Industrial online surface defects detection in continuous casting hot slabs

Álvarez, Ignacio; Marina, Jorge; Enguita, J.M.; Fraga, César G.; Garcia, R.

doi:10.1117/12.827532

Cited by 7 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alvarez et al [14] presented a system that has been used on-line at the ArcelorMittal plant in Avilas, Spain over a period of two years. The system used conoscopic holography to reliably detect defects over 100 mm in length, but a detailed description of the classification process was not provided.…”

Section: B Related Workmentioning

confidence: 99%

Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

Veitch-Michaelis

Tao

Walton

et al. 2016

2016 13th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

We describe a high-accuracy inspection system designed to automatically detect cracks in "as-cast" steel slabs. Real-time slab inspection requires instrumentation capable of withstanding high temperatures above the steel surface as well as coping with the dirty and dusty environment present in a steel mill. Crack detection is also challenging due to the presence of oxidation scale on the slab surface. A bespoke laser triangulation system has been developed, providing images at 250 fps with a calibrated surface resolution of 97 µm from a 1m standoff distance. Cracks are detected using a combination of morphological detection and SVM classifier. Results are reported from laboratory testing and from extended trials at a production steel mill.

show abstract

Section: B Related Workmentioning

confidence: 99%

Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

Veitch-Michaelis

Tao

Walton

et al. 2016

2016 13th Conference on Computer and Robot Vision (CRV)

View full text Add to dashboard Cite

show abstract

“…The most commonly used technique for 3D measurement used for inspecting slab is laser triangular [I]. And recently conoscopic holography method is adopted to inspect hot slab [2,3]. Each method has its own merits and demerits such as long standoff, amount of precision and operating conditions.…”

Section: Introductionmentioning

confidence: 99%

The automated surface inspection system for hot slab

Park¹,

Bae²,

Yun³

et al. 2013

2013 13th International Conference on Control, Automation and Systems (ICCAS 2013)

View full text Add to dashboard Cite

The inspection for hot slab is an important issue to quality operators in steel industry. This paper introduces the automated inspection system for hot slab using interlaced lighting technology. We extract the depth information from surface images so that it make easier to overcome the unclear and noisy backgrounds and detect defects. The test results show 100% and 86% for crack and comer burst defects respectively. The false detection rate is less than 0.1 % for each defect. The results imply that the proposed inspection system is very effective and promising method for inspecting hot slab.

show abstract

“…[11][12][13] Many research institutes have produced their own rolled strip shape measuring devices such as the ABB in Switzerland, Siemens and AEG in Germany, and Mitsubishi in Japan. [14][15][16] Laser triangulation as the most common displacement measurement method has been applied to the shape evaluation of rolled strip, by which the continuous 3D information of the laser stripe plane can be captured by CCD cameras while the inspected object is moved forward. The basic principle of this method is that the laser emitter projects line shaped light onto the object surface, and meanwhile, a calibrated CCD scans the reflective laser stripe modulated by wave shape in real time.…”

Section: Introductionmentioning

confidence: 99%

Study on CCD laser scanning flatness measurement method for hot rolled strip

Zhao

Ouyang

Chen

et al. 2015

Ironmaking & Steelmaking

View full text Add to dashboard Cite

To provide a flexible calibration method and make an accurate machine vision (MV) based flatness measurement strategy a reality in routine production line, an area scan charge coupled device (CCD) laser stripe scanning approach is presented. The applicability of the proposed method is not tied to the strip exclusively. First, we devise an automatic laser stripe imaging quality evaluation method through analysing the characteristics of the image grey gradient of laser stripe, which is a prerequisite for precisely extracting the laser stripe modulated information in hot or reflective object surface; second, a fast system calibration method is designed based on the area scan CCD imaging principle and spatial measurement technologies; here, the practical calibration is an indispensable technique for MV based measurement with large field of view in modern steelmaking lines. The proposed method performs competitively with the state-of-the-art as seen from the comparison of the experimental results. Through online testing, this method also showed considerable promise for hot rolled strip flatness measurement. However, the scheme for eliminating the influence of vibrations related to different applications is not taken into account in the current work.

show abstract

Industrial online surface defects detection in continuous casting hot slabs

Cited by 7 publications

References 6 publications

Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

Crack Detection in "As-Cast" Steel Using Laser Triangulation and Machine Learning

The automated surface inspection system for hot slab

Study on CCD laser scanning flatness measurement method for hot rolled strip

Contact Info

Product

Resources

About