img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2021, Vol. 29 ›› Issue (5): 658-668.doi: 10.11872/j.issn.1005-2518.2021.05.168

• 采选技术与矿山管理 • 上一篇    下一篇

基于主成分分析和PSO-ELM算法的排土场稳定性预测模型

高峰(),吴晓东(),周科平   

  1. 中南大学资源与安全工程学院,湖南 长沙 410083
  • 收稿日期:2020-09-21 修回日期:2021-04-13 出版日期:2021-10-31 发布日期:2021-12-17
  • 通讯作者: 吴晓东 E-mail:csugaofeng@126.com;919119314@qq.com
  • 作者简介:高峰(1981-),男,湖南怀化人,副教授,从事金属矿开采和矿山工程灾害机理相关研究工作。csugaofeng@126.com
  • 基金资助:
    国家自然科学基金项目“高寒冻融区露天矿岩质边坡裂隙网络扩展行为多尺度时空演化机制”(51774323);“十三五”国家重点研发计划课题“硼镁铁矿资源清洁高效利用与固废源头减量关键技术及示范”(2020YFC1909801);校级自主探索基金项目“高原寒区排土场基底软层冻融特性及边坡稳定性分析”(2019zzts984)

Prediction Model of Soil Dump Stability Based on Principal Component Analysis and PSO-ELM Algorithm

Feng GAO(),Xiaodong WU(),Keping ZHOU   

  1. School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China
  • Received:2020-09-21 Revised:2021-04-13 Online:2021-10-31 Published:2021-12-17
  • Contact: Xiaodong WU E-mail:csugaofeng@126.com;919119314@qq.com

摘要:

针对排土场边坡稳定性分析,提出了一种利用主成分分析法降低数据冗余性、粒子群算法优化极限学习机权值阈值的PCA-PSO-ELM排土场边坡稳定性预测模型。确定了土壤黏聚力、内摩擦角、排土场斜角、地基承载力、地震烈度、降雨和降雪条件、排土工艺以及乱采乱挖状况8个排土场稳定性预测指标,针对100组相应排土场数据,采用训练时间、RMSE值和决定系数R2来评价和对比PCA-PSO-ELM模型与BP神经网络模型、ELM模型和PSO-ELM模型预测结果的有效性。研究结果表明:利用经PCA降维处理过的排土场稳定性样本数据作为输入变量去训练和测试PSO-ELM网络模型,预测值与真实值非常接近,其预测精度和效率不仅高于ELM算法,而且远远优于传统BP神经网络算法。经过PCA法优化的PSO-ELM模型与未经PCA处理过的PSO-ELM模型相比,前者在效率相差甚微的基础上大幅缩短了计算时间,证明了该方法具有一定的实用价值。

关键词: 排土场安全, 稳定性评价, 极限学习机, 主成分分析, 人工神经网络, 粒子群算法

Abstract:

Aiming at the stability analysis of dump slope,a PCA-PSO-ELM dump slope stability prediction model is proposed in this paper,which uses principal component analysis method to reduce data redundancy and particle swarm optimization algorithm to optimize the weight threshold of extreme learning machine. Eight prediction indexes of dump stability were determined in this model,including soil cohesion,internal friction angle,dump slope angle,foundation bearing capacity,seismic intensity,rainfall and snowfall conditions,dumping technology and random mining and digging conditions.According to 100 groups of corresponding dump data,training time,RMSE value and determination coefficient R2 were used to evaluate and compare the validity of prediction results of PCA-PSO-ELM model,BP neural network model,ELM model and PSO-ELM model.The research results show that as the input variable to train and test the PSO-ELM network model,the dump stability sample data processed by PCA dimensionality reduction,made predicted value very close to the real value.The prediction accuracy and efficiency are not only higher than the ELM algorithm,but also far better than the traditional BP neural network algorithm.Compared with the PSO-ELM model without PCA treatment,the PSO-ELM model optimized by PCA method can significantly shorten the calculation time on the basis of little difference in efficiency,which proves that the method has certain practical value.

Key words: dump sites’ safety, stability evaluation, extreme learning machine, principal component analysis, artificial neutral network, particle swarm algorithm

中图分类号: 

  • X43

图1

ELM网络结构图"

图2

PSO-ELM模型构建流程"

图3

排土场数据箱线图"

表1

方差及主成分贡献率"

成分初始特征值提取平方和载入
合计方差 百分比累计贡献率/%合计方差 百分比累计贡献率/%
15.55269.40669.4065.55269.40669.406
21.04913.11082.5161.04913.11082.516
30.4145.17987.695
40.3203.99891.693
50.2202.75194.444
60.1722.15196.595
70.1501.87598.470
80.1221.530100.000

表2

主成分因子载荷矩阵"

影响因素主成分
X1X2
黏聚力0.1550.202
内摩擦角0.1590.127
边坡角度0.1260.575
地基承载力0.152-0.358
地震烈度0.1510.390
降雨和降雪条件0.151-0.373
排土工艺0.157-0.113
乱采乱挖0.147-0.367

图4

不同激励函数的PSO-ELM模型中的预测误差与隐层节点数的关系"

图5

PSO-ELM模型不同学习因子的性能比较"

图6

150次迭代中PCA-PSO-ELM模型和PSO-ELM模型的均方误差变化情况"

表3

不同模型的输出结果对比"

样本

编号

真实值预测值
BPNNELMPSO-ELMPCA-PSO-ELM
915(V)5.54434.66995.09365.0850
923(III)3.47793.17143.02143.0184
931(I)1.81001.18420.95210.9028
944(IV)4.96113.86483.86993.8195
951(I)1.16541.43051.09351.0040
964(IV)3.61223.99964.05443.9933
975(V)5.62364.94384.99375.0779
981(I)0.81020.78960.99940.9721
993(III)3.94713.31573.06903.0034
1005(V)4.95324.72094.89554.9943

RMSE 值

时间/s

0.60050.24510.07470.0752
0.35330.176526.946712.9354

图7

多种模型的预测结果对比"

Bishop A W,1955.The use of the slip circle in the stability analysis of slopes[J].Geotechnique,5(1):7-17.
Cao Lanzhu,Wang Zhen,Wang Dong,al et,2017.Numerical simulation of stability during dumping of soft soil dump site[J].Journal of Disaster Prevention and Mitigation Engineering,37(5):776-781.
Castano A,Fernandez-Navarre F,Hervas-Martinez C,2013.PCA-ELM:A robust and pruned extreme learning machine approach based on principal component analysis[J].Neural Processing Letters,37(3):377-392.
Chen Peng,Chen Pengfei,2010.Slope stability analysis of open-pit mine dump[J].Journal of Liaoning Technical University(Natural Science Edition),29(6):1028-1031.
Cho S E,2009.Probabilistic stability analyses of slopes using the ANN-based response surface[J].Computers & Geotechnics,36(5):787-797.
Gordan B,Armaghani D J,Hajihassani M,al et,2016.Prediction of seismic slope stability through combination of particle swarm optimization and neural network[J].Engineering with Computers,32(1):85-97.
He Tingting,Shang Yuequan,Qing Lü,al et,2013.Support vector machine method for slope reliability analysis[J].Rock and Soil Mechanics,34(11):3269-3276.
Hong W P,Song Y S,Lim S G,2005.Stability evaluation of the cut slope using artificial neural network model[J].Journal of the Korean Society of Civil Engineers,25(4C):15-21.
Janbu N,1975.Slope stability computations:In embankment-dam engineering.Textbook.Eds.R.C.Hirschfeld and S.J.Poulos.John Wiley and Sons Inc.Pub.NY,1973,40P[J].International Journal of Rock Mechanics and Mining sciences & Geomechanics Abstracts,12(4):67.
Jolliffe I T,Cadima J,2016.Principal component analysis:A review and recent developments[J].Philosophical Transactions of the Royal Society Mathematical Physical & Engineering Sciences,374(2065):20150202.
Kang F,Li J J,2016.Artificial bee colony algorithm optimized support vector regression for system reliability analysis of slopes[J].Journal of Computing in Civil Engineering,30(3):04015040.
Li Wei,2014.Slope stability analysis and treatment technology of open-pit coal mine dump site[J].Coal Science and Technology,42(10):37-40,5.
Liu D J,Han L S,Hu J,al et,2015.DCPSO-BP model of slope stability research[C] //International Conference on Mechanics,Building Material and Civil Engineering.Pennsylvania:DEStech Publication. Inc.
Liu Z B,Shao J F,Xu W Y,al et,2014.An extreme learning machine approach for slope stability evaluation and prediction[J].Natural Hazards,73(2):787-804.
Lu H J,Du B J,Liu J Y,al et,2017.A kernel extreme learning machine algorithm based on improved particle swam optimization[J].Memetic Computing,9(2):121-128.
Luan Tingting,2015.Research and Application of Early Warning Method of Open-pit Mine Dump Landslide[D].Beijing:University of Science and Technology Beijing.
Morgenstern N R,Price V E,1967.A numerical method for solving the equations of stability of general slip surfaces[J].The Computer Journal,9(4):388-393.
Shao Liangshan,Ma Han,Wen Tingxin,2015.Prediction of slope stability based on RF-ELM model[J].China Safety Science and Technology,11(3):93-98.
Shi L,Yang Y L,Lü J H,2015.PCA-PSO-BP neural network application in IDS[C]// International Power,Electronics & Materials Engineering Conference.Paris:Atlantis Press,145-150.DOI:https://doi.org/10.2991/ipemec-15.2015.29.
doi: https://doi.org/10.2991/ipemec-15.2015.29
Spencer E,1967.A method of analysis of the stability of embankments assuming parallel inter-slice forces[J].Geotechnique,17(1):11-26.
Su Guoshao,Zhao Wei,Peng Lifeng,al et,2014.Gaussian dynamic response surface method for slope failure probability estimation[J].Rock and Soil Mechanics,35(12):3592-3601.
Su Yonghua,Luo Zhengdong,Zhang Panfeng,al et,2013.Active search method of slope stability reliability based on Kriging[J].Chinese Journal of Geotechnical Engineering,35(10):1863-1869.
Su Yonghua,Yang Hongbo,2012.Slope stability reliability algorithm based on proxy model[J].Chinese Journal of Applied Mechanics,29(6):705-710,776.
Tan Xiaohui,Hu Xiaojun,Chu Chengfu,al et,2011.Fuzzy response surface method and its application in the reliability analysis of slope stability[J].Journal of University of Science and Technology of China,41(3):233-237,243.
Wang Biaolong,Meng Fanli,Zeng Chao,al et,2019.Landslide reliability evaluation method of PSO-BP neural network based on natural selection strategy[J].China & Foreign Highway,39(3):1-9.
Wang Yu,Wang Chunlei,Wang Can,al et,2011.Research and application of vector projection response surface for slope reliability evaluation[J].Chinese Journal of Geotechnical Engineering,33(9):1434-1439.
Wen Tingxin,Zhu Jing,2018.Slope stability prediction based on SAPSO-ELM[J].Journal of Safety and Environment,18(6):2146-2150.
Xue X H,2016.Prediction of slope stability based on hybrid PSO and LSSVM[J].Journal of Computing in Civil Engineering,31(1):04016041.
Yi P,Wei K T,Kong X,al et,2015.Cumulative PSO-Kriging model for slope reliability analysis[J].Probabilistic Engineering Mechanics,39:39-45.
Zhai Wenlong,Zhou Hanmin,2015.Application of simplified bishop method and co-thrust method to stability calculation of high step dumping site[J].Modern Mining,31(8):168-170.
Zhang Lijun,Mu Chuanwei,He Fangwei,2015.Stability analysis of dump site slope based on strength reduction finite element method[J].Modern Mining,31(8):159-160.
Zhang Qiwei,Ma Shuzhi,Jia Hongbiao,2015.Comparative analysis of FLAC 3D method and rigid body limit equilibrium method for stability evaluation of mine dumps[J].Mining Research and Development,35(6):45-48.
曹兰柱,王珍,王东,等,2017.软弱基底排土场堆载过程中稳定性数值模拟[J].防灾减灾工程学报,37(5):776-781.
陈鹏,陈鹏飞,2010.露天矿排土场边坡稳定性分析[J].辽宁工程技术大学学报(自然科学版),29(6):1028-1031.
翟文龙,周汉民,2015.简化Bishop法和余推力法在高台阶排土场稳定性计算中的应用[J].现代矿业,31(8):168-170.
何婷婷,尚岳全,吕庆,等,2013.边坡可靠度分析的支持向量机法[J].岩土力学,34(11):3269-3276.
李伟,2014.露天煤矿排土场边坡稳定性分析与治理技术[J].煤炭科学技术,42(10):37-40,5.
栾婷婷,2015.露天矿排土场滑坡预警方法的研究及应用[D].北京:北京科技大学.
邵良杉,马寒,温廷新,2015.基于RF-ELM模型的边坡稳定性预测研究[J].中国安全生产科学技术,11(3):93-98.
苏国韶,赵伟,彭立锋,等,2014.边坡失效概率估计的高斯过程动态响应面法[J].岩土力学,35(12):3592-3601.
苏永华,罗正东,张盼凤,等,2013.基于Kriging的边坡稳定可靠度主动搜索法[J].岩土工程学报,35(10):1863-1869.
苏永华,杨红波,2012.基于代理模型的边坡稳定可靠度算法[J].应用力学学报,29(6):705-710,776.
谭晓慧,胡晓军,储诚富,等,2011.模糊响应面法及其在边坡稳定可靠度分析中的应用[J].中国科学技术大学学报,41(3):233-237,243.
王彪龙,孟凡利,曾超,等,2019.基于自然选择策略的PSO-BP神经网络的滑坡可靠性评价方法[J].中外公路,39(3):1-9.
王宇,王春磊,汪灿,等,2011.边坡可靠性评价的向量投影响应面研究及应用[J].岩土工程学报,33(9):1434-1439.
温廷新,朱静,2018.基于SAPSO-ELM的边坡稳定性预测[J].安全与环境学报,18(6):2146-2150.
张利军,母传伟,何方维,2015.基于强度折减有限元法的排土场边坡稳定性分析[J].现代矿业,31(8):159-160.
张其唯,马淑芝,贾洪彪,2015.矿山排土场稳定性评价的FLAC 3D方法和刚体极限平衡法对比分析[J].矿业研究与开发,35(6):45-48.
[1] 叶光祥,黄智群,王晓军,张树标,苑栋. 基于未确知测度理论的石英脉型钨矿山采空区稳定性评价[J]. 黄金科学技术, 2021, 29(3): 433-439.
[2] 骆正山,黄仁惠,申国臣. 基于KPCA-IPSO-LSSVM的充填管道磨损风险预测[J]. 黄金科学技术, 2021, 29(2): 245-255.
[3] 许瑞, 侯奎奎, 王玺, 刘兴全, 李夕兵. 基于核主成分分析与SVM的岩爆烈度组合预测模型[J]. 黄金科学技术, 2020, 28(4): 575-584.
[4] 陈超民,冷成彪,司国辉. 基于GIS与层次分析法的综合成矿预测——以新疆库米什地区为例[J]. 黄金科学技术, 2020, 28(2): 213-227.
[5] 韩超群,陈建宏,周智勇,杨珊. 基于主成分分析—支持向量机模型的矿岩可爆性等级预测研究[J]. 黄金科学技术, 2019, 27(6): 879-887.
[6] 崔宇,李夕兵,董陇军,白吕. 玲珑金矿微震监测台网布设优化[J]. 黄金科学技术, 2019, 27(3): 417-424.
[7] 段学良,马凤山,赵海军,郭捷,顾鸿宇,刘帅奇. 滨海矿山矿坑涌水源识别与混合比研究[J]. 黄金科学技术, 2019, 27(3): 406-416.
[8] 徐金国,戴兴国,闫泽正. 基于D-S证据理论—正态隶属度的岩土边坡稳定性评价[J]. 黄金科学技术, 2018, 26(6): 780-787.
[9] 周子龙,王亦凡,柯昌涛. “多米诺骨牌”破坏现象下的矿柱群系统可靠度评价[J]. 黄金科学技术, 2018, 26(6): 729-735.
[10] 周智勇, 肖玮, 陈建宏, 李欢. 基于PCA和GM(1,1)的矿山生态环境预测模型[J]. 黄金科学技术, 2018, 26(3): 372-378.
[11] 刘强,李夕兵,梁伟章. 岩体质量分类的PCA-RF模型及应用[J]. 黄金科学技术, 2018, 26(1): 49-55.
[12] 邓高,杨珊. 基于组合预测与变精度粗糙模糊集的采空区稳定性评价[J]. 黄金科学技术, 2017, 25(3): 98-107.
[13] 张钦礼,王兢*,王新民. 基于核主成分分析与PSO-SVM的充填管道失效风险性分级评价模型[J]. 黄金科学技术, 2017, 25(3): 70-76.
[14] 刘志祥,刘奕然,兰明. 矿井涌水量预测的PCA-GA-ELM模型及应用[J]. 黄金科学技术, 2017, 25(1): 61-67.
[15] 史秀志,范玉乾,尚雪义. 基于PCA-BP神经网络模型的充填体强度预测[J]. 黄金科学技术, 2016, 24(3): 64-69.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!