首页 | 本学科首页   官方微博 | 高级检索  
     

基于LS-SVM的压电智能结构损伤主动监测
引用本文:谢建宏,石立华,梁大开,邓海.基于LS-SVM的压电智能结构损伤主动监测[J].压电与声光,2007,29(3):350-353.
作者姓名:谢建宏  石立华  梁大开  邓海
作者单位:1. 江西财经大学,电子学院,江西,南昌,330013
2. 解放军理工大学,工程兵工程学院,江苏,南京,210007
3. 南京航空航天大学,智能材料与结构航空科技重点实验室,江苏,南京,210016
基金项目:国家自然科学基金;江西省教育厅科研项目
摘    要:基于被动监测技术的局限性,搭建了损伤主动监测系统,对监测信号进行了功率谱密度最大值(PSM)特征提取,并提出了一种基于最小二乘支持向量机(LS-SVM)的损伤检测方法。采用该方法,对压电智能复合材料层板进行了损伤定位的研究,并与改进的BP网络进行了对比,结果表明:在相同性能指标下,LS-SVM有比BP网络更高的损伤定位精度及更强的泛化能力。LS-SVM与主动监测技术的融合,为结构实现在线实时准确监测提供了一种新途径。

关 键 词:压电智能结构  主动监测技术  功率谱密度  最小二乘支持向量机
文章编号:1004-2474(2007)03-0350-04
修稿时间:2006-04-07

Active Damage Monitoring for Piezoelectric Smart Structures Based on LS-SVM Technology
XIE Jian-hong,SHI Li-hua,LIANG Da-kai,DENG Hai.Active Damage Monitoring for Piezoelectric Smart Structures Based on LS-SVM Technology[J].Piezoelectrics & Acoustooptics,2007,29(3):350-353.
Authors:XIE Jian-hong  SHI Li-hua  LIANG Da-kai  DENG Hai
Affiliation:1. School of Electronics, Jiangxi University of Finance and Economics, Nanchang 330013, China; 2. Engineering Institute of Engineering Corps, PLA University of Science and Technology, Nanjing 210007, China; 3. Aeronautic Science Key Laboratory for Smart Materials and Structures, NUAA, Nanjing 210016, China
Abstract:Due to the limitation of passive monitoring technology,an active damage monitoring system is set up.In this system,the characteristics of monitoring signals are extracted by the method of power spectrum density maximum(PSM),and least square support vector machine(LS-SVM) is proposed to detect damages.LS-SVM is applied to detect the damage locations for the piezoelectric smart composite laminated plates,and compared with the improved BP neural network.The results show that LS-SVM possesses the advantages such as the higher accuracy,better dissemination ability etc.under the same performance index as BP.The active monitoring technology combined with LS-SVM provides a new approach to carry out on-line,real-time,and accurate monitoring for structural damages.
Keywords:piezoelectric smart structures  active monitoring technology  power spectrum density  least square support vector machine
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号