多自由度非线性结构参数识别的鲁棒性研究  

Robust study on parametric identification of multi-degree-of-freedom nonlinear structure

作　　者：朱旭东[1] 吕西林[1] 

机构地区：[1]同济大学土木工程防灾国家重点实验室,上海200092

出　　处：《中南大学学报（自然科学版）》2013年第1期303-308,共6页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(90815029);国家自然科学基金中日国际合作项目(51021140006)

摘　　要：由于多自由度非线性结构参数识别是反问题,其解具有不确定性,为提高识别效率及识别结果的精度,基于序列二次规划法并通过数值试验分析研究影响参数识别鲁棒性能的各个因素。研究结果表明:噪声不影响识别效率但影响识别结果精度;基于时域信息构建优化目标函数时,时程长度影响识别效率和识别结果的精度,一般时程长度选取8倍结构基本周期时能取得较好效果;在描述非线性力学行为时,Bouc-Wen模型相比双线性模型适应性更强,具有更好的识别效果;非线性结构在激励强度较大情况下识别得到的参数值更具可靠性;对相关性较弱参数,可通过分步骤识别,减小参数识别数量,从而提高参数识别效率。As the parametric identification of multi-degree-of-freedom nonlinear structure is an inverse problem, and the solution may be of nonuniqueness. For improving the efficiency and accuracy of the identification result, numerical experiments based on sequential quadratic programming method were conducted to study the various factors affecting the robust performance. The results show that noise does not affect the efficiency of the identification algorithm but the accuracy of the identification results; since the objective function is constructed from the time-domain information, time-length affects the efficiency and accuracy of the algorithm, and generally can achieve good results when it is taken as 8 times of the basic period; compared to the bilinear model, Bouc-Wen model has better ability in describing the nonlinear mechanical behavior; to nonlinear structure, the identified parameter values are more reliable at larger excitation intensity; for reducing the number of parameter identification and enhancing the efficiency of parameter identification, weak correlation parameters can be identified step by step.

关 键 词：参数识别 鲁棒性 序列二次规划法 优化目标函数 BOUC-WEN模型 

分 类 号：TU311.3[建筑科学—结构工程] O224[理学—运筹学与控制论]