Unsupervised novelty detection-based structural damage localization using a density peaks-based fast clustering algorithm

被引:134
作者
Cha, Young-Jin [1 ]
Wang, Zilong [1 ]
机构
[1] Univ Manitoba, Dept Civil Engn, E1-430 EITC,15 Gillson St, Winnipeg, MB R3T 5V6, Canada
来源
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL | 2018年 / 17卷 / 02期
关键词
Unsupervised novelty detection; structural damage localization; abnormal data; density peaks; fast clustering;
D O I
10.1177/1475921717691260
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Within machine learning, several structural damage detection and localization methods based on clustering and novelty detection methods have been proposed in the recent years in order to monitor mechanical and civil structures. In order to train a machine learning model, an unsupervised mode is preferred because it only requires sufficient normal data from the intact states of a structure for training, and the testing abnormal data from various damage states are generally quite rare. With an unsupervised training mode, the capability of detecting structural damage mainly depends on the identification of abnormal data from the testing data. This identification process is termed unsupervised novelty detection. The premise of unsupervised novelty detection is that a large volume of a normal data set is available first to train a normal model that is established by machine learning algorithms. Then, the trained normal model can be used to identify abnormal data from future testing data. In this article, a new structural damage detection and localization method is proposed using a density peaks-based fast clustering algorithm. In order to realize damage detection, the original density peaks-based fast clustering algorithm is modified to an unsupervised machine learning method by adding training and testing processes. Furthermore, to improve the performance of the proposed method, the Gaussian kernel function of radius is introduced to calculate the local density of data points, and a new damage-sensitive feature using a continuous wavelet transform is also proposed. Damage-sensitive features are extracted from the measured data through sensors installed on a laboratory-scale steel structure. Extensive experimental studies are carried out under various structural damage scenarios in order to validate the performance of the proposed method. The proposed density peaks-based fast clustering method shows satisfactory performance with regard to damage localization under various damage scenarios as compared to a traditional approach.
引用
收藏
页码:313 / 324
页数:12
相关论文
共 25 条
[1]  
Alcover I.F, 2014, THESIS U SURREY GUIL
[2]  
[Anonymous], 2014, C P SOC EXPT MECH SE, DOI DOI 10.1007/978-3-319-04546-7_22
[3]  
Barthorpe RJ, 2010, Ph.D. thesis
[4]  
Benoudjit N., 2002, 10th European Symposium on Artificial Neural Networks. ESANN'2002. Proceedings, P425
[5]  
Cha YJ, 2016, P I MECH ENG F-J RAI, P1
[6]   Structural Damage Detection Using Modal Strain Energy and Hybrid Multiobjective Optimization [J].
Cha, Young-Jin ;
Buyukozturk, Oral .
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2015, 30 (05) :347-358
[7]   Structural damage detection by fuzzy clustering [J].
da Silva, Samuel ;
Dias Junior, Milton ;
Lopes Junior, Vicente ;
Brennan, Michael J. .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2008, 22 (07) :1636-1649
[8]   An experimental evaluation of novelty detection methods [J].
Ding, Xuemei ;
Li, Yuhua ;
Belatreche, Ammar ;
Maguire, Liam P. .
NEUROCOMPUTING, 2014, 135 :313-327
[9]  
Farrar C.R., 2012, Structural Health Monitoring: A Machine Learning Perspective, P161
[10]   Maximum-likelihood estimation of damage location in guided-wave structural health monitoring [J].
Flynn, Eric B. ;
Todd, Michael D. ;
Wilcox, Paul D. ;
Drinkwater, Bruce W. ;
Croxford, Anthony J. .
PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES, 2011, 467 (2133) :2575-2596