基于图像识别的高温熔渣流量测量方法研究

Research on measurement method of high temperature molten slag flow rate based on image identification

中文关键词: 高温熔渣  图像识别  流量检测  算法

英文关键词: high temperature slag  image identification  measurement of flow rate  algorithm

中文摘要:

      熔渣流量是影响高温熔渣离心粒化效果的关键因素。为了测量熔渣流量，提出了一种流量测量方法，利用高速摄影机拍摄液柱流动图像，采用边缘检测、阈值分割等方法，获得液柱直径及流速，计算流量，采用常温甘油溶液作为测试对象进行实验，研究该方法测量精度的影响因素。结果显示，长曝光时间、合理的拍摄帧率、短物距有利于提高测量精度；同时，感兴趣区域（ROI）的位置为距管口2~5倍管径处、ROI长度为1/3~2/3倍管径时，测量精度较高。通过对实际高温熔渣流动过程的检测，其测量误差约9.0%，证明了该方法的实用性。

英文摘要:

      Flow rate is the key factor affecting the centrifugal granulation effect of high temperature molten slag, therefore a method for the measurements of the flow rate using image identification is proposed. Image of the molten slag column can be captured by high-speed camera, diameter and velocity are obtained by edge detection and threshold segmentation, and then flow rate can be calculated. Glycerin solution at room temperature is used to study the influencing factors of measurement accuracy. The results reveal that long exposure time, reasonable frame rate and short object distance are beneficial to improve the measurement accuracy. At the same time, the measurement accuracy is higher when the region of interest (ROI) is located 2~5 times the pipe diameter from the nozzle and the ROI length is 1/3~2/3 times the pipe diameter. The measurement error is about 9.0% when measuring the molten slag, which proves the practicability of the method.