基于红外热成像的煤矸识别方法研究

程刚; 潘择烨; 魏溢凡; 陈杰

doi:10.13272/j.issn.1671-251x.2023100086

基于红外热成像的煤矸识别方法研究

doi: 10.13272/j.issn.1671-251x.2023100086

程刚^1,,
潘择烨^2, ,,
魏溢凡²,
陈杰²

1.
安徽理工大学深部煤矿采动响应与灾害防控国家重点实验室，安徽淮南　232001
2.
安徽理工大学机电工程学院，安徽淮南　232001

基金项目: 安徽省高校协同创新项目（GXXT-2021-076）。

详细信息

作者简介:
程刚（1986—），男，安徽桐城人，副教授，博士，研究方向为煤矿智能开采与光机电一体化，E-mail：chgmech@mail.ustc.edu.cn

通讯作者:
潘择烨（1999—），男，山东烟台人，硕士研究生，研究方向为矿山机电工程，E-mail：Panzeye6894@163.com。

中图分类号: TD67
计量
- 文章访问数: 161
- HTML全文浏览量: 34
- PDF下载量: 34
- 被引次数: 0
出版历程
- 收稿日期: 2023-10-27
- 修回日期: 2024-04-19
- 网络出版日期: 2024-05-10

Research on coal gangue recognition method based on infrared thermal imaging

CHENG Gang^1
,,
PAN Zeye^{2
, ,},
WEI Yifan²,
CHEN Jie²

1.
State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines, Anhui University of Science and Technology, Huainan 232001, China
2.
School of Mechanical and Electrical Engineering, Anhui University of Science and Technology, Huainan 232001, China

摘要

摘要: 基于重介选煤、跳汰选煤、浮选、干法选煤、γ射线检测法的煤矸分选方法投资成本高、分选效率低、环境污染严重，基于CCD相机的煤矸分选方法准确率不高，基于X射线的煤矸分选技术会危害工作人员的健康。红外热成像技术不受光照、粉尘影响，且不会对人体造成伤害。提出了一种基于红外热成像的煤矸识别方法。首先，煤和矸石在传送带的输送下经过加热区域，红外热成像仪监测经均匀加热后的煤和矸石中心点的温度，得到煤和矸石加热后的温度并对经加热区域均匀加热后的煤和矸石进行拍摄，得到煤和矸石的红外灰度图像和红外彩色图像。然后，选用高斯滤波对煤和矸石的红外灰度图像、红外彩色图像进行预处理并提取特征，将红外灰度图像的灰度均值、最大频数对应的灰度值特征和红外彩色图像的G通道一阶矩、G通道二阶矩特征作为分选特征，将上述4个特征作为分类模型的输入。最后，采用支持向量机（SVM）进行分类识别，从而达到识别煤和矸石的目的。实验结果表明：基于红外热成像的煤矸识别方法对烟煤、无烟煤、褐煤的分选准确率均达到了98%以上，有良好的分类效果。
- 煤矸识别 /
- 红外热成像 /
- 红外灰度图像 /
- 红外彩色图像 /
- 灰度均值 /
- SVM /
- 图像预处理
Abstract: Coal and gangue sorting methods based on heavy-medium coal selection technology, jigging technology, flotation technology, dry coal selection technology and γ-ray detection method have high investment costs, low sorting efficiency and serious environmental pollution. The accuracy of the coal gangue sorting method based on CCD cameras is not high, and the X-ray based coal gangue sorting technology can harm the health of personnel. Infrared thermal imaging technology has the advantage of being unaffected by light and dust, and will not cause harm to the human body. A coal gangue recognition method based on infrared thermal imaging has been proposed. Firstly, coal and gangue pass through the heating area under the conveyor belt, and the temperature of the center point of coal and gangue is monitred through an infrared thermal imager to obtain the temperature of the heated coal and gangue. The infrared thermal imager is used to capture the uniformly heated coal and gangue in the heating area, obtaining infrared grayscale and color images of the coal and gangue. Secondly, Gaussian filtering is used to preprocess and extract features from the infrared grayscale images and infrared color images of coal and gangue. The grayscale mean of the infrared grayscale image, the grayscale value feature corresponding to the maximum frequency, and the G-channel first-order moment and G-channel second-order moment features of the infrared color image are used as sorting features. The above four features are used as inputs for the classification model. Finally, support vector machine (SVM) is used for classification and recognition to achieve the goal of recognizing coal and gangue. The experimental results show that the coal gangue recognition method based on infrared thermal imaging has achieved an accuracy rate of over 98% for the sorting of bituminous coal, anthracite, and lignite, and has a good classification effect.
- coal gangue recognition /
- infrared thermal imaging /
- infrared grayscale image /
- infrared color images /
- grayscale mean /
- SVM /
- image preprocessing

HTML全文

图 1 煤矸识别红外热成像实验装置

Figure 1. Experimental device for coal and gangue recognition

下载: 全尺寸图片幻灯片

图 2 煤矸加热后温度

Figure 2. Temperature of coal and gangue after heating

下载: 全尺寸图片幻灯片

图 3 煤矸样本图像

Figure 3. Images of coal and gangue samples

下载: 全尺寸图片幻灯片

图 4 煤样本图像的不同滤波处理结果

Figure 4. Results of different filtering process for a coal sample image

下载: 全尺寸图片幻灯片

图 5 矸石图像滤波结果

Figure 5. Gangue image filtering results

下载: 全尺寸图片幻灯片

图 6 灰度均值和最大频数对应的灰度值的分布曲线

Figure 6. Distribution curves of the grayscale mean and the gray value corresponding to the maximum frequency number

下载: 全尺寸图片幻灯片

图 7 煤矸石图像纹理特征的分布曲线

Figure 7. Distribution curves of texture features of coal and gangue images

下载: 全尺寸图片幻灯片

图 8 具有高区分度的煤矸石图像颜色特征分布曲线

Figure 8. Distribution curves of highly distinguishable colour features of coal and gangue images

下载: 全尺寸图片幻灯片

图 9 特征选择结果

Figure 9. Feature selection results

下载: 全尺寸图片幻灯片

表 1 煤矸石图像滤波结果

Table 1. Filtering results for coal and gangue images

滤波方式	煤图像		矸石图像
滤波方式	MSE	PSNR	MSE	PSNR
高斯滤波	7.1382	39.5949	1.9222	45.2929
中值滤波	7.4326	39.4194	2.3143	44.4865
均值滤波	17.9601	35.5877	9.7932	38.2216

下载: 导出CSV

表 2 煤矸石图像灰度特征分布范围

Table 2. Range of grayscale feature distribution of coal and gangue images

样本	灰度均值	灰度方差	最大频数对应的灰度值	偏度
煤	89.8～163.3	106.9～3301.7	91.0～195.0	−1.8～0.7
矸石	5.4～46.7	9.4～553.6	1.0～67.0	−1.1～2.2

下载: 导出CSV

表 3 煤矸石图像纹理特征参数的分布范围

Table 3. Distribution range of texture feature parameters of coal and gangue images

样本	熵	对比度	相关性	能量	同质性
煤	5.2～7.1	0.03～0.14	0.97～0.99	0.11～0.30	0.93～0.98
矸石	3.2～6.2	0.03～0.25	0.93～0.99	0.11～0.36	0.88～0.98

下载: 导出CSV

表 4 煤矸图像颜色特征参数分布

Table 4. Distribution of colour features of coal and gangue images

样本	R通道一阶矩	G通道一阶矩	B通道一阶矩	R通道二阶矩	G通道二阶矩	B通道二阶矩
煤	12.5～133.9	72.8～152.6	3.9～185.9	23.3～88.6	32.3～83.1	9.1～89.2
矸石	39.1～177.2	0.5～1.9	38.0～188.7	13.2～71.9	0.8～9.1	13.5～75.2

下载: 导出CSV

表 5 部分样本的特征

Table 5. Characteristics of selected samples

样本序号	H₂	C₂	C₁	H₁
煤1	147	59.95	108.14	118.39
煤2	131	46.28	116.56	122.03
煤3	195	62.22	108.43	153.84
煤4	158	58.30	118.04	117.38
矸石1	9	1.77	1.25	10.89
矸石2	17	1.47	1.02	23.03
矸石3	11	1.79	1.23	13.02
矸石4	27	1.40	0.98	29.97

下载: 导出CSV

参考文献(22)

[1]	谢和平,王金华,王国法,等. 煤炭革命新理念与煤炭科技发展构想[J]. 煤炭学报,2018,43(5):1187-1197. XIE Heping,WANG Jinhua ,WANG Guofa,et al. New ideas of coal revolution and layout of coal science and technology development[J]. Journal of China Coal Society,2018,43(5):1187-1197.
[2]	陆小泉. 我国煤炭清洁开发利用现状及发展建议[J]. 煤炭工程,2016,48(3):8-10,14. LU Xiaoquan. Present situation and suggestion for clean coal development and utilization in China[J]. Coal Engineering,2016,48(3):8-10,14.
[3]	常允新,朱学顺,宋长斌,等. 煤矸石的危害与防治[J]. 中国地质灾害与防治学报,2001(2):39-43. CHANG Yunxin,ZHU Xueshun,SONG Changbin,et al. Hazard of gangue and its control[J]. The Chinese Journal of Geological Hazard and Control,2001(2):39-43.
[4]	潘荣锟,余明高,徐俊,等. 矸石山的危害及自燃原因关联分析[J]. 安全与环境工程,2006(2):66-69. PAN Rongkun,YU Minggao,XU Jun,et al. Harm of gangue dump and cause analysis of spontaneous combustion[J]. Safety and Environmental Engineering,2006(2):66-69.
[5]	SAHU L,DEY S. Enrichment of carbon recovery of high ash coal fines using air fluidized vibratory deck separator[J]. International Journal of Coal Science & Technology,2017,4(3):262-273.
[6]	ZHAO Yuemin,YANG Xuliang,LUO Zhenfu,et al. Progress in developments of dry coal beneficiation[J]. International Journal of Coal Science & Technology,2014,1(1):103-112.
[7]	GUPTA N. Evaluation of pneumatic inclined deck separator for high-ash Indian coals[J]. International Journal of Coal Science & Technology,2016,3(2):198-205.
[8]	梁金钢,赵环帅,何建新. 国内外选煤技术与装备现状及发展趋势[J]. 选煤技术,2008(1):60-64,76. LIANG Jin'gang,ZHAO Huanshuai,HE Jianxin. Current status and development trends of coal preparation technology and equipment both in domestic and overseas[J]. Coal Preparation Technology,2008(1):60-64,76.
[9]	王家臣,李良晖,杨胜利. 不同照度下煤矸图像灰度及纹理特征提取的实验研究[J]. 煤炭学报,2018,43(11):3051-3061. WANG Jiachen,LI Lianghui,YANG Shengli. Experimental study on gray and texture features extraction of coal and gangue image under different illuminance[J]. Journal of China Coal Society,2018,43(11):3051-3061.
[10]	吴开兴,宋剑. 基于灰度共生矩阵的煤与矸石自动识别研究[J]. 煤炭工程,2016,48(2):98-101. WU Kaixing,SONG Jian. Automatic coal-gangue identification based on gray level co-occurrence matrix[J]. Coal Engineering,2016,48(2):98-101.
[11]	郭永存,何磊,刘普壮,等. 煤矸双能X射线图像多维度分析识别方法[J]. 煤炭学报,2021,46(1):300-309. GUO Yongcun,HE Lei,LIU Puzhuang,et al. Multi-dimensional analysis and recognition method of coal and gangue dual-energy X-ray images[J]. Journal of China Coal Society,2021,46(1):300-309.
[12]	王文鑫,黄杰,王秀宇,等. X射线透射煤矸智能识别方法[J]. 工矿自动化,2022,48(11):27-32,62. WANG Wenxin,HUANG Jie,WANG Xiuyu,et al. X-ray transmission intelligent coal-gangue recognition method[J]. Journal of Mine Automation,2022,48(11):27-32,62.
[13]	张志强,王萍,于旭东,等. 高精度红外热成像测温技术研究[J]. 仪器仪表学报,2020,41(5):10-18. ZHANG Zhiqiang,WANG Ping,YU Xudong,et al. Study on high accuracy temperature measurement technology of infrared thermal imager[J]. Chinese Journal of Scientific Instrument,2020,41(5):10-18.
[14]	WANG Shixue,LI Kaixiang,TIAN Yuan,et al. Infrared imaging investigation of temperature fluctuation and spatial distribution for a large laminated lithiumion power battery[J]. Applied Thermal Engineering,2019,152:204-214. doi: 10.1016/j.applthermaleng.2019.02.096
[15]	PAN Dong,JIANG Zhaohui,CHEN Zhipeng,et al. Compensation method for molten iron temperature measurement based on heterogeneous features of infrared thermal images[J]. IEEE Transactions on Industrial Informatics,2020,16(11):7056-7066. doi: 10.1109/TII.2020.2972332
[16]	LI Yiwen,ZHANG Puyousen,CHEN Ge,et al. Study on method for measuring coating emissivity by applying active irradiation based on infrared thermal imager[J]. Sensors,2022,22(6):2392. doi: 10.3390/s22062392
[17]	孙继平. 基于图像识别的煤岩界面识别方法研究[J]. 煤炭科学技术,2011,39(2):77-79. SUN Jiping. Study on identified method of coal and rock interface based on image identification[J]. Coal Science and Technology,2011,39(2):77-79.
[18]	刘闯. 综放工作面多放煤口协同放煤方法及煤岩识别机理研究[D]. 焦作:河南理工大学,2018. LIU Chuang. Research on the method of synergetic multi-windows top coal caving and the mechanism of coal-gangue identification in longwall top coal caving working face[D]. Jiaozuo:Henan Polytechnic University,2018.
[19]	张强,孙绍安,张坤,等. 基于主动红外激励的煤岩界面识别[J]. 煤炭学报,2020,45(9):3363-3370. ZHANG Qiang,SUN Shao'an,ZHANG Kun,et al. Coal and rock interface identification based on active infrared excitation[J]. Journal of China Coal Society,2020,45(9):3363-3370.
[20]	马娜,张洪潮,周新. 红外热成像技术在煤矿生产中的应用[J]. 煤炭技术,2021,40(2):130-132. MA Na,ZHANG Hongchao,ZHOU Xin. Application of infrared thermal imaging technology in coal mine production[J]. Coal Technology,2021,40(2):130-132.
[21]	张志强,王萍,于旭东,等. 高精度红外热成像测温技术研究[J]. 仪器仪表学报,2020,41(5):10-18. ZHANG Zhiqiang,WANG Ping,YU Xudong,et al. Study on high accuracy temperature measurement technology of infrared thermal imager[J]. Chinese Journal of Scientific Instrument,2020,41(5):10-18.
[22]	沈虎祥. 某污水处理厂提标工程的运行分析及出水水质预测模拟研究[J]. 苏州科技大学学报(工程技术版),2023,36(2):46-54. SHEN Huxiang. Operation analysis of upgrading project and simulation study on effluent quality prediction of a sewage treatment plant[J]. Journal of Suzhou University of Science and Technology(Engineering and Technology Edition),2023,36(2):46-54.