On-line detection method of continuous casting billet surface quality

Abstract

The invention discloses an on-line detection method of continuous casting billet surface quality. According to the on-line detection method, a laser light source is taken as lightening equipment, an industrial-grade high-precision camera is used as image acquisition equipment, and a corresponding optical filter is arranged on the camera; when the surface of the continuous casting billet is exposed in laser beams, absorption, reflection and refraction features of oxide skin, cracks, recesses, scratches and slag pockets on the laser beams are different, and the difference is collected by the camera, and is shown in forms of imagines; and then defects observed in the imagines are positioned, sorted, preserved and underlined via defect detection algorithm. According to the on-line detection method, the laser light source with high power and the industrial linear array camera are combined, so that technological problems of continuous casting billet surface detection site imagine acquisition are solved; a distributed structure is used for data transmission, storage and processing, system stability is high, and storage and processing speed is fast; the imagine processing algorithm is firmly based on the features of detected objects, so that detection accuracy is high.

Description

technical field [0001] The invention belongs to the field of quality detection of casting slabs, and specifically discloses an online detection method for the surface quality of continuous casting slabs. Background technique [0002] During the production process of the continuous casting slab, affected by the performance of the casting machine and the continuous casting process, various surface defects such as horizontal and vertical cracks, subcutaneous pinholes, slag inclusions, and depressions will inevitably occur. These defects seriously affect the quality of the slab, and even lead to the scrapping of the slab; the slab with defects flows into the continuous rolling process, which affects the quality of the rolled product at the slightest, and even leads to the scrapping of the rolled product. Such as automobile plates and home appliance plates with high surface quality requirements, if there are small defects on the surface of the slab, it will expand to a few meters...

AI Technical Summary

Problems solved by technology

The disadvantages of manual detection are: 1. The detection results are affected by the subjective factors of the inspectors, and lack accuracy, reliability and integrity; 2. It can only be detected when the slab is still or moving very slowly, and it cannot detect tiny 3. The detection of the lower surface is very difficult, and it needs to be realized through the flipping process or set up a special lower surface detection reflector and arrange special personnel to carry out

4. The detected defect data cannot be saved, the historical data on the surface quality of the product cannot be grasped, and the data cannot be statistically analyzed to guide production; 5. The site temperature is high, especially in summer, and the working conditions of the inspectors are very hard , unable to work continuously for a long time

[0004] For the two-dimensional imaging method, the temperature of the billet exceeds 800°C, which itself is a red and bright light source. The pictures taken by the halogen lamp as the area light are often blurred by the interference of the billet light, which greatly reduces the subsequent defect detection. The possibility of output; the light output port of the area array light source is relatively large, and the workload of daily cleaning and maintenance is very large in the high-temperature and high-dust environment of the continuous casting production site; the service life of the halogen light source is only about one month, and the cost of long-term use Higher; if the acquisition camera uses an area array camera, its resolution is limited, and when the detected object is fast, the acquisition speed of the camera will not meet the requirements

The 3D imaging method cannot detect individual defects; in addition, there are high requirements for the installation angle of the equipment and the on-site use environment, and the detection results are very easily interfered by external factors, so it is difficult to use on a large scale

Images