递归神经网络在堆石坝地震响应分析中的应用
|
摘要
针对堆石坝系统的地震响应分析问题,提出了一种递归神经网络建模方法。该神经网络模型包含内部状态神经元的反馈并具有状态空间形式。借助于该网络模型的逼近能力和动态信息存储能力,从观测的结构动态系统输入输出数据中重构原系统的输入输出特性,并对新的输入信号做出相应的预测和响应。分别对理想的有限元响应数据和实测的响应数据进行了仿真。结果表明,所提出的神经网络方法较好地学习了这两组结构系统的动态特性,并显示出较好的预测效果。
A kind of recurrent neural network was applied to the earthquake response analysis for Rock-fill Dam.The neural network model contains the feedback of the state neurons and takes the form of state space representation.With the approximation capability and dynamic information storage capability,the neural network model was trained to reconstruct the input-output characters from the observed input-output data.The model trained could perform response analysis and make prediction for new earthquake wave.Two data sets were used to test the method,the one was from a finite element program,and the other was from a real-life experiment.The responses of Rock-fill dam are well modeled,and the simulation result for new data indicates the better prediction ability.
A kind of recurrent neural network was applied to the earthquake response analysis for Rock-fill Dam.The neural network model contains the feedback of the state neurons and takes the form of state space representation.With the approximation capability and dynamic information storage capability,the neural network model was trained to reconstruct the input-output characters from the observed input-output data.The model trained could perform response analysis and make prediction for new earthquake wave.Two data sets were used to test the method,the one was from a finite element program,and the other was from a real-life experiment.The responses of Rock-fill dam are well modeled,and the simulation result for new data indicates the better prediction ability.
引文
[1]Chen H M,Qi G Z,Yang J C S.Amini F,Neural Network for Structural Dynamic Model Identification[J].Journal of Engineering Mechanics,1995,121(12):1377-1341.
[2]Han M,Han G C,Jiang X,Lian Z.Study of dynamic response of dams with neural network[A].Proceedings of IEEE international conference on Systems,Man,and Cybernatics 2001[C].Piscataway:IEEE Press,2001,134-139.
[3]Hung S,Huang C S,Wen C M,Hsu Y C.Nonparametric Identification of a Building Structure from Experimental Data Using Wavelet Neural Network[J].Computer-Aided Civil and Infrastructure Engineering,2003,18(5):356-368.
[4]Kuzniar K,Maciag E,Obiala R,Waszczyszyn Z.Application of neural networks in natural periods identification and simulation of prefabricated buildings response[J].Soil Dynamics and Earthquake Engineering,2000,20(1-4):217-222.
[5]Elman J L.Finding Structure in Time[J].Cognitive Science,1990,14(2):179-211.
[6]Wei M,Yan G.,Shen Y.Study of non-linear structure's identification using dynamic neural network[J].Chinese Journal of Applied Mechanics,2000,17(2):110-113.
[7]Yao Z F,Zhou J M,Tao YG.Neural network modeling for space structures[J].Nanjing Hangkong Hangtian Daxue Xuebao/Journal of Nanjing University of Aeronautics and Astronautics,2001,33(5):445-448.
[8]Rivals I,Personnaz L.Black-box Modeling with State-Space Neural Networks[A].Neural Adaptive Control Technology[C].World Scientific.1995,237-264.
[9]Gonzalez P A,Zamarreno J M,A short-term temperature forecaster based on a state space neural network[J].Engineering Applications of Artificial Intelligence,2002,15(5):459-464.
[10]Suykens J A K,De Moor B L R,Vandewalle J.Nonlinear system identification using neural state space models,applicable to robust control design[J].International Journal of Control,1995 62(1):129-152.
[11]Ren X M.Identification of nonlinear systems using recurrent neural networks[J].Control Theory and Applications,2001,18(6):944–953.
[12]Han M,Shi Z W,and Wang W.Modeling dynamic system by recurrent neural network with state variables[A],in Advances in Neural Networks-ISNN 2004,Pt 2,Vol.3174,Lecture Notes in Computer Science[C].Berlin:SPRINGER-VERLAG BERLIN,2004,200-205.
[13]De Jesus O,Hagan M T.Backpropagation through time for a general class of recurrent network[A].Proceedings of International Joint Conference of Neural Networks 2001[C].NEW YORK:IEEE Press,2001,2638-2643.
[2]Han M,Han G C,Jiang X,Lian Z.Study of dynamic response of dams with neural network[A].Proceedings of IEEE international conference on Systems,Man,and Cybernatics 2001[C].Piscataway:IEEE Press,2001,134-139.
[3]Hung S,Huang C S,Wen C M,Hsu Y C.Nonparametric Identification of a Building Structure from Experimental Data Using Wavelet Neural Network[J].Computer-Aided Civil and Infrastructure Engineering,2003,18(5):356-368.
[4]Kuzniar K,Maciag E,Obiala R,Waszczyszyn Z.Application of neural networks in natural periods identification and simulation of prefabricated buildings response[J].Soil Dynamics and Earthquake Engineering,2000,20(1-4):217-222.
[5]Elman J L.Finding Structure in Time[J].Cognitive Science,1990,14(2):179-211.
[6]Wei M,Yan G.,Shen Y.Study of non-linear structure's identification using dynamic neural network[J].Chinese Journal of Applied Mechanics,2000,17(2):110-113.
[7]Yao Z F,Zhou J M,Tao YG.Neural network modeling for space structures[J].Nanjing Hangkong Hangtian Daxue Xuebao/Journal of Nanjing University of Aeronautics and Astronautics,2001,33(5):445-448.
[8]Rivals I,Personnaz L.Black-box Modeling with State-Space Neural Networks[A].Neural Adaptive Control Technology[C].World Scientific.1995,237-264.
[9]Gonzalez P A,Zamarreno J M,A short-term temperature forecaster based on a state space neural network[J].Engineering Applications of Artificial Intelligence,2002,15(5):459-464.
[10]Suykens J A K,De Moor B L R,Vandewalle J.Nonlinear system identification using neural state space models,applicable to robust control design[J].International Journal of Control,1995 62(1):129-152.
[11]Ren X M.Identification of nonlinear systems using recurrent neural networks[J].Control Theory and Applications,2001,18(6):944–953.
[12]Han M,Shi Z W,and Wang W.Modeling dynamic system by recurrent neural network with state variables[A],in Advances in Neural Networks-ISNN 2004,Pt 2,Vol.3174,Lecture Notes in Computer Science[C].Berlin:SPRINGER-VERLAG BERLIN,2004,200-205.
[13]De Jesus O,Hagan M T.Backpropagation through time for a general class of recurrent network[A].Proceedings of International Joint Conference of Neural Networks 2001[C].NEW YORK:IEEE Press,2001,2638-2643.
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