Cite

The protection of metallic structural components against corrosion is fundamental to preserve their mechanical properties in aggressive environments. Zn-based coating represents one of the most used techniques to make protective coatings for metallic substrates. In the present paper, two types of novel zinc-based coating are proposed, by employing either a tin addition or an aluminium-tin-copper addition to the traditional zinc bath. The behaviour of steel-coated specimens under bending is experimentally and numerically investigated by considering different bath dipping times. A quite satisfactory agreement 2 between experimental and numerical results is observed, especially under plastic behaviour regime.

show abstract

Investigation of a surface defect and its elimination in automotive grade galvannealed steels

Cited by 16 publications

References 12 publications

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Study of White Patch Defect in Automotive Grade Interstitial Free Steel

Novel zinc-based alloys used to improve the corrosion protection of metallic substrates

Contact Info

Product

Resources

About