尹会永,周鑫龙,郎宁,张历峰,王明丽,吴焘,李鑫
YIN Huiyong,ZHOU Xinlong,LANG Ning,ZHANG Lifeng,WANG Mingli,WU Tao,LI Xin

• 1:山东科技大学地球科学与工程学院
• 2:枣庄矿业(集团)有限责任公司滨湖煤矿
• 3:山东省青岛生态环境监测中心
• 4:宁夏煤炭科学技术研究所有限公司

摘要(Abstract)：

随煤层开采深度的不断增加,煤矿生产过程中面临着复杂的突水机理和多变的突水主控因素,且各因素间相互联系的不确定性,使底板突水预测的难度不断增加。为准确预测底板突水危险性,针对底板突水的小样本、非线性问题,首先利用遗传算法(Genetic Algorithm,GA)将网络随机赋值的初始权值和阈值初次优化,再选取搜索能力强、稳定性较好的麻雀搜索算法(Sparrow SearchAlgorithm,SSA)对权值和阈值进行二次寻优,从而建立SSA-GA-BP神经网络底板突水预测模型。分析整理山东省滨湖煤矿地质及水文地质资料,选取含水层水压、含水层厚度、隔水层厚度、断层密度、断层分维值、渗透系数、单位涌水量、底板破坏深度共8个因素,作为预测底板突水的主控因素,绘制各主控因素3D映射投影曲面图;利用Surfer软件中的克里金插值法提取50个数据点作为模型的输入样本(分为训练集40个,测试集10个),对模型进行训练学习,训练误差精度达到要求后,对滨湖煤矿3个未开采工作面的12个数据点进行突水危险性预测。为了验证所建模型的准确性,利用BP、GA-BP、SSA-GA-BP这3种模型对测试集进行预测;为避免模型仅与BP网络预测对比的片面性,同时选取以熵权法确定权重的模糊综合评判法对测试集进行预测;将各网络模型及方法的预测结果与实际值进行对比分析。结果表明:基于SSA优化的GA-BP神经网络模型突水预测误差较小,预测结果准确率更高,为矿井水害预测预报提供了科学的评价方法和理论依据。
With the increase of coal mining depth, coal production process is faced with complex water inrush mechanism and variable water inrush main control factors, and the uncertainties among the factors make the prediction of floor water inrush more difficult. In order to accurately predict the risk of floor water inrush, aiming at the small sample and non-linear problem of floor water inrush, firstly, genetic Algorithm is used to optimize the initial weights and thresholds of network random assignment, and then Sparrow Search Algorithm with strong search ability and good stability is selected to optimize the weights and thresholds for the second time, so as to establish the SSA-GA-BP neural network floor water inrush prediction model. Based on the analysis of geological and hydrological data of Binhu Coal Mine in Shandong Province, 8 factors including water pressure of aquifer, aquifer thickness, aquiclude thickness, fault density, fractal dimension value of fault, permeability coefficient, unit water inflow and floor failure depth are selected as the main control factors to predict floor water inrush, mapping the main controlling factors of 3 D surface map projection. The Kriging interpolation method in surfer software is used to extract 50 data points as the input samples of the model(including 40 training sets and 10 test sets). The model is trained and studied. After the training error accuracy meets the requirements, the water inrush risk of 12 data points of 3 unmined working faces in Binhu Coal Mine is predicted. To verify the accuracy of the model, BP, GA-BP and SSA-GA-BP models are used to predict the test set; to avoid the one-sideness of comparing the model only with the prediction of BP network, the Fuzzy Comprehensive Evaluation Method, which determines the weight by Entropy Weight Method, is selected to predict the test set. The prediction results of each network model and method are compared with the actual values for analysis. The results show that the water inrush prediction error of GA-BP neural network model optimized by sparrow search algorithm is smaller, and the prediction accuracy is higher,which provides a scientific theoretical basis for mine water disaster prediction.

关键词(KeyWords)： 底板突水预测;麻雀搜索算法;遗传算法;BP神经网络;熵权法;模糊综合评判
prediction of water inrush from floor;Sparrow Search Algorithm;Genetic Algorithm;BP neural network;Entropy Weight Method;Fuzzy Comprehensive Evaluation

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划课题(2017YFC0804101);; 山东省自然科学基金项目(ZR2019MD013)

作者(Author): 尹会永,周鑫龙,郎宁,张历峰,王明丽,吴焘,李鑫
YIN Huiyong,ZHOU Xinlong,LANG Ning,ZHANG Lifeng,WANG Mingli,WU Tao,LI Xin

参考文献(References)：

• [1]武强.我国矿井水防控与资源化利用的研究进展、问题和展望[J].煤炭学报，2014,39(5):795-805.WU Qiang.Progress,problems and prospects of prevention and control technology of mine water and reutilization in China[J].Journal of China Coal Society,2014,39(5):795-805.
• [2]王皓，董书宁，乔伟，等.矿井水害防控远程服务云平台构建与应用[J].煤田地质与勘探，2021,49(1):208-216.WANG Hao,DONG Shuning,QIAO Wei,et al.Construction and application of remote service cloud platform for mine water hazard prevention and control[J].Coal Geology&Exploration,2021,49(1):208-216.
• [3]靳德武.我国煤矿水害防治技术新进展及其方法论思考[J].煤炭科学技术，2017,45(5):141-147.JIN Dewu.New development of water disaster prevention and control technology in China coal mine and consideration on methodology[J].Coal Science and Technology,2017,45(5):141-147.
• [4]虎维岳，田干.我国煤矿水害类型及其防治对策[J].煤炭科学技术，2010,38(1):92-96.HU Weiyue,TIAN Gan.Mine water disaster type and prevention and control counter measures in China[J].Coal Science and Technology,2010,38(1):92-96.
• [5]肖建于，童敏明，姜春露.基于模糊证据理论的煤层底板突水量预测[J].煤炭学报，2012,37(增刊1):131-137.XIAO Jianyu,TONG Minming,JIANG Chunlu.Prediction of water inrush quantity from coal floor based on fuzzy evidence theory[J].Journal of China Coal Society,2012,37(Sup.1):131-137.
• [6]刘景，冯光俊，吴晓军，等.基于层次分析法的富水区预测及其在顶板突水危险性评价中的作用[J].煤矿安全，2019,50(5):204-208.LIU Jing,FENG Guangjun,WU Xiaojun,et al.Prediction of water rich area based on AHP and its role in risk assessment of roof water inrush[J].Safety in Coal Mines,2019,50(5):204-208.
• [7]尹会永，魏久传，刘同彬，等.基于多源信息复合的煤层底板突水评价[J].山东科技大学学报(自然科学版)，2008,27(2):6-9.YIN Huiyong,WEI Jiuchuan,LIU Tongbin,et al.Evaluation of water inrush in seam floor based on multi-originated information complex[J].Journal of Shandong University of Science and Technology(Natural Science),2008,27(2):6-9.
• [8]韩承豪，魏久传，谢道雷，等.基于集对分析-可变模糊集耦合法的砂岩含水层富水性评价：以宁东矿区金家渠井田侏罗系直罗组含水层为例[J].煤炭学报，2020,45(7):2432-2443.HAN Chenghao,WEI Jiuchuan,XIE Daolei,et al.Water-richness evaluation of sandstone aquifer based on set pair analysis-variable fuzzy set coupling method:A case from Jurassic Zhiluo Formation of Jinjiaqu coal mine in Ningdong mining area[J].Journal of China Coal Society,2020,45(7):2432-2443.
• [9]李彦民，周晨阳，李凤莲.基于代价敏感理论的多决策树煤层底板突水预测模型[J].工矿自动化，2020,46(12):76-83.LI Yanmin,ZHOU Chenyang,LI Fenglian.Multi-decision tree prediction model for coal seam floor water inrush based on cost-sensitive theory[J].Industry and Mine Automation,2020,46(12):76-83.
• [10]张晓亮.熵权耦合层次分析赋权在煤层底板突水评价中的应用[J].煤田地质与勘探，2017,45(3):91-95.ZHANG Xiaoliang.Application of entropy weight method and analytic hierarchy process in evaluation of water inrush from coal seam floor[J].Coal Geology&Exploration,2017,45(3):91-95.
• [11]刘伟韬，廖尚辉，刘士亮，等.主成分logistic回归分析在底板突水预测中的应用[J].辽宁工程技术大学学报(自然科学版)，2015,34(8):905-909.LIU Weitao,LIAO Shanghui,LIU Shiliang,et al.Principal component logistic regression analysis in application of water outbursts from coal seam floor[J].Journal of Liaoning Technical University(Natural Science),2015,34(8):905-909.
• [12]YIN Huiyong,ZHOU Wanfang,LAMOREAUX J W,et al.Water inrush conceptual site models for coal mines of China[J].Environmental Earth Sciences,2018,77(22):746.
• [13]赵琳琳，温国锋，邵良杉.煤层底板突水危险性GSPCA-LSSVM评价模型[J].中国安全科学学报，2018,28(2):128-133.ZHAO Linlin,WEN Guofeng,SHAO Liangshan.GSPCA-LSSVM model for evaluating risk of coal floor groundwater bursting[J].China Safety Science Journal,2018,28(2):128-133.
• [14]刘晨雨，魏久传，王杰，等.基于AHP-TFN模型的底板突水危险性预测[J].中国矿业，2019,28(8):124-129.LIU Chenyu,WEI Jiuchuan,WANG Jie,et al.Prediction of floor water inrush risk based on AHP-TFN model[J].China Mining Magazine,2019,28(8):124-129.
• [15]施龙青，曲兴玥，韩进，等.多模型融合评价煤层底板灰岩岩溶突水危险性[J].煤炭学报，2019,44(8):2484-2493.SHI Longqing,QU Xingyue,HAN Jin,et al.Multi-model fusion for assessing the risk of inrush of limestone karst water through mine floor[J].Journal of China Coal Society,2019,44(8):2484-2493.
• [16]于小鸽，韩进，施龙青，等.基于BP神经网络的底板破坏深度预测[J].煤炭学报，2009,34(6):731-736.YU Xiaoge,HAN Jin,SHI Longqing,et al.Forecast of destroyed floor depth based on BP neural networks[J].Journal of China Coal Society,2009,34(6):731-736.
• [17]陈建平，王春雷，王雪冬.基于CNN神经网络的煤层底板突水预测[J].中国地质灾害与防治学报，2021,32(1):50-57.CHEN Jianping,WANG Chunlei,WANG Xuedong.Coal mine floor water inrush prediction based on CNN neural network[J].The Chinese Journal of Geological Hazard and Control,2021,32(1):50-57.
• [18]施龙青，张荣遨，徐东晶，等.基于GWO-Elman神经网络的底板突水预测[J].煤炭学报，2020,45(7):2455-2463.SHI Longqing,ZHANG Rongao,XU Dongjing,et al.Prediction of water inrush from floor based on GWO-Elman neural network[J].Journal of China Coal Society,2020,45(7):2455-2463.
• [19]薛建凯.一种新型的群智能优化技术的研究与应用：麻雀搜索算法[D].上海：东华大学，2020.XUE Jiankai.Research and application of a novel swarm intelligence optimization technique:Sparrow search algorithm[D].Shanghai:Donghua University,2020.
• [20]祁春燕，邱国庆，张海荣.底板突水预测模型的影响因素分析[J].武汉大学学报(信息科学版)，2013,38(2):153-156.QI Chunyan,QIU Guoqing,ZHANG Hairong.Influencing factors analysis of floor water invasion prediction model[J].Geomatics and Information Science of Wuhan University,2013,38(2):153-156.
• [21]YIN Huiyong,SHI Yongli,NIU Huigong,et al.A GIS-based model of potential groundwater yield zonation for a sandstone aquifer in the Juye coalfield,Shangdong,China[J].Journal of Hydrology,2018,557:434-447.
• [22]吕鑫，慕晓冬，张钧，等.混沌麻雀搜索优化算法[J/OL].北京航空航天大学学报，2020:1-10.[2020-08-31].https://doi.org/10.137001j.bh.1001-5965.2020.0298LYU Xin,MU Xiaodong,ZHANG Jun,et al.Chaos sparrow search optimization algorithm[J/OL].Journal of Beijing University of Aeronautics and Astronautics,2020:1-10.[2020-08-31].https://doi.org/10.137001j.bh.1001-5965.2020.0298
• [23]王嵘冰，徐红艳，李波，等.BP神经网络隐含层节点数确定方法研究[J].计算机技术与发展，2018,28(4):31-35.WANG Rongbing,XU Hongyan,LI Bo,et al.Research on method of determining hidden layer nodes in BP neural network[J].Computer Technology and Development,2018,28(4):31-35.
• [24]尹会永，赵涵，徐琳，等.岩体质量分级的改进模糊综合评价法[J].金属矿山，2020(7):53-58.YIN Huiyong,ZHAO Han,XU Lin,et al.Classification of rock mass in mine based on improved fuzzy comprehensive evaluation method[J].Metal Mine,2020(7):53-58.
• [25]李竞赢，刘启蒙，刘瑜，等.基于GIS与熵值法的煤层顶板突水危险性评价[J].煤炭工程，2019,51(8):115-119.LI Jingying,LIU Qimeng,LIU Yu,et al.Risk assessment of water inrush from coal seam roof based on GIS and entropy method[J].Coal Engineering,2019,51(8):115-119.

文章评论(Comment)：