基于LS-SVM的光纤智能结构损伤诊断

针对目前结构损伤诊断方法的局限以及最小二乘支持向量机算法优点,提出采用最小二乘支持向量机来对光纤智能结构损伤位置识别进行研究,并在Matlab中编制了相应的支持向量机程序,建立了相应损伤诊断模型.以实例数据为学习样本和测试样本,讨论了基于最小二乘支持向量机的光纤智能结构损伤诊断可行性.试验研究结果表明,基于最小二乘支持向量机光纤智能结构损伤诊断识别方法具有较高的可靠性和精度且操作方便,是一种性能优良的智能识别方法,为智能结构实现损伤自诊断提供了更为先进的方法.

Application of least square-support vector machine to damage self-diagnosis of fiber smart structures

The self-diagnosis function is one of the main research contents of smart structures.And it is the foundation of other functions realization of smart structures.Aiming at the localization of present structural damage detection methods and by virtue of the least square-support vector machine(LS-SVM) algorithm,the LS-SVM used to detect damages in fiber smart structures is proposed for building damage diagnosis model based on a set of samples; and practical effectiveness of the theory of the LS-SVM for detecting damages is discussed.The experimental research results show that this algorithm is feasible and effective for detecting damages in smart structures.The LS-SVM provides the more advanced method for realizing the self-diagnosis function in fiber smart structures.