结构健康监测中基于多重优化策略的传感器布置方法  

Multiple optimization strategies based sensor placement method for structural health monitoring

作　　者：伊廷华[1,2] 李宏男[1] 顾明[2] 

机构地区：[1]大连理工大学建设工程学部,辽宁大连116023 [2]同济大学土木工程防灾国家重点实验室,上海200092

出　　处：《建筑结构学报》2011年第12期217-223,共7页Journal of Building Structures

基　　金：国家自然科学基金委创新研究群体基金项目(51121005);国家自然科学基金项目(51178083);教育部新世纪优秀人才支持计划项目(NCET-10-0287);辽宁省自然科学基金项目(201102030)

摘　　要：如何在满足测试要求的前提下确定所需传感器的数目并优化其布设位置,已成为结构健康监测中亟待解决的问题。提出一种基于多重优化策略的传感器分步布设方法,首先以模态向量矩阵列主元正交三角分解得到传感器的初始布设位置;然后以模态置信度矩阵的最大非对角元为目标函数,采用逐步累积法,逐步增加可降低此初始布置模态置信度矩阵非对角元的传感器测点,并考虑非对角元均值的变化幅度,确定所需传感器的数量;最后通过基于二重结构编码的广义遗传算法优化传感器的布设位置。以600 m高的广州新电视塔为例,分析了传感器优化布置方案,发现对于刚度有突变的结构(如电视塔的塔身和天线),应对两者分开考虑传感器的布设。How to determine the quantity of the sensors and the optimal sensor placement to satisfy the testing requirements is a primary problem to be solved in the structural health monitoring.A new step-by-step sensor placement method based on the multiple optimization strategies was proposed.The initial sensor placement was firstly obtained by the QR-factorization.Then the maximum off-diagonal element of the modal assurance criterion（MAC） matrix was taken as the target function.The freedoms of the structure by the forward sequential sensor placement algorithm were gradually added to reduce the off-diagonal element of the MAC.Considering the change extent of the off-diagonal element＇s mean value,the quantity of the sensors could be determined.Finally,the plan of optimal sensor placement could be obtained by the dual-structure codes-based generalized genetic algorithm.In the end,the analysis of the optimal sensor placement for the 600 m Guangzhou New TV Tower（GNTVT） was performed.The results show that,for the structures with stiffness mutation（like the main tower and antennary mast of GNTVT）,the sensor placement had better to be considered for each part separately.

关 键 词：传感器优化布置 模态置信度矩阵 逐步累积法 广义遗传算法 

分 类 号：TU973.23[建筑科学—结构工程] O329[理学—一般力学与力学基础]