基于分峰思想的煤岩显微组分识别与统计分析

doi:10.16180/j.cnki.issn1007-7820.2023.04.002

Abstract

Abstract:

In view of the low accuracy of the existing methods to identify coal macerals, a method for identifying and statistical analysis of coal macerals based on the idea of peak splitting is proposed in this study. The peak offset range of vitrinite of each coal type is determined from the point of view of individual particle, and an adaptive peak finding algorithm is proposed to select the effective peak point of coal and rock particles. In the coal macerals identification stage, the multi-strategy peak position identification algorithm is designed to classify the coal and rock particles into active-inert particles requiring peak clustering and pure vitrinite particles, inertinite particles and exinite particles without peak clustering, and the peak positions of coal and rock particles requiring peak clustering are selected. Then, Gaussian fitting is carried out based on peak splitting rules and statistical methods to determine the threshold values of exinite, vitrinite, and inertinite respectively, and complete the clustering and segmentation of coal and rock particles. The experimental results show that the proposed method can effectively identify single coal particles and realize quantitative statistics of maceral content, with an accuracy of 96.85% and the minimum entropy of 0.615 3. Compared with the traditional method, the proposed method has higher accuracy and has better practical application significance.

Key words: coal macerals, the idea of peak splitting, statistical analysis method, adaptive peak finding algorithm, coal and rock particles, multi-strategy, peak splitting rules, Gaussian fitting, clustering

CLC Number:

TQ531

CHEN Chun,SHU Huisheng,KAN Xiu,SUN Weizhou. Identification and Statistical Analysis of Coal Macerals Based on the Idea of Peak Splitting[J].Electronic Science and Technology, 2023, 36(4): 9-20.

Figures/Tables 23

Figure 1.

Table 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Table 2.

Table 3.

Figure 6.

Table 4.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

算法1 基于多策略的分峰峰位识别算法

输入:各煤岩颗粒γ的反射率分布标准差std,通过自适应寻峰算法选取的所有有效峰(x_pj,y_pj),j=1,2,…,v。v为峰的个数。令镜质组峰偏移范围为[α, β],且峰位值为η。其中,E表示壳质组颗粒,V表示镜质组颗粒,I表示惰质组颗粒,B表示活惰结合颗粒。
输出:煤岩颗粒γ的所属类别,需要分峰的分峰峰位点(

x p b,

y_pb)。
if std≤0.2 and ν=1:
γ ∈ V
end if
if (std≤0.2 and ν>1) or std>0.2:
if $ j_k ∈ [1, ν],k=1,2,…,u,

x p j k

∈ [α, β]:
if ν=1:
γ ∈ V
else:
let x_pc=

x p j k 0

when

y p j k 0

=max{

y p j k

,k ∈ [1, u]}
if " k ∈ [1, u],k1k₀, max{

y p j k

,k∈ [1, u], k1k₀}<

y p j k 0

/2 :

γ∈ B and x_pb =x_pc
end if
if $ k_l ∈ [1, u],k_l1k₀, l∈ [1, w], min{

y p j k l

, k_l∈ [1, u], k_l1k₀,
l∈ [1, w]}≥

y p j k 0

/2 :
if abs(

x p j k 0

)- η=min{abs(

x p j k l

)- η, k_l∈ [1, u],k_l1k₀,
l∈ [1, w]} :
then γ ∈ B and x_pb =

x p j k 0

end if
end if
else:
if " j ∈ [1, v],

x p j

< α:
γ∈ E
elif " j ∈ [1, v],

x p j

> β:
γ ∈ I
else:
γ∈ B and x_pb =min{

x p j k

, j_k[1, v], k ∈ [1, u]}
end if
end if
end if
输出煤岩颗粒γ的所属类别,需要分峰的分峰峰位点(x_pb, y_pb)。

Figure 12.

Figure 13.

Table 5.

Figure 14.

Table 6.

Figure 15.

Figure 16.

References 22

[1]	边春杨, 徐秀丽, 姜雨. 煤岩显微组分对焦炭性能影响的研究进展[J]. 煤炭加工与综合利用, 2021(9):82-85.
	Bian Chunyang, Xu Xiuli, Jiang Yu. Research progress on the influence of coal maceral on coke properties[J]. Coal Processing & Comprehensive Utilization, 2021(9):82-85.
[2]	李明珠, 艾福龙. 煤岩在炼焦配煤中的应用[J]. 冶金能源, 2021, 40(4):14-16.
	Li Mingzhu, Ai Fulong. Application of coal rock in coal blending[J]. Energy for Metallurgical Industry, 2021, 40(4):14-16.
[3]	李涛, 方田, 韩永宁, 等. 煤岩自动测试技术浅谈[J]. 冶金能源, 2016, 35(3):57-60.
	Li Tao, Fang Tian, Han Yongning, et al. Coal petrologic automatic test technology[J]. Energy for Metallurgical Industry, 2016, 35(3):57-60.
[4]	王越, 白向飞, 曲思建. 煤岩显微组分自动识别技术研究进展[J]. 煤质技术, 2021, 36(1):49-57.
	Wang Yue, Bai Xiangfei, Qu Sijian. Research progress on automatic coal maceral identification[J]. Coal Quality Technology, 2021, 36(1):49-57.
[5]	王培珍, 殷子睆, 王高, 等. 一种基于PCA与RBF-SVM的煤岩显微组分镜质组分类方法[J]. 煤炭学报, 2017, 42(4):977-984.
	Wang Peizhen, Yin Zihuan, Wang Gao, et al. A classification method of vitrinite for coal macerals based on the PCA and RBF-SVM[J]. Journal of China Coal Society, 2017, 42(4):977-984.
[6]	王培珍, 任将, 杜存铃, 等. 基于Tamura纹理特征的煤岩壳质组显微组分分类[J]. 安徽工业大学学报(自然科学版), 2018, 35(2):131-136.
	Wang Peizhen, Ren Jiang, Du Cunling, et al. Classification of macerals in exinite of coal based on Tamura features[J]. Journal of Anhui University of Technology(Natural Science), 2018, 35(2):131-136.
[7]	王培珍, 翟羽佳, 王慧, 等. 基于曲波变换和压缩感知的煤岩惰质组分类[J]. 中国矿业大学学报, 2019, 48(5):1119-1125.
	Wang Peizhen, Zhai Yujia, Wang Hui, et al. Classification for inertinite of coal based on curvelet transform and compressive sensing[J]. Journal of China University of Mining & Technology, 2019, 48(5):1119-1125.
[8]	Wang H, Lei M, Li M, et al. Intelligent estimation of vitrinite reflectance of coal from photomicrographs based on machine learning[J]. Energies, 2019, 12(20):3855-3855. doi: 10.3390/en12203855
[9]	王洪栋. 基于机器学习的煤岩显微图像分析研究[D]. 徐州: 中国矿业大学, 2019.
	Wang Hongdong. Research on photomicrograph analysis of coal based on machine learning[D]. Xuzhou: China University of Mining and Technology, 2019.
[10]	宋孝忠. 煤岩显微图像假边界对显微组分组自动识别的影响[J]. 煤田地质与勘探, 2019, 47(6):45-50.
	Song Xiaozhong. Effect of false boundary of microscopic image on automatic identification of maceral group[J]. Coal Geology & Exploration, 2019, 47(6):45-50.
[11]	宋孝忠, 张群. 煤岩显微组分组图像自动识别系统与关键技术[J]. 煤炭学报, 2019, 44(10):3085-3097.
	Song Xiaozhong, Zhang Qun. Automatic image recognition system and key technologies of maceral group[J]. Journal of China Coal Society, 2019, 44(10):3085-3097.
[12]	宋孝忠. 烟煤显微组分组图像自动识别技术研究及应用[D]. 北京: 煤炭bepaly手机下载总院, 2020.
	Song Xiaozhong. Research and application of automatic image recognition technology for maceral groups in bituminous coal[D]. Beijing: China Coal Research Institute, 2020.
[13]	邹丹平, 冯涛, 李咸伟, 等. 基于EM的直方图逼近及其应用[J]. 中国图象图形学报, 2005, 10(11):1458-1461.
	Zou Danping, Feng Tao, Li Xianwei, et al. Histogram approximation based on expectation maximization and its application[J]. Journal of Image and Graphics, 2005, 10(11):1458-1461.
[14]	O'Brien G, Jenkins B, Esterle J, et al. Coal characterisation by automated coal petrography[J]. Fuel, 2003, 82(9):1067-1073. doi: 10.1016/S0016-2361(02)00428-3
[15]	闫超, 孙占全, 田恩刚, 等. 基于深度学习的医学图像分割技术研究进展[J]. 电子科技, 2021, 34(2):7-11.
	Yan Chao, Sun Zhanquan, Tian Engang, et al. Research progress of medical image segmentation based on deep learning[J]. Electronic Science and Technology, 2021, 34(2):7-11.
[16]	刘婕梅. 基于卷积神经网络的煤岩壳质组显微图像多组分识别[D]. 马鞍山: 安徽工业大学, 2019.
	Liu Jiemei. CNN based multi-component recognition of coal exinite microscopic image[D]. Ma'anshan: Anhui University of Technology, 2019.
[17]	吴德忠, 刘泉声, 黄兴, 等. 基于边界跟踪和神经网络的煤岩界面识别方法研究[J]. 煤炭工程, 2021, 53(6):140-146.
	Wu Dezhong, Liu Quansheng, Huang Xing, et al. Coal-rock interface recognition method based on boundary tracking algorithm and artificial neural network[J]. Coal Engineering, 2021, 53(6):140-146.
[18]	王越, 白向飞, 张宇宏, 等. 煤岩自动测试系统图像灰度与反射率关系研究[J]. 煤炭转化, 2014, 37(2):25-27.
	Wang Yue, Bai Xiangfei, Zhang Yuhong, et al. Relationship between gray value of images and reflectance in automatic coal petrography[J]. Coal Conversion, 2014, 37(2):25-27.
[19]	陈洪博, 白向飞, 李振涛, 等. 图像法测定煤岩组分反射率工作曲线的建立与应用[J]. 煤炭学报, 2014, 39(3):562-567.
	Chen Hongbo, Bai Xiangfei, Li Zhentao, et al. Working curve establishing and application of determining maceral reflectance by image analysis method[J]. Journal of China Coal Society, 2014, 39(3):562-567.
[20]	贺佳, 史永林, 李昊堃, 等. 炼焦煤镜质体反射率及其分布图辨识与分析[J]. 中国冶金, 2021, 31(6):45-53.
	He Jia, Shi Yonglin, Li Haokun, et al. Identification and analysis of vitrinite reflectance and its distribution of coking coal[J]. China Metallurgy, 2021, 31(6):45-53.
[21]	袁小翠, 黄志开, 马永力, 等. Otsu阈值分割法特点及其应用分析[J]. 南昌工程学院学报, 2019, 38(1):85-90.
	Yuan Xiaocui, Huang Zhikai, Ma Yongli, et al. Analysis of characteristics and application of Otsu threshold method[J]. Journal of Nanchang Institute of Technology, 2019, 38(1):85-90.
[22]	李凯勇. 基于数据挖掘的图像特征分割技术[J]. 现代电子技术, 2020, 43(15):60-64.
	Li Kaiyong. Image feature segmentation technology based on data mining[J]. Modern Electronics Technique, 2020, 43(15):60-64.

煤岩批次	煤岩编号	标定灰度	标定反射率/%	反射率关系式
1	C₁	87	0.591	g=6 061x+52.00
	C₂	108	0.905
	C₃	156	1.721
	C₄	156	1.721
2	C₅	94	0.591	g=5 966x+59.61
	C₆	115	0.905
	C₇	162	1.721
3	C₈	89	0.591	g=5 966x+54.69
	C₉	110	0.905
	C₁₀	157	1.721

编号	颗粒类别	形态特征	占比
1	纯镜质组颗粒	表面平滑,std低	较多
2	纯壳质组颗粒	表面平滑,std低	很少
3	纯惰质组颗粒	表面突兀,std高	较多
4	壳质组-镜质组-惰质组颗粒	表面较突兀,std较高	多
5	镜质组-惰质组颗粒	表面较突兀,std较高	多
6	壳质组-镜质组颗粒	表面平滑,std低	较多
7	壳质组-惰质组颗粒	表面较突兀,std较高	少

定义	说明
n	总数据点个数
w₁	窗长
μ	在一个窗长w₁内,满足峰值条件的最大半宽与窗长半宽的比例

定义	说明
n	总数据点个数
w₂	窗长
θ	在一个窗长w₂内,满足拐点定义的条件下,左右端点相对拐点的导数平均变化率

镜质组峰位	正态分布最大标准差
≤ 1.0%	0.10
> 1.0%	0.12

Identification and Statistical Analysis of Coal Macerals Based on the Idea of Peak Splitting

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 23

References 22

Related Articles 15

Metrics

Comments

Recommended 10

方法	准确率/%	纯度/%	熵
多阈值Otsu法	73.73	86.41	0.726 1
K-means算法	83.77	89.33	0.680 5
本文算法	96.85	90.28	0.615 3

[1]	CHENG Shunda,CHENG Ying,SUN Shijiang. Tumor Intelligent Auxiliary Diagnosis Method Based on Machine Learning [J]. Electronic Science and Technology, 2022, 35(5): 56-59.
[2]	JIN Xiao,WU Fei,YAN Song,LU Wenxia,ZHANG Zhongyi. Fingerprint Location Method of Metro Station Based on GAWK-means [J]. Electronic Science and Technology, 2022, 35(2): 34-39.
[3]	DUAN Jundong,HUANG Hongye,WANG Shuaiqiang. EV Clustering Optimization Community Load Strategy Based on Flexible Optimization Mechanism [J]. Electronic Science and Technology, 2022, 35(12): 64-71.
[4]	FANG Kai,SHI Zhicai,JIA Yuanyuan. K-Anonymity Data Publishing Algorithm Based on Hybrid Clustering [J]. Electronic Science and Technology, 2022, 35(12): 78-83.
[5]	LIN Jing,HU Demin,WANG Kuihao. Differential Privacy Fuzzy Clustering Location Protection Method [J]. Electronic Science and Technology, 2022, 35(11): 64-71.
[6]	XU Hangfan,LIU Cong,TANG Jiangang,PENG Dunlu. Accelerated Spectral Clustering Based on Improved Landmark Selection [J]. Electronic Science and Technology, 2021, 34(5): 47-53.
[7]	ZHANG Tianhao,LI Haolin. A Method of Laser Center Extraction Based on Gaussian Fitting [J]. Electronic Science and Technology, 2020, 33(5): 72-76.
[8]	YANG Shanshan,ZHANG Daxing,GUO Jiawei,WANG Shitiao. Copy-move Detection Algorithm Combining Keypoints and Block Advantages [J]. Electronic Science and Technology, 2020, 33(3): 38-43.
[9]	MIAO Ran,LI Feifei,CHEN Qiu. Scene Recognition Algorithm Based on Convolutional Neural Networks and Multi-Scale space Encoding [J]. Electronic Science and Technology, 2020, 33(12): 54-58.
[10]	LAN Jiman. Design of Data Mining System Based on Cloud Computing [J]. Electronic Science and Technology, 2019, 32(8): 70-74.
[11]	ZHANG Changqing,YANG Nan. Design of Real-time Road Condition Detection System Based on Big Data Analysis of Vehicle Network [J]. Electronic Science and Technology, 2019, 32(8): 66-70.
[12]	SUN Zhen,WANG Kai,WANG Yagang. A Modified Routing Algorithm Based on Time Competition Clustering [J]. Electronic Science and Technology, 2019, 32(8): 27-32.
[13]	LI Qi,ZHANG Xin,ZHANG Pingkang,ZHANG Hang. Improved CFSFDP Algorithm Based on Spark Framework [J]. Electronic Science and Technology, 2019, 32(5): 38-44.
[14]	ZHANG Yurun,WU Fei,MAO Wankui. Indoor Location Algorithm Based on WiFi-geomagnetism [J]. Electronic Science and Technology, 2019, 32(5): 49-54.
[15]	WANG Kang,WU Chunxue. A Busy Coefficient Based on Dual Cluster Head Algorithm of Adaptive WSN for Energy Consumption Optimization [J]. Electronic Science and Technology, 2019, 32(2): 56-60.