ANFIS技术实现磁流变阻尼器的逆向建模及其应用

INVERSE MODELLING OF MR DAMPER BASED ON ANFIS TECHNIQUE AND ITS APPLICATION

提出一种利用自适应神经模糊推理系统(ANFIS)技术有效解决磁流变(MR)阻尼器所固有的高度非线性动特性问题的方法。基于ANFIS技术建立了对于工程应用至关重要的MR阻尼器的逆向智能模型,成功地辨识出描述其阻尼力-输入电压关系的逆向动特性。在此基础上提出了一种基于最优控制的智能半主动控制策略。数值仿真结果表明了所提出方法的有效性和实用性,将其应用于工程结构振动控制,能够取得良好的效果。

An approach that can effectively solve the inherent highly nonlinear dynamics problem of magnetorheological (MR) damper is proposed by using adaptive neuro-fuzzy inference system (ANFIS) technique. The intelligent inver model of MR damper is established based on ANFIS technique, which can successfully identify the inverse dynamic characteristics of MR damper, portraying the relationship between the target control force and the command voltage. An intelligent semi-active control strategy is then proposed based on this inverse model and optimal control theory. Numerical simlations illustrate that the proposed methods are effective and applicable.