A method for predicting the tar yield of tar-rich coals based on the BP neural network using multiple indicators of coal petrography and coal quality

Authors

QIAO Junwei, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China Shaanxi; Provincial Key Laboratory of Geological Support for Coal Green Exploitation, Xi’an University of Science and Technology, Xi’an 710054, China; Geological Research Institute for Coal Green Mining, Xi’an University of Science and Technology, Xi’an 710054, ChinaFollow
WANG Changjian, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China
ZHAO Hongchao, Shaanxi Coal and Chemical Industry Group Co. Ltd., Xi’an 710100, China
SHI Qingmin, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China Shaanxi; Provincial Key Laboratory of Geological Support for Coal Green Exploitation, Xi’an University of Science and Technology, Xi’an 710054, China; Geological Research Institute for Coal Green Mining, Xi’an University of Science and Technology, Xi’an 710054, China
ZHANG Yu, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China
FAN Qi, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China
WANG Duo, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China
YUAN Dandan, College of Geology and Environment, Xi’an University of Science and Technology, Xi’an 710054, China

Abstract

Objective Tar yield, the most important coal quality parameter for coal utilization through low-temperature pyrolysis, determines the clean utilization of tar-rich coals. However, various constraints result in limited test data on tar yield in the geological exploration stage of coals, substantially restricting the fine-scale assessment and efficient utilization of tar-rich coals. Methods To achieve more scientific and accurate fine-scale tar-rich coal assessments, this study examined 1073 sets of lithotype and coal quality data obtained previously from a Jurassic coalfield in northern Shaanxi. From these data, 141 sets with 20 lithotype and coal quality parameters regarding macerals, proximate analysis, ultimate analysis, and ash composition analysis were selected. Then, employing the back propagation (BP) neural network algorithm, this study constructed two tar yield prediction models based on 20 lithotype and coal quality indices and four proximate analysis indices each (also referred to as the first and second models, respectively). Finally, it assessed the accuracy and rationality of the results of both prediction models. Results and Conclusions The results are as follows: (1) The first model exhibited a mean square error (MSE) of 0.30 in the final training and a mean absolute error (MAE) of 0.65 for the prediction results of the test set data. In contrast, the second model yielded a MSE of 1.07 in the final training, with a MAE of 1.35 for the prediction results of the test set data. For the prediction results of the superset data, the first and second models yielded MAEs of 0.84 and 1.34, respectively, suggesting that the first model features higher goodness of fit and generalization performance. (2) The importance of 20 lithotype and coal quality indices in the first prediction model was further quantitatively analyzed using the Shapley additive explanation (SHAP) algorithm. The results reveal that factors including vitrinite, hydrogen and carbon elements, Fe₂O₃, moisture, volatile constituents, exinite, and oxygen content prove to be the positive factors influencing the tar yield, whereas Al₂O₃, inertinite, fixed carbon, ash content, and SiO₂ content serve as negative factors influencing the tar yield. The intrinsic relationships between both the lithotype and coal quality and the tar yield, derived from the first model, align well with the general understanding of the geological factors influencing the tar yield. Therefore, the first prediction model can effectively predict the tar yield of the Jurassic coalfield in northern Shaanxi, providing support for the clean and efficient utilization of tar-rich coals in northern Shaanxi.

Keywords

tar yield, back propagation (BP) neural network, machine learning, tar-rich coal, Jurassic coalfield in northern Shaanxi

DOI

10.12363/issn.1001-1986.23.12.0860

Recommended Citation

QIAO Junwei, WANG Changjian, ZHAO Hongchao, et al. (2024) "A method for predicting the tar yield of tar-rich coals based on the BP neural network using multiple indicators of coal petrography and coal quality," Coal Geology & Exploration: Vol. 52: Iss. 7, Article 12.
DOI: 10.12363/issn.1001-1986.23.12.0860
Available at: https://cge.researchcommons.org/journal/vol52/iss7/12

Reference

[1] 王双明，刘浪，赵玉娇，等. “双碳” 目标下赋煤区新能源开发：未来煤矿转型升级新路径[J]. 煤炭科学技术，2023，51(1)：59−79.

WANG Shuangming，LIU Lang，ZHAO Yujiao，et al. New energy exploitation in coal-endowed areas under the target of “double carbon”：A new path for transformation and upgrading of coal mines in the future[J]. Coal Science and Technology，2023，51(1)：59−79.

[2] LI Guangyu，WANG Luping，WANG Chaowei，et al. Experimental study on coal gasification in a full-scale two-stage entrained-flow gasifier[J]. Energies，2020，13(18)：4937.

[3] 王双明，申艳军，宋世杰，等. “双碳” 目标下煤炭能源地位变化与绿色低碳开发[J]. 煤炭学报，2023，48(7)：2599−2612.

WANG Shuangming，SHEN Yanjun，SONG Shijie，et al. Change of coal energy status and green and low-carbon development under the “dual carbon” goal[J]. Journal of China Coal Society，2023，48(7)：2599−2612.

[4] 马丽，王双明，段中会，等. 陕西省富油煤资源潜力及开发建议[J]. 煤田地质与勘探，2022，50(2)：1−8.

MA Li，WANG Shuangming，DUAN Zhonghui，et al. Potential of oil-rich coal resources in Shaanxi Province and its new development suggestion[J]. Coal Geology & Exploration，2022，50(2)：1−8.

[5] 王双明，王虹，任世华，等. 西部地区富油煤开发利用潜力分析和技术体系构想[J]. 中国工程科学，2022，24(3)：49−57.

WANG Shuangming，WANG Hong，REN Shihua，et al. Potential analysis and technical conception of exploitation and utilization of tar-rich coal in western China[J]. Strategic Study of CAE，2022，24(3)：49−57.

[6] 马丽，段中会，杨甫，等. “双碳” 背景下煤炭原位地下热解采油意义研究[J]. 中国煤炭地质，2022，34(4)：5−7.

MA Li，DUAN Zhonghui，YANG Fu，et al. Study on the significance of coal in situ underground pyrolytic oil production under carbon peaking and carbon neutrality background[J]. Coal Geology of China，2022，34(4)：5−7.

[7] 曹代勇，魏迎春，宁树正. 绿色煤炭基础地质工作框架刍议[J]. 煤田地质与勘探，2018，46(3)：1−5.

CAO Daiyong，WEI Yingchun，NING Shuzheng. The framework of basic geological works for green coal[J]. Coal Geology & Exploration，2018，46(3)：1−5.

[8] 杜芳鹏，李聪聪，乔军伟，等. 陕北府谷矿区煤炭资源清洁利用潜势及方式探讨[J]. 煤田地质与勘探，2018，46(3)：11−14.

DU Fangpeng，LI Congcong，QIAO Junwei，et al. Discussion on the potential and way of clean utilization of coal resources in Fugu mining area，northern Shaanxi[J]. Coal Geology & Exploration，2018，46(3)：11−14.

[9] 乔军伟，宁树正，秦云虎，等. 特殊用煤研究进展及工作前景[J]. 煤田地质与勘探，2019，47(1)：49−55.

QIAO Junwei，NING Shuzheng，QIN Yunhu，et al. The research progress and work prospect of special purpose coal[J]. Coal Geology & Exploration，2019，47(1)：49−55.

[10] 王双明，师庆民，王生全，等. 富油煤的油气资源属性与绿色低碳开发[J]. 煤炭学报，2021，46(5)：1365−1377.

WANG Shuangming，SHI Qingmin，WANG Shengquan，et al. Resource property and exploitation concepts with green and low-carbon of tar-rich coal as coal-based oil and gas[J]. Journal of China Coal Society，2021，46(5)：1365−1377.

[11] TANNER J，KABIR K B，MÜLLER M，et al. Low temperature entrained flow pyrolysis and gasification of a Victorian brown coal[J]. Fuel，2015，154：107−113.

[12] 樊义龙，王宁波，徐红东，等. 低温煤焦油产率和性质影响因素的研究[J]. 洁净煤技术，2010，16(6)：36−39.

FAN Yilong，WANG Ningbo，XU Hongdong，et al. Analysis influencing factors of yield and properties of low-temperature tar[J]. Clean Coal Technology，2010，16(6)：36−39.

[13] 宁树正，张莉，徐小涛，等. 新疆北部早、中侏罗世富油煤分布规律及控制因素[J]. 煤炭科学技术，2024，52(1)：244−254.

NING Shuzheng，ZHANG Li，XU Xiaotao，et al. Distribution of early and middle Jurassic tar-rich coal and its geological controls in northern Xinjiang[J]. Coal Science and Technology，2024，52(1)：244−254.

[14] 田瀚，冯周，王金锋，等. 陕西省煤岩焦油产率测井评价方法研究 [J/OL]. 地球物理学进展：1–13[2024-05-08]. http://kns.cnki.net/kcms/detail/11.2982.P.20231109.1731.014.html.

TIAN Han，FENG Zhou，WANG Jinfeng，et al. Study on logging evaluation method of coal tar yield in Shaanxi Province[J/OL]. Progress in Geophysics：1–13[2024-05-08]. http://kns.cnki.net/kcms/detail/11.2982.P.20231109.1731.014.html.

[15] 师庆民，王双明，王生全，等. 神府南部延安组富油煤多源判识规律[J]. 煤炭学报，2022，47(5)：2057−2066.

SHI Qingmin，WANG Shuangming，WANG Shengquan，et al. Multi-source identification and internal relationship of tar-rich coal of the Yan’an Formation in the south of Shenfu[J]. Journal of China Coal Society，2022，47(5)：2057−2066.

[16] 郭晨，王生全，师庆民，等. 神府南部矿区低阶煤化学组成与工艺性质：特征、关系与实践[J]. 煤田地质与勘探，2021，49(1)：87−99.

GUO Chen，WANG Shengquan，SHI Qingmin，et al. Chemical compositions and technological properties of low-rank coals in the South Shenfu mining area：Characteristics，relationship and practice[J]. Coal Geology & Exploration，2021，49(1)：87−99.

[17] 师庆民，耿旭虎，王双明，等. 基于煤体真密度和自然伽马响应规律的富油煤判识[J/OL]. 煤田地质与勘探：1–11[2024-05-08]. http://kns.cnki.net/kcms/detail/61.1155.p.20231129.1114.002.html.

SHI Qingmin，GENG Xuhu，WANG Shuangming，et al. Identification of tar-rich coal based on true density and natural gamma response[J/OL]. Coal Geology & Exploration：1–11[2024-05-08]. http://kns.cnki.net/kcms/detail/61.1155.p.20231129.1114.002.html.

[18] 闫和平，段中会，王金锋. 黄陵矿区富油煤焦油产率与补偿密度关系模型预测方法研究[J]. 中国煤炭地质，2022，34(10)：25−30.

YAN Heping，DUAN Zhonghui，WANG Jinfeng. Study on the relationship model between oil-rich coal tar yield and compensation density in Huangling mining area[J]. Coal Geology of China，2022，34(10)：25−30.

[19] 赵军龙，闫和平，王金锋，等. 基于测井信息的煤焦油产率预测方法研究[J]. 地球物理学进展，2023，38(4)：1702−1712.

ZHAO Junlong，YAN Heping，WANG Jinfeng，et al. Research on coal tar productivity prediction method based on logging information[J]. Progress in Geophysics，2023，38(4)：1702−1712.

[20] 谢青，李宁，姚征，等. 黄陵矿区富油煤焦油产率特征及主控地质因素分析[J]. 中国煤炭，2020，46(11)：83−90.

XIE Qing，LI Ning，YAO Zheng，et al. Research on the tar yield characteristics and main control factors of tar-rich coal in Huangling mining area[J]. China Coal，2020，46(11)：83−90.

[21] 孙杰，邹卓，张莉，等. 新疆北部矿区煤中焦油产率分析及热解生油实验研究[J]. 中国煤炭地质，2023，35(5)：14−19.

SUN Jie，ZOU Zhuo，ZHANG Li，et al. Analysis of tar yield and experimental study on oil generation from coal pyrolysis in northern Xinjiang[J]. Coal Geology of China，2023，35(5)：14−19.

[22] 周永章，王俊，左仁广，等. 地质领域机器学习、深度学习及实现语言[J]. 岩石学报，2018，34(11)：3173−3178.

ZHOU Yongzhang，WANG Jun，ZUO Renguang，et al. Machine learning，deep learning and Python language in field of geology[J]. Acta Petrologica Sinica，2018，34(11)：3173−3178.

[23] 冯志威，马力，陈彦龙，等. 基于BP神经网络理论的岩石硬度识别[J]. 西安科技大学学报，2021，41(1)：121−127.

FENG Zhiwei，MA Li，CHEN Yanlong，et al. Rock hardness identification based on BP neural network theory[J]. Journal of Xi’an University of Science and Technology，2021，41(1)：121−127.

[24] 来兴平，万培烽，单鹏飞，等. 基于免疫粒子群混合算法优化BP网络的矿压预测方法[J]. 西安科技大学学报，2023，43(1)：1−8.

LAI. Xingping，WAN Peifeng，SHAN Pengfei，et al. Mine pressure prediction method based on immune algorithm-particle swarm optimization BP network[J]. Journal of Xi’an University of Science and Technology，2023，43(1)：1−8.

[25] 孔彪，朱思想，胡相明，等. 基于改进鲸鱼算法优化BP神经网络的煤自燃预测研究[J]. 矿业安全与环保，2023，50(5)：30−36.

KONG Biao，ZHU Sixiang，HU Xiangming，et al. Study on prediction of coal spontaneous combustion based on MSWOA-BP[J]. Mining Safety & Environmental Protection，2023，50(5)：30−36.

[26] 姚征，罗乾周，李宁，等. 陕北石炭–二叠纪富油煤赋存特征及影响因素[J]. 煤田地质与勘探，2021，49(3)：50−61.

YAO Zheng，LUO Qianzhou，LI Ning，et al. Occurrence characteristics of Carboniferous-Permian tar-rich coal and its influencing factors in northern Shaanxi[J]. Coal Geology & Exploration，2021，49(3)：50−61.

[27] 杨甫，段中会，马丽，等. 陕西省富油煤分布及受控地质因素[J]. 煤炭科学技术，2023，51(3)：171−181.

YANG Fu，DUAN Zhonghui，MA Li，et al. Distribution and controlled geological factors of oil-rich coal in Shaanxi Province[J]. Coal Science and Technology，2023，51(3)：171−181.

[28] SHI Qingmin，LI Chunhao，WANG Shuangming，et al. Variation of molecular structures affecting tar yield：A comprehensive analysis on coal ranks and depositional environments[J]. Fuel，2023，335：127050.

[29] FAN Jinwen，DU Meili，LIU Lei，et al. Macerals particle characteristics analysis of tar-rich coal in northern Shaanxi based on image segmentation models via the U-Net variants and image feature extraction[J]. Fuel，2023，341：127757.

[30] 曹代勇，魏迎春，王安民，等. 显微组分大分子结构演化差异性及其动力学机制：研究进展与展望[J]. 煤田地质与勘探，2021，49(1)：12−20.

CAO Daiyong，WEI Yingchun，WANG Anmin，et al. The evolution difference of macromolecular structures and its dynamic mechanism of coal macerals：Research status and prospect[J]. Coal Geology & Exploration，2021，49(1)：12−20.

[31] 张宁，许云，乔军伟，等. 陕北侏罗纪富油煤有机地球化学特征[J]. 煤田地质与勘探，2021，49(3)：42−49.

ZHANG Ning，XU Yun，QIAO Junwei，et al. Organic geochemistry of the Jurassic tar-rich coal in northern Shaanxi Province[J]. Coal Geology & Exploration，2021，49(3)：42−49.

[32] 张蕾，韩智坤，舒浩，等. 陕北富油煤低温热解提油基础特性[J]. 煤炭工程，2022，54(9)：124−128.

ZHANG Lei，HAN Zhikun，SHU Hao，et al. Basic characteristics of tar extraction in low temperature pyrolysis of tar-rich coal from northen Shaanxi[J]. Coal Engineering，2022，54(9)：124−128.

[33] HU Erfeng，ZENG Xi，MA Dachao，et al. Effect of the moisture content in coal on the pyrolysis behavior in an indirectly heated fixed-bed reactor with internals[J]. Energy & Fuels，2017，31(2)：1347−1354.

[34] 刘阳，刘捷成，俞海淼，等. 新型镍基镁渣催化重整松木热解挥发分焦油析出特性研究[J]. 化工学报，2019，70(8)：2991−2999.

LIU Yang，LIU Jiecheng，YU Haimiao，et al. Characteristics of tar formation during catalytic reforming of pyrolysis volatile from pine saw dust over novel Ni-based magnesium slag catalyst[J]. CIESC Journal，2019，70(8)：2991−2999.

[35] 石晓莉，陈水渺，孙宝林，等. 不同水分褐煤快速热解试验研究[J]. 洁净煤技术，2018，24(4)：60−64.

SHI Xiaoli，CHEN Shuimiao，SUN Baolin，et al. Experimental study on flash pyrolysis of lignite with different moisture contents[J]. Clean Coal Technology，2018，24(4)：60−64.

[36] GUO Huina，SHI Hang，WU Yuxin，et al. Mineral transformation during rapid heating and cooling of Zhundong coal ash[J]. Fuel，2022，310：122269.

[37] 李伍，杨文斌，战星羽，等. 煤有机大分子碳结构石墨化机制[J]. 煤炭学报，2023，48(2)：855−868.

LI Wu，YANG Wenbin，ZHAN Xingyu，et al. Graphitization mechanism of coal organic macromolecular carbon structure[J]. Journal of China Coal Society，2023，48(2)：855−868.

[38] 李祥，刘翠茹，李春艳. 煤的元素分析与工业分析关系的逐层分析与模型构建[J]. 中国煤炭，2017，43(4)：99−104.

LI Xiang，LIU Cuiru，LI Chunyan. Layer-by-layer analysis and model establishment of relationship between ultimate and industrial analysis of coal[J]. China Coal，2017，43(4)：99−104.

[39] 石振，成帅，陈兆辉，等. 神木烟煤热解产物分布及主要元素的迁移规律[J]. 过程工程学报，2016，16(5)：802−811.

SHI Zhen，CHENG Shuai，CHEN Zhaohui，et al. Distribution of products and migration of main elements during pyrolysis of Shenmu bituminous coal[J]. The Chinese Journal of Process Engineering，2016，16(5)：802−811.

[40] 李梅，杨俊和，夏红波，等. 典型炼焦高硫煤热解过程中硫迁移规律研究[J]. 煤炭转化，2013，36(4)：41−45.

LI Mei，YANG Junhe，XIA Hongbo，et al. Behavior of sulfur transformation during pyrolysis of high-sulfur coking coals[J]. Coal Conversion，2013，36(4)：41−45.

[41] 矫天禹. 矿物质组分对煤流化床热解特性影响的实验研究[D]. 杭州：浙江大学，2018.

JIAO Tianyu. Experiments on the effects of mineral components on coal during fludized bed pyrolysis process[D]. Hangzhou：Zhejiang University，2018.

[42] 杨玉坤. 煤灰及其矿物组分对煤热解影响的实验研究[D]. 杭州：浙江大学，2017.

YANG Yukun. Experimental study on influence of coal ash and its mineral matter on coal pvrolvsis[D]. Hangzhou：Zhejiang University，2017.

[43] 矫天禹，王勤辉，唐健，等. 氧化铁对煤流化床热解特性影响的实验研究[J]. 能源工程，2019(1)：1−6.

JIAO Tianyu，WANG Qinhui，TANG Jian，et al. Experiments on the effects of Fe₂O₃ on coal during fluidized bed pyrolysis process[J]. Energy Engineering，2019(1)：1−6.

[44] 王美君，杨会民，何秀风，等. 铁基矿物质对西部煤热解特性的影响[J]. 中国矿业大学学报，2010，39(3)：426−430.

WANG Meijun，YANG Huimin，HE Xiufeng，et al. Effect of Fe-based minerals on pyrolysis characteristics of coal from western China[J]. Journal of China University of Mining & Technology，2010，39(3)：426−430.

[45] 贾永斌，黄戒介，程中虎，等. 煤快速热解过程中氧化钙对焦油裂解的影响[J]. 煤炭转化，2001，24(2)：53−57.

JIA Yongbin，HUANG Jiejie，CHENG Zhonghu，et al. Effect of CaO on tar cracking in a rapid-pyrolysis fixed bed reactor[J]. Coal Conversion，2001，24(2)：53−57.

[46] HINTON G E，OSINDERO S，TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation，2006，18(7)：1527−1554.

[47] BAI Guangxing，XU Tianlong. Coal mine safety evaluation based on machine learning：A BP neural network model[J]. Computational Intelligence and Neuroscience，2022，2022：5233845.

[48] DOUCET L S，TETLEY M G，LI Zhengxiang，et al. Geochemical fingerprinting of continental and oceanic basalts：A machine learning approach[J]. Earth-Science Reviews，2022，233：104192.

[49] 侯霖莉，吴松，易建洲，等. 基于机器学习的绿泥石微量元素判别矿床类型[J/OL]. 地球科学：1–24[2024-05-08]. http://kns.cnki.net/kcms/detail/42.1874.p.20230912.1324.002.html.

HOU Linli，WU Song，YI Jianzhou，et al. Discriminating deposit types using chlorite trace elements based on machine learning[J/OL]. Earth Science：1–24[2024-05-08]. http://kns.cnki.net/kcms/detail/42.1874.p.20230912.1324.002.html.