Novelty detection for SHM using raw acceleration measurements

Abstract

Summary Structural health monitoring is a problem that can be addressed at many levels. One of the most promising approaches used in damage assessment problems is based on pattern recognition. The idea is to extract features from data that characterize only the normal condition and to use them as a template or reference. During structural monitoring, data are measured, and appropriate features are extracted as well as compared with the reference. Any significant deviations are considered as signal novelty or possible damage. Several studies present in the literature are based on the comparison of measured vibration data such as natural frequencies and vibration modes in undamaged and damaged states of the structure. This methodology has proven to be efficient; however, its application may not be the most adequate in cases where the engineer needs to know with certain imperativeness the condition of a given structure. This paper proposes a novelty detection approach where the concept of symbolic data analysis is used to manipulate raw vibration data (i.e., acceleration measurements). These quantities (transformed into symbolic data) are combined to three unsupervised classification techniques: hierarchy agglomerative, dynamic clouds and soft c‐means clustering. In order to attest the robustness of this approach, experimental tests are performed on a simply supported beam considering different damage scenarios. Moreover, this paper presents a study with tests conducted on a motorway bridge, in France, where thermal variation effects also play a major role. In summary, results obtained confirm the efficiency of the proposed methodology. Copyright © 2015 John Wiley & Sons, Ltd.

Unsupervised real‐time SHM technique based on novelty indexes

“…On the other hand, some authors chose to employ symbolic data analysis. An SDO can perform a great fusion of information present in massive series of classical dynamic data (raw signals), transforming them into a more compact, yet rich representation.…”

Bridge Damage Detection Based on Vibration Data: Past and New Developments

“…The most accurate number of clusters identified is then compared to the indices obtained from each of the evaluated partitions to define the most truthful number of clusters. Additional information on the dynamic cloud clustering algorithm and other novelty detection techniques is detailed in the study by Alves et al (2015b).…”

Mode shape-based damage detection in plate structure without baseline data

“…Several advantages and limitations of these methods were also pointed out. Many studies confirm that mode shapes and corresponding mode shape curvatures are highly sensitive to damage and can be used for detection and quantification of the damage. Maia et al in performed extensive numerical simulations on a beam structure to compare damage identification sensitivity within different methods, based on the changes of mode shape, mode shape slope, mode shape curvature and mode shape curvature square, respectively.…”

“…The researchers justified their approach stating that it is possible to make 3D deformation pattern scans of real objects with high accuracy; post‐processing of the obtained graphical images, the method permits a convenient access to the object by scanning from a distance; however, it is possible to acquire data that only form visible surfaces. Dincal et al in proposed a damage detection procedure for beam structures, employing Euler‐Bernoulli beam theory. This procedure is based on the assumption that internal stresses in a structure are invariant before and after the application of damage.…”

“…The algorithm was validated in an experiment using a cantilevered beam capturing the location, extent and severity of the damage with no significant errors. The same team of authors in attempted to evaluate their own damage identification mechanism by using field measurements – modal data from the Interstate 40 bridge, where four incremental damage sites were introduced via torch cuts in the web and flange of the girder of the bridge. The researchers used the modal flexibility matrix, which was used to approximate the transverse displacements of structure.…”