Citation: | LIU Shiwei,ZHAO Jiaxin,YUAN Lezhong,et al. Prediction of failure depth of coal seam floor in pressure mining based on small sample enhancement of MTD class distribution[J]. Coal Science and Technology,2024,52(S2):175−185. DOI: 10.12438/cst.2023-1360 |
The prediction method of machine learning has been widely used in the prediction and evaluation of the failure depth of coal seam floor in pressure mining. However, there are often some problems in the construction of the prediction model, such as high acquisition cost, difficulty in collecting and strong randomness of the measured data. The prediction performance of the model built based on a small number of samples is often severely restricted by the prediction accuracy and generalization ability. Through literature research, 50 sets of measured data samples were collected, and MTD similar distribution virtual sample generation technology was introduced to generate virtual samples to further expand and enhance the measured samples of coal seam floor failure depth.Machine learning algorithms such as ADE-ELM, GA-PSO-BP and BP were used to build a prediction model of coal seam floor failure depth before and after virtual sample enhancement, and the prediction accuracy of the model before and after enhancement was compared and analyzed. The results show that the distribution of virtual samples generated by this method is basically consistent with that of measured samples. The accuracy of the prediction models enhanced with virtual samples is significantly improved, among which the PCA-ADE-ELM prediction model enhanced with small distributed samples of MTD class has the best prediction effect, and the error of the enhanced model can be reduced by 42.95%~51.27%. MTD similar distribution virtual sample generation technology is used to enhance small samples, and the prediction model of failure depth of coal seam floor under pressure can be built to more accurately predict the failure depth of coal seam floor under the influence of multiple factors. Through comparison and analysis with the standard empirical prediction results and the slip line field theory prediction results, the failure depth of 19105 working face of Yunjialing Mine predicted by this method is relatively large, which is conducive to the safe production management of working face. The relevant research results provide favorable support for the safe and efficient mining of confined above-water coal seam of Ordovician limestone.
[1] |
张吉雄,张强,周楠,等. 煤基固废充填开采技术研究进展与展望[J]. 煤炭学报,2022,47(12):4167−4181.
ZHANG Jixiong,ZHANG Qiang,ZHOU Nan,et al. Research progress and prospect of coal based solid waste backfilling mining technology[J]. Journal of China Coal Society,2022,47(12):4167−4181.
|
[2] |
SUN W J,ZHOU W F,JIAO J. Hydrogeological classification and water inrush accidents in China’s coal mines[J]. Mine Water and the Environment,2016,35(2):214−220. doi: 10.1007/s10230-015-0363-3
|
[3] |
WANG P P,JIANG Y D,REN Q S. Roof hydraulic fracturing for preventing floor water inrush under multi aquifers and mining disturbance:A case study[J]. Energies,2022,15(3):1187. doi: 10.3390/en15031187
|
[4] |
DUAN H F,ZHAO L J. New evaluation and prediction method to determine the risk of water inrush from mining coal seam floor[J]. Environmental Earth Sciences,2021,80(1):30. doi: 10.1007/s12665-020-09339-y
|
[5] |
靳德武. 我国煤层底板突水问题的研究现状及展望[J]. 煤炭科学技术,2002,30(6):1−4. doi: 10.3969/j.issn.0253-2336.2002.06.001
JIN Dewu. Research status and outlook of water outburst from seam floor in China coal mines[J]. Coal Science and Technology,2002,30(6):1−4. doi: 10.3969/j.issn.0253-2336.2002.06.001
|
[6] |
袁亮. 我国煤炭资源高效回收及节能战略研究[J]. 中国矿业大学学报(社会科学版),2018,20(1):3−12. doi: 10.3969/j.issn.1009-105x.2018.01.001
YUAN Liang. Strategies of high efficiency recovery and energy saving for coal resources in China[J]. Journal of China University of Mining & Technology (Social Sciences),2018,20(1):3−12. doi: 10.3969/j.issn.1009-105x.2018.01.001
|
[7] |
LIU Y,LIU S L,HUO Z C,et al. Failure characteristics of coal seam floor and risk assessment of water inrush caused by underground coal mining[J]. Energy Exploration and Exploitation,2023,41(2):677−695. doi: 10.1177/01445987221144332
|
[8] |
LIU Y,ZHU J Z,LIU Q M,et al. Mechanism analysis of delayed water inrush from Karst collapse column during roadway excavation based on seepage transition theory:A case study in PanEr coal mine[J]. Energies,2022,15(14):4987. doi: 10.3390/en15144987
|
[9] |
HE T,LI G D,SUN C,et al. Floor failure characteristics of thick coal seam mining above confined aquifer[J]. Mining,Metallurgy & Exploration,2022,39(4):1553−1562.
|
[10] |
ZHANG P S,OU Y C,SUN B Y,et al. A case study of floor failure characteristics under fully mechanised caving mining conditions in extra-thick coal seams[J]. Journal of Geophysics and Engineering,2020,17(5):813−826. doi: 10.1093/jge/gxaa031
|
[11] |
李杨杨,张士川,孙熙震,等. 煤层采动底板突水演变过程可视化试验平台研制与试验研究[J]. 煤炭学报,2021,46(11):3515−3524.
LI Yangyang,ZHANG Shichuan,SUN Xizhen,et al. Development and experimental study on visualization test platform for water inrush evolution process of coal seam mining floor[J]. Journal of China Coal Society,2021,46(11):3515−3524.
|
[12] |
WANG W M,YUAN Y,LIANG X K,et al. Experimental study on floor damage and slurry material ratio optimization in deep and high confined water mining[J]. Processes,2022,10(9):1806. doi: 10.3390/pr10091806
|
[13] |
QI Y,WANG W,GE J Q,et al. Development characteristics of the rock fracture field in strata overlying a mined coal seam group[J]. PLoS One,2022,17(10):e0268955. doi: 10.1371/journal.pone.0268955
|
[14] |
LIU W T,DU Y H,LIU Y B,et al. Failure characteristics of floor mining-induced damage under deep different dip angles of coal seam[J]. Geotechnical and Geological Engineering,2019,37(2):985−994. doi: 10.1007/s10706-018-0666-9
|
[15] |
郭惟嘉,张士川,孙文斌,等. 深部开采底板突水灾变模式及试验应用[J]. 煤炭学报,2018,43(1):219−227.
GUO Weijia,ZHANG Shichuan,SUN Wenbin,et al. Experimental and analysis research on water inrush catastrophe mode from coal seam floor in deep mining[J]. Journal of China Coal Society,2018,43(1):219−227.
|
[16] |
于小鸽,韩进,施龙青,等. 基于BP神经网络的底板破坏深度预测[J]. 煤炭学报,2009,34(6):731−736. doi: 10.3321/j.issn:0253-9993.2009.06.003
YU Xiaoge,HAN Jin,SHI Longqing,et al. Forecast of destroyed floor depth based on BP neural networks[J]. Journal of China Coal Society,2009,34(6):731−736. doi: 10.3321/j.issn:0253-9993.2009.06.003
|
[17] |
施龙青,张荣遨,韩进,等. 基于GWO改进的PCA-BP神经网络煤层底板破坏深度预测模型[J]. 矿业研究与开发,2020,40(2):88−93.
SHI Longqing,ZHANG Rongao,HAN Jin,et al. Prediction model of failure depth of coal seam floor based on PCA-BP neural network improved by GWO[J]. Mining Research and Development,2020,40(2):88−93.
|
[18] |
邵良杉,周玉. 基于PSO-ELM-Boosting模型的底板破坏深度预测[J]. 中国安全科学学报,2018,28(4):24−29.
SHAO Liangshan,ZHOU Yu. Prediction of destroyed floor depth based on SO-ELM-Boosting model[J]. China Safety Science Journal,2018,28(4):24−29.
|
[19] |
WANG Z C,ZHAO W T,HU X. Analysis of prediction model of failure depth of mine floor based on fuzzy neural network[J]. Geotechnical and Geological Engineering,2019,37(1):71−76. doi: 10.1007/s10706-018-0591-y
|
[20] |
LI D C,CHEN C C,CHANG C J,et al. A tree-based-trend-diffusion prediction procedure for small sample sets in the early stages of manufacturing systems[J]. Expert Systems with Applications,2012,39(1):1575−1581. doi: 10.1016/j.eswa.2011.08.071
|
[21] |
CHAO G Y,TSAI T I,LU T J,et al. A new approach to prediction of radiotherapy of bladder cancer cells in small dataset analysis[J]. Expert Systems with Applications,2011,38(7):7963−7969. doi: 10.1016/j.eswa.2010.12.035
|
[22] |
余国锋. 基于微震和神经网络的煤层底板突水预警技术研究[D]. 淮南:安徽理工大学,2022.
YU Guofeng. Study on early warning technology of water inrush in coal seam floor based on microseism and neural network[D]. Huainan:Anhui University of Science & Technology,2022.
|
[23] |
ZHANG Y X,WANG X Z,WANG Y F,et al. Detection of tomato water stress based on terahertz spectroscopy[J]. Frontiers in Plant Science,2023,14:1095434. doi: 10.3389/fpls.2023.1095434
|
[24] |
宫凤强,王天成,黄天朗. 基于正态信息扩散原理的极值型工程参数概率分布推断方法[J]. 中南大学学报(自然科学版),2020,51(6):1692−1702. doi: 10.11817/j.issn.1672-7207.2020.06.024
GONG Fengqiang,WANG Tiancheng,HUANG Tianlang. An inference method for probability distribution of extreme value engineering parameters based on normal information diffusion principle[J]. Journal of Central South University (Science and Technology),2020,51(6):1692−1702. doi: 10.11817/j.issn.1672-7207.2020.06.024
|
[25] |
MENG Z P,LI G Q,XIE X T. A geological assessment method of floor water inrush risk and its application[J]. Engineering Geology,2012,143:51−60.
|
[26] |
ZHANG W,ZHANG D S,QI D H,et al. Floor failure depth of upper coal seam during close coal seams mining and its novel detection method[J]. Energy Exploration & Exploitation,2018,36(5):1265−1278.
|