Article
Engineering, Multidisciplinary
Tadhg Buckley, Vikram Pakrashi, Bidisha Ghosh
Summary: A statistical damage-detection methodology is introduced to improve the accuracy of bridge structural damage monitoring by using a dynamic harmonic regression time-series model. Prediction intervals from this model are used as statistical control limits to judge the structural health status. The potential and effectiveness of this method have been demonstrated on strain data sampled at 1-minute intervals from a full-scale damaged pre-stressed concrete bridge.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Civil
Yail J. Kim
Summary: This paper presents the behavior of a timber bridge strengthened with lag bolts, carbon fiber reinforced polymer (CFRP) sheets, and hollow structural sections (HSS). The magnitude of the truck load dominates the degree of dispersion in girder deflections and alters the shape of probability density functions. The effectiveness of strengthening is apparent in reducing the exceedance probability and increasing reliability indices. The HSS option is more efficient at the system level, while CFRP is most efficient at the member level.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Mechanical
K. Maes, L. Van Meerbeeck, E. P. B. Reynders, G. Lombaert
Summary: This paper investigates the feasibility of structural health monitoring based on natural frequencies for a steel bowstring railway bridge in Leuven, Belgium. Data from an ongoing long-term monitoring campaign on the bridge, including acceleration measurements on the bridge deck and the arches, are used in the study. The research focuses on removing the effects of environmental conditions, such as temperature, which can impact the modal characteristics of the structure and lead to false-positive or false-negative damage detection. Through comparing standard linear regression and robust principal component analysis (PCA), the study aims to assess the success rate of these techniques in removing natural frequency variations resulting from changes in environmental conditions, considering both the actual retrofit and smaller structural modifications.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Materials Science, Multidisciplinary
Li Zhu, Ying Wang, Guangpan Zhou, Bing Han
Summary: This study presents the structural health monitoring system of an I-shaped steel-concrete composite girder bridge during construction and vehicle load tests. The measured results showed that strains in the concrete slab and steel beams stabilized after an initial rapid change, indicating that the composite girder was in an elastic working state under the vehicle load tests. The research provides guidance for the construction control and safety evaluation of similar bridges in the future.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2022)
Article
Engineering, Civil
Numa J. Bertola, Guillaume Henriques, Eugen Bruhwiler
Summary: The examination of existing civil structures must be differentiated from designing new structures. To have sustainable and circular asset management, the behavior of these existing structures must be better understood to avoid unnecessary maintenance and replacements. Monitoring data collected through bridge load testing, structural health monitoring, and non-destructive tests may provide useful information that could significantly influence their structural-safety evaluations.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2023)
Article
Chemistry, Multidisciplinary
Dimitrios G. Dimogianopoulos, Dionysios E. Mouzakis
Summary: The framework utilizes sensing elements incorporated into one component to monitor the condition of joints between composite components, with contactless recording of structural response to vibratory input. By introducing external loading, changes to the sensing element induce voltage for signal detection, allowing for the identification of failing joints without dedicated equipment.
APPLIED SCIENCES-BASEL
(2021)
Review
Construction & Building Technology
Donghui Xu, Xiang Xu, Michael C. Forde, Antonio Caballero
Summary: In recent years, there has been an increasing installation of Structural Health Monitoring (SHM) systems on bridges worldwide, providing crucial data for bridge assessment and maintenance. Machine Learning (ML) has gained popularity in SHM studies as it can detect damages and perform condition assessment on bridge structures caused by material deterioration. This article summarizes and discusses various ML applications in bridge SHM, providing detailed critiques of each application type, and presents recommendations for future research to fill current gaps.
CONSTRUCTION AND BUILDING MATERIALS
(2023)
Article
Construction & Building Technology
Yixian Li, Limin Sun, Wei Zhang, Satish Nagarajaiah
Summary: The study introduces a novel bridge damage identification algorithm based on equivalent damage load and principal component analysis, which provides a robust indicator for damage detection. Experimental results demonstrate the applicability and reliability of the proposed damage indicator under various damage scenarios and loading conditions.
STRUCTURAL CONTROL & HEALTH MONITORING
(2021)
Article
Chemistry, Multidisciplinary
Xin Duan, Xi Chu, Weizhu Zhu, Zhixiang Zhou, Rui Luo, Junhao Meng
Summary: A method for structural full-field displacement monitoring and damage identification under natural texture conditions is proposed in this study. The feature points of the structure are extracted using the image scale-invariant feature transform, and a calculation theory for the structure's full-field displacement vector is established based on the analysis of the feature points' relative position change. The validation results show that the proposed method exhibits good performance in damage identification.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Lingyu Zhou, Lifan Zou, Lei Zhao, Yahui Yuan, Akim D. Mahunon, Yongzhi Gong
Summary: The study investigated the evolution of mechanical properties of steel rebars in the China Railway Track System Type II (CRTS II) ballastless track-bridge structural system subjected to repeated train loads. Experimental results showed that the strain amplitude of the steel bar changes proportionally to the fatigue stress amplitude. The mechanical properties of the rebar enhanced under the first million fatigue loading cycles and gradually degraded from the three millionth cycle to the end of the test. The finite element simulation provided a good agreement with the experimental data, validating the proposed calculation method.
APPLIED SCIENCES-BASEL
(2021)
Review
Construction & Building Technology
Zhiguo He, Wentao Li, Hadi Salehi, Hao Zhang, Haiyi Zhou, Pengcheng Jiao
Summary: Integrated structural health monitoring ensures the functionality and operation of bridges through mechanism analysis, monitoring technology, and data analytics. This review discusses the current process and future trends of bridge monitoring, focusing on cutting-edge SHM technologies, data transmission and analytics methods, and prediction and early-warning models.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Engineering, Geological
Wen Xie, Yangyang Bao, Jing Wang, Qing Lyu, Limin Sun
Summary: Shear links are effective in reducing seismic damage and improving the resilience of tall RC bridge bents. They decrease the maximum curvature and reinforced strain, and enhance the stiffness of the bridge bents. Both experimental and numerical analyses confirm the positive effects of shear links in controlling seismic damage and improving the seismic resilience.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2023)
Review
Construction & Building Technology
Siti Shahirah Saidin, Adiza Jamadin, Sakhiah Abdul Kudus, Norliyati Mohd Amin, Muhamad Azhan Anuar
Summary: This paper introduces a bridge health monitoring system based on dynamic characteristics for assessing the health state of bridge structures. It discusses advanced concepts and applications of bridge safety evaluation methods, and comprehensively evaluates different vibration techniques.
INTERNATIONAL JOURNAL OF CONCRETE STRUCTURES AND MATERIALS
(2022)
Article
Optics
Jordan Curt, Matteo Capaldo, Francois Hild, Stephane Roux
Summary: This paper presents the advantages of using Digital Image Correlation (DIC) in the field of structural health monitoring and proposes a specific DIC technique. By training, a reduced kinematic basis and amplitude distribution can be determined, and non-iterative processing is achieved using filtering and extractors.
OPTICS AND LASERS IN ENGINEERING
(2022)
Article
Chemistry, Multidisciplinary
Xiaofei Li, Qinghang Meng, Mengpu Wei, Heming Sun, Tian Zhang, Rongrong Su
Summary: The number of bridges has increased, leading to a decrease in structural safety due to longer service time. However, research on safety management and identification of water bridge substructure damage is limited. This paper proposes a method combining deep learning and point cloud algorithm to detect concrete cracks accurately, and a BIM-based integrated management system for underwater bridge structures.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Civil
Zhen Sun, Xiao-Wei Ye
Summary: This paper proposes an approach to estimate the fatigue life of modular expansion joints under stochastic traffic load, and validates it using expansion joints in a cable-stayed bridge. The study finds that vehicle velocities, horizontal impact component, surface irregularities, and damping ratios of the expansion joints have an impact on the fatigue life.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Civil
Zhen Sun, Joao Santos, Elsa Caetano
Summary: This study proposes a method using images and support vector machine to classify trains with different numbers of carriages. The method accurately predicts different train types and achieves higher accuracy and shorter computation time compared to other machine learning algorithms.
JOURNAL OF BRIDGE ENGINEERING
(2022)
Article
Construction & Building Technology
Zhen Sun, Joao Santos, Elsa Caetano
Summary: This paper proposes a machine-learning-based method to predict fatigue damage in long-span suspension bridges using monitored parameters of temperature, wind, train, and roadway loads. The results show that the method achieves high accuracy and provides valuable information for maintenance work.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Engineering, Civil
Kang Yang, Youliang Ding, Hanwei Zhao, Fangfang Geng, Zhen Sun
Summary: This paper proposes a damage identification methodology based on the bridge influence line (IL) under a moving vehicle, which includes data pre-processing, IL extraction, and damage detection. The effectiveness of this approach is verified through field tests on a real girder bridge.
BALTIC JOURNAL OF ROAD AND BRIDGE ENGINEERING
(2022)
Article
Engineering, Multidisciplinary
Xiaoming Lei, Dionysius M. Siringoringo, Zhen Sun, Yozo Fujino
Summary: This article investigates an approach for estimating bridge displacement responses under multiple loads using a residual autoencoder model. The proposed approach showed a high accuracy of over 95% and outperformed other models in accuracy and efficiency. Wind load was found to be the most influential factor.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Engineering, Mechanical
Zhen Sun, Dionysius M. Siringoringo, Shi-zhi Chen, Jun Lu
Summary: Long-span cable-supported bridges are susceptible to significant deformations due to temperature, wind, and vehicle loads, which can result in malfunction or failure of important components. This study proposes a condition assessment approach using girder end displacement measurements, incorporating data preprocessing, feature characterization, datasets preparation and splitting, and anomaly detection. The approach employs a physics-based correlation between temperature and displacement for noise detection, calculates hourly cumulative displacement as the feature, and uses the isolation forest algorithm for anomaly detection. The proposed approach successfully detects viscous damper malfunction and a specific holiday period, demonstrating its potential for predictive and preventive maintenance of bridges.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Engineering, Civil
Qiang-Ming Zhong, Shi-Zhi Chen, Zhen Sun, Lu-Chao Tian
Summary: This study proposes an applicable fully automatic OMA method by comparing clustering algorithms, and investigates its performance through numerical analysis and measured data from an actual bridge. The results demonstrate that this method functions well in the tested scenarios and has potential for wide application in actual engineering.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Xiao-Wei Ye, Zhen Sun, Jun Lu
Summary: This paper proposes a data-driven approach based on machine learning algorithms to predict the vibration amplitudes of long-span cable-stayed bridge girders and towers for early warning. By using monitoring data and predicted results, the proposed approach can assist bridge operators in managing and maintaining bridges to avoid damage and accidents caused by excessive vibrations.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Zhen Sun, Xiao-Wei Ye, Jun Lu
Summary: This paper develops a data-driven approach to predict the amplitude of stay cable vibration in strong winds. The model uses an ensemble learning model and considers wind speed, wind direction, turbulence intensity, and deck acceleration as input variables. The deck acceleration, which takes into account the deck-cable interaction and vehicle effects, significantly improves the accuracy of the prediction. The approach is validated using data from structural health monitoring of a cable-stayed bridge during three typhoon events.
STRUCTURE AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Engineering, Civil
Zhen Sun, Joao Santos, Elsa Caetano, Catarina Oliveira
Summary: This paper develops an approach to interpreting cumulative displacement in long-span suspension bridges, considering multiple loads. The study reveals that trainload is the most influential parameter in cumulative displacement, followed by roadway traffic. The findings can guide the maintenance of relevant bridge components to prevent premature damage.
JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING
(2023)
Article
Engineering, Mechanical
Patricia Vanova, Zhen Sun, Odin-Eliott Odinson, Zhiyu Jiang
Summary: Structural health monitoring is crucial for maintaining and extending the lifespan of bridges under complex loading conditions and damage scenarios. This study applies vibration-based methods to monitor the structural health of a Warren-type truss bridge. By obtaining natural frequencies and modal shapes through modal identification, and using a calibrated numerical model, damage scenarios are simulated to assess the dynamic responses of the bridge. The analysis shows that damaged members exhibit significant changes in accelerations, particularly in locations near their supports.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Engineering, Mechanical
Zhen Sun, Elsa Caetano, Sergio Pereira, Carlos Moutinho
Summary: This paper proposes a crack detection method for concrete bridges using a binary classification algorithm and the histogram of oriented gradient (HOG) feature. The method involves collecting images with and without cracks, calculating the HOG feature as input variables, and detecting cracks with a binary classification algorithm. The SVM model and Bayesian optimization are used for crack detection and hyperparameter selection, respectively. The method is verified with existing datasets and shows higher accuracy and computation efficiency compared to other methods.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Engineering, Multidisciplinary
Xiaoming Lei, Dionysius M. Siringoringo, You Dong, Zhen Sun
Summary: This study develops an interpretable ensemble learning model called eXtreme Gradient Boosting (XGBoost) to predict the critical displacements of a cable-stayed bridge's girder and pylon using monitoring data. The SHapley Additive exPlanations (SHAP) method is employed to assess the importance of input variables in predicting structural displacements. The performance of the ensemble learning model is compared with other machine learning and conventional methods, demonstrating an average accuracy with R2 of 84.13% for all five displacement predictions. The findings enhance our understanding of bridge displacement and facilitate effective management and maintenance of cable-stayed bridges.
Article
Engineering, Mechanical
Zhen Sun, Mengjin Sun, Dionysius M. Siringoringo, You Dong, Xiaoming Lei
Summary: A hierarchical convolutional neural network (HCNN) model was developed to predict bearing displacement in cable-supported bridges using comprehensive loads as predictors. The model achieved an accuracy of over 95.6% and outperformed traditional CNN models and other models in terms of accuracy and efficiency. The study also found that traffic loads played an important role in predicting displacement, and the proposed approach could facilitate predictive maintenance in long-span bridges.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Proceedings Paper
Engineering, Civil
Zhen Sun, Elsa Caetano, Joao Santos
Summary: This study proposes an adaptive multi-category train schedule validation approach based on bridge monitoring data to address fatigue issues in long-span cable-supported bridges. By establishing a database and calculating fatigue damage, the number of different types of trains in a typical daily schedule can be obtained and checked.
EUROPEAN WORKSHOP ON STRUCTURAL HEALTH MONITORING (EWSHM 2022), VOL 1
(2023)