基于IGSA-BP网络的瓦斯涌出量预测模型
|
摘要
为提高煤矿瓦斯涌出量预测的精度和效率,提出一种基于改进的万有引力算法(IGSA)的BP神经网络IGSA-BP瓦斯涌出量预测模型。由于BP神经网络的初始权值和阈值对网络的预测精度和收敛速度有较大影响,采用改进的万有引力算法训练BP神经网络的初始权值和阈值,引入粒子群算法记忆与社会信息交流的思想,对万有引力算法(GSA)的速度与位置更新公式进行改进,采用Tent混沌映射增加GSA种群的多样性,使算法避免陷入局部极值并增强GSA的遍历搜索能力。结果表明,改进的万有引力BP神经网络预测结果的误差在0. 20 m~3/min以内,与未经改进的万有引力BP神经网络和粒子群BP神经网络相比,预测精度分别提高了近5倍和10倍,说明该方法对煤矿瓦斯涌出量具有更好的预测精度和收敛速度。
In order to improve the accuracy and efficiency of gas emission prediction in coal mine,a BP neural network IGSA-BP gas emission prediction model based on improved gravitation search algorithm was proposed. Because the initial weight and threshold of BP neural network have great influence on the prediction accuracy and convergence speed of the network,the improved universal gravity search algorithm is used to train the initial weight and threshold of BP neural network. This paper introduces the idea of particle swarm optimization( PSO) memory and social information exchange,improves the speed and position updating formula of GSA,and uses Tent chaotic mapping to increase the diversity of GSA population. The algorithm can avoid falling into local extremum and enhance the traversal search ability of GSA. The results show that the prediction error of the improved gravitational BP neural network is less than 0. 20 m~3/min. Compared with the unmodified gravitational search algorithm BP neural network and particle swarm BP neural network,the prediction accuracy is improved by nearly 5 times and 10 times,respectively,which shows that the method has better prediction accuracy and convergence speed for coal mine gas emission.
In order to improve the accuracy and efficiency of gas emission prediction in coal mine,a BP neural network IGSA-BP gas emission prediction model based on improved gravitation search algorithm was proposed. Because the initial weight and threshold of BP neural network have great influence on the prediction accuracy and convergence speed of the network,the improved universal gravity search algorithm is used to train the initial weight and threshold of BP neural network. This paper introduces the idea of particle swarm optimization( PSO) memory and social information exchange,improves the speed and position updating formula of GSA,and uses Tent chaotic mapping to increase the diversity of GSA population. The algorithm can avoid falling into local extremum and enhance the traversal search ability of GSA. The results show that the prediction error of the improved gravitational BP neural network is less than 0. 20 m~3/min. Compared with the unmodified gravitational search algorithm BP neural network and particle swarm BP neural network,the prediction accuracy is improved by nearly 5 times and 10 times,respectively,which shows that the method has better prediction accuracy and convergence speed for coal mine gas emission.
引文
[1]付华,邵良杉.煤矿瓦斯灾害特征挖掘与融合预测[M].北京:科学出版社,2011.FU H,SHAO L SH.Mining Characteristics and Fusion Prediction of Coal Mine Gas Disaster[M].Beijing:Science Press.
[2]林海飞,李树刚,赵鹏翔,等.我国煤矿覆岩采动裂隙带卸压瓦斯抽采技术研究进展[J].煤炭科学技术,2018,46(1):28-35.LIN H F,LI SH G,ZHAO P X,et al.Research progress of pressure relief gas extraction technology in mining fractured zone of overlying strata in China's coal mines[J].Coal Science and Technology,2018,46(1):28-35.
[3]朱丽媛,李忠华,刘瀚琦.深部开采煤岩瓦斯动力灾害统一发生机制及监测技术[J].安全与环境学报,2017,17(3):937-942.ZHU L Y,LI ZH H,LIU H Q.The unified occurrence mechanism and monitoring technology of coal-rock gas dynamic disasters in deep mining[J].Journa of Safety and Environment,2017,17(3):937-942.
[4]权国林,赵琳琳,邵良杉.基于主成分灰关联的瓦斯涌出量预测模型[J].辽宁工程技术大学学报(自然科学版)2017,36(4):366-370.QUAN G L,ZHAO L L,SHAO L SH.Based on the principal component grey relation of gas emission prediction model[J].Journal of Liao Ning Engineering Technology University(Natural Science Edition),2017,36(4):366-370.
[5]徐青伟,王兆丰.瓦斯涌出量预测的GM(1,1)模型改进[J].煤炭技术,2015,34(1):147-149.XU Q W,WANG ZH F.Gas emission prediction GM(1,1)model to improve[J].Journal of Coal Technology,2015(1):147-149.
[6]吕伏,梁冰,孙维吉,等.基于主成分回归分析法的回采工作面瓦斯涌出量预测[J].煤炭学报,2012,37(1):113-116.LYU F,LIANG B,SUN W J,et al.Based on the principal component regression analysis of the working face gas emission prediction[J].Journal of Coal,2012,37(1):113-116.
[7]樊保龙,白春华,李建平.基于LMD-SVM的采煤工作面瓦斯涌出量预测[J].采矿与安全工程学报,2013,30(6):946-952.FAN B L,BAI CH H,LI J P.Prediction of gas emission from coal face based on LMD-SVM[J].Journal of Mining and Safety Engineering,2013,30(6):946-952.
[8]董晓雷,贾进章,白洋,等.基于SVM耦合遗传算法的回采工作面瓦斯涌出量预测[J].安全与环境学报,2016,16(2):114-118.DONG X L,JIA J ZH,BAI Y,et al.Prediction for gasgushing amount from the working face of stope based on the SVM coupling genetic algorithm[J].Journal of Safety and Environment,2016,16(2):114-118..
[9]王艳晖,李国勇,王炳萱.MFOA-SVM在采煤工作面瓦斯涌出量预测中的应用[J].矿业安全与环保,2016,43(2):54-58.WANG Y H,LI G Y,WANG B X.Application of MFOA-SVM in coalface gas emission prediction[J].Mining Safety and Environmental Protection,2016,43(2):54-58.
[10]王生全,刘柏根,张召召.遗传算法的BP网络模型进行瓦斯涌出量预测[J].西安科技大学学报,2012,32(1):51-56.WANG SH Q,LIU B G,ZHANG ZH ZH.Genetic algorithm BP network model for prediction of gas emission[J].Journal of Xi'an University of Science and Technology,2012,32(1):51-56.
[11]雷文杰,刘瑞涛,苏国韶.灰色关联优化BP神经网络预测工作面瓦斯涌出量[J].矿业安全与环保,2013,40(5):34-37.LEI W J,LIU R T,SU G SH.Grey correlation optimization BP neural network to predict gas emission from working face[J].Mining Safety and Environmental Protection,2012,32(1):51-56.
[12]卢国斌,康晋恺,白刚,等.PCA-BP神经网络在回踩工作面瓦斯涌出量预测中的应用[J].辽宁工程技术大学学报(自然科学版),2015,34(12):1329-1334.Lu G b,KANG J k,BAI G,et al.PCA-BP neural network to the prediction of gas emission in the back step of the working face[J].Journal of Liaoning Technical University(Natural Science Edition),2015,34(12):1329-1334.
[13]李树刚,马彥阳,林海飞.基于因子分析法的瓦斯涌出量预测指标选取[J].西安科技大学学报,2017,37(4):461-466.LI SH G,MA Y Y,LIN H F.Selection of prediction indexes for gas emission based on factor analysis[J].Journal of Xi'an University of Science and Technology,2017,37(4):461-466.
[14]姚青华,邱本花.基于改进BP神经网络的矿井瓦斯浓度预测算法[J].煤炭技术,2017,36(5):182-184.YAO Q H,QIU B H.Prediction algorithm of mine gas concentration based on improved BP neural network[J].Coal Technology,2017,36(5):182-184.
[15]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器学报,2015,29(8):1157-1163.LIU CH,MA Y.Nonlinear correction of PSD with genetic algorithm based on neural network[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1157-1163.
[16]焦敬品,李勇强,吴斌等.基于BP神经网络的管道泄漏声信号识别方法研究[J].仪器仪表学报,2016,37(11):2588-2596.JIAO J P,LI Y Q,WU B,et al.Research on acoustic signal recognition method for pipeline leakage with BPneural network[J].Chinese Journal of Scientific Instrument,2016,37(11):2588-2596.
[17]李小珉,尹明.基于遗传算法的BP神经网络电子系统状态预测方法研究[J].电子测量技术,2016,39(9):182-186.LI X M,YIN M.Research on BP neural network state prediction method for electronic system based on genetic algorithm[J].Electronic Measurement Technology,2016,39(9):182-186.
[18]丁硕,巫庆辉,常晓恒,等.基于灰色BP神经网络的实验材料供应预测[J].国外电子测量技术,2016,35(12):78-82.DING SH,WU Q H,CHANG X H,et al.Prediction of laboratory equipment support based on grey relation analysis and BP neural network[J].Foreign Electronic Measurement Technology,2016,35(12):78-82.
[19]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.YUAN P,MAO J L,XIANG F H,et al.Grid fault diagnosis based on improved genetic optimization BPneural network[J].Journal of Power System and Automation,2017,29(1):118-122.
[19]宋涛,舒涛,雷荣强,等.基于蚁群神经网络的发射系统故障诊断[J].火力与指挥控制,2015,40(9):143-146.SONG T,SHU T,LEI R Q,et al.Research on fault diagnosis for launch system based on ant colony neural network[J].Fire Control&Command Control,2015,40(9):143-146.
[21]张捍东,陶刘送.粒子群优化BP算法在液压系统故障诊断中应用[J].系统仿真学报,2016,28(5):1186-1190.ZHANG H D,TAO L S.Application of PSO-BPalgorithm in hydraulic system fault diagnosis[J].Journal of System Simulation,2016,28(5):1186-1190.
[22]ESMAT R,HOSSEIN N,SAEID S.GSA:A gravitational search algorithm[J].Information Sciences,2009,179(13):2232-2248.
[23]TIZHOOSH H.Opposition-based learning:A new scheme for machine intelligence[C].Proceedings of the International Conference on Computational Intelligence for Modeling Control and Automation,2005:695-701.
[2]林海飞,李树刚,赵鹏翔,等.我国煤矿覆岩采动裂隙带卸压瓦斯抽采技术研究进展[J].煤炭科学技术,2018,46(1):28-35.LIN H F,LI SH G,ZHAO P X,et al.Research progress of pressure relief gas extraction technology in mining fractured zone of overlying strata in China's coal mines[J].Coal Science and Technology,2018,46(1):28-35.
[3]朱丽媛,李忠华,刘瀚琦.深部开采煤岩瓦斯动力灾害统一发生机制及监测技术[J].安全与环境学报,2017,17(3):937-942.ZHU L Y,LI ZH H,LIU H Q.The unified occurrence mechanism and monitoring technology of coal-rock gas dynamic disasters in deep mining[J].Journa of Safety and Environment,2017,17(3):937-942.
[4]权国林,赵琳琳,邵良杉.基于主成分灰关联的瓦斯涌出量预测模型[J].辽宁工程技术大学学报(自然科学版)2017,36(4):366-370.QUAN G L,ZHAO L L,SHAO L SH.Based on the principal component grey relation of gas emission prediction model[J].Journal of Liao Ning Engineering Technology University(Natural Science Edition),2017,36(4):366-370.
[5]徐青伟,王兆丰.瓦斯涌出量预测的GM(1,1)模型改进[J].煤炭技术,2015,34(1):147-149.XU Q W,WANG ZH F.Gas emission prediction GM(1,1)model to improve[J].Journal of Coal Technology,2015(1):147-149.
[6]吕伏,梁冰,孙维吉,等.基于主成分回归分析法的回采工作面瓦斯涌出量预测[J].煤炭学报,2012,37(1):113-116.LYU F,LIANG B,SUN W J,et al.Based on the principal component regression analysis of the working face gas emission prediction[J].Journal of Coal,2012,37(1):113-116.
[7]樊保龙,白春华,李建平.基于LMD-SVM的采煤工作面瓦斯涌出量预测[J].采矿与安全工程学报,2013,30(6):946-952.FAN B L,BAI CH H,LI J P.Prediction of gas emission from coal face based on LMD-SVM[J].Journal of Mining and Safety Engineering,2013,30(6):946-952.
[8]董晓雷,贾进章,白洋,等.基于SVM耦合遗传算法的回采工作面瓦斯涌出量预测[J].安全与环境学报,2016,16(2):114-118.DONG X L,JIA J ZH,BAI Y,et al.Prediction for gasgushing amount from the working face of stope based on the SVM coupling genetic algorithm[J].Journal of Safety and Environment,2016,16(2):114-118..
[9]王艳晖,李国勇,王炳萱.MFOA-SVM在采煤工作面瓦斯涌出量预测中的应用[J].矿业安全与环保,2016,43(2):54-58.WANG Y H,LI G Y,WANG B X.Application of MFOA-SVM in coalface gas emission prediction[J].Mining Safety and Environmental Protection,2016,43(2):54-58.
[10]王生全,刘柏根,张召召.遗传算法的BP网络模型进行瓦斯涌出量预测[J].西安科技大学学报,2012,32(1):51-56.WANG SH Q,LIU B G,ZHANG ZH ZH.Genetic algorithm BP network model for prediction of gas emission[J].Journal of Xi'an University of Science and Technology,2012,32(1):51-56.
[11]雷文杰,刘瑞涛,苏国韶.灰色关联优化BP神经网络预测工作面瓦斯涌出量[J].矿业安全与环保,2013,40(5):34-37.LEI W J,LIU R T,SU G SH.Grey correlation optimization BP neural network to predict gas emission from working face[J].Mining Safety and Environmental Protection,2012,32(1):51-56.
[12]卢国斌,康晋恺,白刚,等.PCA-BP神经网络在回踩工作面瓦斯涌出量预测中的应用[J].辽宁工程技术大学学报(自然科学版),2015,34(12):1329-1334.Lu G b,KANG J k,BAI G,et al.PCA-BP neural network to the prediction of gas emission in the back step of the working face[J].Journal of Liaoning Technical University(Natural Science Edition),2015,34(12):1329-1334.
[13]李树刚,马彥阳,林海飞.基于因子分析法的瓦斯涌出量预测指标选取[J].西安科技大学学报,2017,37(4):461-466.LI SH G,MA Y Y,LIN H F.Selection of prediction indexes for gas emission based on factor analysis[J].Journal of Xi'an University of Science and Technology,2017,37(4):461-466.
[14]姚青华,邱本花.基于改进BP神经网络的矿井瓦斯浓度预测算法[J].煤炭技术,2017,36(5):182-184.YAO Q H,QIU B H.Prediction algorithm of mine gas concentration based on improved BP neural network[J].Coal Technology,2017,36(5):182-184.
[15]刘春,马颖.遗传算法和神经网络结合的PSD非线性校正[J].电子测量与仪器学报,2015,29(8):1157-1163.LIU CH,MA Y.Nonlinear correction of PSD with genetic algorithm based on neural network[J].Journal of Electronic Measurement and Instrumentation,2015,29(8):1157-1163.
[16]焦敬品,李勇强,吴斌等.基于BP神经网络的管道泄漏声信号识别方法研究[J].仪器仪表学报,2016,37(11):2588-2596.JIAO J P,LI Y Q,WU B,et al.Research on acoustic signal recognition method for pipeline leakage with BPneural network[J].Chinese Journal of Scientific Instrument,2016,37(11):2588-2596.
[17]李小珉,尹明.基于遗传算法的BP神经网络电子系统状态预测方法研究[J].电子测量技术,2016,39(9):182-186.LI X M,YIN M.Research on BP neural network state prediction method for electronic system based on genetic algorithm[J].Electronic Measurement Technology,2016,39(9):182-186.
[18]丁硕,巫庆辉,常晓恒,等.基于灰色BP神经网络的实验材料供应预测[J].国外电子测量技术,2016,35(12):78-82.DING SH,WU Q H,CHANG X H,et al.Prediction of laboratory equipment support based on grey relation analysis and BP neural network[J].Foreign Electronic Measurement Technology,2016,35(12):78-82.
[19]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.YUAN P,MAO J L,XIANG F H,et al.Grid fault diagnosis based on improved genetic optimization BPneural network[J].Journal of Power System and Automation,2017,29(1):118-122.
[19]宋涛,舒涛,雷荣强,等.基于蚁群神经网络的发射系统故障诊断[J].火力与指挥控制,2015,40(9):143-146.SONG T,SHU T,LEI R Q,et al.Research on fault diagnosis for launch system based on ant colony neural network[J].Fire Control&Command Control,2015,40(9):143-146.
[21]张捍东,陶刘送.粒子群优化BP算法在液压系统故障诊断中应用[J].系统仿真学报,2016,28(5):1186-1190.ZHANG H D,TAO L S.Application of PSO-BPalgorithm in hydraulic system fault diagnosis[J].Journal of System Simulation,2016,28(5):1186-1190.
[22]ESMAT R,HOSSEIN N,SAEID S.GSA:A gravitational search algorithm[J].Information Sciences,2009,179(13):2232-2248.
[23]TIZHOOSH H.Opposition-based learning:A new scheme for machine intelligence[C].Proceedings of the International Conference on Computational Intelligence for Modeling Control and Automation,2005:695-701.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |