Abstract
This paper investigates the time series representation methods and similarity measures for sensor data feature extraction and structural damage pattern recognition. Both model-based time series representation and dimensionality reduction methods are studied to compare the effectiveness of feature extraction for damage pattern recognition. The evaluation of feature extraction methods is performed by examining the separation of feature vectors among different damage patterns and the pattern recognition success rate. In addition, the impact of similarity measures on the pattern recognition success rate and the metrics for damage localization are also investigated. The test data used in this study are from the System Identification to Monitor Civil Engineering Structures (SIMCES) Z24 Bridge damage detection tests, a rigorous instrumentation campaign that recorded the dynamic performance of a concrete box-girder bridge under progressively increasing damage scenarios. A number of progressive damage test case datasets and damage test data with different damage modalities are used. The simulation results show that both time series representation methods and similarity measures have significant impact on the pattern recognition success rate.
Highlights
Time series is one of the most commonly used data formats in real world
To investigate the effectiveness of time series representation methods and similarity measures applied to structural damage pattern recognition, the Z24 Bridge test datasets are used as validation data in this paper [14]
This paper presents the research results of three feature extraction methods: autoregressive model, discrete Fourier transform, and discrete wavelet transform, for structural damage pattern recognition
Summary
Time series is one of the most commonly used data formats in real world. It is being generated in a tremendous speed from almost every application area. A number of representation methods and similarity measures have been proposed to extract features from time series data for indexing, classification, and clustering. For long time series data, model-based and dimensionality reduction methods are more effective. Similarity measure is important for both evaluating feature extraction methods and time series classification. This paper examines several time series representation methods and similarity measures for structural damage feature extraction and pattern recognition. The performance of representation methods and similarity measures are evaluated utilizing acceleration data collected from the Z24 Bridge as part of the System Identification to Monitor Civil Engineering Structures (SIMCES) project.
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
