基于ACO−KELM的采空区遗煤温度预测模型研究

翟小伟; 王辰; 郝乐; 李心田; 侯钦元; 马腾

doi:10.13272/j.issn.1671-251x.18226

基于ACO−KELM的采空区遗煤温度预测模型研究

翟小伟^{1, 2, 3,},
王辰^{1, 2, 3, ,},
郝乐^{1, 2, 3},
李心田^{1, 2, 3},
侯钦元^{1, 2, 3},
马腾^{1, 2, 3}

1.
西安科技大学安全科学与工程学院，陕西西安　710054
2.
西安科技大学陕西省煤火灾害防控重点实验室，陕西西安　710054
3.
陕西高校青年创新团队矿山应急救援创新团队，陕西西安　710054

基金项目: 国家自然科学基金资助项目（52274229）；陕西省教育厅青年创新团队建设科研计划项目（21JP078）。

详细信息

作者简介:
翟小伟（1979—），男，陕西富平人，教授，博士研究生导师，博士，主要从事煤火灾害防治、灾害监测预警与应急救援等方面的科研工作，E-mail：zhaixw@xust.edu.cn

通讯作者:
王辰（2000—），男，陕西宝鸡人，硕士研究生，主要从事煤火灾害防治方面的科研工作，E-mail：710586226@qq.com。

中图分类号: TD752
计量
- 文章访问数: 61
- HTML全文浏览量: 22
- PDF下载量: 14
出版历程
- 收稿日期: 2024-10-24
- 修回日期: 2024-12-09
- 网络出版日期: 2024-12-30
- 刊出日期: 2024-12-24

Study on the temperature prediction model of residual coal in goaf based on ACO-KELM

ZHAI Xiaowei^{1, 2, 3,},
WANG Chen^{1, 2, 3, ,},
HAO Le^{1, 2, 3},
LI Xintian^{1, 2, 3},
HOU Qinyuan^{1, 2, 3},
MA Teng^{1, 2, 3}

1.
College of Safety Science and Engineering, Xi'an University of Science and Technology, Xi'an 710054, China
2.
Shaanxi Province Key Laboratory of Coal Fire Disaster Prevention and Control, Xi'an University of Science and Technology, Xi'an 710054, China
3.
Mine Emergency Rescue Innovation Team, The Youth Innovation Team of Shaanxi Universities, Xi'an 710054, China

摘要

摘要:
现有采空区遗煤温度预测研究多侧重于温度与气体浓度之间的关系，较少考虑采空区内遗煤温度与距工作面距离及漏风风速之间的复杂非线性关系。针对该问题，提出了一种基于蚁群优化算法优化核极限学习机（ACO−KELM）的采空区遗煤温度预测模型。在葫芦素煤矿21404工作面采空区布置束管及分布式光纤，对21404工作面采空区内O₂，CO，CO₂浓度和温度数据进行采集，同时结合采空区内漏风强度和距工作面水平距离构建KELM模型，通过ACO对KELM模型中的正则系数和核参数进行寻优，获得最优超参数组合，进而得到性能最优的KELM模型。与基于极限学习机（ELM）和基于随机森林（RF）算法的预测模型相比，ACO−KELM模型在测试集上的平均绝对误差为0.070 1℃，均方根误差为0.074 8℃，较基于ELM模型分别降低了65%和195%，较基于RF模型分别降低了53%和156%；ACO−KELM模型在测试集上的判定系数为0.963 5，与训练集的判定系数仅相差0.01，说明该模型未陷入过拟合且拟合程度较高。
- 采空区遗煤 /
- 煤自燃 /
- 遗煤温度预测 /
- 核极限学习机 /
- 蚁群算法 /
- 漏风强度 /
- 指标气体分析法 /
- 漏风风速
Abstract:
Existing studies on the temperature prediction of residual coal in goafs have mainly focused on the relationship between temperature and gas concentration, with limited attention given to the complex nonlinear relationships between the residual coal temperature in the goaf, the distance from the working face, and the air leakage velocity. To address this gap, a prediction model based on ant colony optimization (ACO) and kernel extreme learning machine (KELM) (ACO-KELM) was proposed. In the 21404 working face goaf of Hulususu Coal Mine, beam tubes and distributed fiber optics were arranged to collect data on O₂ concentration, CO concentration, CO₂ concentration, and temperature within the goaf. Simultaneously, the air leakage intensity and horizontal distances from the working face were incorporated to construct the KELM model. ACO was employed to optimize the regularization coefficients and kernel parameters in the KELM model, thereby obtaining the best-performing hyperparameter combination and generating the optimal KELM model. Compared to the prediction models based on extreme learning machine (ELM) and random forest (RF) algorithms, the ACO-KELM model achieved an average absolute error of 0.0701 ℃ and a root mean square error (RMSE) of 0.0748 ℃ on the test set, reducing these errors by 65% and 195%, respectively, compared to the ELM-based model, and by 53% and 156%, respectively, compared to the RF-based model. The coefficient of determination (R²) for the ACO-KELM model on the test set was 0.9635, which was only 0.01 lower than that of the training set, indicating that the model was not overfitted and demonstrated a high degree of accuracy.
- goaf residual coal /
- coal spontaneous combustion /
- residual coal temperature prediction /
- Kernel Extreme Learning Machine /
- Ant Colony Optimization /
- air leakage intensity /
- gas analysis method /
- air leakage velocity

HTML全文

图 1 ACO−KELM模型预测流程

Figure 1. Prediction process of ACO（ant colony optimization)-KELM(kernel extreme learning machine ) model

下载: 全尺寸图片幻灯片

图 2 采空区气体及温度采集

Figure 2. Gas and temperature data collection in the goaf

下载: 全尺寸图片幻灯片

图 3 采空区气体体积分数与距离−温度变化曲线

Figure 3. Gas volume fraction and temperature variation curves in the goaf

下载: 全尺寸图片幻灯片

图 4 煤低温氧化实验装置

Figure 4. Low-temperature oxidation experimental device for coal

下载: 全尺寸图片幻灯片

图 5 采空区漏风强度、温度变化曲线

Figure 5. Air leakage intensity and temperature variation curves in the goaf

下载: 全尺寸图片幻灯片

图 6 ACO−KELM进化收敛曲线

Figure 6. ACO-KELM evolutionary convergence curve

下载: 全尺寸图片幻灯片

图 7 不同模型煤温真实值与预测值对比

Figure 7. Comparison of real and predicted coal temperatures for different models

下载: 全尺寸图片幻灯片

表 1 不同模型评价指标对比

Table 1 Comparison of evaluation metrics for different models

模型	MAE/℃		RMSE/℃		R²
模型	训练集	测试集	训练集	测试集	训练集	测试集
基于ELM	0.244 8	0.203 1	0.291 4	0.221 1	0.812 6	0.834 8
基于RF	0.198 4	0.150 1	0.201 1	0.192 0	0.835 5	0.851 1
ACO−KELM	0.094 6	0.070 1	0.086 2	0.074 8	0.954 1	0.963 5

下载: 导出CSV

参考文献(27)

[1]	朱兴攀,许敏,王鹏,等. 分布式温度监测系统在煤自燃预警中的应用[J]. 煤炭工程,2019,51(10):24-27. ZHU Xingpan,XU Min,WANG Peng,et al. Research and application of seamless temperature monitoring system for early warning of coal spontaneous combustion[J]. Coal Engineering,2019,51(10):24-27.
[2]	汪伟,梁然,祁云,等. 基于PSO−BPNN的煤自燃危险性预测模型[J]. 中国安全科学学报,2023,33(7):127-132. WANG Wei,LIANG Ran,QI Yun,et al. Prediction model of coal spontaneous combustion risk based on PSO-BPNN[J]. China Safety Science Journal,2023,33(7):127-132.
[3]	邓军,雷昌奎,曹凯,等. 采空区煤自燃预测的随机森林方法[J]. 煤炭学报,2018,43(10):2800-2808. DENG Jun,LEI Changkui,CAO Kai,et al. Random forest method for predicting coal spontaneous combustion in gob[J]. Journal of China Coal Society,2018,43(10):2800-2808.
[4]	翟小伟 ,周翔 ,宋波波,等. 基于ARIMA模型的矿井灾害预测方法研究[J]. 煤炭技术,2024,43(6):165-168. ZHAI Xiaowei,ZHOU Xiang,SONG Bobo,et al. Research on mine disaster prediction method based on ARIMA model[J]. Coal Technology,2024,43(6):165-168.
[5]	刘晨,谢军,辛林. 煤自燃预测预报理论及技术研究综述[J]. 矿业安全与环保,2019,46(3):92-95,99. DOI: 10.3969/j.issn.1008-4495.2019.03.020 LIU Chen,XIE Jun,XIN Lin. Review of theory and technology research on prediction of coal spontaneous combustion[J]. Mining Safety & Environmental Protection,2019,46(3):92-95,99. DOI: 10.3969/j.issn.1008-4495.2019.03.020
[6]	王凯,姚纪凯,翟小伟,等. 煤自燃阶段性预测预报临界指标实验研究[J]. 煤炭技术,2018,37(6):165-167. WANG Kai,YAO Jikai,ZHAI Xiaowei,et al. Investigation on prediction critical indexes of stages of coal spontaneous combustion[J]. Coal Technology,2018,37(6):165-167.
[7]	骆大勇,刘振. 许疃煤矿煤炭自燃指标气体优选与应用[J]. 矿业安全与环保,2021,48(5):69-74. LUO Dayong,LIU Zhen. Optimization and application of coal spontaneous combustion index gas in Xutuan Coal Mine[J]. Mining Safety & Environmental Protection,2021,48(5):69-74.
[8]	武福生. 预测煤自燃的复合气体指标优选实验研究[J]. 工矿自动化,2018,44(7):61-65. WU Fusheng. Experimental study on composite gas indexes optimization for coal spontaneous combustion prediction[J]. Industry and Mine Automation,2018,44(7):61-65.
[9]	张春,隋彦臣. 基于网格优化双层随机森林的采空区煤氧化升温预测研究[J]. 中国安全生产科学技术,2024,20(5):177-183. ZHANG Chun,SUI Yanchen. Prediction of coal oxidation temperature rise in goaf based on grid optimization double-layer random forest[J]. Journal of Safety Science and Technology,2024,20(5):177-183.
[10]	张天宇,鲁义,施式亮,等. 基于支持向量机分类算法的多煤种煤自燃危险性预测[J]. 湖南科技大学学报(自然科学版),2019,34(2):11-17. ZHANG Tianyu,LU Yi,SHI Shiliang,et al. Prediction on coal spontaneous combustion risk for multi-coal based on SVM[J]. Journal of Hunan University of Science & Technology(Natural Science Edition),2019,34(2):11-17.
[11]	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.
[12]	邓军,周少柳,马砺,等. 基于PCA−PSOSVM的煤自燃程度预测研究[J]. 矿业安全与环保,2016,43(5):27-31. DOI: 10.3969/j.issn.1008-4495.2016.05.007 DENG Jun,ZHOU Shaoliu,MA Li,et al. Research on prediction method of coal spontaneous combustion degree based on PCA-PSOSVM[J]. Mining Safety & Environmental Protection,2016,43(5):27-31. DOI: 10.3969/j.issn.1008-4495.2016.05.007
[13]	昝军才,魏成才,蒋可娟,等. 基于BP神经网络的煤自燃温度预测研究[J]. 煤炭工程,2019,51(10):113-117. ZAN Juncai,WEI Chengcai,JIANG Kejuan,et al. Prediction of coal spontaneous combustion temperature based on BP neural network[J]. Coal Engineering,2019,51(10):113-117.
[14]	杨玉中,任立刚. 多物理场耦合下采空区煤自燃三带数值模拟研究[J/OL]. 安全与环境学报:1-11[2024-10-22]. https://doi.org/10.13637/j.issn.1009-6094.2024.0932. YANG Yuzhong,REN Ligang. Numerical simulation of the three zones of spontaneous coal combustion in goaf under multi-physical field coupling[J/OL]. Journal of Safety and Environment:1-11[2024-10-22]. https://doi.org/10.13637/j.issn.1009-6094.2024.0932.
[15]	叶正亮,尚博,胡冕,等. 浅埋煤层大采高工作面地表裂隙漏风研究[J]. 中国煤炭,2024,50(8):72-77. YE Zhengliang,SHANG Bo,HU Mian,et al. Study on air leakage from surface cracks on shallow-buried working face with large mining height[J]. China Coal,2024,50(8):72-77.
[16]	许建民,邓冬冬,宋雷,等. 基于多级视野自适应蚁群算法的移动机器人路径规划[J/OL]. 农业机械学报:1-13[2024-08-12]. http://kns.cnki.net/kcms/detail/11.1964.s.20240712.1521.007.html. XU Jianmin,DENG Dongdong,SONG Lei,et al. Mobile robotpath planning based on multi-level field of view adaptive ant colony algorithm[J/OL]. Transactions of the Chinese Society for Agricultural Machinery:1-13[2024-08-12]. http://kns.cnki.net/kcms/detail/11.1964.s.20240712.1521.007.html.
[17]	宋绍剑,王尧,林小峰. 基于蚁群算法优化回声状态网络的研究[J]. 计算机工程与科学,2017,39(12):2326-2332. DOI: 10.3969/j.issn.1007-130X.2017.12.023 SONG Shaojian,WANG Yao,LIN Xiaofeng. Echo state network based on ant colony algorithm[J]. Computer Engineering & Science,2017,39(12):2326-2332. DOI: 10.3969/j.issn.1007-130X.2017.12.023
[18]	王雨虹,孙远星,包伟川,等. 基于数据均衡化与改进鲸鱼算法优化核极限学习机的变压器故障诊断方法[J]. 信息与控制,2023,52(2):235-244,256. WANG Yuhong,SUN Yuanxing,BAO Weichuan,et al. Transformer fault diagnosis method based on data equalization and kernel-based extreme learning machine of improved whale algorithm[J]. Information and Control,2023,52(2):235-244,256.
[19]	翟小伟,成倬. 柴家沟矿4(−2)煤层自燃标志气体优选实验研究[J]. 煤矿安全,2019,50(11):18-23. ZHAI Xiaowei,CHENG Zhuo. Experimental study on optimization selection of coal spontaneous combustion index gases in 4(-2) coal seam of Chaijiagou Mine[J]. Safety in Coal Mines,2019,50(11):18-23.
[20]	王崇景,杨峰,李可可,等. 复采工作面煤自燃危险区域划分及综合治理技术研究[J]. 煤炭工程,2024,56(1):86-92. WANG Chongjing,YANG Feng,LI Keke,et al. Classification and comprehensive management technology of coal spontaneous combustion hazardous areas in the remining face[J]. Coal Engineering,2024,56(1):86-92.
[21]	武向强. 基于分布式光纤测温系统的采空区自燃“三带” 动态变化研究[D]. 徐州:中国矿业大学,2023. WU Xiangqiang. Study on dynamic change of spontaneous combustion "three zones" in goaf based on distributed optical fiber temperature measurement system[D]. Xuzhou:China University of Mining and Technology,2023.
[22]	张建业,陈举师,孙新. 漏风测定和煤温监测防治采空区煤炭自燃技术[J]. 矿业安全与环保,2016,43(3):60-63. DOI: 10.3969/j.issn.1008-4495.2016.03.016 ZHANG Jianye,CHEN Jushi,SUN Xin. Control technology for coal spontaneous combustion in gobs based on air leakage determination and coal temperature monitoring[J]. Mining Safety & Environmental Protection,2016,43(3):60-63. DOI: 10.3969/j.issn.1008-4495.2016.03.016
[23]	翟小伟,李心田,侯钦元,等. 漏风条件下采空区煤自燃分级预警方法研究及应用[J/OL]. 煤炭科学技术:1-8[2024-08-30]. http://kns.cnki.net/kcms/detail/11.2402.TD.20240716.1114.002.html. ZHAI Xiaowei,LI Xintian,HOU Qinyuan,et al. Research and application of classification warning method for coal spontaneous combustion in goaf under air leakage[J/OL]. Coal Science and Technology:1-8[2024-08-30]. http://kns.cnki.net/kcms/detail/11.2402.TD.20240716.1114.002.html.
[24]	宋涛,王建文,王凯,等. 柠条塔煤矿S12002采空区自燃危险区域划分[J]. 陕西煤炭,2022,41(2):18-22. DOI: 10.3969/j.issn.1671-749X.2022.02.004 SONG Tao,WANG Jianwen,WANG Kai,et al. Division of spontaneous combustion dangerous area in S12002 goaf of Ningtiaota Coal Mine[J]. Shaanxi Coal,2022,41(2):18-22. DOI: 10.3969/j.issn.1671-749X.2022.02.004
[25]	王斌,贾澎涛,郭风景,等. 基于多特征融合的煤自燃温度深度预测模型[J]. 中国矿业,2024,33(2):84-90. DOI: 10.12075/j.issn.1004-4051.20230635 WANG Bin,JIA Pengtao,GUO Fengjing,et al. Deep prediction model of coal spontaneous combustion temperature based on multi-feature fusion[J]. China Mining Magazine,2024,33(2):84-90. DOI: 10.12075/j.issn.1004-4051.20230635
[26]	班鸿榆. 袁店二井煤自燃特性及采空区煤自燃预警技术研究[D]. 淮南:安徽理工大学,2022. BAN Hongyu. Study on the characteristics of coal spontaneous combustionin Yuandian No. 2 Well and the warning technology of coalspontaneous combustion in goafa[D]. Huainan:Anhui University of Science and Technology,2022.
[27]	郑学召,李梦涵,张嬿妮,等. 基于随机森林算法的煤自燃温度预测模型研究[J]. 工矿自动化,2021,47(5):58-64. ZHENG Xuezhao,LI Menghan,ZHANG Yanni,et al. Research on the prediction model of coal spontaneous combustion temperature based on random forest algorithm[J]. Industry and Mine Automation,2021,47(5):58-64.

施引文献(24)

期刊类型引用(17)

1.	张九零，白阳，范酒源，李江涛，陈建广. 深部邻近采空区多漏风条件下自燃“三带”分布规律研究. 安全. 2024(02): 50-57 . 百度学术
2.	魏引尚，康思凡，王凯凯，季朝阳，李巍. 局部自然风压对倾斜通风巷道风流稳定性的影响. 煤炭技术. 2024(04): 146-150 . 百度学术
3.	李江涛，张九零，范酒源，白阳. 多漏风通道采空区自燃“三带”划分研究. 华北理工大学学报(自然科学版). 2024(02): 50-58 . 百度学术
4.	吴峻民. 大气压变化对采空区压力参数影响的研究. 陕西煤炭. 2024(07): 123-126 . 百度学术
5.	郭军，王磊，杜文涛，刘荫，陈昌明，张科峰，李岱霖. 通风方式对沿空留巷采空区煤自燃影响规律研究. 工矿自动化. 2024(11): 142-151 . 本站查看
6.	何志华，杨应迪. 基于三维仿真的运输斜井风流逆反分析及防控方法. 山西能源学院学报. 2024(06): 29-32 . 百度学术
7.	曹宁宁. 大气压变化对采空区瓦斯外涌的影响研究. 煤. 2023(01): 90-92 . 百度学术
8.	孙维丽，张立魁. 低负压矿井自然风压变化规律研究. 山东煤炭科技. 2023(04): 120-122+131 . 百度学术
9.	高常华，孙帅，姜明栋. 深井自然风压及采空区流场动态演化规律研究. 山东煤炭科技. 2023(08): 122-125 . 百度学术
10.	姬周飞. 自然风压对矿井通风系统的影响研究. 工矿自动化. 2023(S1): 142-146 . 本站查看
11.	朱兴攀，王洋，任晓伟，晏立，张林江，刘文永，金永飞，陈玉良. 不同季节条件下浅埋煤层采空区地表垂直漏风规律研究. 工矿自动化. 2023(10): 104-109 . 本站查看
12.	云传贵. 基于自然风压的采空区漏风规律研究. 煤. 2022(03): 23-27 . 百度学术
13.	臧燕杰. 近距离煤层工作面自然风压变化及漏风规律研究. 山东煤炭科技. 2022(05): 113-116 . 百度学术
14.	李艳昌，靖泽浩，贾进章. 切顶卸压沿空留巷“Y”型通风模式下采空区漏风规律研究. 自然灾害学报. 2022(03): 184-189 . 百度学术
15.	郭武奎，孙国辉，曹宁宁. 大气压对采空区压力变化的影响研究. 山东煤炭科技. 2022(08): 222-224+227 . 百度学术
16.	李亚俊，吴洁葵，李印洪，姚银佩. 基于最小生成树原理的矿井通风网络监测布局优化. 矿业研究与开发. 2021(07): 172-175 . 百度学术
17.	刘思鑫，李洪先，王国芝，朱明凯，任广意. 基于SF_6示踪试验的孤岛面采空区漏风规律研究. 煤炭技术. 2021(12): 166-170 . 百度学术