基于动态模糊神经网络的结构主动控制仿真分析
|
摘要
在模糊控制中,如何更加合理地生成控制规则,是其应用的一个重要问题。本文采用动态模糊神经网络(DFNN)算法,并借助于最优控制算法的样本数据,实现建筑结构振动控制中的模糊规则自动提取。首先,介绍了DFNN的结构和算法;其次,采用DFNN算法设计了二输入单输出及四输入单输出两种模糊控制器,对顶层设置AMD控制装置的五层钢框架模型结构进行模糊控制仿真分析。仿真结果表明,两种模糊控制器对顶层位移和加速度反应峰值的控制效果达到50%和30%以上,对地震输入和结构参数的变化均具有较好的鲁棒性;相比二输入模糊控制器,四输入模糊控制器的控制效果更好。本文研究为地震作用下建筑结构AMD模糊控制提供了新的思路和方法。
How to generate fuzzy rules for structural vibration control is a key issue.In this paper,a dynamic fuzzy neural network(DFNN) algorithm is adopted to extract fuzzy rules based on the example data obtained from the performance of the system under optimal control algorithm.First,the structure and algorithm of DFNN is introduced.Then,two fuzzy controllers are developed based on DFNN algorithm,one is two-input and single-output while the other is four-input and single-output.Numerical simulation is carried out for a five-storey frame model with AMD installed on the top floor.The simulation results show that both controllers are very effective in reducing the responses of the model structure under seismic excitation and the reduction of more than 50% and 30% in relative displacement and acceleration can be achieved respectively.Moreover,the robustness of the fuzzy controllers is demonstrated through the change of seismic input and structural parameters.The performance of the four-input controller is better than that of the two-input controller,which can provide a new idea and method for structural AMD fuzzy control.
How to generate fuzzy rules for structural vibration control is a key issue.In this paper,a dynamic fuzzy neural network(DFNN) algorithm is adopted to extract fuzzy rules based on the example data obtained from the performance of the system under optimal control algorithm.First,the structure and algorithm of DFNN is introduced.Then,two fuzzy controllers are developed based on DFNN algorithm,one is two-input and single-output while the other is four-input and single-output.Numerical simulation is carried out for a five-storey frame model with AMD installed on the top floor.The simulation results show that both controllers are very effective in reducing the responses of the model structure under seismic excitation and the reduction of more than 50% and 30% in relative displacement and acceleration can be achieved respectively.Moreover,the robustness of the fuzzy controllers is demonstrated through the change of seismic input and structural parameters.The performance of the four-input controller is better than that of the two-input controller,which can provide a new idea and method for structural AMD fuzzy control.
引文
[1]张微敬,欧进萍.智能控制算法及其在结构振动控制中的应用[J].世界地震工程,2002,18(2):32-36.
[2]Battaini M,Casciati F,Faravelli L.Fuzzy control of structural vibration:An active mass system driven by a fuzzy controller[J].Earthquake En-gng.Struct.Dyn,1998,27:1267-1276.
[3]张利芬,欧进萍.结构模糊控制规则优化生成的遗传算法[J].地震工程与工程振动,2001,21(4):47-50.
[4]Leng G,Prasad G,McGinnity TM.An on-line algorithm for creating self-organizing fuzzy neural networks[J].Neural Networks,2004,17(10):1477-1493.
[5]Er MJ,Wu S.A fast learning algorithm for parsimonious fuzzy neural systems[J].Fuzzy Sets and Systems,2002,126:337-351.
[6]Chen S,Cowan C F N,Grant P M.Orthogonal least squares learning algorithmfor radial basis function networks[J].IEEE Transactions on Neu-ral Networks,1991,2(2):302-309.
[7]张微敬,欧进萍.基于单片机模糊控制器的AMD主动控制试验研究[J].建筑结构学报,2006,27(1):37-39.
[2]Battaini M,Casciati F,Faravelli L.Fuzzy control of structural vibration:An active mass system driven by a fuzzy controller[J].Earthquake En-gng.Struct.Dyn,1998,27:1267-1276.
[3]张利芬,欧进萍.结构模糊控制规则优化生成的遗传算法[J].地震工程与工程振动,2001,21(4):47-50.
[4]Leng G,Prasad G,McGinnity TM.An on-line algorithm for creating self-organizing fuzzy neural networks[J].Neural Networks,2004,17(10):1477-1493.
[5]Er MJ,Wu S.A fast learning algorithm for parsimonious fuzzy neural systems[J].Fuzzy Sets and Systems,2002,126:337-351.
[6]Chen S,Cowan C F N,Grant P M.Orthogonal least squares learning algorithmfor radial basis function networks[J].IEEE Transactions on Neu-ral Networks,1991,2(2):302-309.
[7]张微敬,欧进萍.基于单片机模糊控制器的AMD主动控制试验研究[J].建筑结构学报,2006,27(1):37-39.
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