结构振动控制中神经网络应用的新进展
|
摘要
介绍了作者近年来应用神经网络在结构振动控制研究中所取得的一些进展，包括：（１）提出了 自递归神经网络（ＳＰNＮ），这种网络的学习收敛速度比一般的ＢＰ网络快得多；（２）应用自递归神经网 络预测了结构地震响应，预测结果与结构实际响应相当吻合；（３）提出了一种基于自递归神经网络的 最优跟踪控制方法，可以稳定跟踪期望控制响应；（４）引入了结构化前馈神经网络求解多态混合控制 结构，响应过程中不同状态下的 Ｌｙａｐｕｎｏｖ方程，该法简单、快速，能够满足在线控制要求。
Some achievements obtained by authors in recent years on application of neural network in structural vibration control are introduced as follows : (l) a new self recurrent neural network(SRNN) is presented which learning speed is faster than BP's; (2) the predicted response by SRNN is consistent with real structural response,(3)an optimal tracking control algorithm for structural seismic response based on SRNN is presented. Neurocontroller can control structural response to track the desired response steadily by minimizing the quadratic performance index through learning control, (4) by introducing feedforward structural neural network, Lyapunov equation of different structure's state can be solved on-line simply and fast in control process.
Some achievements obtained by authors in recent years on application of neural network in structural vibration control are introduced as follows : (l) a new self recurrent neural network(SRNN) is presented which learning speed is faster than BP's; (2) the predicted response by SRNN is consistent with real structural response,(3)an optimal tracking control algorithm for structural seismic response based on SRNN is presented. Neurocontroller can control structural response to track the desired response steadily by minimizing the quadratic performance index through learning control, (4) by introducing feedforward structural neural network, Lyapunov equation of different structure's state can be solved on-line simply and fast in control process.
引文
[l] Yao J T P. Concept of structural control[J]. J. Struct. Engrg., 1972, 98(7)f 1567~ 1574.
[2] Yang J N. Application of optimal control theory to civil engineering structures[J]. J. Engrg. Mech.. ASCE.1975. 101:891 ~ 838.
[3] Martin C R. Soong T T. Model control of multistory structures[J]. J. Engrg. Mech.. ASCE. 1976, 102:613 ~ 623.
[4] Udwadia F E, Tabaie S. Pulse control of structural and mechanical systems[J]. J. Engrg. Mech.. ASCE, 1981,107(6):1011 ~ 1028.
[5] Yang J N, Akbarpour A. New optimal control algorithms for structural control[J]. J. Engrg. Engrg., ASCE, 1987,l 13(9):1369 ~ 1386.
[6] Nareendra K S. Parthasarath K. identification and control of dynamic systems using neural networks[J]. IEEE Trans.on Neural Network. 1990. l(l):4 ~ 27.
[7] Miller W. Werbos P J. Neurfal Network l'or control[M]. MIT Press. 1992.
[8] Warwick K et al. Neural networks for control and system[M]. Peter peregrius Lted., London, 1992.
[9] Ghaboussi J, Joghataie A. Active control of structures using neural networks[J]. J. Engrg. Mech.. ASCE. 1985. 121(4):555 ~ 567.
[10]吴建军.基于神经网络的结构地震响应控制[D]天津大学博士学位论文, 1998.
[11]何玉敖,吴建军.应用自递归神经网络预测结构响应[J].土木工程学报, 1998, 2.
[12]何玉敖,吴建军.预测结构动态响应的自递归神经网络方法[A].第二届全国建筑结构振动会议论文集[C]北京:中国建筑工业出版社,1997.
[I3] He Y A(何玉 ), Wu J.J(吴建军 ) Control of structural seismic response by selfrecurrent neural network(SRNN)[J].Eathquake Engineering & Structural Dynamic, 1998, 27.
[14]何玉敖,吴建军.线性结构振动的人工神经网络控制[A].第二届全国建筑结构振动会议论文集[C]北京:中国建筑工业出版社,1997
[15] Polycarpou M M, loannou P A. Learning and convergence analysis of neural - type structural network[J]. IEEETrails. on Neural Network. 1992, 3(1): 39 ~ 50.
[16] He Y A. Wu J J. Ail optimal tracking control of structural seismic response using self'- recurrentneural networks (SRNN) [A]. The proceeding of second world conference on structural control[C]. Japan, 1998.
[17] Yang J N, Danielians A, Liu S C. Aseismic hybrid control systems for building structures under strongearthquakes[J]. Intelligent Mat. Syst. Struct.. 1990, l(4):432 ~ 446.
[18] Kobori T, Koshika N, Yamada K, Ikeda Y. Seismic - response - controlled structuctre with active mass driver system. Part 1: Desing[J]. Earthquake Engrg. Struct. Dyn., I991. 20:133 ~ 149.
[19] Kobori T, Koshika N, K Yamada, Ikeda Y. Seismic- response - controlled structure with active mass driveer system,Part 2: Verfication[J]. Earthquake Engrg. Struct. Dyn., 1991, 20 : 151 ~ 166.
[20]刘文锋高层建筑在地震作用下的多态混合控制[D]天津大学博士学位论文,1995
[21] He Y A, Wu J J. Multi - state hybrid control of structures basing on neural network[A]. The proceeding of second worldconference on structural contro[C], Japan, 1998.
[22]李桂青,欧进萍非线性体系受平稳随机荷载的首次通过问题[D].地震工程与工程振动,1982,2.
[2] Yang J N. Application of optimal control theory to civil engineering structures[J]. J. Engrg. Mech.. ASCE.1975. 101:891 ~ 838.
[3] Martin C R. Soong T T. Model control of multistory structures[J]. J. Engrg. Mech.. ASCE. 1976, 102:613 ~ 623.
[4] Udwadia F E, Tabaie S. Pulse control of structural and mechanical systems[J]. J. Engrg. Mech.. ASCE, 1981,107(6):1011 ~ 1028.
[5] Yang J N, Akbarpour A. New optimal control algorithms for structural control[J]. J. Engrg. Engrg., ASCE, 1987,l 13(9):1369 ~ 1386.
[6] Nareendra K S. Parthasarath K. identification and control of dynamic systems using neural networks[J]. IEEE Trans.on Neural Network. 1990. l(l):4 ~ 27.
[7] Miller W. Werbos P J. Neurfal Network l'or control[M]. MIT Press. 1992.
[8] Warwick K et al. Neural networks for control and system[M]. Peter peregrius Lted., London, 1992.
[9] Ghaboussi J, Joghataie A. Active control of structures using neural networks[J]. J. Engrg. Mech.. ASCE. 1985. 121(4):555 ~ 567.
[10]吴建军.基于神经网络的结构地震响应控制[D]天津大学博士学位论文, 1998.
[11]何玉敖,吴建军.应用自递归神经网络预测结构响应[J].土木工程学报, 1998, 2.
[12]何玉敖,吴建军.预测结构动态响应的自递归神经网络方法[A].第二届全国建筑结构振动会议论文集[C]北京:中国建筑工业出版社,1997.
[I3] He Y A(何玉 ), Wu J.J(吴建军 ) Control of structural seismic response by selfrecurrent neural network(SRNN)[J].Eathquake Engineering & Structural Dynamic, 1998, 27.
[14]何玉敖,吴建军.线性结构振动的人工神经网络控制[A].第二届全国建筑结构振动会议论文集[C]北京:中国建筑工业出版社,1997
[15] Polycarpou M M, loannou P A. Learning and convergence analysis of neural - type structural network[J]. IEEETrails. on Neural Network. 1992, 3(1): 39 ~ 50.
[16] He Y A. Wu J J. Ail optimal tracking control of structural seismic response using self'- recurrentneural networks (SRNN) [A]. The proceeding of second world conference on structural control[C]. Japan, 1998.
[17] Yang J N, Danielians A, Liu S C. Aseismic hybrid control systems for building structures under strongearthquakes[J]. Intelligent Mat. Syst. Struct.. 1990, l(4):432 ~ 446.
[18] Kobori T, Koshika N, Yamada K, Ikeda Y. Seismic - response - controlled structuctre with active mass driver system. Part 1: Desing[J]. Earthquake Engrg. Struct. Dyn., I991. 20:133 ~ 149.
[19] Kobori T, Koshika N, K Yamada, Ikeda Y. Seismic- response - controlled structure with active mass driveer system,Part 2: Verfication[J]. Earthquake Engrg. Struct. Dyn., 1991, 20 : 151 ~ 166.
[20]刘文锋高层建筑在地震作用下的多态混合控制[D]天津大学博士学位论文,1995
[21] He Y A, Wu J J. Multi - state hybrid control of structures basing on neural network[A]. The proceeding of second worldconference on structural contro[C], Japan, 1998.
[22]李桂青,欧进萍非线性体系受平稳随机荷载的首次通过问题[D].地震工程与工程振动,1982,2.
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