中文摘要：

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。

英文摘要：

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.