基于遗传优化神经网络的高速公路路基沉降量预测
|
摘要
控制路基沉降是公路工程中的一个关键技术问题,而路基沉降与其影响因素之间存在着线性、非线性关系。当输入自变量较多时,用传统神经网络建模容易出现过拟合现象,导致网络模型预测精度较低。针对此问题,本文用遗传算法对神经网络模型的权值和阈值进行优化,同时讨论遗传参数的设定对输出结果的影响。通过对成南高速的实测数据进行仿真,试验结果表明:优化后的BP神经网络具有较高的预测精度,预测效果明显优于传统神经网络模型的输出结果,该预测方法可作为高速公路路基长期沉降预测的一种有效辅助手段。
Controlling subgrade settlement is essential in highway engineering. Subgrade settlement has a linear and nonlinear relationship with its influencing factors. Over-fitting easily occurs in traditional neural network modeling in the presence of numerous input independent variables and results in the low prediction accuracy of the network model. This work aims to address these issues. Thus, the ability of the genetic algorithm to optimize the weight and threshold of the neural network is investigated, and the influence of the set of genetic parameters on the output results is discussed. Experiments with the proposed method show that the optimized BP neural network has higher prediction accuracy and better prediction effect than the traditional neural network model in the simulation of measured data for the Chengdu—Nanchong Highway. The prediction method can be used as an effective auxiliary means for predicting the long-term settlement of highway subgrades.
Controlling subgrade settlement is essential in highway engineering. Subgrade settlement has a linear and nonlinear relationship with its influencing factors. Over-fitting easily occurs in traditional neural network modeling in the presence of numerous input independent variables and results in the low prediction accuracy of the network model. This work aims to address these issues. Thus, the ability of the genetic algorithm to optimize the weight and threshold of the neural network is investigated, and the influence of the set of genetic parameters on the output results is discussed. Experiments with the proposed method show that the optimized BP neural network has higher prediction accuracy and better prediction effect than the traditional neural network model in the simulation of measured data for the Chengdu—Nanchong Highway. The prediction method can be used as an effective auxiliary means for predicting the long-term settlement of highway subgrades.
引文
[1] 马云峰.差分法在路基沉降预测中的应用[J].公路工程,2012,37(5):180-182.MA Yunfeng.Difference Method in the Prediction of Subgrade Settlement[J].Highway Engineering,2012,37(5):180-182.
[2] 胡荣光.基于分层总和法的路基沉降时序规律多元非线性回归分析[J].铁道工程学报,2009,26(3):7-10.HU Guangrong.Multivariate Nonlinear Regression Analysis of Time Series Law to Subgrade Settlement of High-speed Railway Based on the Foundation of Layer-summation[J].Journal of Railway Engineering Society,2009,26(3):7-10.
[3] 潘林有,谢新宇.用曲线拟合的方法预测软土地基沉降[J].岩土力学,2004,25(7):1053-1058.PAN Linyou,XIE Xinyu.Observation Settlement Prediction by Curve Fitting Methods[J].Rock and Soil Mechanics,2004,25(7):1053-1058.
[4] 李洪峰,单炜,王立海.经验公式法在季冻地区软土地基沉降预测中的应用[J].东北林业大学学报,2007,35(12):45-47.LI Hongfeng,SHAN Wei,WANG Lihai.Application of Experience Formula to the Settlement Forecast of Soft Foundation Treatment in Seasonal Freezing Area[J].Journal of Northeast Forestry University,2007,35(12):45-47.
[5] 邓成发,杨凤根.软土路基沉降的非线性有限元分析[J].国防交通工程与技术,2007,5(1):23-25.DENG Chengfa,YANG Fenggen.Nonlinear Finite Element Analysis of the Settlement of Soft Soil Road Beds[J].Traffic Engineering and Technology for National Defence,2007,5(1):23-25.
[6] 苏晓成,周天来,刘志峰.拟静力法公路路基结构抗震稳定性研究[J].地震工程学报,2014,36(3):482-488.SU Xiaocheng,ZHOU Tianlai,LIU Zhifeng.Seismic Stability Analysis of Highway Subgrade Based on the Pseudo-static Method[J].China Earthquake Engineering Journal,2014,36(6):482-488.
[7] 鱼欢,郑俊杰,曹文昭,等.非对称交通荷载作用下拓宽路堤动力特性分析[J].地震工程学报,2017,39(6):1112-1117.YU Huan,ZHENG Junjie,CAO Wenzhao,et al.Dynamic Characteristics Analysis of Widening Embankmengts under Asymmtric Traffic Loading[J].China Earthguake Engineering Journal,2017,39(6):1112-1117.
[8] 蔡润,武震,云欢,等.基于BP和SOM神经网络相结合的地震预测研究[J].四川大学学报(自然科学版),2018,55(2):307-315.CAI Run,WU Zhen,YUN Huan,et al.Research on Earthquake Prediction Based on BP and SOM Neural Network[J].Journal of Sichuan University (Nature Science Edition),2018,55(2):307-315.
[9] XING S,JU J,XING J.Research on Hot-rolling Steel Products Quality Control Based on BP Neural Network Inverse Model[M].Neural Computing & Applications:Springer London,2018,1-8.
[10] TU X,ZHOU Y F,ZHAO P,et al.Modeling the Static Friction in a Robot Joint by Genetically Optimized BP Neural Network[J].Journal of Intelligent and Robotic Systems,2018,3(4):1-13.
[11] ASIM K M,MARTíNEZ-áLVAREZ F,BASIT A,et al.Earthquake Magnitude Prediction in Hindukush Region Using Machine Learning Techniques[J].Natural Hazards,2017,85:1-16.
[12] 徐昕军,勾妍妍,杨峰.基于探地雷达与概率神经网络的城市道路路基病害预警模型研究[J].科学技术与工程,2017,17(17):118-124.XU Xinjun,GOU Yanyan,YANG Feng.Research on Early Warning Model of Roadbed Diseases under Urban Roads Based on GPR and Probabilistic Neural Network[J]. Science Technology and Engineering,2017,17(17):118-124.
[13] 王睿,漆泰岳,冯剑,等.基于遗传算法的BP神经网络隧道施工参数正反演分析与应用[J].铁道学报,2016,38(4):98-104.WANG Rui,QI Taiyue,FENG Jian,et al.Application of Genetic Algorithm Based ANN to Forward and Back Analysis on Tunnel Construction Parameters[J].Journal of The China Railway Society,2016,38(4):98-104.
[14] 谭云亮,王春秋.岩石本构关系的径向基函数神经网络快速逼近模型[J].岩土工程学报,2001,23(1):14-17.TAN Yunliang,WANG Chunqiu.A Fast Approaching Model for Rock Constitution Equation by Radial Basis Function Neural Network[J].Chinese Journal of Geotechnical Engineering,2001,23(1):14-17.
[15] 王靖涛,杨毅,张曦映.考虑应力路径的砂土的神经网络本构关系模型[J].岩石力学与工程学报,2002,21(10):1487-1489.WANG Jingtao,YANG Yi,ZHANG Xiying.Neural Network Constitutive Model of Sand Soil in Consideration of Stress Paths[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(10):1487-1489.
[16] 胡卫东,曹文贵.基于粒子群BP网络混合算法的边坡稳定性评价[J].铁道科学与工程学报,2015,12(1):66-71.HU Weidong,CAO Wengui.Slope Stability Evaluation Based on Hybrid Lgorithm of Particle Swarm Optimization and BP Neural Network[J].Journal of Railway Science and Engineering,2015,12(1):66-71.
[17] 刘飞,刘智权,宋丹,等.基于BP神经网络和均匀设计的边坡敏感性分析[J].水电能源科学,2014,32(10):113-115.LIU Fei,LIU Zhiquan,SONG Dan,et al.Sensitivity Analysis of Slope Stability Based on BP Neural Network and Uniform Design[J].Water Resources and Power,2014,32(10):113-115.
[18] KAUNDA R B,CHASE R B,KEHEW A E,et al.Neural Network Modeling Applications in Active Slope Stability Problems[J].Environmental Earth Sciences,2010,60(7):1545-1558.
[19] 王佳信,周宗红,付斌,等.因子分析-概率神经网络模型在边坡稳定性评价中的应用[J].水文地质工程地质,2018,45(2):123-130.WANG Jiaxin,ZHOU Zonghong,FU Bin,et al.Application of Factor Analysis and Probabilistic Neural Network Model on Evaluation of the Slope Stability,2018,45(2):123-130.
[20] 丁丽宏,马强.基于组合权重的模糊物元模型在边坡稳定性评价中的应用[J].地震工程学报,2017,39(5):946-950,980.DING Lihong,MA Qiang.Application of Model Based on Coefficients of Combined Weights to Evaluate Slope Stability[J].China Earthquake Engineering Journal,2017,39(5):946-950,980.
[21] 崔雍,楚小刚,董嘉,等.基于神经网络的桩基竖向承载力预测研究[J].铁道工程学报,2016,33(4):65-69.CUI Yong,CHU Xiaogang,DONG Jia,et al.Prediction Research on the Vertical Bearing Capacity of Pile Foundation Based on Neural Network[J].Journal of Railway Engineering Society,2016,33(4):65-69.
[22] 王成华,张薇.人工神经网络在桩基工程中的应用综述[J].岩土力学,2002,23(2):173-178.WANG Chenghua,ZHANG Wei.Application of Artificial Neural Networks to Pile Foundation Engineering[J].Rock and Soil Mechanics,2002,23(2):173-178.
[23] 徐世强,梁武星,屈战辉.BP神经网络在预测路基沉降中的应用[J].西安工业大学学报,2006,26(5):452-456.XU Shiqiang,LIANG Wuxing,QU Zhanhui.Application of BP Neural Networks in Forecast the Final Settlement of Highway Roadbed[J].Journal of Xi'an Technological University,2006,26(5):452-456.
[2] 胡荣光.基于分层总和法的路基沉降时序规律多元非线性回归分析[J].铁道工程学报,2009,26(3):7-10.HU Guangrong.Multivariate Nonlinear Regression Analysis of Time Series Law to Subgrade Settlement of High-speed Railway Based on the Foundation of Layer-summation[J].Journal of Railway Engineering Society,2009,26(3):7-10.
[3] 潘林有,谢新宇.用曲线拟合的方法预测软土地基沉降[J].岩土力学,2004,25(7):1053-1058.PAN Linyou,XIE Xinyu.Observation Settlement Prediction by Curve Fitting Methods[J].Rock and Soil Mechanics,2004,25(7):1053-1058.
[4] 李洪峰,单炜,王立海.经验公式法在季冻地区软土地基沉降预测中的应用[J].东北林业大学学报,2007,35(12):45-47.LI Hongfeng,SHAN Wei,WANG Lihai.Application of Experience Formula to the Settlement Forecast of Soft Foundation Treatment in Seasonal Freezing Area[J].Journal of Northeast Forestry University,2007,35(12):45-47.
[5] 邓成发,杨凤根.软土路基沉降的非线性有限元分析[J].国防交通工程与技术,2007,5(1):23-25.DENG Chengfa,YANG Fenggen.Nonlinear Finite Element Analysis of the Settlement of Soft Soil Road Beds[J].Traffic Engineering and Technology for National Defence,2007,5(1):23-25.
[6] 苏晓成,周天来,刘志峰.拟静力法公路路基结构抗震稳定性研究[J].地震工程学报,2014,36(3):482-488.SU Xiaocheng,ZHOU Tianlai,LIU Zhifeng.Seismic Stability Analysis of Highway Subgrade Based on the Pseudo-static Method[J].China Earthquake Engineering Journal,2014,36(6):482-488.
[7] 鱼欢,郑俊杰,曹文昭,等.非对称交通荷载作用下拓宽路堤动力特性分析[J].地震工程学报,2017,39(6):1112-1117.YU Huan,ZHENG Junjie,CAO Wenzhao,et al.Dynamic Characteristics Analysis of Widening Embankmengts under Asymmtric Traffic Loading[J].China Earthguake Engineering Journal,2017,39(6):1112-1117.
[8] 蔡润,武震,云欢,等.基于BP和SOM神经网络相结合的地震预测研究[J].四川大学学报(自然科学版),2018,55(2):307-315.CAI Run,WU Zhen,YUN Huan,et al.Research on Earthquake Prediction Based on BP and SOM Neural Network[J].Journal of Sichuan University (Nature Science Edition),2018,55(2):307-315.
[9] XING S,JU J,XING J.Research on Hot-rolling Steel Products Quality Control Based on BP Neural Network Inverse Model[M].Neural Computing & Applications:Springer London,2018,1-8.
[10] TU X,ZHOU Y F,ZHAO P,et al.Modeling the Static Friction in a Robot Joint by Genetically Optimized BP Neural Network[J].Journal of Intelligent and Robotic Systems,2018,3(4):1-13.
[11] ASIM K M,MARTíNEZ-áLVAREZ F,BASIT A,et al.Earthquake Magnitude Prediction in Hindukush Region Using Machine Learning Techniques[J].Natural Hazards,2017,85:1-16.
[12] 徐昕军,勾妍妍,杨峰.基于探地雷达与概率神经网络的城市道路路基病害预警模型研究[J].科学技术与工程,2017,17(17):118-124.XU Xinjun,GOU Yanyan,YANG Feng.Research on Early Warning Model of Roadbed Diseases under Urban Roads Based on GPR and Probabilistic Neural Network[J]. Science Technology and Engineering,2017,17(17):118-124.
[13] 王睿,漆泰岳,冯剑,等.基于遗传算法的BP神经网络隧道施工参数正反演分析与应用[J].铁道学报,2016,38(4):98-104.WANG Rui,QI Taiyue,FENG Jian,et al.Application of Genetic Algorithm Based ANN to Forward and Back Analysis on Tunnel Construction Parameters[J].Journal of The China Railway Society,2016,38(4):98-104.
[14] 谭云亮,王春秋.岩石本构关系的径向基函数神经网络快速逼近模型[J].岩土工程学报,2001,23(1):14-17.TAN Yunliang,WANG Chunqiu.A Fast Approaching Model for Rock Constitution Equation by Radial Basis Function Neural Network[J].Chinese Journal of Geotechnical Engineering,2001,23(1):14-17.
[15] 王靖涛,杨毅,张曦映.考虑应力路径的砂土的神经网络本构关系模型[J].岩石力学与工程学报,2002,21(10):1487-1489.WANG Jingtao,YANG Yi,ZHANG Xiying.Neural Network Constitutive Model of Sand Soil in Consideration of Stress Paths[J].Chinese Journal of Rock Mechanics and Engineering,2002,21(10):1487-1489.
[16] 胡卫东,曹文贵.基于粒子群BP网络混合算法的边坡稳定性评价[J].铁道科学与工程学报,2015,12(1):66-71.HU Weidong,CAO Wengui.Slope Stability Evaluation Based on Hybrid Lgorithm of Particle Swarm Optimization and BP Neural Network[J].Journal of Railway Science and Engineering,2015,12(1):66-71.
[17] 刘飞,刘智权,宋丹,等.基于BP神经网络和均匀设计的边坡敏感性分析[J].水电能源科学,2014,32(10):113-115.LIU Fei,LIU Zhiquan,SONG Dan,et al.Sensitivity Analysis of Slope Stability Based on BP Neural Network and Uniform Design[J].Water Resources and Power,2014,32(10):113-115.
[18] KAUNDA R B,CHASE R B,KEHEW A E,et al.Neural Network Modeling Applications in Active Slope Stability Problems[J].Environmental Earth Sciences,2010,60(7):1545-1558.
[19] 王佳信,周宗红,付斌,等.因子分析-概率神经网络模型在边坡稳定性评价中的应用[J].水文地质工程地质,2018,45(2):123-130.WANG Jiaxin,ZHOU Zonghong,FU Bin,et al.Application of Factor Analysis and Probabilistic Neural Network Model on Evaluation of the Slope Stability,2018,45(2):123-130.
[20] 丁丽宏,马强.基于组合权重的模糊物元模型在边坡稳定性评价中的应用[J].地震工程学报,2017,39(5):946-950,980.DING Lihong,MA Qiang.Application of Model Based on Coefficients of Combined Weights to Evaluate Slope Stability[J].China Earthquake Engineering Journal,2017,39(5):946-950,980.
[21] 崔雍,楚小刚,董嘉,等.基于神经网络的桩基竖向承载力预测研究[J].铁道工程学报,2016,33(4):65-69.CUI Yong,CHU Xiaogang,DONG Jia,et al.Prediction Research on the Vertical Bearing Capacity of Pile Foundation Based on Neural Network[J].Journal of Railway Engineering Society,2016,33(4):65-69.
[22] 王成华,张薇.人工神经网络在桩基工程中的应用综述[J].岩土力学,2002,23(2):173-178.WANG Chenghua,ZHANG Wei.Application of Artificial Neural Networks to Pile Foundation Engineering[J].Rock and Soil Mechanics,2002,23(2):173-178.
[23] 徐世强,梁武星,屈战辉.BP神经网络在预测路基沉降中的应用[J].西安工业大学学报,2006,26(5):452-456.XU Shiqiang,LIANG Wuxing,QU Zhanhui.Application of BP Neural Networks in Forecast the Final Settlement of Highway Roadbed[J].Journal of Xi'an Technological University,2006,26(5):452-456.