Email Alerts
RSS
Prediction of permeability coefficients of coarse-grained soil based on GA-BP neural network
-
摘要: 针对粗粒土渗透性能受颗粒级配、密实程度等因素影响而呈现明显差异，提出一种粗粒土渗透系数预测方法。收集并整理得到93组粗粒土数据，以全级配(d10~d100)和孔隙比作为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粗粒土渗透系数预测模型。结果表明：该GA-BP神经网络经过55次迭代之后精度满足要求；87组训练样本预测结果的平均相对误差为5.10%，其中有75%的样本相对误差小于平均相对误差；6组检测样本预测结果的平均相对误差为6.39%，该网络模型泛化性能良好。采用GA-BP神经网络，由全级配和孔隙比能较好地预测粗粒土的渗透系数，且收敛速度、预测精度及泛化性能均优于标准的BP神经网络模型。Abstract: In view of the obvious difference in the permeability of the coarse grained soil, effected by factors such as gradation of grain and compaction degree, a prediction method for the permeability of the coarse-grained soil is proposed in this study. 93 groups of data of the coarse-grained soil are collected and obtained. Taking the full gradation(d10~ d100) and the porosity ratio as the input variables of the BP neural network, a prediction model for the permeability coefficients of the coarse-grained soil is developed on the basis of the BP neural network and genetic algorithm, by using the genetic algorithm to optimize the BP neural network′s initial weights and thresholds. The research results show that the accuracy of the GA-BP neural network meets the requirements after 55 iterations. And the mean relative error of the predicted results of 87 groups of the training samples is 5.10%. Moreover, a relative error of 75% of the training samples is less than the mean relative error. In addition, the mean relative error of 6 groups of the testing samples is 6.39%, which indicates that the generalization performance of the network model is high. It is concluded that the permeability coefficients of the coarse-grained soil can be well predicted by applying the GA-BP neural network considering the full gradation and void ratio. Moreover, The convergence rate, the prediction accuracy and the generalization performance of the GA-BP neural network are better than those of the standard BP neural network model. And the model based on the GA-BP neural network can provide technical references and support for the selection and improvement of the coarse-grained soil in practical engineering.
-
Key words:
- coarse-grained soil /
- permeability coefficient /
- BP neural network /
- genetic algorithm /
- void ratio /
- gradation
-
表 1 检测样本的预测结果
Table 1. Predicted results of testing samples
编号 来源 试验值/(cm·s-1) BP神经网络 GA-BP神经网络 预测值/(cm·s-1) 相对误差/% 预测值/(cm·s-1) 相对误差/% S1 文献[19] 8.32×10-2 7.99×10-2 3.97 8.75×10-2 5.17 S2 文献[20] 3.50×10-1 2.38×10-1 31.97 3.33×10-1 5.01 S3 文献[21] 2.20×10-2 2.10×10-2 4.55 2.31×10-2 4.85 S4 文献[21] 5.70×10-2 5.29×10-2 7.19 5.43×10-2 4.75 S5 文献[8] 1.42×10-2 1.27×10-2 10.56 1.31×10-2 8.13 S6 文献[22] 3.13×10-3 2.58×10-3 17.57 3.46×10-3 10.44 
下载: 导出CSV
-
[1] GB/T50145—2007土的工程分类标准[S]. GB/T50145—2007 Standard for engineering classification of soil[S]. (in Chinese) [2] 刘建坤, 于钱米, 刘景宇, 等.细粒土不均匀分布对粗粒土力学特性的影响[J].岩土工程学报, 2017, 39(3): 562-572. http://d.old.wanfangdata.com.cn/Periodical/ytgcxb201703025 LIU Jiankun, YU Qianmi, LIU Jingyu, et al. Influence of non-uniform distribution of fine soil on mechanical properties of coarse-grained soil[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(3): 562-572. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/ytgcxb201703025 [3] 朱国胜, 张家发, 陈劲松, 等.宽级配粗粒土渗透试验尺寸效应及边壁效应研究[J].岩土力学, 2012, 33(9): 2569-2574. http://d.old.wanfangdata.com.cn/Periodical/ytlx201209002 ZHU Guosheng, ZHANG Jiafa, CHEN Jinsong, et al. Study of size and wall effects in seepage test of broadly graded coarse materials[J]. Rock and Soil Mechanics, 2012, 33(9): 2569-2574. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/ytlx201209002 [4] 黄达, 曾彬, 王庆乐.粗粒土孔隙比及级配参数与渗透系数概率的相关性研究[J].水利学报, 2015, 46(8): 900-907. http://d.old.wanfangdata.com.cn/Periodical/slxb201508003 HUANG Da, ZENG Bin, WANG Qingle. Study on probabilistic relation between permeability coefficient and void ratio and grain composition of coarse grained soils using Copula theory[J]. Journal of Hydraulic Engineering, 2015, 46(8): 900-907. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/slxb201508003 [5] 邵生俊, 李建军, 杨扶银.粗粒土孔隙特征及其对泥浆渗透性的影响[J].岩土工程学报, 2009, 31(1): 59-65. doi: 10.3321/j.issn:1000-4548.2009.01.010 SHAO Shengjun, LI Jianjun, YANG Fuyin. Pore characteristics of coarse grained soil and their effect on slurry permeability[J]. Chinese Journal of Geotechnical Engineering, 2009, 31(1): 59-65. (in Chinese) doi: 10.3321/j.issn:1000-4548.2009.01.010 [6] 黄文熙.土的工程性质[M].北京:水利电力出版社, 1983. HUANG Wenxi. Engineering properties of soils[M]. Beijing: China Water & Power Press, 1983. (in Chinese) [7] 李文波.粗粒土物理力学特性研究[D].昆明: 昆明理工大学, 2015. http://cdmd.cnki.com.cn/Article/CDMD-10674-1015635927.htm LI Wenbo. Study on physical and mechanical properties of coarse grained soil[D]. Kunming: Kunming University of Science and Technology, 2015. (in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10674-1015635927.htm [8] 张宜健.不同粒径级砂性土渗透特性试验研究[D].西安: 西安建筑科技大学, 2013. http://cdmd.cnki.com.cn/Article/CDMD-10703-1014010117.htm ZHANG Yijian. Investigation on permeability of sands with different particle size[D]. Xi'an: Xi'an University of Architecture and Technology, 2013. (in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10703-1014010117.htm [9] 张国栋, 廖爱明, 李泯蒂, 等.碎石土渗透特性试验研究[J].水利水运工程学报, 2016(5): 91-95. http://slsygcxb.cnjournals.org/ch/reader/view_abstract.aspx?file_no=201605013&flag=1 ZHANG Guodong, LIAO Aiming, LI Mindi, et al. Model test studies on permeability of gravel soil[J]. Hydro-Science and Engineering, 2016(5): 91-95. (in Chinese) http://slsygcxb.cnjournals.org/ch/reader/view_abstract.aspx?file_no=201605013&flag=1 [10] 王俊杰, 卢孝志, 邱珍锋, 等.粗粒土渗透系数影响因素试验研究[J].水利水运工程学报, 2013(6): 16-20. doi: 10.3969/j.issn.1009-640X.2013.06.003 WANG Junjie, LU Xiaozhi, QIU Zhenfeng, et al. Experimental studies on influence factors of permeability coefficients of coarse-grained soil[J]. Hydro-Science and Engineering, 2013(6): 16-20. (in Chinese) doi: 10.3969/j.issn.1009-640X.2013.06.003 [11] 朱崇辉, 刘俊民, 王增红.粗粒土的颗粒级配对渗透系数的影响规律研究[J].人民黄河, 2005, 27(12): 79-81. doi: 10.3969/j.issn.1000-1379.2005.12.036 ZHU Chonghui, LIU Junmin, WANG Zenghong. Experimental study on osmosis of cohesion less soils[J]. Yellow River, 2005, 27(12): 79-81. (in Chinese) doi: 10.3969/j.issn.1000-1379.2005.12.036 [12] 刘杰.土的渗流稳定与渗流控制[M].北京:水利电力出版社, 1992. LIU Jie. Seepage stability and seepage control of soil[M]. Beijing: Water Resources and Electric Power Press, 1992. (in Chinese) [13] AGUS S S, LEONG E C, RAHARDJO H. Estimating permeability functions of Singapore residual soils[J]. Engineering Geology, 2005, 78(1): 119-133. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=df9c9fdfcf4674cd90b6e219ebf8d992 [14] SONG J X, CHEN X H, CHENG C, et al. Feasibility of grain-size analysis methods for determination of vertical hydraulic conductivity of streambeds[J]. Journal of Hydrology, 2009, 375(3): 428-437. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d0e67ed04ab70e99bf9e57fea43d26d1 [15] 唐晓松, 郑颖人, 董诚.应用神经网络预估粗颗粒土的渗透系数[J].岩土力学, 2007, 28(增刊1): 133-136, 143. http://d.old.wanfangdata.com.cn/Conference/6471875 TANG Xiaosong, ZHENG Yingren, DONG Cheng. The prediction of seepage coefficient of coarse-grained soil by neurotic network[J]. Rock and Soil Mechanics, 2007, 28(Suppl1): 133-136. (in Chinese) http://d.old.wanfangdata.com.cn/Conference/6471875 [16] 王双, 李小春, 王少泉, 等.碎石土级配特征对渗透系数的影响研究[J].岩石力学与工程学报, 2015, 34(增刊2): 4394-4402. http://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2015S2092.htm WANG Shuang, LI Xiaochun, WANG Shaoquan, et al. Study of gravel-soil gradation characteristics influence on the permeability coefficient[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34(Suppl2): 4394-4402. (in Chinese) http://www.cnki.com.cn/Article/CJFDTOTAL-YSLX2015S2092.htm [17] 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, 904. doi: 10.3785/j.issn.1008-973X.2012.05.010 WANG Deming, WANG Li, ZHANG Guangming. Short-term wind speed forecast model for wind farms based on genetic BP neural network[J]. Journal of Zhejiang University (Engineering Science), 2012, 46(5): 837-841, 904. (in Chinese) doi: 10.3785/j.issn.1008-973X.2012.05.010 [18] 彭基伟, 吕文华, 行鸿彦, 等.基于改进GA-BP神经网络的湿度传感器的温度补偿[J].仪器仪表学报, 2013, 34(1): 153-160. doi: 10.3969/j.issn.0254-3087.2013.01.022 PENG Jiwei, LYU Wenhua, XING Hongyan, et al. Temperature compensation for humidity sensor based on improved GA-BP neural network[J]. Chinese Journal of Scientific Instrument, 2013, 34(1): 153-160. (in Chinese) doi: 10.3969/j.issn.0254-3087.2013.01.022 [19] 李文波.粗粒土渗透特性影响因素及渗透规律试验研究[J].价值工程, 2013(36): 105-107. http://d.old.wanfangdata.com.cn/Periodical/jzgc201336057 LI Wenbo. The influence factors of coarse-grained soil permeability characteristics and testing study on seepage law of the coarse-grained soil[J]. Value Engineering, 2013(36): 105-107. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/jzgc201336057 [20] 鲁华征.级配碎石设计方法研究[D].西安: 长安大学, 2006. http://cdmd.cnki.com.cn/Article/CDMD-11941-2006163340.htm LU Huazheng. Design method of graded grave[D]. Xi'an: Chang'an University, 2006. (in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-11941-2006163340.htm [21] 朱崇辉.粗粒土的渗透特性研究[D].西安: 西北农林科技大学, 2006. http://cdmd.cnki.com.cn/Article/CDMD-10712-2006179665.htm ZHU Chonghui. Study on the coarse-grained soil permeability characteristic[D]. Xi'an: Northwest A & F University, 2006. (in Chinese) http://cdmd.cnki.com.cn/Article/CDMD-10712-2006179665.htm [22] 谢定松, 蔡红, 魏迎奇, 等.粗粒土渗透试验缩尺原则与方法探讨[J].岩土工程学报, 2015, 37(2): 369-373. http://d.old.wanfangdata.com.cn/Periodical/ytgcxb201502026 XIE Dingsong, CAI Hong, WEI Yingqi, et al. Scaling principle and method in seepage tests on coarse materials[J]. Chinese Journal of Geotechnical Engineering, 2015, 37(2): 369-373. (in Chinese) http://d.old.wanfangdata.com.cn/Periodical/ytgcxb201502026 [23] SL237—1999土工试验规程[S]. SL237—1999 Specification of soil test[S]. (in Chinese) [24] 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. CHEN Ming. MATLAB neural network principles and examples[M]. Beijing: Tsinghua University Press, 2013. (in Chinese) [25] 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. doi: 10.7667/j.issn.1674-3415.2013.16.017 WANG Yuanzhang, WU Chunhua, ZHOU Diqing, et al. A survey of fault diagnosis for PV array based on BP neural network[J]. Power System Protection and Control, 2013, 41(16): 108-114. (in Chinese) doi: 10.7667/j.issn.1674-3415.2013.16.017 -
点击查看大图
图(3) / 表 (1)
计量
- 文章访问数: 369
- HTML全文浏览量: 17
- PDF下载量: 154
- 被引次数: 0
