Dissimilarity-vector spaces based on Dynamic Time Warpings of spectral/time-frequency information for structural health monitoring

This paper presents a powerful data representation, so far unexplored for data-based Structural Health Monitoring, relying on the dissimilarity pattern recognition paradigm and the proximity-learning, pro-viding highly discriminant dissimilarity-based vector spaces, -also called generalized dissimilarity ker-nels-, where any classifier can be trained for damage classification issues. Conventionally, these damage detection tasks involve a domain-dependent and, quite often, non-trivial preprocessing step by which is computed a feature set from each observation. A crucial consequence is that valuable struc-tural information could be lost in this feature extraction step, leading to models with poor performance. In particular, in this paper we introduce a novel type of dissimilarity-based vector spaces for structural health diagnosis, building up them on a direct pairwise comparison between spectral/time-frequency structural information via the Dynamic Time Warping distance, without a previous feature extraction step, for learning one-class classifiers and using only undamaged data during training. The very sound results, using two data sets widely referenced in the scientific literature, clearly show its potential to complement the state-of-art of pattern recognition algorithms that are used on data-based Structural Health Monitoring.(c) 2022 Elsevier Ltd. All rights reserved.

Automated summary

This paper presents a new data representation method using dissimilarity pattern recognition and proximity learning, which provides highly discriminant dissimilarity-based vector spaces for damage classification in Structural Health Monitoring. Compared with traditional methods, this method does not require complex preprocessing steps and directly compares spectral/time-frequency structural information, resulting in improved performance.