img

QQ群聊

img

官方微信

高级检索

黄金科学技术

• 采选技术与矿山管理 • 上一篇    下一篇

矿井涌水量预测的PCA-GA-ELM模型及应用

刘志祥,刘奕然,兰明   

  1. 中南大学资源与安全工程学院,湖南  长沙   410083
  • 收稿日期:2016-06-30 修回日期:2016-11-14 出版日期:2017-02-28 发布日期:2017-05-12
  • 作者简介:刘志祥(1967-),男,湖南宁乡人,教授,博士生导师,从事岩石力学与采矿工程研究工作。liuzx@sina.com
  • 基金资助:

    国家自然科学基金项目“冲击载荷下岩石节理本构方程及其对应力波传播的影响”(编号:41372278)、“金属矿海底基岩开采裂隙分形演化与突水混沌孕育机制”(编号:51674288)和国家科技支撑计划项目“复杂地下金属矿二步开采与回收技术”(编号:2013BAB02B05)联合资助

Research on PCA-GA-ELM Model of Mine Inflow Prediction

LIU Zhixiang,LIU Yiran,LAN Ming   

  1. School of  Resources and Safety Engineering,Central South University,Changsha   410083,Hunan,China
  • Received:2016-06-30 Revised:2016-11-14 Online:2017-02-28 Published:2017-05-12

摘要:

为了快速有效地预测矿井涌水量,并进一步提高预测的准确性,在分析矿井涌水量影响因素的基础上,提出一种将主成分分析法(PCA)、遗传算法(GA)与极限学习机(ELM)相结合的矿井涌水量预测新方法。根据矿井涌水实例数据,综合选取9个主要因素作为矿井涌水量的预测指标,通过PCA对数据进行降维预处理,并针对ELM算法的不足,结合GA算法对其进行优化训练,建立矿井涌水量预测的PCA-GA-ELM模型。对模型进行训练及检验,并将PCA-GA-ELM模型与GA-ELM模型、单一ELM模型的预测结果进行对比分析,其预测结果与实际情况更吻合。该模型预测效果优于GA-ELM模型和ELM模型,可对矿井涌水量进行更准确有效的预测,提供科学的参考依据,指导矿山生产。

关键词: 矿井涌水量, 主成分分析, 遗传算法, ELM模型, 预测

Abstract:

In order to predict mine inflow more rapidly and effectively,and improve the prediction accuracy,a new method combining principal component analysis(PCA),genetic algorithm(GA) and extreme learning machine(ELM) for mine inflow prediction was proposed based on the analyses of mine inflow influence factors.According to the engineering example,9 main factors were selected as the prediction indexes,and PCA was used to reduce data dimension.Considering the disadvantage of ELM,GA was used to optimize the related parameters of ELM,and then PCA-GA-ELM model of mine inflow prediction was built.Then the model was trained and tested,and the prediction results of PCA-GA-ELM,GA-ELM and ELM model were comparatively analyzed.The prediction results fit better than the other two models with the actual situation.The PCA-GA-ELM model was superior to GA-ELM model and ELM,and it can be effectively applied to mine inflow prediction,which provided scientific references and guidance in mining production.

Key words: mine inflow, principal component analysis, genetic algorithm, ELM model, prediction

中图分类号: 

  • X935

[1] Chen Zhaoyan.Coalfield Hydrologic Geology[M].Beijing:China Coal Industry Publishing House,1989:7-35.[陈兆炎.煤田水文地质学[M].北京:煤炭工业出版社,1989:7-35.]
[2] Wang H,Luo A,Chai R,et al.Application of GM model in coal mine water inflow prediction[C]//2015 Seventh International Conference on Measuring Technology and Mechatronics Automation. IEEE,2015:192-195.
[3] Zhang Wenquan,Li Jiaxiang,Zhang Hongri,et al.A study on fuzzy prediction and control strategies of water flow from colliery roof[J].Mining Research and Development,2001,21(2):18-20. [张文泉,李家祥,张红日,等.矿井顶板涌水量的模糊预测与防治决策研究[J].矿业研究与开发,2001,21(2):18-20.]
[4] Jiang Su,Sun Yajun,Yang Lan,et al.Mine inrush water prediction based on BP neural network method[J].Coal Geology of China,2007,19(2):38-40.[姜素,孙亚军,杨兰,等.基于BP神经网络方法的矿井涌水量预测[J].中国煤田地质,2007,19(2):38-40.]
[5] Huang Cunhan,Feng Tao,Wang Weijun,et al.Mine water inrush prediction based on fractal and support vector machines[J].Journal of China Coal Society,2010,35(5):806-810. [黄存捍,冯涛,王卫军,等.基于分形和支持向量机矿井涌水量的预测[J].煤炭学报,2010,35(5):806-810.]
[6] Wei W,Shi L,Lu X,et al.Prediction of mine water inflow based on support vector machine[C]//2011 Workshop on Digital Media and Digital Content Management.IEEE,2011:326-329.
[7] Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:A new learning scheme of feedforward neural networks[C]//Proceedings of IEEE International Joint Conference on Neural Networks.New York:IEEE,2004:985-990.
[8] Massumi A,Gholami F.The influence of seismic intensity parameters on structural damage of RC buildings using principal components analysis[J].Applied Mathematical Modelling,2015,40(3):2161-2176.
[9] Lu Jintao,Li Xibing,Gong Fengqiang,et al.Recognizing of mine water inrush sources based on principal components analysis and fisher discrimination analysis method[J].China Safety Science Journal,2012,22(7):109-115.[鲁金涛,李夕兵,宫凤强,等.基于主成分分析与Fisher判别分析法的矿井突水水源识别方法[J].中国安全科学学报,2012,22(7):109-115.]
[10] Li Pei,Chen Ying,Ma Xiaoping,et al.Research of coal mine water burst forecasting method based on PCA-ELM[J].Industry and Mine Automation,2013,39(9):46-50.[李培,陈颖,马小平,等.基于PCA-ELM的煤矿突水预测方法研究[J].工矿自动化,2013,39(9):46-50.]
[11] Bian Xia,Mi Liang.Development on genetic algorithm theory and its application[J].Application Research of Computers,2010,27(7):2425-2429.[边霞,米良.遗传算法理论及其应用研究进展[J].计算机应用研究,2010,27(7):2425-2429.]
[12] Han Yibo.Gas emission prediction based on GA-ELM[J].Safety in Coal Mines,2015,46(4):166-169.[韩义波.基于GA-ELM的瓦斯涌出量预测[J].煤矿安全,2015,46(4):166-169.]
[13] Liu Qin,Ma Fengshan.Report on hydrogeological research in Xinli mining area[R].Beijing:Institute of Geology and Geophysics,Chinese Academy of Sciences,2007.[刘钦,马凤山.新立矿区水文地质研究报告[R].北京:中国科学院地质与地球物理研究所,2007.]
[14] Fan Limin,Wang Shuangming,Liu Shehu,et al.Outcome characteristics and influencing factor of coal mining waste water in Yushen mining area[J].Journal of Xi’an University of Science and Technology,2009,29(1):7-11.[范立民,王双明,刘社虎,等.榆神矿区矿井涌水量特征及影响因素[J].西安科技大学学报,2009,29(1):7-11.]
[15] Liu Zhixiang,Sun Jingjing,Tang Zhixiang.A risk rating model for seawater inrush in coastal metal deposits and its engineering application[J].Mining and Metallurgical Engineering,2015,35(1):6-9,13.[刘志祥,孙晶晶,唐志祥.滨海金属矿床海水涌入危险性等级评价模型及应用[J].矿冶工程,2015,35(1):6-9,13.]

[1] 李地元, 杨博, 刘子达, 刘永平, 赵君杰. 基于集成树算法的岩石黏聚力和内摩擦角预测方法[J]. 黄金科学技术, 2024, 32(5): 847-859.
[2] 任珩, 李沛霖, 李金潞. 基于黄金尾矿处理与综合利用研究的文献计量分析[J]. 黄金科学技术, 2024, 32(5): 939-948.
[3] 邓高, 李琪. 基于改进灰色模型的钢铁工业生产能耗预测研究[J]. 黄金科学技术, 2024, 32(3): 548-558.
[4] 张勇, 李水平, 荆鹏, 冯攀. 河南嵩县九仗沟金矿床地球化学特征与勘查模式[J]. 黄金科学技术, 2024, 32(2): 258-269.
[5] 周昌微, 谢贤平, 都喜东. 基于曲线拟合和神经网络的独头巷道CO浓度预测研究[J]. 黄金科学技术, 2024, 32(1): 75-81.
[6] 樊忠平, 张望, 王卫. 陕西省山阳—商南金矿成矿规律及找矿预测研究[J]. 黄金科学技术, 2023, 31(4): 560-579.
[7] 邓红卫, 罗亮. 基于SMA算法优化随机森林的PPV预测模型[J]. 黄金科学技术, 2023, 31(4): 624-634.
[8] 黄爽, 贾明涛, 鲁芳. 基于启发式遗传算法的地下采场作业计划优化模型[J]. 黄金科学技术, 2023, 31(4): 669-679.
[9] 王大福,刘建中,王泽鹏,陈发恩,杨成富,徐良易,李俊海,刘婧珂,潘启权,龙成雄,汪小勇. 贵州贞丰县卡务地区金矿地质特征与找矿预测[J]. 黄金科学技术, 2023, 31(3): 433-442.
[10] 寸小妮,薛玉山,王瑜亮,刘新伟. 陕西龙头沟金矿黄铁矿标型特征及其找矿意义[J]. 黄金科学技术, 2023, 31(1): 64-77.
[11] 符安宗,余欣朗,李成禄,杨文鹏,杨元江,郑博,赵瑞君. 元素比值在嫩江—黑河地区金成矿预测的应用初探[J]. 黄金科学技术, 2022, 30(6): 822-834.
[12] 蔡焕花,冯绍平,郭淳,王小涛,杨光忠,黄岚,张争辉. 豫西铁岭金铅矿床地质特征及找矿潜力分析[J]. 黄金科学技术, 2022, 30(6): 866-876.
[13] 杨珊,李文文,陈建宏. 基于PCA-RBF网络模型的硫化矿自燃安全性研究[J]. 黄金科学技术, 2022, 30(6): 958-967.
[14] 陈海龙,徐质彬,杨晓弘,杨海燕,吴圣刚,郑伯仁,高磊,陈俊辉. 烃汞叠加晕法在湖南万古金矿区及其外围深部找矿中的应用[J]. 黄金科学技术, 2022, 30(3): 366-381.
[15] 温廷新,苏焕博. 基于MICE_RF的组合赋权—极限随机树岩爆预测模型[J]. 黄金科学技术, 2022, 30(3): 392-403.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!