摘要
针对半主动变阻尼器建立了地震作用下多层建筑结构基于支持向量机(SVM)的半主动控制算法.首先,运用动力缩聚法建立多层建筑结构模型,利用LQR原理获得LQR控制器;然后,构造SVM模型,通过机器学习、离线训练使其兼作控制系统状态观测器和控制器.
Employing semi-active variable dampers,the support vector machine(SVM) based semi-active control algorithm is proposed in the present paper for seismic multistory building structures.Firstly,the LQR controller for the model of a multistory structure formulated using the dynamic dense method is obtained by use of the LQR control theory.Then,a SVM model,which is used as the control system observer and controller,is designed and trained to emulate the performance of the LQR controller.
引文
[1]Li Chunxiang,Liu Qing.Support Vector Machine Based Semi-active Control of Seismic Structures:A New Control Strategy[J].The Structural Design of Tall and Special Buildings(2009)DOI:10.1002/tal.557.
[2]Zhang J,Sato T.Experimental Verification of the Support Vector Regression Based Structural Identification Method by UsingShaking Table Test Data[J].Structural Control and Health Monitoring,2008(15):505-517.
[3]Dong Yinfeng,Li Yingmin,Lai Ming,et al.Nonlinear Structural Response Prediction Based on Support Vector Machines[J].Journal of Sound and Vibration,2008(3-5):886-897.
[4]Oh C K,Sohn H.Damage Diagnosis Under Environmental and Operational Variations Using Unsupervised Support VectorMachine[J].Journal of Sound and Vibration(2009)DOI:10.1016.
[5]孙清,史庆轩,张可,等.半主动变阻尼结构的振动台试验研究[J].建筑结构学报,2003(6):24-26.