应用GA-BP神经网络预估砾类土的最大干密度
|
摘要
建立砾类土最大干密度预估模型,为控制砾类土工程填筑压实质量、选取满足工程压实性能要求的砾类土提供最大干密度预估参考。颗粒级配是决定砾类土最大干密度的关键因素,收集并整理得到92组砾类土数据,以全级配(d_(10)～d_(100))作为BP(GA-BP)神经网络的输入变量,利用遗传算法优化BP神经网络的初始权值与阀值,构建基于BP神经网络和遗传算法的砾类土最大干密度预估模型,并与BP神经网络进行对比。86组训练样本预估结果的平均相对误差为0.54%,决定系数为0.983;6组检测样本预估结果的平均相对误差为0.57%,证明该网络模型泛化性能良好。采用GA-BP神经网络,由全级配能较好地预估砾类土最大干密度,收敛速度、预估精度及泛化性能均优于标准的BP神经网络模型。
A model of estimating the maximum dry density of gravel soil is established to provide reference for controlling the compaction quality of gravel soil projects and selecting the gravel soil which meets engineering requirements. In the light that particle gradation is the crucial factor that determines the maximum dry density of gravel soil, 92 groups of data of gravel soil are collected and obtained, of which full gradation(d_(10)-d_(100)) is used as the input variable of back propagation(BP) neural network. Furthermore, genetic algorithm(GA) is adopted to optimize the initial weights and thresholds of the BP neural network, based on which the estimation model for maximum dry density of gravel soil is constructed. In addition, the GA-BP neural network model is compared with BP neural network model. According to estimation results, the mean relative error of the predicted results of 86 groups of training samples is 0.54%, and the coefficient of determination is 0.983; the mean relative error of the predicted results of 6 groups of test samples is 0.57%, which indicates that the proposed model is of good generalization performance. It is concluded that the maximum dry density of gravel soil could be well predicted by applying GA-BP neural network in consideration of full gradation. GA-BP neural network model is superior than conventional BP neural network model in terms of convergence rate, prediction accuracy and generalization performance.
A model of estimating the maximum dry density of gravel soil is established to provide reference for controlling the compaction quality of gravel soil projects and selecting the gravel soil which meets engineering requirements. In the light that particle gradation is the crucial factor that determines the maximum dry density of gravel soil, 92 groups of data of gravel soil are collected and obtained, of which full gradation(d_(10)-d_(100)) is used as the input variable of back propagation(BP) neural network. Furthermore, genetic algorithm(GA) is adopted to optimize the initial weights and thresholds of the BP neural network, based on which the estimation model for maximum dry density of gravel soil is constructed. In addition, the GA-BP neural network model is compared with BP neural network model. According to estimation results, the mean relative error of the predicted results of 86 groups of training samples is 0.54%, and the coefficient of determination is 0.983; the mean relative error of the predicted results of 6 groups of test samples is 0.57%, which indicates that the proposed model is of good generalization performance. It is concluded that the maximum dry density of gravel soil could be well predicted by applying GA-BP neural network in consideration of full gradation. GA-BP neural network model is superior than conventional BP neural network model in terms of convergence rate, prediction accuracy and generalization performance.
引文
[1] GB/T 50145—2007,土的工程分类标准[S].北京:中国计划出版社, 2008.
[2] 于林平,李胜德,高潮,等.以神经网络法预测非均质土石混合料最大干密度[J].岩石力学与工程学报,2004,23(增1): 4347-4350.
[3] 冯瑞玲,王园,谢永利.粗粒土振动压实特性试验[J].中国公路学报,2007,20(5):19-23.
[4] 万连宾.砂砾石筑坝压实质量控制指标确定方法探讨[J]. 水利水电技术,2014,45(6):2-3,7.
[5] 朱俊高,翁厚洋,吴晓铭,等.粗粒料级配缩尺后压实密度试验研究[J].岩土力学,2010,31(8):2394-2398.
[6] 左永振,张伟,潘家军,等.粗粒料级配缩尺方法对其最大干密度的影响研究[J].岩土力学,2015,36(增1): 417-422.
[7] 刘源,宋晓东,聂志红,等.客运专线铁路路基粗粒土填料最大干密度的BP神经网络预测[J].铁道科学与工程学报,2014,11(3):107-110.
[8] 王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012,46(5): 837-841.
[9] 廖强,赵斌.剔除延伸法在砂卵砾石最大干密度试验中的应用[J].水力发电,2016,42(5):102-105.
[10] 盛小涛,定培中,朱国胜.缩尺方法对粗粒料密度和渗透性影响的试验研究[J].人民长江,2016,47(24):80-83.
[11] 包卫星,郭小龙,杨万精.干旱荒漠区天然砂砾路基填料压实特性分析[J].中国公路学报,2017,30(2):18-24.
[12] 朱崇辉,严宝文,刘俊民,等.超粒径粗粒土最大干密度试验研究[J].岩石力学与工程学报,2007,26(增2): 4090-4094.
[13] 叶文美.巨粒土填筑路基压实度的试验研究[C]//中国公路学会2004年学术年会论文集.北京:人民交通出版社, 2004:96-100.
[14] JTG E40—2007,公路土工试验规程[S].北京:人民交通出版社,2007.
[15] 陈明.MATLAB神经网络原理与实例精解[M].北京:清华大学出版社,2013.
[16] 王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013,41(16): 108-114.
[2] 于林平,李胜德,高潮,等.以神经网络法预测非均质土石混合料最大干密度[J].岩石力学与工程学报,2004,23(增1): 4347-4350.
[3] 冯瑞玲,王园,谢永利.粗粒土振动压实特性试验[J].中国公路学报,2007,20(5):19-23.
[4] 万连宾.砂砾石筑坝压实质量控制指标确定方法探讨[J]. 水利水电技术,2014,45(6):2-3,7.
[5] 朱俊高,翁厚洋,吴晓铭,等.粗粒料级配缩尺后压实密度试验研究[J].岩土力学,2010,31(8):2394-2398.
[6] 左永振,张伟,潘家军,等.粗粒料级配缩尺方法对其最大干密度的影响研究[J].岩土力学,2015,36(增1): 417-422.
[7] 刘源,宋晓东,聂志红,等.客运专线铁路路基粗粒土填料最大干密度的BP神经网络预测[J].铁道科学与工程学报,2014,11(3):107-110.
[8] 王德明,王莉,张广明.基于遗传BP神经网络的短期风速预测模型[J].浙江大学学报(工学版),2012,46(5): 837-841.
[9] 廖强,赵斌.剔除延伸法在砂卵砾石最大干密度试验中的应用[J].水力发电,2016,42(5):102-105.
[10] 盛小涛,定培中,朱国胜.缩尺方法对粗粒料密度和渗透性影响的试验研究[J].人民长江,2016,47(24):80-83.
[11] 包卫星,郭小龙,杨万精.干旱荒漠区天然砂砾路基填料压实特性分析[J].中国公路学报,2017,30(2):18-24.
[12] 朱崇辉,严宝文,刘俊民,等.超粒径粗粒土最大干密度试验研究[J].岩石力学与工程学报,2007,26(增2): 4090-4094.
[13] 叶文美.巨粒土填筑路基压实度的试验研究[C]//中国公路学会2004年学术年会论文集.北京:人民交通出版社, 2004:96-100.
[14] JTG E40—2007,公路土工试验规程[S].北京:人民交通出版社,2007.
[15] 陈明.MATLAB神经网络原理与实例精解[M].北京:清华大学出版社,2013.
[16] 王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013,41(16): 108-114.
© 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 |