基于X射线和结构光相机的煤矸石分拣方法研究

Research on Coal Gangue Sorting Method Based on X-Ray and Structured Light Camera

为了提高煤炭产量,减少污染物排放,在煤矿生产中必须进行煤矸石分离.常用的双能R值方法受物料厚度影响较大,无法满足大范围厚度的煤矸石分选需求.针对该问题,提出了一种联合R值曲线拟合和物料厚度信息的煤矸石识别方法.建立煤和矸石的低能透射信号值和R值的关系散点图,探究R值算法的适用范围和极限厚度.首先利用R值算法进行初步识别,再通过结构光相机获取R值相对应的厚度信息,与极限厚度比较后进一步识别煤矸石.最后计算识别为煤的部分占整个物体的比率,通过所求占比实现煤矸石的分选.实验结果证明,该方法可以识别50 mm~300 mm范围的煤矸石,煤的最低识别率大于80%,矸石的最高识别率低于10%,整体识别准确率高于96%.

In order to increase coal production and reduce pollutant emissions,coal gangue must be separated in coal mine production.The commonly used R value method was greatly affected by the thickness of the material and could not meet the needs of coal gangue separation in a wide range of thickness.To solve this problem,a coal gangue identification method combining R value curve fitting and material thickness information was proposed.Establish a scatterplot of the relationship between the low-energy transmission signal value and R value of coal and gangue,and the applicable range and limit thickness of the R value algorithm was explored.First use the R value algorithm for preliminary identification,and then use the structured light camera to obtain the thickness information corresponding to the R value,and compare it with the limit thickness to further identify the gangue.The experimental results prove that the method can effectively identify coal gangue in the range of 50 mm~300 mm,the minimum recognition rate of coal is greater than 80%,and the highest recognition rate of gangue is less than 10%.The overall recognition accuracy rate is higher than 96%.