Damage Detection Of Bridge Structures Research Articles

Transfer learning for structure damage detection of bridges through dynamic distribution adaptation

In recent years, the rapid increase in the number of bridges not only brings convenience to people but also means that more bridges are at potential safety risks. How to quickly and accurately identify damage that occurs in bridges is a primary problem for society to solve. Machine learning, which can train a classifier for bridge damage detection from existing labeled data, has been widely applied to damage detection of bridge structures. However, the method can have limitations such as the difficulty of collecting sufficient damage data, the heavy workload of the data labeling task, and the failure of the classifier when the bridge structure changes, which limits the application of machine learning in structural damage detection. In order to achieve damage detection of bridges with different spans without target labeling, a dynamic distribution adaptation network (DDAN) containing a feature extraction module and a dynamic distribution adaptation (DDA) module is designed in this paper. DDAN uses the feature extraction module to extract features, and then the DDA module acquires the extracted features to dynamically adapt the probability distribution for calibrating the features in the source and target domains which makes the feature distributions in the source and target domains approximate. In order to verify the feasibility of this paper's method, DDAN is applied to the damage detection of simply supported box girder bridges with different spans through numerical simulation in this paper, where the damage features of a 32 m bridge (source domain) are transferred to a 24 m bridge (target domain), and damage localization and quantification of the target bridge is achieved without damage labels on the target bridge. The results show that DDAN possesses a better classification effect as well as faster convergence speed than the network without domain adaptation and traditional deep domain adaptation networks, and has important application prospects in damage detection of bridges with different spans.

Enhancing bridge damage assessment: Adaptive cell and deep learning approaches in time-series analysis

In recent years, the application of Deep Learning (DL) for damage detection in Structural Health Monitoring (SHM) using time-series data has garnered significant attention from the global scientific community. By incorporating numerous filters and units in their architecture, these models facilitate feature extraction making the processing of large time-series datasets in SHM more effective. However, optimizing of the number of filters and units is a challenge, often relying on scientists' experience or previous models without a systematic method for measurement or automatic selection. Therefore, this study proposes a novel framework to enhance the accuracy and efficiency of SHM for damage detection in bridge structures by using metaheuristic algorithms, Electric Eel Foraging Optimization (EEFO) algorithm, to optimize hyperparameters of DL model. This DL model combines the advantages of each traditional model. Specifically, 1D Convolutional Neural Network (1DCNN) is employed for features extraction, Gated Recurrent Units (GRU) for identifying long-term dependencies, and Residual Networks (ResNet) for avoiding vanishing gradient problem which often happens in DL model during training, referred to as 1DCNN-GRU-ResNet. The time-series dataset generated from Cua Rao bridge is used to demonstrate the effectiveness of the proposed method. 1DCNN-GRU-ResNet after optimization (1DCNN-GRU-ResNet-opt) achieves 91.6 %, significantly surpassing traditional 1DCNN (82.5 %), GRU (79.9 %), 1DCNN-GRU (85.7 %), and 1DCNN-GRU-ResNet (89.3 %) in the test set. The proposed 1DCNN-GRU-ResNet-opt approach demonstrates considerable potential in practical applications for SHM, offering high accuracy and efficiency.

Damage Detection in Bridge Structures through Compressed Sensing of Crowdsourced Smartphone Data

Traditional bridge health monitoring methods that necessitate sensor installation are not only costly but also time-consuming. In contrast, utilizing smartphone data collected from vehicles as they traverse bridges offers an efficient and cost-effective alternative. This paper introduces a cutting-edge damage detection framework for indirect monitoring of bridge structures, leveraging a substantial volume of acceleration data collected from smartphones in vehicles passing over the bridge. Our innovative approach addresses the challenge of collecting and transmitting high-frequency data while preserving smartphone battery life and data plans through the integration of compressed sensing (CS) into the crowdsensing-based monitoring framework. CS employs random sampling and signal recovery from a significantly reduced number of samples compared to the requirements of the Nyquist–Shannon sampling theorem. In the proposed framework, acceleration signals from vehicles are initially acquired using smartphone sensors, undergo compression, and are then transmitted for signal reconstruction. Subsequently, feature extraction and dimensionality reduction are performed using Mel-frequency cepstral coefficients and principal component analysis. Damage indexes are computed based on the dissimilarity between probability distribution functions utilizing the Wasserstein distance metric. The efficacy of the proposed methodology in bridge monitoring has been substantiated through the utilization of numerical models and a lab-scale bridge. Furthermore, the feasibility of implementing the framework in a real-world application has been investigated, leveraging the smartphone data from 102 vehicle trips on the Golden Gate Bridge. The results demonstrate that damage detection using the reconstructed signals obtained through compressed sensing achieves comparable performance to that obtained with the original data sampled at the Nyquist measurement sampling rate. However, it is observed that to retain severity information within the signals for accurate damage severity identification, the compression level should be limited to 20%. These findings affirm that compressed sensing significantly reduces the data collection requirements for crowdsensing-based monitoring applications, without compromising the accuracy of damage detection while preserving essential damage-sensitive information within the dataset.

Partial‐Model‐Based Damage Identification of Long‐Span Steel Truss Bridge Based on Stiffness Separation Method

Damage detection in bridge structures has always been challenging, particularly for long‐span bridges with complex structural forms. In this study, a partial‐model‐based damage detection method was proposed for the damage identification of long‐span steel truss bridges. The proposed method employs partial models to estimate the parameters using the stiffness separation method. This approach obviates the need to construct complete stiffness information for the structure. In contrast, it depends solely on the arrangement of the structural members and material information in the recognized area. This technique can effectively circumvent the construction of an overall structural model and reduce the complexity of damage identification in large structures. A full‐scale long‐span steel truss bridge in service was used to illustrate the feasibility of the proposed method. The locations of the three partial models were considered in the model analysis, and the parameter estimation efficiency of the Nelder–Mead simplex and quasi‐Newton algorithms were compared.

Damage detection of bridge structures under moving loads based on CEEMD and PSD sensitivity analysis

Damage detection of bridge structures under moving loads based on CEEMD and PSD sensitivity analysis

Vibration based damage detection of bridge structures

The task of identifying damage to the load-bearing beams of large-span bridge structures using vibration diagnostic methods has been implemented, taking into account experimental uncertainties associated with natural phenomena and technological processes. The methodology for localizing damage is based on the analysis of dynamic characteristics of the structure, such as natural frequencies and modes of vibration. The study presents research on a finite element model of a bridge structure using a method for determining a damage indicator based on normalizing the values of vibration modes with respect to the values of vibration area.

STRUCTURAL HEALTH MONITORING METHODS OF BRIDGESTRUCTURES: AREVIEWOFEXISTING METHODS WITH RECOMMENDATIONS

Bridges are a crucial part of the transport infrastructure and represent an important asset of a society. One of the crucial parts of that asset goes to monitoring and maintenance since the bridge damage could yield to severe consequences in human lives and material damage. Periodic inspection keeps these structures operational and increases bridge integrity. Different methods have been proposed by different researchers for bridge damage detection based on different theories and methodologies. Various review papers on bridge damage detection are published in the literature in the last few decades. In this paper, a concise review of literature on damage detection in bridge structures based on various methodologies is carried out. The purpose of this paper is to critically examine various methods that have been proposed for bridge damage identification along with some recommendations to improve these methods. The gaps, limitations, and superiority of the existing methods have been identified, and future applications which are important for bridge inspection are covered.

Application of couple sparse coding in smart damage detection of truss bridges

Damage detection in bridge structures plays a crucial role in the ‘in-time’ maintenance of such structures, which subsequently prevents further propagation of the damage, and likely collapse of the structure. Currently, the applications of machine learning algorithms are growing in the smart damage detection of structures. This work focuses on application of a new machine learning algorithm to identify the location and severity of damage in truss bridges. Frequency response functions are used as damage features, and are compressed using principal component analysis. Couple sparse coding is adopted as a classification method to learn the relationship between the bridge damage features and its damage states. Two truss bridges are used to test the proposed method and determine its accuracy in the detection of damage to truss bridges. It is found that the proposed method provides a reliable detection of damage location and severity in truss bridges.

Damage Detection of Bridge Structures Under Vehicle Loads Using Moving-Window Correlation Coefficient of Signals with Limited Sensors

Based on the moving-window correlation coefficient of signals, a damage detection method is proposed for bridge structures. The signals collected by two sensors during the vehicle crossing the bridge are intercepted as windowed pair time series, and the damage index is defined based on the correlation of them. The damage vector is composed of damage indices from the beginning to end according to the moving direction of the window, and the damage location can be determined by the peak information of all the damage vectors which are obtained by different sensor pairs. First, the damage detection method and corresponding detection steps are introduced. Then, the proposed method is validated by numerical simulation, and the influence of moving window length, moving step, the number of sensors, deviation of vehicle parameters and road-surface roughness on damage localization are discussed, respectively. Finally, the proposed method is validated by experiments using a two-axis vehicle and a steel–concrete composite beam. The results show that the proposed method can effectively identify the damage location. High-pass filtering of the raw data to remove trend items and wavelet noise reduction can significantly improve the accuracy of damage detection, and can accurately locate the damage in the presence of road-surface roughness. The damage detection result is not sensitive to vehicle parameter deviation, and the damage location can still be accurately identified when the vehicle weight or speed deviates 50% from the vehicle parameters in the reference data. In addition, the proposed method can make full use of the damage information between sensors, and can accurately identify the damage location with limited sensors. The number of sensors can be flexibly determined considering both accuracy and economy.

Damage detection of bridge structures under unknown seismic excitations using support vector machine based on transmissibility function and wavelet packet energy

Since it may be hard to obtain the exact external load in practice, damage identification of bridge structures using only structural responses under unknown seismic excitations is an important but challenging task. Since structural responses are determined by both structural properties and seismic excitation, it is necessary to remove the effects of external excitation and only retain the structural information for structural damage identification. In this paper, a data-driven approach using structural responses only is proposed for structural damage alarming and localization of bridge structures. The transmissibility functions (TF) of structural responses are used to eliminate the influence of unknown seismic excitations. Moreover, the inverse Fourier transform of TFs and wavelet packet transform are used to reduce the influence of frequency bands and to extract the damagesensitive feature, respectively. Based on Support vector machines (SVM), structural responses under ambient excitations are used for training SVM. Then, structural responses under unknown seismic excitations are also processed accordingly and used for damage alarming and localization by the trained SMV. The numerical simulation examples of beam-type bridge and a cablestayed bridge under unknown seismic excitations are studied to illustrate the performance of the proposed approach.

Damage Detection of Truss Structures by Reduction of Degrees of Freedom Using the Serep Method

Damage detection of bridge structures during their operating lifetime is essential. In this paper, two approaches, All Degrees of Freedom and Reduction of the Degrees of Freedom methods, are used to detect the damages in structures. The first method considers All Degrees of Freedom of the structure and the second method, Reduction of the Degrees of Freedom. Since the sensors are installed only on a few degrees of freedom, the responses are available for some of them. The Degrees of Freedom must be reduced and System Equivalent Reduction Expansion Process method is one of the most efficient ways to solve the problem. This research aimed to identify the damage of structures using the Modal Strain Energy method by reducing the structural degree of freedom. Two standard examples are used and the results compared to different damage cases to examine the efficiency of the mentioned method. The results illustrated the proper performance of the Reduction of the Degrees of Freedom method to identify the damage in truss structures. By increasing the number of modes, Reduction of the Degrees of Freedom method detects considerably more accurate the damaged elements, especially when the noise is considered. Also, based on the outcomes to identify damaged elements, it is possible to consider more modes instead of more sensors.

Detectability of Bridge-Structural Damage Based on Fiber-Optic Sensing through Deep-Convolutional Neural Networks

Improving the accuracy and efficiency of damage detection of bridge structures is a major challenge in engineering practice. This paper aims to address this issue by monitoring the continuous bridge deflection based on the fiber optic sensing technology and applying a deep-learning algorithm to perform structural damage detection. With a scaled-down bridge model, three categories of damage scenarios plus an intact state were simulated. A 13-layer supervised learning model based on the deep convolutional neural networks was proposed. After the training process of original continuous deflection under 10-fold cross-validation, the model accuracy can reach 96.9% for damage classification with the performance outperforming that of the other four methods (random forest = 81.6%, support vector machine = 79.9%, k-nearest neighbor = 77.7%, and decision tree = 74.8%). The proposed model also demonstrated its decent abilities in automatically extracting damage features and distinguishing damage from structurally symmetrical locations.

Damage detection in bridge structures under moving loads with phase trajectory change of multi-type vibration measurements

This paper presents a non-model based damage detection approach for bridge structures under moving loads based on the phase trajectory change of multi-type vibration measurements. A brief theoretical background on the vibration of a simply-supported bridge with a crack under moving load is described. The phase trajectories of multi-type dynamic responses are obtained and a damage index is defined as the separated distance between the trajectories of undamaged and damaged structures to indicate the damage location. Numerical studies on a simply-supported beam structure are conducted to investigate the sensitivity and robustness of the proposed approach to accurately identify the damage location. Experimental studies demonstrate that the proposed approach can be used to successfully identify the shear connection failure in a composite bridge model subjected to moving loads.

Information-theoretical noninvasive damage detection in bridge structures.

Damage detection of mechanical structures such as bridges is an important research problem in civil engineering. Using spatially distributed sensor time series data collected from a recent experiment on a local bridge in Upper State New York, we study noninvasive damage detection using information-theoretical methods. Several findings are in order. First, the time series data, which represent accelerations measured at the sensors, more closely follow Laplace distribution than normal distribution, allowing us to develop parameter estimators for various information-theoretic measures such as entropy and mutual information. Second, as damage is introduced by the removal of bolts of the first diaphragm connection, the interaction between spatially nearby sensors as measured by mutual information becomes weaker, suggesting that the bridge is "loosened." Finally, using a proposed optimal mutual information interaction procedure to prune away indirect interactions, we found that the primary direction of interaction or influence aligns with the traffic direction on the bridge even after damaging the bridge.

Output-only damage detection using vehicle-induced displacement response and mode shape curvature index

Most of the existing bridge superstructure damage detection methods are based on acceleration or strain response due to ambient excitation. This paper proposes a bridge damage detection procedure that utilizes vehicle-induced displacement response without requiring prior knowledge about the traffic excitation and road surface roughness. This study is partially motivated by the recent advances in convenient measurement of structural displacements enabled by video-based sensors. Vehicle–bridge interaction analysis shows that when subjected to moving vehicles, the bridge displacement response is dominated by the first-order mode component. This justifies the proposed damage detection method that only requires the first-order mode shape curvature. While conventionally the mode shapes are extracted based on operational modal analysis, the first-order mode shape is extracted by directly analyzing the power spectral density functions of measured bridge displacement responses under vehicle excitations. Numerical simulations are carried out to investigate the feasibility and performance of the proposed damage detection method using three damage scenarios including damage at single, double, and multiple locations, each involving several extents of damage defined by the reduction in element stiffness. The results reveal that all the damage cases can be successfully identified. Furthermore, the damage detection performance is evaluated for cases involving different classes of road surface roughness and less measurement points. The study demonstrates the potential of the proposed model-free and time-efficient method for damage detection of bridge structures. Copyright © 2016 John Wiley & Sons, Ltd.

A Damage Detection Algorithm Utilizing Dynamic Displacement of Bridge under Moving Vehicle

A damage detection method is proposed, which utilizes dynamic displacement of bridge structures under moving vehicle. The problem is first elaborated with closed-form solution of dynamic displacement, which is decomposed into quasi-static component and dynamic component. Dynamic curvature is defined as second derivative of the dynamic displacement for detecting damage location and estimating damage extent. Damage is modeled by local reduction of stiffness in this paper. Numerical study was conducted on a simply supported beam to verify the proposed method. Vehicle model is analyzed with Newmark’s method using Matlab to obtain the contact force acting on the bridge. Beam model is established in commercial finite element software ABAQUS. The effects of road surface roughness and vehicle-bridge interaction are both considered in the analysis. In order to identify damage location and extent, dynamic curvature was calculated with midspan displacement. Parametric study on measurement noise level, damage location, damage extent, and multiple damage cases is performed, and the analysis results show both reliability and efficacy of this method in damage detection of bridge structures. At last, conclusions are drawn for its application to bridges in engineering practice.

Damage detection in structures under traveling loads by Hilbert–Huang transform

Hilbert–Huang transform (HHT) is an innovative data-processing technique for analyzing nonstationary and nonlinear signals. A novel HHT-based method for damage detection of bridge structures under a traveling load is proposed. The technique uses a single point measurement and is able to identify the presence and the location of the damage along the beam. The measured data are processed by the HHT technique, and none a priori information is needed about the response of the undamaged structure. Damage location is revealed by direct inspection of the first instantaneous frequency, which presents a sharp crest in correspondence of the damaged section. The identification capabilities of the proposed technique are studied varying the damage locations, crack depths and velocity of the moving load. The effect of ambient noise is also taken into account. Theoretical as well as numerical results show the identification is rather accurate, results are not very sensitive to the crack depth and ambient noise, while they are sensibly affected by the damage location and by the speed of the moving load as well. Theoretical analysis identifies a characteristic load velocity interval, depending both on the first natural frequency of the bridge and the damage location, within which the HHT can be successfully applied.

The tap-scan method for damage detection of bridge structures

Damage detection plays a very important role to the maintenance of bridge structures. Traditional damage detection methods are usually based on structural dynamic properties, which are acquired from pre-installed sensors on the bridge. This is not only time-consuming and costly, but also suffers from poor sensitivity to damage if only natural frequencies and mode shapes are concerned in a noisy environment. Recently, the idea of using the dynamic responses of a passing vehicle shows a convenient and economical way for damage detection of bridge structures. Inspired by this new idea and the well-established tap test in the field of non-destructive testing, this paper proposes a new method for obtaining the damage information through the acceleration of a passing vehicle enhanced by a tapping device. Since no finger-print is required of the intact structure, this method can be easily implemented in practice. The logistics of this method is illustrated by a vehicle-bridge interaction model, along with the sensitivity analysis presented in detail. The validity of the method is proved by some numerical examples, and remarks are given concerning the potential implementation of the method as well as the directions for future research.

Damage Detection of Bridge Structures Using Modal Flexibility under Temperature Variations

Changes in the measured structural responses, such as deflections and modal properties, induced by damage could be significantly smaller than those by environmental effects such as temperature and temperature gradients. To make the structural health monitoring more reliable and applicable to real structures, it is highly desirable to develop a methodology to distinguish the changes due to the structural damage from those by the environmental variations. In this study, a novel method to extract the damage-induced deflection under temperature variations is presented using the outlier analysis on the correlation of deflection components obtained using the modal flexibility matrix. The main idea is that temperature change in a bridge would produce global increase or decrease in deflections over the whole bridge. On the other hand, structural damages may cause local variations in deflections near the damage locations. Hence, the correlation analysis between the deflection measurements may show high abnormality near the damage locations. The proposed procedure may be summarized: (1) identification of the modal flexibility matrix from acceleration measurements, (2) calculation of the positive-bending-Inspection-load deflection using the modal flexibility for each damage and temperature case, (3) construction of the outlier-threshold for the correlation of the intact deflection at different locations, and (4) damage detection using the outlier analysis on the correlation of the deflection for damage cases. To verify the applicability of the proposed method, a series of laboratory tests were carried out on a bridge model with a steel box-girder. Nineteen experiments were carried out for the first 2 days under daily temperature variations to construct the correlation data for the intact deflection, and 51 experiments were performed for two damage scenarios for the next 12 days. It has been found that the damage existence and location were detected successfully for a case with relatively small damage under the temperature variations.

Instantaneous damage detection of bridge structures and experimental verification

An extended Kalman filtering (EKF) method was developed and applied to instantaneously identify elemental stiffness values of a structure during damaging seismic events based on vibration measurement. This method is capable of dealing with nonlinear as well as linear structural responses. Identification of the structural elemental stiffness enables location as well as quantification of structural damage. The instantaneous stiffness values during an event can provide highly useful information for post-event capacity estimation. In this study, a large-scale shaking table test of a three-bent concrete bridge model was performed in order to verify the proposed damage detection method. The bridge model was shaken to different damage levels by a sequence of earthquake motions with increasing intensities. The elemental stiffness values of the structure were instantaneously identified in real time during the damaging earthquake excitations using the EKF method. The identified stiffness degradations and their locations agreed well with the structural damage observed by visual inspection and strain measurements. More importantly, the seismic response accelerations analytically simulated using the instantaneous stiffness values thus identified agreed well with the measured accelerations, demonstrating the accuracy of the identified stiffness. This study presents an experimental verification of a structural damage detection method using a realistic bridge model subjected to realistic seismic damage. Copyright © 2007 John Wiley & Sons, Ltd.