Surface-defect detecting method, surface-defect detecting apparatus, steel-material manufacturing method, steel-material quality management method, steel-material manufacturing facility, surface-defect determination model generating method, and surface-defect determination model
AssigneeJfe Steel Corporation
InventorsHiroaki Ono, Masami Tate
Life of this patent
Estimating the term…
Abstract
A surface-defect detecting method of optically detecting a surface defect of a steel material, the method including: an irradiation step of irradiating an examination target part with illumination light beams from different directions by using two or more distinguishable light sources; and a detection step of detecting a surface defect in the examination target part based on the degree of overlapping of bright portions extracted from two or more images formed by reflected light beams of the illumination light beams.
Claims22
A surface-defect detecting method of optically detecting a surface defect of a steel material, the method comprising:
- irradiating an examination target part with illumination light beams from different directions by using two or more distinguishable light sources;
- and
- detecting a surface defect in the examination target part based on the degree of overlapping of bright portions extracted from two or more images formed by reflected light beams of the illumination light beams,
- wherein each image of the two or more images is from a same area of the steel material and the degree of overlapping of bright portions extracted from the two or more images is determined from the same area.
A steel-material manufacturing method comprising a step of manufacturing a steel material while detecting a surface defect of the steel material by using a surface-defect detecting method of optically detecting the surface defect of the steel material, the surface-defect detecting method including:
- irradiating an examination target part with illumination light beams from different directions by using two or more distinguishable light sources;
- and
- detecting a surface defect in the examination target part based on the degree of overlapping of bright portions extracted from two or more images formed by reflected light beams of the illumination light beams,
- wherein each image of the two or more images is from a same area of the steel material and the degree of overlapping of bright portions extracted from the two or more images is determined from the same area.
A steel-material quality management method comprising managing the quality of a steel material by classifying the steel material based on existence of a surface defect by using a surface-defect detecting method of optically detecting the surface defect of the steel material, the surface-defect detecting method including:
- irradiating an examination target part with illumination light beams from different directions by using two or more distinguishable light sources;
- and
- detecting a surface defect in the examination target part based on the degree of overlapping of bright portions extracted from two or more images formed by reflected light beams of the illumination light beams,
- wherein each image of the two or more images is from a same area of the steel material and the degree of overlapping of bright portions extracted from the two or more images is determined from the same area.
A surface-defect detecting apparatus configured to optically detect a surface defect of a steel material, the apparatus comprising:
- two or more distinguishable light sources configured to irradiate an examination target part with illumination light beams from different directions;
- and
- an image processing device configured to detect a surface defect in the examination target part based on the degree of overlapping of bright portions extracted from two or more images formed by reflected light beams of the illumination light beams,
- wherein each image of the two or more images is from a same area of the steel material and the degree of overlapping of bright portions extracted from the two or more images is determined from the same area.
Dependencies are inferred from the claim text.