PCA-BP神经网络模型预测导水裂隙带高度

doi:10.16265/j.cnki.issn1003-3033.2017.03.018

摘要/Abstract

摘要： 导水裂隙带高度的预测对煤矿安全开采有重要意义,而传统回归方法未考虑因素间相关系数对预测结果的影响。选取采深、煤层倾角、煤层厚度、煤层硬度、岩层结构、顶板岩石单轴抗压强度、开采厚度和采空区斜长作为预测导水裂隙带高度的影响因素,建立基于PCA-BP神经网络的导水裂隙带高度预测模型。测试结果表明,煤层厚度对导水裂隙带高度的影响最大,其余各因素对导水裂隙带高度的影响较大,采深和开采厚度对导水裂隙带高度的影响较小;PCA-BP神经网络模型的训练速度和预测效果均优于BP神经网络模型,且最大预测误差仅为5.58%。

关键词: 导水裂隙带高度; 主成分分析(PCA); 神经网络; 影响因素; 相关系数

Abstract: The prediction of the height of water flowing fractured zone is of great importance for coal mining safety. However, traditional regression methods haven't considered the influence of correlation coefficients between factors on prediction performance. In this paper, the mining depth, coal seam inclination angle, coal seam thickness, coal seam hardness, rock structure, the uniaxial compressive strength of rock, mining thickness and goaf plagioclase were identified as the influencing factors for height forecast of water flowing fractured zone. Then a PCA-BP neutral network was developed to forecast the height of water flowing fractured zone. Results show that the coal seam thickness has the greatest influence on the height forecast of water flowing fractured zone, while the mining depth and mining thickness have a smaller influence, and the others have a middle influence,and that the speed of convergence and prediction accuracy of the PCA-BP neutral network are both better than that of the BP neutral network with the highest prediction error of 5.58%.

Key words: height of water flowing fractured zone, principle component analysis(PCA), neutral networks, influencing factor, correlation coefficient

中图分类号:

X936

谢晓锋, 李夕兵, 尚雪义, 翁磊, 邓青林. PCA-BP神经网络模型预测导水裂隙带高度[J]. 中国安全科学学报, 2017, 27(3): 100-105.

XIE Xiaofeng, LI Xibing, SHANG Xueyi, WENG Lei, DENG Qinglin. Prediction of height of water flowing fractured zone based on PCA-BP neural networks model[J]. China Safety Science Journal, 2017, 27(3): 100-105.

参考文献

[1] 施龙青, 辛恒奇, 翟培合, 等. 大采深条件下导水裂隙带高度计算研究[J]. 中国矿业大学学报, 2012, 41(1): 37-41.
SHI Longqing, XIN Hengqi, ZHAI Peihe, et al. Calculating the height of water flowing fracture zone in deep mining[J]. Journal of China University of Mining & Technology, 2012, 41(1): 37-41.
[2] 陈荣华, 白海波, 冯梅梅. 综放面覆岩导水裂隙带高度的确定[J]. 采矿与安全工程学报, 2006, 23(2): 220-223.
CHEN Ronghua, BAI Haibo, FENG Meimei. Determination of the height of water flowing fractured zone in overburden strata above fully-mechanized top-coal caving face[J]. Journal of Mining & Safety Engineering, 2006, 23(2): 220-223.
[3] 栾元重, 李静涛, 班训海, 等. 近距煤层开采覆岩导水裂隙带高度观测研究[J]. 采矿与安全工程学报, 2010,27(1):139-142.
LUAN Yuanzhong, LI Jingtao, BAN Xunhai, et al. Observational research on the height of water flowing fractured zone in repeated mining of short-distance coal seams[J]. Journal of Mining & Safety Engineering, 2010, 27(1): 139-142.
[4] 王金安, 尚新春, 刘红, 等. 采空区坚硬顶板破断机理与灾变塌陷研究[J]. 煤炭学报, 2008, 33(8): 850-856.
WANG Jin'an, SHANG Xinchun, LIU Hong, et al. Study on fracture mechanism and catastrophic collapse of strong roof strata above the mined area[J]. Journal of China Coal Society, 2008, 33(8): 850-856.
[5] 陈忠辉, 冯竞竞, 肖彩彩, 等. 浅埋深厚煤层综放开采顶板断裂力学模型[J]. 煤炭学报, 2007, 32(5): 449-453.
CHEN Zhonghui, FENG Jingjing, XIAO Caicai, et al. Fracture mechanical model of key roof for fully mechanized top-coal caving in shallow thick coal seam[J]. Journal of China Coal Society, 2007, 32(5): 449-453.
[6] 许延春, 李振华, 贾安立, 等. 深厚松散层薄基岩条件下覆岩破坏高度实测分析[J]. 煤炭科学技术, 2010,38(7):21-23.
XU Yanchun, LI Zhenhua, JIA Anli, et al. Site measurement and analysis on failure height of overburden strata under thick loose alluvium and thin bedrock[J]. Coal Science and Technology, 2010, 38(7): 21-23.
[7] 贺桂成, 肖富国, 张志军, 等. 康家湾矿含水层下采场导水裂隙带发育高度预测[J]. 采矿与安全工程学报, 2011, 28(1):122-126.
HE Guicheng, XIAO Fuguo, ZHANG Zhijun, et al. Prediction of the height of the transmissive fractured belt of a mining stope under aquifer in Kangjiawan Mine[J]. Journal of Mining & Safety Engineering, 2011, 28(1): 122-126.
[8] 许家林, 王晓振, 刘文涛, 等. 覆岩主关键层位置对导水裂隙带高度的影响[J]. 岩石力学与工程学报, 2009,28(2):380-385.
XU Jialin, WANG Xiaozhen, LIU Wentao, et al. Effects of primary key stratum location on height of water flowing fracture zone[J]. Chinese Journal of Rock Mechanics and Engineering, 2009, 28(2): 380-385.
[9] 路军, 许家林, 王露, 等. 断层采动活化对导水裂隙带高度影响的模拟实验研究[J]. 中国煤炭, 2012, 38(1): 36-40.
LU Jun, XU Jialin, WANG Lu, et al. Physical simulation of height of water-flowing fractured zone influenced by fault activation after coal extraction[J]. China Coal News, 2012, 38(1): 36-40.
[10] 李振华, 许延春, 李龙飞, 等. 基于BP神经网络的导水裂隙带高度预测[J]. 采矿与安全工程学报, 2015,32(6):905-910.
LI Zhenhua, XU Yanchun, LI Longfei, et al. Forecast of the height of water flowing fractured zone based on BP neural networks[J]. Journal of Mining & Safety Engineering, 2015, 32(6): 905-910.
[11] 孙云普, 王云飞, 郑晓娟. 基于遗传-支持向量机法的煤层顶板导水断裂带高度的分析[J]. 煤炭学报, 2009,34(12):1 610-1 615.
SUN Yunpu, WANG Yunfei, ZHENG Xiaojuan. Analysis the height of water conducted zone of coal seam roof based on GA-SVR[J]. Journal of China Coal Society, 2009, 34(12): 1 610-1 615.
[12] 张宏伟, 朱志洁, 霍丙杰, 等. 基于改进的FOA-SVM导水裂隙带高度预测研究[J]. 中国安全科学学报, 2013,23(10):10-15.
ZHANG Hongwei, ZHU Zhijie, HUO Bingjie, et al. Water flowing fractured zone height prediction based on improved FOA-SVM[J]. China Safety Science Journal, 2013, 23(10): 10-15.
[13] 郭超, 张宏伟, 宋卫华, 等. 熵权属性测度理论在导水裂隙带高度预测中的应用[J]. 中国安全生产科学技术, 2014, 10(12): 87-91.
GUO Chao, ZHANG Hongwei, SONG Weihua, et al. Application of entropy weight attribute measure theory for predicting the height of water flowing fractured zone[J]. Journal of Safety Science and Technology, 2014, 10(12): 87-91.
[14] 陈建宏, 刘浪, 周智勇, 等. 基于主成分分析与神经网络的采矿方法优选[J]. 中南大学学报:自然科学版, 2010, 41(5): 1 967-1 972.
CHEN Jianhong, LIU Lang, ZHOU Zhiyong, et al. Optimization of mining methods based on combination of principal component analysis and neural networks[J]. Journal of Central South University:Science and Technology, 2010, 41(5): 1 967-1 972.
[15] MORALES-ESTEBAN A, MARTíNEZ-LVAREZ F, REYES J. Earthquake prediction in seismogenic areas of the Iberian Peninsula based on computational intelligence[J]. Tectonophysics, 2013, 593(3): 121-134.