Abstract

Dealing with complex engineering problems characterized by Big Data, particularly in structural engineering, has recently received considerable attention due to its high societal importance. Data-driven structural health monitoring (SHM) methods aim at assessing the structural state and detecting any adverse change caused by damage, so as to guarantee structural safety and serviceability. These methods rely on statistical pattern recognition, which provides opportunities to implement a long-term SHM strategy by processing measured vibration data. However, the successful implementation of the data-driven SHM strategies when Big Data are to be processed is still a challenging issue, since the procedures of feature extraction and/or feature classification may end up being time-consuming and complex. To enhance the current damage detection procedures, in this work we propose an unsupervised learning method based on time series analysis, deep learning and the Mahalanobis distance metric for feature extraction, dimensionality reduction and classification. The main novelty of this strategy is the simultaneous dealing with the significant issue of Big Data analytics for damage detection, and distinguishing damage states from the undamaged one in an unsupervised learning manner. Large-scale datasets relevant to a cable-stayed bridge have been handled to validate the effectiveness of the proposed data-driven approach. Results have shown that the approach is highly successful in detecting early damage, even when Big Data are to be processed.

Highlights

  • Structural health monitoring (SHM) is a necessity for the today society, to preserve valuable and important civil structures and guarantee their health and integrity in order to avoid human and economic losses [1, 2]

  • The central core of all these methods relies upon statistical pattern recognition and consists of feature extraction and feature classification

  • Departing from the previously mentioned cited works, the main objective of this paper is to propose an unsupervised learning method for early damage detection via time series analysis for feature extraction through an AutoRegressive Moving Average (ARMA) model, a deep autoencoder neural network for dimensionality reduction, and the Mahalanobis distance metric for feature classification

Read more

Summary

Introduction

Structural health monitoring (SHM) is a necessity for the today society, to preserve valuable and important civil structures and guarantee their health and integrity in order to avoid human and economic losses [1, 2]. Due to recent advances in sensing and data acquisition systems, the processing of raw measured data by the SHM system is not a major challenge. On this basis, data-driven methods have been increasingly received attention among civil engineers and researchers for monitoring civil structures [3]. The central core of all these methods relies upon statistical pattern recognition and consists of feature extraction and feature classification The former step is a signal processing strategy, aiming at extracting meaningful information (called here damage-sensitive features) from raw measured data (e.g. acceleration time histories), while the latter one is a machine learning algorithm for analyzing and classifying the extracted features for early damage detection, localization and. Proc. 2020, 1, Firstpage-Lastpage; doi: FOR PEER REVIEW www.mdpi.com/journal/engproc

Objectives
Methods
Conclusion
Full Text
Paper version not known

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