Abstract
This work presents a structural health monitoring (SHM) approach for the detection and classification of structural changes. The proposed strategy is based on t-distributed stochastic neighbor embedding (t-SNE), a nonlinear procedure that is able to represent the local structure of high-dimensional data in a low-dimensional space. The steps of the detection and classification procedure are: (i) the data collected are scaled using mean-centered group scaling (MCGS); (ii) then principal component analysis (PCA) is applied to reduce the dimensionality of the data set; (iii) t-SNE is applied to represent the scaled and reduced data as points in a plane defining as many clusters as different structural states; and (iv) the current structure to be diagnosed will be associated with a cluster or structural state based on three strategies: (a) the smallest point-centroid distance; (b) majority voting; and (c) the sum of the inverse distances. The combination of PCA and t-SNE improves the quality of the clusters related to the structural states. The method is evaluated using experimental data from an aluminum plate with four piezoelectric transducers (PZTs). Results are illustrated in frequency domain, and they manifest the high classification accuracy and the strong performance of this method.
Highlights
Structural health monitoring (SHM) is a crucial process for engineering structures because it checks the correct behavior of the structure and determines whether it needs some type of maintenance
A structural health monitoring (SHM) strategy for detection and classification of structural changes based on a two-step data integration (type E unfolding [15] and the so-called mean-centered group scaling (MCGS)), data transformation using principal component analysis (PCA), and a two-step data reduction combining PCA and t-distributed stochastic neighbor embedding (t-stochastic neighbor embedding (SNE)) has been proposed
The first structural state corresponds to the healthy state of the structure, that is, the square aluminum plate with no damage, noted as D0; the second, third, and fourth structural states correspond to the plate with an added mass at the positions indicated in Figures 3 and 5, noted as D1, D2, and D3, respectively
Summary
Structural health monitoring (SHM) is a crucial process for engineering structures because it checks the correct behavior of the structure and determines whether it needs some type of maintenance. The healthy state of the structure has to remain between the specified limits or threshold, but these limits may change due to the aging of the structure and its use, or due to the environmental and operational conditions (EOC). In SHM systems, detection and classification of structural changes are essential in order to know the current state of the structure for security and to reduce costs of inspection and maintenance. If damage is detected and classified precisely at the time it occurs, some action may be taken before a human and/or economic disaster occurs, reducing the probability of accidents and the maintenance costs. With the goal of obtaining information about the state of the structure, data are collected by a sensor network, which is placed along the structure.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
