Department of Computer Science and Engineering, University of Oviedo, Campus de Viesques, Gijón, Asturias 33204, Spain.
Sensors (Basel). 2013 Aug 9;13(8):10287-305. doi: 10.3390/s130810287.
Sintering is a complex industrial process that applies heat to fine particles of iron ore and other materials to produce sinter, a solidified porous material used in blast furnaces. The sintering process needs to be carefully adjusted, so that the combustion zone reaches the bottom of the material just before the discharge end. This is known as the burn-through point. Many different parameters need to be finely tuned, including the speed and the quantities of the materials mixed. However, in order to achieve good results, sintering control requires precise feedback to adjust these parameters. This work presents a sensor to monitor the sintering burn-through point based on infrared thermography. The proposed procedure is based on the acquisition of infrared images at the end of the sintering process. At this position, infrared images contain the cross-section temperatures of the mixture. The objective of this work is to process this information to extract relevant features about the sintering process. The proposed procedure is based on four steps: key frame detection, region of interest detection, segmentation and feature extraction. The results indicate that the proposed procedure is very robust and reliable, providing features that can be used effectively to control the sintering process.
烧结是一个复杂的工业过程，它将铁矿和其他材料的细颗粒加热，生产出用于高炉的固结多孔材料烧结矿。烧结过程需要仔细调整，使燃烧区在物料到达出料端之前刚好到达底部。这被称为穿透点。许多不同的参数需要精细调整，包括材料的混合速度和数量。然而，为了获得良好的结果，烧结控制需要精确的反馈来调整这些参数。这项工作提出了一种基于红外热成像的监测烧结穿透点的传感器。所提出的方法基于在烧结过程结束时获取红外图像。在这个位置，红外图像包含混合物的横截面温度。这项工作的目的是处理这些信息，提取有关烧结过程的相关特征。所提出的方法基于四个步骤：关键帧检测、感兴趣区域检测、分割和特征提取。结果表明，所提出的方法非常稳健可靠，提供的特征可有效用于控制烧结过程。
