Deep learning for data anomaly detection and data compression of a long‐span suspension bridge

Abstract

As intelligent sensing and sensor network systems have made progress and low-cost online structural health monitoring has become possible and widely implemented, large quantities of highly heterogeneous data can be acquired during the monitoring. This has resulted in exceeding the capacity of traditional data analytics techniques, especially in monitoring large-scale or critical civil structures. In particular, data storage has become a big challenge, hence, resulting in the emergence of data compression and reconstruction as a new area in structural health monitoring (SHM) of large infrastructure systems. SHM data generally include anomalies that can disturb structural analysis and assessment. The fundamental reasons for the abnormality of data are extremely complex. Therefore, reconstruction of the abnormal data is generally difficult and poses serious challenges to achieve high-accuracy after data has been compressed. Considering these significant challenges, in this paper, a novel deeplearning-enabled data compression and reconstruction framework is proposed that can be divided into two phases: (a) a one-dimensional Convolutional Neural Network (CNN) that extracts features directly from the input signals is designed to detect abnormal data with validated high accuracy; (b) a new SHM data compression and reconstruction method based on Autoencoder structure is further developed, which can recover the data with high-accuracy under such a low compression ratio. To validate the proposed approach, acceleration data from the SHM system of a long-span bridge in China are employed. In the abnormal data detection phase, the results show that the proposed method can detect anomaly with high accuracy. Subsequently, smaller reconstruction errors can be achieved even by using only 10% compression ratio for the normal data.

Noncontact cable force estimation with unmanned aerial vehicle and computer vision

“…Long-span bridges and high-rise buildings are critical infrastructures in modern society. Structural health monitoring with © 2020 Computer-Aided Civil and Infrastructure Engineering intelligent sensors and deep-learning technique is an effective method for ensuring the safety of civil infrastructures (Bao, Tang, Li, & Zhang, 2018;Ni, Zhang, & Noori, 2020;Oh, Kim, Kim, Park, & Adeli, 2017;Perez-Ramirez et al, 2019;Rafiei & Adeli, 2017). For long-span bridges, inclined cables and vertical hangers are essential components for supporting the bridge, therefore tension forces of them need to be measured accurately.…”

Machine learning and image processing approaches for estimating concrete surface roughness using basic cameras

“…For SHM, Rafiei and Adeli (2017b) used machine learning for the global health monitoring of high‐rise buildings and large structures with the implementation of the restricted Boltzmann machine and neural dynamic classification algorithm. Rafiei and Adeli (2018b) proposed unsupervised deep Boltzmann machine, among other techniques, to extract features from the frequency domain of the recorded signals for condition assessment; Ni, Zhang, and Noori (2019) proposed one‐dimensional CNN to detect abnormality in data collected from sensors; a combination between CNN and transfer learning is proposed by Azimi and Pekcan (2019) for SHM of structures based on conventional and compressed data collected from sensors; CNN was also utilized to categorize the damages of 2‐span bridge tested under shake table excitations based on measured acceleration only (Khodabandehlou, Pekcan, & Fadali, 2019); Sajedi and Liang (2020) used machine learning algorithm for vibration‐based SHM technique and performed semantic damage segmentation in a grid environment framework applicable for large‐scale SHM; other SHM applications can be found in Azimi, Eslamlou, and Pekcan (2020).…”

Cable force estimation of a long‐span cable‐stayed bridge with microwave interferometric radar

“…With a large spanning capacity and beautiful shape, the cable‐stayed bridge has occupied a dominant position in the construction of the long‐span bridges. Since cables are one of the most critical structural components for ensuring the overall structural integrity and safety of cable‐stayed bridges, accurate estimation of the cable force is of great importance for both the internal force distribution and the structural safety of the overall bridge structure (Ni, Zhang, & Chen, 2019; Ni, Zhang, & Noori, 2019; Sun, Nagayama, Nishio, & Fujino, 2018; Svensson, 2013; Yoon, Shin, & Spencer, 2018). In particular, the portable and rapid cable force measurement plays an extremely vital role in the evaluation of initial damage and the formulation of recovery plans for ensuring the security of the bridge.…”