基于PCA-LM-BP融合的砂土液化预测评价模型
|
摘要
采用主成分分析法(principal component analysis,PCA)对影响砂土液化的8个因素进行主成分提取,得到3个主成分。然后采用BP神经网络对提取主成分后的数据进行训练,并应用Levenberg-Marquardt(LM)算法对BP神经网络进行优化,建立了基于PCA-LM-BP融合的砂土液化预测评价模型,并结合工程实例将预测结果与BP神经网络模型预测结果进行比较分析。结果表明,本预测评价模型的判别结果具有更高的准确性,符合实际工程的需要。
The principal component analysis(PCA)is used to analyze eight factors affecting the liquefaction of sandy soil by principal component analysis,and three principal components are extracted.Meanwhile,BP neural network is used to train the data after the extraction of the main component,and the BP neural network is optimized by Levenberg-Marquardt(LM)algorithm.The prediction model of sand liquefaction based on PCA-LM-BP fusion is established.In addition,the prediction results are compared with the prediction results of BP neural network model,which are obtained by the proposed model.The prediction model has higher accuracy,and it meets the needs of practical engineering.
The principal component analysis(PCA)is used to analyze eight factors affecting the liquefaction of sandy soil by principal component analysis,and three principal components are extracted.Meanwhile,BP neural network is used to train the data after the extraction of the main component,and the BP neural network is optimized by Levenberg-Marquardt(LM)algorithm.The prediction model of sand liquefaction based on PCA-LM-BP fusion is established.In addition,the prediction results are compared with the prediction results of BP neural network model,which are obtained by the proposed model.The prediction model has higher accuracy,and it meets the needs of practical engineering.
引文
[1]李智毅,杨裕云.工程地质学概论[M].武汉:中国地质大学出版社,1994:40-41.LI Zhiyi,YANG Yuyun.An introduction to engineering geology[M].Wuhan:China University of Geosciences Publishing House,1994:40-41.(in Chinese)
[2]陈奎,刘兴昌.砂土地震液化的神经网络预测[J].中国地质灾害与防治学报,2000,22(1):15-18.CHEN Kui,LIU Xingchang.The prediction of BP neural network to sand liquefaction during earthquake[J].Chinese Journal of Geological Hazard and Control,2000,22(1):15-18.(in Chinese)
[3]陈海军,郦能惠,聂德新,等.岩爆预测的人工神经网络模型[J].岩土工程学报,2002,24(2):229-232.CHEN Haijun,LI Nenghui,NIE Dexin,et al.A model for prediction of rock burst by artificial neural network[J].Chinese Journal of Geotechnical Engineering,2002,24(2):229-232.(in Chinese)
[4]马骥.基于MATLAB的BP神经网络在砂土液化评价中的应用[J].水文地质工程地质,2004,31(2):54-58.MA Ji.Application of BP neural network based on MATLAB to the evaluation of sandy soil seismic liquefaction[J].Hydrogeology Engineering Geology,2004,31(2):54-58.(in Chinese)
[5]蔡煜东,宫家文,姚林声.砂土液化预测的人工神经网络模型[J].岩土工程学报,1993,15(6):53-58.CAI Yudong,GONG Jiawen,YAO Linsheng.Artificial neural network model for prediction of liquefaction of sandy soil[J].Chinese Journal of Geotechnical Engineering,1993,15(6):53-58.(in Chinese)
[6]任文杰.人工神经网络在地基土液化判别及等级评价中的应用[D].天津:河北工业大学,2002.REN Wenjie.Application of artificial neural network in estimation and grade evaluation of foundation soil liquefaction[D].Tianjin:Hebei University of Technology,2002.(in Chinese)
[7]向东进.多元统计分析引论[M].武汉:中国地质大学出版社,2005:131-132.XIANG Dongjin.Multivariate statistical analysis introduction[M].Wuhan:China University of Geosciences Publishing House,2005:131-132.(in Chinese)
[8]李亮,褚雪松.BP神经网络模型在空间变异土坡可靠度分析中的预测精度[J].中国科技论文,2016,11(13):1478-1482.LI Liang,CHU Xuesong.Prediction accuracy of back propagation artificial neural network model in the reliability analysis of spatially variable slope[J].China Sciencepaper,2016,11(13):1478-1482.(in Chinese)
[9]楼旭伟,楼辉波,朱剑锋.基于遗传算法径向基神经网络的交通流预测[J].中国科技论文,2013,8(11):1141-1144.LOU Xuwei,LOU Huibo,ZHU Jianfeng.Prediction of traffic flow of optimized radial basis function neural network based on genetic algorithm[J].China Sciencepaper,2013,8(11):1141-1144.(in Chinese)
[10]赵建军,贺宇航,黄润秋,等.基于因子分析法的边坡稳定性评价指标权重[J].西南交通大学学报,2015,50(2):325-330.ZHAO Jianjun,HE Yuhang,HUANG Runqiu,et al.Weights of slope stability evaluation indexes based on factor analysis method[J].Journal of Southwest Jiaotong University,2015,50(2):325-330.(in Chinese)
[11]王金亮,翁秀红.基于主成分分析法的泥石流危险度综合评价[J].地质灾害与环境保护,2013,24(1):88-92.WANG Jinliang,WENG Xiuhong.Comprehensive evaluation of the risk of debris flows based on principal component analysis[J].Geological Hazards and Environmental Protection,2013,24(1):88-92.(in Chinese)
[2]陈奎,刘兴昌.砂土地震液化的神经网络预测[J].中国地质灾害与防治学报,2000,22(1):15-18.CHEN Kui,LIU Xingchang.The prediction of BP neural network to sand liquefaction during earthquake[J].Chinese Journal of Geological Hazard and Control,2000,22(1):15-18.(in Chinese)
[3]陈海军,郦能惠,聂德新,等.岩爆预测的人工神经网络模型[J].岩土工程学报,2002,24(2):229-232.CHEN Haijun,LI Nenghui,NIE Dexin,et al.A model for prediction of rock burst by artificial neural network[J].Chinese Journal of Geotechnical Engineering,2002,24(2):229-232.(in Chinese)
[4]马骥.基于MATLAB的BP神经网络在砂土液化评价中的应用[J].水文地质工程地质,2004,31(2):54-58.MA Ji.Application of BP neural network based on MATLAB to the evaluation of sandy soil seismic liquefaction[J].Hydrogeology Engineering Geology,2004,31(2):54-58.(in Chinese)
[5]蔡煜东,宫家文,姚林声.砂土液化预测的人工神经网络模型[J].岩土工程学报,1993,15(6):53-58.CAI Yudong,GONG Jiawen,YAO Linsheng.Artificial neural network model for prediction of liquefaction of sandy soil[J].Chinese Journal of Geotechnical Engineering,1993,15(6):53-58.(in Chinese)
[6]任文杰.人工神经网络在地基土液化判别及等级评价中的应用[D].天津:河北工业大学,2002.REN Wenjie.Application of artificial neural network in estimation and grade evaluation of foundation soil liquefaction[D].Tianjin:Hebei University of Technology,2002.(in Chinese)
[7]向东进.多元统计分析引论[M].武汉:中国地质大学出版社,2005:131-132.XIANG Dongjin.Multivariate statistical analysis introduction[M].Wuhan:China University of Geosciences Publishing House,2005:131-132.(in Chinese)
[8]李亮,褚雪松.BP神经网络模型在空间变异土坡可靠度分析中的预测精度[J].中国科技论文,2016,11(13):1478-1482.LI Liang,CHU Xuesong.Prediction accuracy of back propagation artificial neural network model in the reliability analysis of spatially variable slope[J].China Sciencepaper,2016,11(13):1478-1482.(in Chinese)
[9]楼旭伟,楼辉波,朱剑锋.基于遗传算法径向基神经网络的交通流预测[J].中国科技论文,2013,8(11):1141-1144.LOU Xuwei,LOU Huibo,ZHU Jianfeng.Prediction of traffic flow of optimized radial basis function neural network based on genetic algorithm[J].China Sciencepaper,2013,8(11):1141-1144.(in Chinese)
[10]赵建军,贺宇航,黄润秋,等.基于因子分析法的边坡稳定性评价指标权重[J].西南交通大学学报,2015,50(2):325-330.ZHAO Jianjun,HE Yuhang,HUANG Runqiu,et al.Weights of slope stability evaluation indexes based on factor analysis method[J].Journal of Southwest Jiaotong University,2015,50(2):325-330.(in Chinese)
[11]王金亮,翁秀红.基于主成分分析法的泥石流危险度综合评价[J].地质灾害与环境保护,2013,24(1):88-92.WANG Jinliang,WENG Xiuhong.Comprehensive evaluation of the risk of debris flows based on principal component analysis[J].Geological Hazards and Environmental Protection,2013,24(1):88-92.(in Chinese)