Machine-learning-based damage identification methods with features derived from moving principal component analysis
Machine-learning-based damage identification methods with features derived from moving principal component analysis
复制标题
基于机器学习的损伤识别方法，其特征源自移动主成分分析
DOI：
10.1080/15376494.2019.1710308
复制
发表时间：
2020
影响因子：
2.8
通讯作者：
Jiang Zhenyu
中科院分区：
文献类型：
--
作者：
Zhang Ge;Tang Liqun;Liu Zejia;Zhou Licheng;Liu Yiping;Jiang Zhenyu
摘要为了提高工程结构的损伤识别性能，提出了基于移动主成分分析(MPCA)特征的基于机器学习的损伤识别方法。以前，机器学习算法通常直接使用结构响应作为输入。这些方法显示出较低的损伤识别能力，并且容易受到噪声的影响。本文采用主成分分析得到的结构响应的特征向量作为输入。应用几种传统的机器学习算法进行了验证。结果表明，与应变和频率相比，它们的特征向量作为机器学习算法的输入具有更好的损伤识别性能。
Abstract This paper aims to propose machine-learning-based damage identification methods with features derived from moving principal component analysis (MPCA) to improve the damage identification performance for engineering structures. Previously, machine learning algorithms have usually used structural responses as inputs directly. These methods show low damage identification capabilities and are susceptible to noise. In this paper, the eigenvectors of structural responses derived from MPCA are employed as inputs instead. Several traditional machine learning algorithms are applied for verification. The results demonstrate that as compared to strains and frequencies, their eigenvectors as inputs for machine learning algorithms render better performances for damage identification.