2019 Pittsburgh AISTech

Sessions Speakers Exhibitors Products Press Releases Show Specials Floor Plan Buzz

Efficient Determination of Misalignment of Ladle Shroud Using Machine Vision (Room 407)

Ladle shroud misalignment affects steel quality and operation, as it undermines the performance of impact pads and dams, thus causing adverse flow conditions, increasing the chance of open eye formation, decreasing residence time for inclusion flotation and increasing refractory wear. An efficient stereo vision disparity map algorithm was developed to reliably detect shroud misalignment by optimizing the performance of a stereo vision system. The computed disparity map generated true depth information of the shroud, which was directly correlated to misalignment. Extensive experiments were conducted to demonstrate that this approach can provide consistent results in noisy data sets to detect misalignment.