A SMOGN-based MPSO-BP model to predict the height of a hydraulically conductive fracture zone

Authors

LIU Qi, College of Energy and Mining Engineering, Shandong University of Science and Technology, Qingdao 266590, China; State Key Laboratory of Mining Disaster Prevention and Control Co-founded by Shandong Province and the Ministry of Science and Technology, Shandong University of Science and Technology, Qingdao 266590, China; Anhui Provincial Key Laboratory of Building Structure and Underground Engineering, Anhui Jianzhu University, Hefei 230601, ChinaFollow
LIANG Zhihao, College of Energy and Mining Engineering, Shandong University of Science and Technology, Qingdao 266590, China
ZI Jianxiao, Feicheng Mining Group Liangbaosi Energy Co., Ltd., Jining 272400, China

Abstract

Objective The height of a hydraulically conductive fracture zone, a significant factor influencing roof water inrushes and groundwater resource loss, is identified as a research focus of the prevention and control of mine water disasters. Methods To accurately predict the heights of hydraulically conductive fracture zones in coal seam roofs, five parameters were selected as the primary factors influencing hydraulically conductive fracture zones the mining depth: mining height, coal seam inclination, the length of the mining face along its dip direction, proportional coefficient of hard rocks (i.e., the ratio of the cumulative thickness of hard rocks within the statistical height above the coal seam roof to the statistical height), and mining method. A total of 200 measured samples concerning the heights of hydraulically conductive fracture zones were collected as the model dataset. First, over-sampling of the original dataset was conducted using the synthetic minority over-sampling technique for regression (SmoteR) combined with the introduction of Gaussian Noise (SMOGN). In conjunction with 8-fold cross-validation, the optimal back propagation (BP) neural network structure was determined by using the mean absolute error (denoted by E_MA), root mean square error (denoted by E_RMS), and coefficient of determination (denoted by R²) as the assessment indices of the regression model. Then, the initial weights and thresholds of the BP neural network were optimized using the mutation particle swarm optimization (MPSO) algorithm. Finally, the optimized prediction model, i.e., the MPSO-BP model, was applied to the engineering field. Results and Conclusions The results indicate that based on the original dataset, the BP neural network, using the Huber loss and Adam first-order optimization algorithm, enhanced the training speed and stability. Consequently, the optimal activation function was determined at Tanh and the optimal hidden layer node number at 12. The MPSO-BP model yielded the optimal performance where the MPSO population number was 50. After SMOGN and MPSO, the training set yielded an E_MA value of 0.163, an E_RMS value of 0.216, and an R² value of 0.948, and these values were 0.260, 0.341, and 0.901, respectively, for the validation set. The field application indicated that the MPSO-BP model yielded relative errors of below 9% in the prediction. Therefore, the integration of the SMOGN and MPSO can significantly enhance the stability and generalization capability of the prediction model, the sample distribution characteristics, the sample utilization efficiency, and the predicted effects of the model. This study can serve as a reference for the training and prediction of models for the heights of hydraulically conductive fracture zones.

Keywords

prevention and control of mine water hazard, over-sampling for regression, hydraulically conductive fracture zone, height prediction, mutation particle swarm optimization (MPSO) algorithm, model optimization

DOI

10.12363/issn.1001-1986.24.03.0186

Recommended Citation

LIU Qi, LIANG Zhihao, ZI Jianxiao, et al. (2024) "A SMOGN-based MPSO-BP model to predict the height of a hydraulically conductive fracture zone," Coal Geology & Exploration: Vol. 52: Iss. 11, Article 7.
DOI: 10.12363/issn.1001-1986.24.03.0186
Available at: https://cge.researchcommons.org/journal/vol52/iss11/7

Reference

[1] 刘峰，郭林峰，张建明，等. 煤炭工业数字智能绿色三化协同模式与新质生产力建设路径[J]. 煤炭学报，2024，49(1)：1−15.

LIU Feng，GUO Linfeng，ZHANG Jianming，et al. Synergistic mode of digitalization-intelligentization-greeniation of the coal industry and it’s path of building new coal productivity[J]. Journal of China Coal Society，2024，49(1)：1−15.

[2] 钱鸣高，许家林. 煤炭开采与岩层运动[J]. 煤炭学报，2019，44(4)：973−984.

QIAN Minggao，XU Jialin. Behaviors of strata movement in coal mining[J]. Journal of China Coal Society，2019，44(4)：973−984.

[3] 刘奇，刘相林，曹广勇，等. 基于OFDR的采动覆岩铰接结构回转角度及“三带” 变形表征研究[J]. 煤炭科学技术，2024，52(3)：63−73.

LIU Qi，LIU Xianglin，CAO Guangyong，et al. Study on rotation angle and three-zone deformation characterization of hinged structure of mining overburden rock based on OFDR[J]. Coal Science and Technology，2024，52(3)：63−73.

[4] 国家安全监管总局，国家煤矿安监局，国家能源局，等. 建筑物、水体、铁路及主要井巷煤柱留设与压煤开采规范[M]. 北京：煤炭工业出版社，2017.

[5] 范立民. 保水采煤面临的科学问题[J]. 煤炭学报，2019，44(3)：667−674.

FAN Limin. Some scientific issues in water-preserved coal mining[J]. Journal of China Coal Society，2019，44(3)：667−674.

[6] 来兴平，张旭东，单鹏飞，等. 厚松散层下三软煤层开采覆岩导水裂隙发育规律[J]. 岩石力学与工程学报，2021，40(9)：1739−1750.

LAI Xingping，ZHANG Xudong，SHAN Pengfei，et al. Study on development law of water-conducting fractures in overlying strata of three soft coal seam mining under thick loose layers[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(9)：1739−1750.

[7] 刘奇，牛家宝，李青海，等. 采动覆岩裂隙演化的光纤监测耦合性及分带表征[J]. 煤炭学报，2024，49(3)：1345−1357.

LIU Qi，NIU Jiabao，LI Qinghai，et al. Deformation zoning characterization of mining rock mass based on partition coupling optical fiber sensing[J]. Journal of China Coal Society，2024，49(3)：1345−1357.

[8] 李星亮，黄庆享. 水体下特厚煤层综放开采导水裂隙带高度发育特征研究[J]. 采矿与安全工程学报，2022，39(1)：54−61.

LI Xingliang，HUANG Qingxiang. High development characteristics of water flowing fractured zone in fully-mechanized top-caving mining of extremely thick coal seam under water[J]. Journal of Mining & Safety Engineering，2022，39(1)：54−61.

[9] 李恒，何滔，郭宾. 西北生态脆弱区浅埋煤层保水开采隔水层稳定性评价方法[J]. 煤田地质与勘探，2023，51(11)：92−98.

LI Heng，HE Tao，GUO Bin. A method for evaluating aquiclude stability in the water conservation-based mining of shallowly buried coal seams in ecologically vulnerable areas in northwest China[J]. Coal Geology & Exploration，2023，51(11)：92−98.

[10] 许家林，朱卫兵，王晓振. 基于关键层位置的导水裂隙带高度预计方法[J]. 煤炭学报，2012，37(5)：762−769.

XU Jialin，ZHU Weibing，WANG Xiaozhen. New method to predict the height of fractured water-conducting zone by location of key strata[J]. Journal of China Coal Society，2012，37(5)：762−769.

[11] 黄万朋，高延法，王波，等. 覆岩组合结构下导水裂隙带演化规律与发育高度分析[J]. 采矿与安全工程学报，2017，34(2)：330−335.

HUANG Wanpeng，GAO Yanfa，WANG Bo，et al. Evolution rule and development height of permeable fractured zone under combined-strata structure[J]. Journal of Mining & Safety Engineering，2017，34(2)：330−335.

[12] HE Jianghui，LI Wenping，FAN Kaifang，et al. A method for predicting the water-flowing fractured zone height based on an improved key stratum theory[J]. International Journal of Mining Science and Technology，2023，33(1)：61−71.

[13] DAI Bing，CHEN Ying. A novel approach for predicting the height of the water-flow fracture zone in undersea safety mining[J]. Remote Sensing，2020，12(3)：358.

[14] 李超峰，刘英锋，李抗抗. 导水裂隙带高度井下仰孔探测装置改进及应用[J]. 煤炭科学技术，2018，46(5)：166−172.

LI Chaofeng，LIU Yingfeng，LI Kangkang. Equipment improvement and application on determining height of water flowing fractured zone in upward slant hole[J]. Coal Science and Technology，2018，46(5)：166−172.

[15] 郭小铭，刘英锋，谷占兴. 彬长矿区煤层开采导水裂隙带高度探测及计算[J]. 采矿与岩层控制工程学报，2023，5(5)：91−100.

GUO Xiaoming，LIU Yingfeng，GU Zhanxing. Detection and calculation of the height of water flowing fractured zone of coal roof in Binchang mining area[J]. Journal of Mining and Strata Control Engineering，2023，5(5)：91−100.

[16] 伊永杰. 保德煤矿8#煤层覆岩导水裂隙带高度发育特征研究[J]. 中国矿业，2023，32(1)：121−126.

YI Yongjie. Study on the development characteristics of overburden water flowing fracture height in No.8 coal seam of Baode Coal Mine[J]. China Mining Magazine，2023，32(1)：121−126.

[17] 王晶，王晓蕾. 下保护层开采时被保护层裂隙发育与渗透特征[J]. 采矿与岩层控制工程学报，2021，3(3)：62−70.

WANG Jing，WANG Xiaolei. Seepage characteristic and fracture development of protected seam caused by mining protecting strata[J]. Journal of Mining and Strata Control Engineering，2021，3(3)：62−70.

[18] 范立民，孙强，马立强，等. 论保水采煤技术体系[J]. 煤田地质与勘探，2023，51(1)：196−204.

FAN Limin，SUN Qiang，MA Liqiang，et al. Technological system of water-conserving coal mining[J]. Coal Geology & Exploration，2023，51(1)：196−204.

[19] 田睿，孟海东，陈世江，等. 基于深度神经网络的岩爆烈度分级预测[J]. 煤炭学报，2020，45(增刊1)：191−201.

TIAN Rui，MENG Haidong，CHEN Shijiang，et al. Prediction of intensity classification of rockburst based on deep neural network[J]. Journal of China Coal Society，2020，45(Sup.1)：191−201.

[20] 柴华彬，张俊鹏，严超. 基于GA-SVR的采动覆岩导水裂隙带高度预测[J]. 采矿与安全工程学报，2018，35(2)：359−365.

CHAI Huabin，ZHANG Junpeng，YAN Chao. Prediction of water-flowing height in fractured zone of overburden strata based on GA-SVR[J]. Journal of Mining & Safety Engineering，2018，35(2)：359−365.

[21] 邵良杉，周玉. QGA-RFR模型在导水裂隙带高度预测中的应用[J]. 中国安全科学学报，2018，28(3)：19−24.

SHAO Liangshan，ZHOU Yu. Application of QGA-RFR model in prediction of height of water flowing fractured zone[J]. China Safety Science Journal，2018，28(3)：19−24.

[22] 胡小娟，李文平，曹丁涛，等. 综采导水裂隙带多因素影响指标研究与高度预计[J]. 煤炭学报，2012，37(4)：613−620.

HU Xiaojuan，LI Wenping，CAO Dingtao，et al. Index of multiple factors and expected height of fully mechanized water flowing fractured zone[J]. Journal of China Coal Society，2012，37(4)：613−620.

[23] 李博，吴煌，李腾. 基于加权的综采导水裂隙带高度多元非线性回归预测方法研究[J]. 采矿与安全工程学报，2022，39(3)：536−545.

LI Bo，WU Huang，LI Teng. Height prediction of water-conducting fractured zone under fully mechanized mining based on weighted multivariate nonlinear regression[J]. Journal of Mining & Safety Engineering，2022，39(3)：536−545.

[24] 娄高中，谭毅. 基于PSO-BP神经网络的导水裂隙带高度预测[J]. 煤田地质与勘探，2021，49(4)：198−204.

LOU Gaozhong，TAN Yi. Prediction of the height of water flowing fractured zone based on PSO-BP neural network[J]. Coal Geology & Exploration，2021，49(4)：198−204.

[25] 王旭，尹尚先，徐斌，等. 综采工作条件下覆岩导水裂隙带高度预测模型优化[J]. 煤炭科学技术，2023，51(增刊1)：284−297.

WANG Xu，YIN Shangxian，XU Bin，et al. Study on height optimization prediction model of overburden water-conducting fracture zone under fully mechanized mining[J]. Coal Science and Technology，2023，51(Sup.1)：284−297.

[26] 方安然，李旦，张建秋. 异常值和未知观测噪声鲁棒的非线性滤波器[J]. 航空学报，2021，42(7)：324675.

FANG Anran，LI Dan，ZHANG Jianqiu. Nonlinear filter robust to outlier and unknown observation noise[J]. Acta Aeronautica et Astronautica Sinica，2021，42(7)：324675.

[27] 赵杰，张春元，刘超，等. 递归最小二乘循环神经网络[J]. 自动化学报，2022，48(8)：2050−2061.

ZHAO Jie，ZHANG Chunyuan，LIU Chao，et al. Recurrent neural networks with recursive least squares[J]. Acta Automatica Sinica，2022，48(8)：2050−2061.

[28] 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.

[29] 马亚杰，武强，章之燕，等. 煤层开采顶板导水裂隙带高度预测研究[J]. 煤炭科学技术，2008，36(5)：59−62.

MA Yajie，WU Qiang，ZHANG Zhiyan，et al. Research on prediction of water conducted fissure height in roof of coal mining seam[J]. Coal Science and Technology，2008，36(5)：59−62.

[30] 魏世荣，赵延林，戚春前，等. 多煤层开采导水裂隙带发育与覆岩破坏高度规律[J]. 湖南科技大学学报(自然科学版)，2022，37(2)：18−26.

WEI Shirong，ZHAO Yanlin，QI Chunqian，et al. On development law of water conducting fracture zone and overburden failure height in multi-coal seam mining[J]. Journal of Hunan University of Science and Technology (Natural Science Edition)，2022，37(2)：18−26.

[31] 邬建宏，潘俊锋，高家明，等. 黄陇侏罗纪煤田导水裂隙带高度预测研究[J]. 煤炭科学技术，2023，51(增刊1)：231−241.

WU Jianhong，PAN Junfeng，GAO Jiaming，et al. Research on prediction of the height of water-conducting fracture zone in Huanglong Jurassic Coalfield[J]. Coal Science and Technology，2023，51(Sup.1)：231−241.

[32] 杨国勇，陈超，高树林，等. 基于层次分析–模糊聚类分析法的导水裂隙带发育高度研究[J]. 采矿与安全工程学报，2015，32(2)：206−212.

YANG Guoyong，CHEN Chao，GAO Shulin，et al. Study on the height of water flowing fractured zone based on analytic hierarchy process and fuzzy clustering analysis method[J]. Journal of Mining & Safety Engineering，2015，32(2)：206−212.

[33] 邱梅，许高瑞，宋光耀，等. PCA-WNN模型在导水裂隙带高度预测中的应用研究[J]. 河南理工大学学报(自然科学版)，2023，42(6)：27−36.

QIU Mei，XU Gaorui，SONG Guangyao，et al. Research on application of PCA-WNN model in predicting the development height of water-flowing fractured zones[J]. Journal of Henan Polytechnic University (Natural Science)，2023，42(6)：27−36.

[34] 赵德星. 基于Elman神经网络的导水裂隙带高度预测模型[J]. 山西煤炭，2022，42(2)：8−14.

ZHAO Dexing. Prediction model for the height of water flowing fractured zones based on Elman neural network[J]. Shanxi Coal，2022，42(2)：8−14.

[35] 徐树媛，张永波，孙灏东，等. 基于RBF核ε-SVR的导水裂隙带高度预测模型研究[J]. 安全与环境学报，2021，21(5)：2022−2029.

XU Shuyuan，ZHANG Yongbo，SUN Haodong，et al. Predictable testing and determination of the height of the fractured water-conducting zone based on the ε-SVR model via the RBF kernel function[J]. Journal of Safety and Environment，2021，21(5)：2022−2029.

[36] 谭文侃，叶义成，胡南燕，等. LOF与改进SMOTE算法组合的强烈岩爆预测[J]. 岩石力学与工程学报，2021，40(6)：1186−1194.

TAN Wenkan，YE Yicheng，HU Nanyan，et al. Severe rock burst prediction based on the combination of LOF and improved SMOTE algorithm[J]. Chinese Journal of Rock Mechanics and Engineering，2021，40(6)：1186−1194.

[37] GAVAS R D，DAS M，GHOSH S K，et al. Spatial-SMOTE for handling imbalance in spatial regression tasks[J]. Multimedia Tools and Applications，2024，83(5)：14111−14132.

[38] MURARI A，ROSSI R，SPOLLADORE L，et al. A practical utility-based but objective approach to model selection for regression in scientific applications[J]. Artificial Intelligence Review，2023，56(2)：2825−2859.

[39] WEN Zhidan，WANG Qiang，MA Yue，et al. Remote estimates of suspended particulate matter in global lakes using machine learning models[J]. International Soil and Water Conservation Research，2024，12(1)：200−216.

[40] LIU Xiaowei，LONG Zhilin，ZHANG Wei，et al. A multi-strategy hybrid machine learning model for predicting glass-formation ability of metallic glasses based on imbalanced datasets[J]. Journal of Non-Crystalline Solids，2023，621：122645.

[41] RUDD D H，HUO Huan，XU Guandong. Predicting financial literacy via semi-supervised learning[M]//Lecture notes in computer science. Cham：Springer International Publishing，2022：304–319.

[42] BRANCO P，TORGO L，RIBEIRO R P. SMOGN：A pre-processing approach for imbalanced regression[C]//Proceedings of the First International Workshop on Learning with Imbalanced Domains：Theory and Applications. Proceedings of Machine Learning Research：PMLR，2017：36–50.

[43] 寻博辉，吕义清，姚星. 导水裂隙带发育高度预测模型对比研究[J]. 煤炭科学技术，2023，51(3)：190−200.

XUN Bohui，LYU Yiqing，YAO Xing. Comparison of prediction models for the development height of water-conducting fractured zone[J]. Coal Science and Technology，2023，51(3)：190−200.

[44] 侯朋远，徐帅，梁瑞余，等. 基于BP神经网络的采空区激光探测环境误差修正[J]. 中南大学学报(自然科学版)，2020，51(3)：758−766.

HOU Pengyuan，XU Shuai，LIANG Ruiyu，et al. Environmental error correction of 3D laser detection for goaf based on BP neural network[J]. Journal of Central South University (Science and Technology)，2020，51(3)：758−766.

[45] 李晓晨，白音包力皋，李向东，等. 基于IPSO-BP神经网络的高含沙水体对鱼类影响预测方法[J]. 水利学报，2023，54(3)：291−301.

LI Xiaochen，BAIYIN Baoligao，LI Xiangdong，et al. A prediction method for the impact of hyper-concentrated flow on fishes based on the IPSO-BP neural network[J]. Journal of Hydraulic Engineering，2023，54(3)：291−301.

[46] 张瑶，罗林根，王辉，等. 基于MPSO-MLE的变电站设备异常声源定位方法[J]. 高电压技术，2020，46(9)：3145−3153.

ZHANG Yao，LUO Lingen，WANG Hui，et al. Method of locating abnormal acoustic source of substation equipment based on MPSO-MLE[J]. High Voltage Engineering，2020，46(9)：3145−3153.

[47] HUBER P J. Robust estimation of a location parameter[J]. The Annals of Mathematical Statistics，1964，35(1)：73−101.

[48] 虞浩跃，沈韬，朱艳，等. 基于双向长短期记忆网络的太赫兹光谱识别[J]. 光谱学与光谱分析，2019，39(12)：3737−3742.

YU Haoyue，SHEN Tao，ZHU Yan，et al. Terahertz spectral recognition based on bidirectional long short-term memory recurrent neural network[J]. Spectroscopy and Spectral Analysis，2019，39(12)：3737−3742.

[49] 宁永香，崔希民. 矿山边坡地表变形的PSO-ELM预测模型[J]. 煤田地质与勘探，2020，48(6)：201−206.

NING Yongxiang，CUI Ximin. PSO-ELM prediction model for surface deformation of mine slope[J]. Coal Geology & Exploration，2020，48(6)：201−206.

[50] 石守桥，吴复柱，边凯. 弱胶结覆岩导水裂隙带高度预测及三维空间发育特征[J]. 采矿与安全工程学报，2022，39(6)：1154−1160.

SHI Shouqiao，WU Fuzhu，BIAN Kai. Height prediction and three-dimensional development characteristics of water-conducting fracture zone in weakly cemented overburden[J]. Journal of Mining & Safety Engineering，2022，39(6)：1154−1160.