首页|选煤厂大煤块智能图像识别方法研究

选煤厂大煤块智能图像识别方法研究

扫码查看
针对现有选煤厂大煤块识别受到大煤块与矸石线性不可分影响,导致识别效率低、识别精度差的问题,设计了一种选煤厂大煤块智能图像识别方法.首先,应用图像采集设备获取煤块混合图像,并对图像进行增强、去噪等操作,以完成图像预处理.然后,计算煤块的面积和厚度,以获取煤块与矸石的物质特征.最后,基于煤块与矸石的X射线衰减曲线完成识别阈值的设定,并结合最小二乘支持向量机解决煤块与矸石的线性不可分问题,从而完成大煤块图像的智能识别.对比试验结果表明,所提方法应用效果较好、识别率及识别精度较高、识别速度较快,总体性能优于对比方法.该方法可大幅提升大煤块图像识别效果,有较高的应用价值.
Study of Intelligent Image Recognition Method for Large Coal Blocks in Coal Preparation Plant
Aiming at the problem that the recognition of large coal blocks in existing coal preparation plant is affected by the linear inseparability of large coal blocks and gangue,which leads to low recognition efficiency and poor recognition accuracy,an intelligent image recognition method for large coal blocks in coal preparation plant is designed.Firstly,the image acquisition equipment is applied to obtain the mixed image of coal blocks,and the image enhanced,denoised and other operations are performed to complete the image preprocessing.Then,the area and thickness of the coal block are calculated to obtain the material characteristics of the coal block and gangue.Finally,based on the X-ray attenuation curves of the coal block and gangue,the identification threshold is set,and combined with the least-squares support vector machine to solve the linear indivisibility problem of the coal block and gangue,to complete the intelligent identification of large coal block images.Comparison test results show that the proposed method has better application effect,higher recognition rate and recognition accuracy,and faster recognition speed,which is better than the comparison method.The method can greatly improve the recogniton effect of large coal block images and has high application value.

Coal preparation plantIntelligent imageLarge coal blocks recognitionX-ray attenuation curvesLinear indivisibilitySupport vector machine

张文军

展开 >

中煤科工集团北京华宇工程有限公司,河南 平顶山 467000

选煤厂 智能图像 大煤块识别 X射线衰减曲线 线性不可分 支持向量机

2024

自动化仪表
中国仪器仪表学会 上海工业自动化仪表研究院

自动化仪表

CSTPCD
影响因子:0.655
ISSN:1000-0380
年,卷(期):2024.45(10)