以时松孝次收集的砂土液化数据为研究对象，选取黏粒含量ρc、相对密实度Dr、临界深度ds、竖向有效应力σ′、地下水位dw、地震震级M、最大地面水平加速度αmax和标准贯入次数SPT-N等8个砂土液化的主要影响因素作为RBF神经网络的输入参数，利用MATLAB7.0中的神经网络工具箱，对部分样本数据进行训练和测试。并利用建立的RBF神经网络模型分析了各因素对砂土液化的影响规律。结果表明：砂土液化判别指标随αmax的增加而增大，随SPT-N和dw的增加而减小。研究成果表明，建立的RBF网络模型完全满足砂土液化判别的精度要求，能够精确模拟输入和输出之间复杂的非线性映射关系，具有较高的预测精度，具有重要的工程应用价值。
Abstract
The neural network toolbox of MATLAB7.0 was used to train and test some sample data of sand liquefaction collected by Tokimatsu Kohji. Eight eigenvectors clay content (ρc),relative compaction(Dr),critical depth of soil layer(ds),vertical effective stress(σ′),groundwater level(dw),magnitude of earthquake(M),maximum horizontal ground acceleration(αmax) and standard penetration number(SPT-N) were selected as input parameters of the RBF neural network. Furthermore,the established RBF neural network model was used to analyze the effect of each factor on the sand liquefaction. Results of the relative contribution of each factor showed that αmax was the biggest influencing factor on the evaluation index of sand liquefaction,followed by SPT-N and dw. The evaluation index increased with the rise of αmax,while reduced with the increase of SPT-N and dw. The evaluation index shows a logarithmic relation with αmax,cubic polynomial relation with SPT-N,and a negative linear relation with dw . It’s revealed that the established RBF network model fully meets the requirement of evaluation accuracy for sand liquefaction. It can simulate the complex nonlinear mapping relation between the input and output data and also gives high prediction precision.
关键词
砂土液化 /
评价指标 /
RBF神经网络 /
液化等级
Key words
sand iquefaction /
evaluation index /
RBF neural network /
liquefaction level
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］ RAHMAN M S,WANG Jun. Fuzzy Neural Network Models for Liquefaction Prediction［J］. Soil Dynamics and Earthquake Engineering,2002,22(8):685-694.
［2］ BAZIAR M H,JAFARIAN Y. Assessment of Liquefaction Triggering Using Strain Energy Concept and ANN Model Capacity Energy［J］. Soil Dynamics and Earthquake Engineering,2007,27(12): 1056-1072.
［3］ 李方明.人工神经网络在砂土液化判别及震陷预估中的应用［D］.南京：南京工业大学,2005.(LI Fang-ming. Application of Artificial Neural Network in the Estimation of Sand Liquefaction and the Prediction of Earthquake-Induced Ground Settlement［D］. Nanjing: Nanjing University of Technology,2005.(in Chinese))
［4］ CETIN K O,SEED R B,KIUREGHIAN A D,et al. Standard Penetration Test-Based Probabilistic and Deterministic Assessment of Seismic Soil Liquefaction Potential［J］. Journal of Geotechnical and Geoenvironmental Engineering,ASCE,2004,(12): 1313-1340.
［5］ 季倩倩.砂土地震液化的优化判别［J］. 岩土工程技术,2001,(3): 155-159.(JI Qian-qian. Fuzzy Evaluation for Seismic Liquefaction Discrimination of Sands［J］ Geotechnical Engineering Technique,2001,(3): 155-159.(in Chinese))
［6］ 赵艳林,杨绿峰,吴敏哲.砂土液化的灰色综合评判［J］.自然灾害学报，2000,9(1): 72-79. (ZHAO Yan-lin,YANG Lv-feng,WU Min-zhe. Grey Synthetical Evaluation of Liquefaction of Sands［J］. Journal of Natural Disasters,2000,9(1): 72-79.(in Chinese))
［7］ HANNA A M,DERIN U,SAYGILI G. Neural Network Model for Liquefaction Potential in Soil Deposits Using Turkey and Taiwan Earthquake Data［J］. Soil Dynamics and Earthquake Engineering,2007,27(6): 521-540.
［8］ 张德丰. MATLAB/Simulink建模与仿真实例精讲［M］.北京:机械工业出版社,2010.(ZHANG De-feng. MATLAB/Simulink Modeling and Simulation Examples［M］. Beijing: China Machine Press,2010.(in Chinese))
［9］ 周瑞林,刘 燕,赵胜利. 基于RBF神经网络的砂土液化预测［J］. 河南大学学报 (自然科学版 ),2005,35 (4):101-105.(ZHOU Rui-lin,LIU Yan,ZHAO Sheng-li. Application of RBF Neural Network to Prediction of Sands Liquefaction Potential［J］. Journal of Henan University (Natural Science),2005,35(4):101-105.(in Chinese))
［10］陈国兴,李方明. 基于径向基函数神经网络模型的砂土液化概率判别方法［J］. 岩土工程学报,2006,28(3): 301-306.(CHEN Guo-xing,LI Fang-ming. Probabilistic Estimation of Sand Liquefaction Based on Neural Network Model of Radial Basis Function［J］. Chinese Journal of Geotechnical Engineering,2006,28(3):301-306.(in Chinese))
［11］李菊凤,宁立波,周建伟,等. 基于 RBF神经网络的软基沉降预测研究［J］. 湖南科技大学学报 (自然科学版),2005,20(3):49-53.(LI Ju-feng,NING Li-bo,ZHOU Jian-wei,et al. Research of Settlement Prediction of Soft Foundation Based on RBF Neural Networks［J］. Journal of Hunan University of Science & Technology (Natural Science Edition),2005,20(3): 49-53.(in Chinese))
［12］TOKIMATSU KOHJI. Empirical Correlation of Soil Liquefaction Based on SPT N-Value and Fines Content［J］. Soils and Foundation,1983,23(4): 56-74.
［13］陈国兴,李方明.基于RBF神经网络模型的砂土液化震陷预估法［J］.自然灾害学报,2008,17(1):180-186.(CHEN Guo-xing,LI Fang-ming. Seismic Settlement Estimation of Sand Liquefaction Based on RBF Neural Network Model［J］. Journal of Natural Disasters,2008,17(1):180-186.(in Chinese))
PDF(1001 KB)
