半主动TLCD对固定式海洋平台的离散神经网络滑模控制

TLCD semi-active control methodology for fixed offshore platform using discrete-time neural networks sliding mode law

主要研究了半主动调液柱型阻尼器(TLCD)对固定式海洋平台的离散神经网络滑模变结构控制方法。首先建立了平台结构-TLCD控制系统微分方程及其离散化状态空间表达,然后阐述了基于神经网络的滑模变结构控制的基本算法和控制策略,最后应用该神经网络滑模变结构控制策略对一个已建成的实际海洋平台结构的TLCD半主动控制问题进行了数值仿真分析。仿真分析的结果证明了该方法的有效性。

In this paper, a semi-actively tuned liquid column damper（TLCD） based on discrete-time neural networks sliding mode law is proposed to vibration control of fixed offshore platforms excited by earthquake. Firsdy, the numerical model of a fixed offshore plafform-TLCD system is given and its continuous state equation is set up and discretized. And then, the theory of neural networks sliding mode control （NNSMC） is simply discussed and the semi-active control strategy is established and implemented by NNSMC. Lastly, an actual platform, as the numerical simulated example, has been used to fully verify the effectiveness of this control method.