吕伟才;黄晖;池深深;韩必武;

• 1:安徽理工大学测绘学院
• 2:淮南矿业(集团)有限责任公司
• 3:安徽理工大学地球与环境学院

摘要(Abstract)：

在分析BP神经网络不足的基础上,为提高概率积分法进行开采沉陷预计时所采用的预计参数的正确性,该文建立了地质采矿条件与预计参数之间的非线性关系,以我国43个地表移动观测站的实测数据为训练和测试样本,采用多种群遗传算法(MPGA)优化BP神经网络的权值和阈值,构建新的概率积分法参数解算方法。计算结果表明,较单纯的BP神经网络算法和标准的遗传算法而言,MPGA算法优化的BP神经网络算法解算的预计参数具有更高的相对精度,这对于获取待研究区域的高精度概率积分法预计参数具有良好的指导意义。

关键词(KeyWords)： 开采沉陷;概率积分法;预计参数;BP神经网络;多种群遗传算法

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41474026,41602357,41404002,41704008);; 淮南矿业(集团)有限责任公司项目(HNKY-JTJS(2018)-178,HNKY-JTJS(2017)-122,HNKY-JTJS(2013)-28)

作者(Authors): 吕伟才;黄晖;池深深;韩必武;

DOI: 10.16251/j.cnki.1009-2307.2019.09.006

参考文献(References)：

• [1] 余学祥,吕伟才,柯福阳,等.煤矿开采沉陷自动化监测系统[M].北京:测绘出版社,2014:48-57.(YU Xuexiang,LYU Weicai,KE Fuyang,et al.Automatic Monitoring system for coal mining subsidence[M].Beijing:Mapping Publishing House,2014:48-57.)
• [2] 王磊,陈元非.主断面移动与变形归化计算模型及鲁棒性求参新方法[J].岩石力学与工程学报,2016,35(9):1823-1829.(WANG Lei,CHEN Yuanfei.A modified model for movement and deformation in main sectional plane and a new robustness method for calculating parameters[J].Chinese Journal of Rock Mechanics and Engineering,2016,35(9):1823-1829.)
• [3] 池深深,王磊,李楠,等.顾及数据新鲜度函数Knothe的开采沉陷最优组合预测模型及应用[J].煤矿安全,2018,49(5):230-234.(CHI Shenshen,WANG Lei,LI Nan,et al.Research on optimal combination model of mining subsidence considering data freshness function Knothe and its application[J].Safety in Coal Mines,2018,49(5):230-234.)
• [4] 周大伟,安士凯,张静,等.概率积分参数选取的主成分回归分析[J].辽宁工程技术大学学报(自然科学版),2013,32(11):1528-1532.(ZHOU Dawei,AN Shikai,ZHANG Jing,et al.A principal component regression analysis for calculating probability integration method parameters[J].Journal of Liaoning Technical University(Natural Science),2013,32(11):1528-1532.)
• [5] 禹建丽,黄鸿琦,苗满香.基于主成分分析与神经网络的多响应参数优化[J].系统仿真学报,2018,30(1):176-183,190.(YU Jianli,HUANG Hongqi,MIAO Manxiang. Multi-response parameters optimization based on PCA and neural network[J].Journal of System Simulation,2018,30(1):176-183,190.)
• [6] 赵忠明,施天威,董伟,等.灰色关联分析与BP神经网络的概率积分法参数预测[J].测绘科学,2017,42(7):36-40.(ZHAO Zhongming,SHI Tianwei,DONG Wei,et al.The prediction of probability-integral method parameters based on grey relational analysis and BP neural network[J].Science of Surveying and Mapping,2017,42(7):36-40.)
• [7] 陈星,武丽芳,王福明.基于GA-BP神经网络的股票预测研究[J].山西电子技术,2014(1):93-94.(CHEN Xing,WU Lifang,WANG Fuming.The research of stock prediction based on GA-BP neural network[J].Shanxi Electronic Technology,2014(1):93-94.)
• [8] 张涛,胡海峰,廉旭刚.开采沉陷预计参数的广适应性BP神经网络反演方法[J].中国矿业,2016,25(S2):251-255.(ZHANG Tao,HU Haifeng,LIAN Xugang.Wide adaptive BP neural network method for mining subsidence prediction parameters inversion[J].China Mining Magazine,2016,25(S2):251-255.)
• [9] 陈林,黄腾,郑浩.变形预测的小波神经网络模型改进[J].测绘科学,2017,42(9):112-115.(CHEN Lin,HUANG Teng,ZHENG Hao.The model improvement of wavelet neural network in deformation prediction[J].Science of Surveying and Mapping,2017,42(9):112-115.)
• [10]杜孙稳,张锦,邓增兵,等.基于GA-BP神经网络的地基干涉雷达监测效能分析[J].大地测量与地球动力学,2017,37(8):876-880.(DU Sunwen,ZHANG Jin,DENG Zengbing,et al.GB-SAR monitoring effectiveness analysis using genetic algorithm optimized BP neural network[J].Journal of Geodesy and Geodynamics,2017,37(8):876-880.)
• [11]邓传军,欧阳斌,陈艳红.一种基于PSO-BP神经网络的建筑物沉降预测模型[J].测绘科学,2018,43(6):27-31.(DENG Chuanjun,OUYANG Bin,CHEN Yanhong.A buliding settlement prediction model based on PSO-BP neural network[J].Science of Surveying and Mapping,2018,43(6):27-31.)
• [12]丰秋林,郑南山,刘晨,等.BP神经网络辅助的GNSS反射信号土壤湿度反演[J].测绘科学,2018,43(8):157-162.(FENG Qiulin,ZHENG Nanshan,LIU Chen,et al.BP neural network assisted soil moisture retrieval using GNSS satellite reflected signal[J].Science of Surveying and Mapping,2018,43(8):157-162.)
• [13]周斌,曹勇,王禹林,等.基于BP神经网络的大型螺纹旋风铣削表面粗糙度预测[J].组合机床与自动化加工技术,2015(7):5-7.(ZHOU Bin,CAO Yong,WANG Yulin,et al.Prediction of surface roughness of largescale thread hard whirling based on BP neural network[J].Modular Machine Tool &Automatic Manufacturing Technique,2015(7):5-7.)
• [14]郭文兵,邓喀中,邹友峰.概率积分法预计参数选取的神经网络模型[J].中国矿业大学学报,2004,33(3):322-326.(GUO Wenbing,DENG Kazhong,ZOU Youfeng.Artificial neural network model for predicting parameters of probability integral method[J].Journal of China University of Mining &Technology,2004,33(3):322-326.)
• [15]施建俊,李庆亚,张琪,等.基于Matlab和BP神经网络的爆破振动预测系统[J].爆炸与冲击,2017,37(6):1087-1092.(SHI Jianjun,LI Qingya,ZHANG Qi,et al.Forecast system for blasting vibration velocity peak based on Matlab and BP neural network[J].Explosion and Shock Waves,2017,37(6):1087-1092.)