• Smart Structures and Systems
• /
• v.11 no.1
• /
• pp.1-17
• /
• 2013

This paper intended to investigate the feasibility of bridge health monitoring using a linear system parameter of a time series model identified from traffic-induced vibrations of bridges through a laboratory moving vehicle experiment on scaled model bridges. This study considered the system parameter of the bridge-vehicle interactive system rather than modal ones because signals obtained under a moving vehicle are not the responses of the bridge itself but those of the interactive system. To overcome the shortcomings of modal parameter-based bridge diagnosis using a time series model, this study considered coefficients of Autoregressive model (AR coefficients) as an early indicator of anomaly of bridges. This study also investigated sensitivity of AR coefficients in detecting anomaly of bridges. Observations demonstrated effectiveness of using AR coefficients as an early indicator for anomaly of bridges.

• Structural Engineering and Mechanics
• /
• v.81 no.5
• /
• pp.647-664
• /
• 2022

The powerful data mapping capability of computational deep learning methods has been recently explored in academic works to develop strategies for structural health monitoring through appropriate characterization of dynamic responses. In many cases, these studies concern laboratory prototypes and finite element models to validate the proposed methodologies. Therefore, the present work aims to investigate the capability of a deep learning algorithm called Sparse Autoencoder (SAE) specifically focused on detecting structural alterations in real-case studies. The idea is to characterize the dynamic responses via SAE models and, subsequently, to detect the onset of abnormal behavior through the Shewhart T control chart, calculated with SAE extracted features. The anomaly detection approach is exemplified using data from the Z24 bridge, a classical benchmark, and data from the continuous monitoring of the San Vittore bell-tower, Italy. In both cases, the influence of temperature is also evaluated. The proposed approach achieved good performance, detecting structural changes even under temperature variations.

• Structural Engineering and Mechanics
• /
• v.77 no.4
• /
• pp.495-508
• /
• 2021

This study devises a novel approach, namely quadruple 1D convolutional neural network, for detecting connection stiffness reduction in steel truss bridge structure using experimental and numerical modal data. The method is developed based on expertise in two domains: firstly, in Structural Health Monitoring, the mode shapes and its high-order derivatives, including second, third, and fourth derivatives, are accurate indicators in assessing damages. Secondly, in the Machine Learning literature, the deep convolutional neural networks are able to extract relevant features from input data, then perform classification tasks with high accuracy and reduced time complexity. The efficacy and effectiveness of the present method are supported through an extensive case study with the railway Nam O bridge. It delivers highly accurate results in assessing damage localization and damage severity for single as well as multiple damage scenarios. In addition, the robustness of this method is tested with the presence of white noise reflecting unavoidable uncertainties in signal processing and modeling in reality. The proposed approach is able to provide stable results with data corrupted by noise up to 10%.

• Smart Structures and Systems
• /
• v.6 no.3
• /
• pp.309-333
• /
• 2010

Civil infrastructure, in both its construction and maintenance, represents the largest societal investment in this country, outside of the health care industry. Despite being the lifeline of US commerce, civil infrastructure has scarcely benefited from the latest sensor technological advances. Our future should focus on harnessing these technologies to enhance the robustness, longevity and economic viability of this vast, societal investment, in light of inherent uncertainties and their exposure to service and even extreme loadings. One of the principal means of insuring the robustness and longevity of infrastructure is to strategically deploy smart sensors in them. Therefore, the objective is to develop novel, durable, smart sensors that are especially applicable to major infrastructure and the facilities to validate their reliability and long-term functionality. In some cases, this implies the development of new sensing elements themselves, while in other cases involves innovative packaging and use of existing sensor technologies. In either case, a parallel focus will be the integration and networking of these smart sensing elements for reliable data acquisition, transmission, and fusion, within a decision-making framework targeting efficient management and maintenance of infrastructure systems. In this paper, prudent and viable sensor and health monitoring technologies have been developed and used in several large structural systems. Discussion will also include several practical bridge health monitoring applications including their design, construction, and operation of the systems.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.6
• /
• pp.359-366
• /
• 2018

Social infrastructure facilities that have been under construction since the country's high-growth period are undergoing rapid aging, and safety assessments of large structures such as bridge tunnels, which can be directly linked to large-scale casualties in the event of an accident, are necessary. Wireless smart sensor networks that improve SHM(Structural Health Monitoring) based on existing wire sensors are difficult to construct economical and efficient system due to short signal reach. The LPWAN, Low Power Wide Area Network, is becoming popular with the Internet of Things and it is possible to construct economical and efficient SHM by applying it to structural health monitoring. This study examines the applicability of LoRa LPWAN to structural health monitoring and proposes a channel usage pre-planning based LoRa network operation method that can efficiently utilize bandwidth while resolving conflicts between channels caused by using license - exempt communication band.

• Smart Structures and Systems
• /
• v.24 no.5
• /
• pp.567-585
• /
• 2019

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.

• Smart Structures and Systems
• /
• v.11 no.5
• /
• pp.453-476
• /
• 2013

DuraMote is a remote sensing system developed for the "NIST TIP project: next generation SCADA for prevention and mitigation of water system infrastructure disaster". It is designed for supervisory control and data acquisition (SCADA) of ruptures in water pipes. Micro-electro mechanical (MEMS) accelerometers, which record the vibration of the pipe wall, are used detect the ruptures. However, the performance of Duramote cannot be verified directly on a water distribution system because it lacks an acceptable recordable level of ambient vibration. Instead, a long-span cable-stayed bridge is an ideal test-bed to validate the accuracy, the reliability, and the robustness of DuraMote because the bridge has an acceptable level of ambient vibration. The acceleration data recorded on the bridge were used to identify the modal properties of the structure and to verify the performance of DuraMote. During the test period, the bridge was subjected to heavy rain, wind, and a typhoon but the system demonstrates its robustness and durability.

• Structural Monitoring and Maintenance
• /
• v.9 no.2
• /
• pp.179-200
• /
• 2022

This paper proposes a data-driven methodology for online early damage identification under changing environmental conditions. The proposed method relies on two data analysis methods: feature-based method and hybrid principal component analysis (PCA) and kernel PCA to separate damage from environmental influences. First, spectral sub-band features, namely, spectral sub-band centroids (SSCs) and log spectral sub-band energies (LSSEs), are proposed as damage-sensitive features to extract damage information from measured structural responses. Second, hybrid modeling by integrating PCA and kernel PCA is performed on the spectral sub-band feature matrix for data normalization to extract both linear and nonlinear features for nonlinear procedure monitoring. After feature normalization, suppressing environmental effects, the control charts (Hotelling T² and SPE statistics) is implemented to novelty detection and distinguish damage in structures. The hybrid PCA-KPCA technique is compared to KPCA by applying support vector machine (SVM) to evaluate the effectiveness of its performance in detecting damage. The proposed method is verified through numerical and full-scale studies (a Bridge Health Monitoring (BHM) Benchmark Problem and a cable-stayed bridge in China). The results demonstrate that the proposed method can detect the structural damage accurately and reduce false alarms by suppressing the effects and interference of environmental variations.

• Steel and Composite Structures
• /
• v.29 no.4
• /
• pp.527-544
• /
• 2018

The paper presents the study on a change in modal parameters and structural stiffness of cable-stayed Fiberline Bridge made entirely of Glass Fiber Reinforced Polymer (GFRP) composite used for 20 years in the fjord area of Kolding, Denmark. Due to this specific location the bridge structure was subjected to natural aging in harsh environmental conditions. The flexural properties of the pultruded GFRP profiles acquired from the analyzed footbridge in 1997 and 2012 were determined through three-point bending tests. It was found that the Young's modulus increased by approximately 9%. Moreover, the influence of the temperature on the storage and loss modulus of GFRP material acquired from the Fiberline Bridge was studied by the dynamic mechanical analysis. The good thermal stability in potential real temperatures was found. The natural vibration frequencies and mode shapes of the bridge for its original state were evaluated through the application of the Finite Element (FE) method. The initial FE model was created using the real geometrical and material data obtained from both the design data and flexural test results performed in 1997 for the intact composite GFRP material. Full scale experimental investigations of the free-decay response under human jumping for the experimental state were carried out applying accelerometers. Seven natural frequencies, corresponding mode shapes and damping ratios were identified. The numerical and experimental results were compared. Based on the difference in the fundamental natural frequency it was again confirmed that the structural stiffness of the bridge increased by about 9% after 20 years of service life. Data collected from this study were used to validate the assumed FE model. It can be concluded that the updated FE model accurately reproduces the dynamic behavior of the bridge and can be used as a proper baseline model for the long-term monitoring to evaluate the overall structural response under service loads. The obtained results provided a relevant data for the structural health monitoring of all-GFRP bridge.

• Smart Structures and Systems
• /
• v.5 no.4
• /
• pp.345-355
• /
• 2009

This article describes the development of a fiber optic accelerometer based on Fiber Bragg Gratings (FBG). The accelerometer utilizes the stiffness of the optical fiber and a lumped mass in the design. Acceleration is measured by the FBG in response to the vibration of the fiber optic mass system. The wavelength shift of FBG is proportional to the change in acceleration, and the gauge factor pertains to the shift in wavelength as a function of acceleration. Low frequency version of the accelerometer was developed for applications in monitoring bridges. The accelerometer was first evaluated in laboratory settings and then employed in a demonstration project for condition assessment of a bridge. Laboratory experiments involved evaluation of the sensitivity and resolution of measurements under a series of low frequency low amplitude conditions. The main feature of this accelerometer is single channel multiplexing capability rendering the system highly practical for application in condition assessment of bridges. This feature of the accelerometer was evaluated by using the system during ambient vibration tests of a bridge. The Frequency Domain Decomposition method was employed to identify the mode shapes and natural frequencies of the bridge. Results were compared with the data acquired from the conventional accelerometers.