Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Download Full-text

A Data-Driven Approach to Structural Health Monitoring of Bridge Structures Based on the Discrete Model and FFT-Deep Learning

Journal of Vibration Engineering & Technologies ◽

10.1007/s42417-021-00343-5 ◽

2021 ◽

Author(s):

Thanh Q. Nguyen

Keyword(s):

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

Discrete Model ◽

Data Driven ◽

Structural Health ◽

Bridge Structures ◽

Data Driven Approach

Download Full-text

Computer vision and deep learning–based data anomaly detection method for structural health monitoring

Structural Health Monitoring ◽

10.1177/1475921718757405 ◽

2018 ◽

Vol 18 (2) ◽

pp. 401-421 ◽

Cited By ~ 57

Author(s):

Yuequan Bao ◽

Zhiyi Tang ◽

Hui Li ◽

Yufeng Zhang

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

Deep Neural Networks ◽

Detection Method ◽

Monitoring Systems ◽

Structural Health ◽

Health Monitoring Systems ◽

Incorrect Data

The widespread application of sophisticated structural health monitoring systems in civil infrastructures produces a large volume of data. As a result, the analysis and mining of structural health monitoring data have become hot research topics in the field of civil engineering. However, the harsh environment of civil structures causes the data measured by structural health monitoring systems to be contaminated by multiple anomalies, which seriously affect the data analysis results. This is one of the main barriers to automatic real-time warning, because it is difficult to distinguish the anomalies caused by structural damage from those related to incorrect data. Existing methods for data cleansing mainly focus on noise filtering, whereas the detection of incorrect data requires expertise and is very time-consuming. Inspired by the real-world manual inspection process, this article proposes a computer vision and deep learning–based data anomaly detection method. In particular, the framework of the proposed method includes two steps: data conversion by data visualization, and the construction and training of deep neural networks for anomaly classification. This process imitates human biological vision and logical thinking. In the data visualization step, the time series signals are transformed into image vectors that are plotted piecewise in grayscale images. In the second step, a training dataset consisting of randomly selected and manually labeled image vectors is input into a deep neural network or a cluster of deep neural networks, which are trained via techniques termed stacked autoencoders and greedy layer-wise training. The trained deep neural networks can be used to detect potential anomalies in large amounts of unchecked structural health monitoring data. To illustrate the training procedure and validate the performance of the proposed method, acceleration data from the structural health monitoring system of a real long-span bridge in China are employed. The results show that the multi-pattern anomalies of the data can be automatically detected with high accuracy.

Download Full-text

Data-Driven Structural Health Monitoring Using Feature Fusion and Hybrid Deep Learning

IEEE Transactions on Automation Science and Engineering ◽

10.1109/tase.2020.3034401 ◽

2020 ◽

pp. 1-17 ◽

Cited By ~ 1

Author(s):

Hung V. Dang ◽

Hoa Tran-Ngoc ◽

Tung V. Nguyen ◽

T. Bui-Tien ◽

Guido De Roeck ◽

...

Keyword(s):

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

Feature Fusion ◽

Data Driven ◽

Structural Health

Download Full-text

A combined finite element and hierarchical Deep learning approach for structural health monitoring: Test on a pin-joint composite truss structure

Mechanical Systems and Signal Processing ◽

10.1016/j.ymssp.2021.107735 ◽

2021 ◽

Vol 157 ◽

pp. 107735

Author(s):

Panagiotis Seventekidis ◽

Dimitrios Giagopoulos

Keyword(s):

Finite Element ◽

Deep Learning ◽

Structural Health Monitoring ◽

Health Monitoring ◽

Truss Structure ◽

Learning Approach ◽

Structural Health ◽

Monitoring Test

Download Full-text

Review of piezoelectric impedance based structural health monitoring: Physics-based and data-driven methods

Advances in Structural Engineering ◽

10.1177/13694332211038444 ◽

2021 ◽

pp. 136943322110384

Author(s):

Xingyu Fan ◽

Jun Li ◽

Hong Hao

Keyword(s):

Structural Health Monitoring ◽

Health Monitoring ◽

Structural Damage ◽

Low Frequency ◽

Data Driven ◽

Mode Shapes ◽

Monitoring Methods ◽

Destructive Testing ◽

Electromechanical Impedance ◽

Structural Health

Vibration based structural health monitoring methods are usually dependent on the first several orders of modal information, such as natural frequencies, mode shapes and the related derived features. These information are usually in a low frequency range. These global vibration characteristics may not be sufficiently sensitive to minor structural damage. The alternative non-destructive testing method using piezoelectric transducers, called as electromechanical impedance (EMI) technique, has been developed for more than two decades. Numerous studies on the EMI based structural health monitoring have been carried out based on representing impedance signatures in frequency domain by statistical indicators, which can be used for damage detection. On the other hand, damage quantification and localization remain a great challenge for EMI based methods. Physics-based EMI methods have been developed for quantifying the structural damage, by using the impedance responses and an accurate numerical model. This article provides a comprehensive review of the exciting researches and sorts out these approaches into two categories: data-driven based and physics-based EMI techniques. The merits and limitations of these methods are discussed. In addition, practical issues and research gaps for EMI based structural health monitoring methods are summarized.

Download Full-text