基于模糊控制的人工神经网络模拟在土质边坡安全预测中的应用
|
摘要
从最优化角度出发,用神经网络解决模糊控制系统的规则提取问题,给出可靠的基于BP算法的可靠神经网络模拟过程,对模糊子集个数的选取与系统复杂性、精确性之间的关系进行讨论。为获得边坡复杂工况下的安全特征,建立基于模糊控制的人工神经网络边坡安全预测模型,由大量样本进行网络训练。研究结果表明:所建立的模型预测精度较高,且实用易行;边坡的坡度、内摩擦角、凝聚力对边坡的安全系数影响较大;该预测模型可用于处理普遍存在的不确定性、非线性复杂工程问题;通过模糊控制调整模型,可对不同工程对象进行较精确的模拟分析。
Based on optimal consideration,the problem of abstracting rule of a fuzzy control system by introducing neural network was solved.A reliable learning procedure for the neural network based on BP algorithm was suggested and the relationship among the number of fuzzy sets and the complexity and accuracy of fuzzy controller was investigated.Furthermore,in order to obtain safety characteristics of slope with complicated working behaviours,the prediction of the slope stability was presented on the foregoing artificial neural network under fuzzy controller,and many samples were collected to carry on the network training.The results show that the prediction models are accurate and easy to operate.The safety factor is affected largely by the parameters of the slope stability such as the slope gradient,rubbing angle inside and coagulate force.Theoretical model can be used to study the uncertainty and nonlinearity in engineering.With the help of fuzzy controlling system which is applicable for model's adjustment,it is of convenience to simulate the working behavior of diverse cases accurately.
Based on optimal consideration,the problem of abstracting rule of a fuzzy control system by introducing neural network was solved.A reliable learning procedure for the neural network based on BP algorithm was suggested and the relationship among the number of fuzzy sets and the complexity and accuracy of fuzzy controller was investigated.Furthermore,in order to obtain safety characteristics of slope with complicated working behaviours,the prediction of the slope stability was presented on the foregoing artificial neural network under fuzzy controller,and many samples were collected to carry on the network training.The results show that the prediction models are accurate and easy to operate.The safety factor is affected largely by the parameters of the slope stability such as the slope gradient,rubbing angle inside and coagulate force.Theoretical model can be used to study the uncertainty and nonlinearity in engineering.With the help of fuzzy controlling system which is applicable for model's adjustment,it is of convenience to simulate the working behavior of diverse cases accurately.
引文
[1]黄苏南,邵惠鹤,张钟俊.控制理论与应用[M].上海:上海交通大学出版社,1994:327386.HUANG Su-nan,SHAO Hui-he,ZHANG Zhong-jun.Control theory and application[M].Shanghai:Shanghai Jiaotong University Press,1994:327386.
[2]Zadeh L A.Fuzzy sets[J].Information and Control,1965(8):338353.
[3]徐晓龙,孙炳楠.基于智能算法的高层建筑非线性地震反应的MR阻尼器半主动控制[J].工程力学,2008,25(1):209216.XU Xiao-long,SUN Bing-nan.Intelligent algorithm based semi-active control of MR damper of nonlinear seismic response for high-rise buildings[J].Engineering Mechanics,2008,25(1):209216.
[4]刘强.MR智能基础隔震结构抗震性能分析[J].低温建筑技术,2008,122(2):5355.LIU Qiang.Seismic response with MR analysis of intelligent base isolated structure damper based on the application of ANFS[J].Low Temperature Architecture Technology,2008,122(2):5355.
[5]罗旭.基于蚁群学习算法的模糊小波神经网络控制[J].福建电脑,2008(1):6061.LUO Xu.Fuzzy-wavelet neural network control based on ant-colony optimization[J].Fujian Computer Technology,2008(1):6061.
[6]Hunt Y,Haas R,Smith R M.Neural networks for control systems:A survey.Automatica[M].NY:Pergamon Press,1992:10831112.
[7]Marzuki K,JIANG Zhong-ping,CHEN Ben-mei,et al.IEEE CSM[C]//Decision and Control.Proceedings of47th IEEE Conference.London:IET CNF,1992,12(3):58.
[8]Nguyen D H,Widraw B.IEEE CSM[C]//Power Delivery.London:IEEE JNL,IEEE Transactions,1990:1218.
[9]李平,孙优贤,周晋晖.控制理论与应用[M].浙江:浙江大学出版社,1995:246.LI Ping,SUN You-xian,ZHOU Jing-hui.Controlling theory and application[M].Zhejiang:Zhejiang University Press,1995:246.
[10]杨煌普,许晓鸣,张钟俊.模式识别与人工智能[M].上海:上海交通大学出版社,1994:353.YANG Huang-pu,XU Xiao-ming,ZHANG Zhong-jun.Model identification and artificial intelligence[M].Shanghai:Shanghai Jiaotong University Press,1994:353.
[11]毛昶熙,段祥宝.渗流数值计算与程序应用[M].南京:河海大学出版社,1999:3197MAO Chang-xi,DUAN Xiang-bao.Seepage numerical calculation and program application[M].Nanjing:Hohai University Press,1999:3197.
[12]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1994:44102.ZHANG Li-ming.Artificial neural network model and application[M].Shanghai:Fudan University Press,1994:44102.
[13]斯华龄.电脑人脑化[M].北京:北京大学出版社,1993:1376.SI Hua-ling.Artificial computational technology[M].Beijing:Peking University Press,1993:1376
[14]陆金桂.基于神经网络的结构近似分析方法[J].中国科学:A辑,1994,24(6):714.LU Jin-gui.Structure approximate analytical theory based on neural network[J].Science of China:Volume A,1994,24(6):714.
[15]周继成,周清山,韩飘杨,等.人工神经网络-第六代计算机的实现[M].北京:科学普及出版社,1991:57121.ZHOU Ji-cheng,ZHOU Qing-shan,HAN Piao-yang,et al.Artificial neural network-sixth grade simulation with computer technology[M].Beijing:Science Popularization Press,1991:57121.
[16]陈祖煜,邵长明.最优化方法在确定边坡最小安全系数方面的应用[J].岩土工程学报,1998,10(4):113.CHEN Zhu-yu,SHAO Chang-ming.Optimization theory on minimal safety factor calculation of slope stability[J].Chinese Jounal of Geotechnical Engineering,1998,10(4):113.
[2]Zadeh L A.Fuzzy sets[J].Information and Control,1965(8):338353.
[3]徐晓龙,孙炳楠.基于智能算法的高层建筑非线性地震反应的MR阻尼器半主动控制[J].工程力学,2008,25(1):209216.XU Xiao-long,SUN Bing-nan.Intelligent algorithm based semi-active control of MR damper of nonlinear seismic response for high-rise buildings[J].Engineering Mechanics,2008,25(1):209216.
[4]刘强.MR智能基础隔震结构抗震性能分析[J].低温建筑技术,2008,122(2):5355.LIU Qiang.Seismic response with MR analysis of intelligent base isolated structure damper based on the application of ANFS[J].Low Temperature Architecture Technology,2008,122(2):5355.
[5]罗旭.基于蚁群学习算法的模糊小波神经网络控制[J].福建电脑,2008(1):6061.LUO Xu.Fuzzy-wavelet neural network control based on ant-colony optimization[J].Fujian Computer Technology,2008(1):6061.
[6]Hunt Y,Haas R,Smith R M.Neural networks for control systems:A survey.Automatica[M].NY:Pergamon Press,1992:10831112.
[7]Marzuki K,JIANG Zhong-ping,CHEN Ben-mei,et al.IEEE CSM[C]//Decision and Control.Proceedings of47th IEEE Conference.London:IET CNF,1992,12(3):58.
[8]Nguyen D H,Widraw B.IEEE CSM[C]//Power Delivery.London:IEEE JNL,IEEE Transactions,1990:1218.
[9]李平,孙优贤,周晋晖.控制理论与应用[M].浙江:浙江大学出版社,1995:246.LI Ping,SUN You-xian,ZHOU Jing-hui.Controlling theory and application[M].Zhejiang:Zhejiang University Press,1995:246.
[10]杨煌普,许晓鸣,张钟俊.模式识别与人工智能[M].上海:上海交通大学出版社,1994:353.YANG Huang-pu,XU Xiao-ming,ZHANG Zhong-jun.Model identification and artificial intelligence[M].Shanghai:Shanghai Jiaotong University Press,1994:353.
[11]毛昶熙,段祥宝.渗流数值计算与程序应用[M].南京:河海大学出版社,1999:3197MAO Chang-xi,DUAN Xiang-bao.Seepage numerical calculation and program application[M].Nanjing:Hohai University Press,1999:3197.
[12]张立明.人工神经网络的模型及其应用[M].上海:复旦大学出版社,1994:44102.ZHANG Li-ming.Artificial neural network model and application[M].Shanghai:Fudan University Press,1994:44102.
[13]斯华龄.电脑人脑化[M].北京:北京大学出版社,1993:1376.SI Hua-ling.Artificial computational technology[M].Beijing:Peking University Press,1993:1376
[14]陆金桂.基于神经网络的结构近似分析方法[J].中国科学:A辑,1994,24(6):714.LU Jin-gui.Structure approximate analytical theory based on neural network[J].Science of China:Volume A,1994,24(6):714.
[15]周继成,周清山,韩飘杨,等.人工神经网络-第六代计算机的实现[M].北京:科学普及出版社,1991:57121.ZHOU Ji-cheng,ZHOU Qing-shan,HAN Piao-yang,et al.Artificial neural network-sixth grade simulation with computer technology[M].Beijing:Science Popularization Press,1991:57121.
[16]陈祖煜,邵长明.最优化方法在确定边坡最小安全系数方面的应用[J].岩土工程学报,1998,10(4):113.CHEN Zhu-yu,SHAO Chang-ming.Optimization theory on minimal safety factor calculation of slope stability[J].Chinese Jounal of Geotechnical Engineering,1998,10(4):113.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心