基于数据挖掘的结构模糊控制规则生成与仿真分析

结合智能控制与现代控制理论,在结构控制领域,提出了直接从已有主动控制算法的成功数据样本中提取模糊控制规则的思想和方法。以顶层设置AMD控制装置的五层钢框架模型结构为例,阐述了提取模糊控制规则的步骤,仿真结果证实了所设计的二输入单输出模糊控制器的有效性和鲁棒性。通过76层Benchmark风振模型的模糊控制仿真分析,进一步验证了这种充分利用主动控制算法获取模糊规则思想的有效性。研究成果使结构振动模糊控制器的设计具有一定的依据,为AMD模糊控制走向工程应用奠定了理论基础。

Generating Fuzzy Rules and Simulating for Fuzzy Control of Structural Vibration Based on Data Mining

A new idea and approach which combined the experience of modern control theory and the advantage of intelligent control was developed to generate fuzzy rules for structural vibration control by learning from examples. The procedure of extracting fuzzy rules was provided. Some fuzzy controllers were developed using two input variable and one output variable for a five-storey frame controlled by an active mass damper. The simulation results show good performances by these fuzzy controllers. Moreover, the study on the benchmark building regarding the vibration control of tall building under wind excitation using fuzzy controller was reported. The fuzzy controller was found to be significantly more effective. The proposed method is referential to the design of fuzzy controller and can provide a necessary foundation for the practical structural control.