LAUSR

Accurately measuring the mass flow of molten iron at the bottom of a blast furnace is of great significance for energy savings and efficient operation in the iron making process. However, the lack of texture information on the surface of molten iron will severely limit the accuracy of conventional displacement reconstruction algorithms. To this end, this article presents a methodology based on trusted region stacking, which can estimate an accurate displacement distribution of the molten iron surface through automatic location, tracking, and stacking of the trusted region. Subsequently, a falling motion model of the molten iron was proposed, and combined with the displacement distribution of the molten iron surface, the accurate measurement of the molten iron velocity at the outlet of the swing nozzle was realized even if the image of the molten iron there is missing. Therefore, the mass flow of molten iron is determined with the a priori information of the outlet shape of the swing nozzle. Industrial experiments illustrate that the proposed method can stably and accurately measure the molten iron mass flow and estimate the weight of molten iron in the iron ladle.