Bridge Damage Research Articles

Hybrid vehicle scanning techniques for detection of damaged hangers in tied-arch railway bridges

Regular monitoring of the hanger system is essential for preserving structural integrity in tied-arch bridges. This proactive monitoring enables preventive maintenance and early detection of hanger damage. To confront this issue, we propose a novel scanning method for assessing the impact of damaged hangers on the dynamic behaviour of single-span tied-arch railway bridges. Using each hanger as a positional reference, this method employs an instrumented vehicle as a mobile scanner to indirectly acquire vibration data from the traversed bridge deck. The hybrid approach integrates vehicle-bridge interaction (VBI) dynamics, vehicle scanning method (VSM), and moving windowed Fourier transform (mw-FT) technique to generate time–frequency spectrograms from the collected signals. In this representation, the time axis indicates the duration of the inspection vehicle traversing the bridge deck. By analysing frequency shifts within the spectrogram, we can identify damaged hangers through observed variations in frequency content over time. Numerical studies demonstrate the efficacy of the proposed hybrid vehicle scanning technique in detecting potential hanger damage in tied-arch railway bridges.

Forensic Analysis on Damage of a Cable-Stayed Bridge without Backstays Using BIM Information

Serious cracks were found in the pylon of a cable-stayed bridge without backstays. Based on forensic damage investigation, this paper uses the finite element (FE) method incorporating Building Information Modeling (BIM) to analyze the causes of cracking. The BIM model is established based on the survey of design, construction, and service information of the bridge. Then, FE analysis is conducted using BIM information. Finally, the causes of cracking in different regions of the pylon are explained in detail. The results show that the FE simulation agrees well with the inspected distribution of cracks, and the causes of cracks are closely related to the pylon construction process. The main cause of the cracks is the shrinkage difference between concrete segments of different ages. The anchorage effect of stayed cables also causes inclined cracks perpendicular to the cable direction. The combination of temperature load and concrete shrinkage results in cracks at the root of the pylon, and the reduction in cable forces exacerbates the cracking.

Implementation of explanatory texts output for bridge damage in a bridge inspection web system

Bridge photographs contain significant technical information, such as damaged structural parts and types of damage, yet interpreting these details is not always straightforward. Despite the advancements in image analysis for bridge inspection, there remains a significant gap in converting these images into comprehensible explanatory texts that can be readily used by less experienced engineers and administrative staff for effective maintenance decision-making. In this study, we developed a model that generates explanatory texts from bridge images based on a deep learning model, and we also developed a web system that can be utilized during bridge inspections. The proposed method enables the provision of user-friendly, text-based explanations of bridge damage within images, allowing relatively inexperienced engineers and administrative staff without extensive technical expertise to understand the representation of bridge damage in text form. Additionally, we have developed a system that continually trains and improves its performance by accumulating data as users interact with it. This paper describes the image captioning technique for generating explanatory texts and the structure of the web system.

A novel cross-domain identification method for bridge damage based on recurrence plot and convolutional neural networks

A novel cross-domain identification method for bridge damage based on recurrence plot and convolutional neural networks

Structural damage, clogging, collapsing: Analysis of the bridge damage at the rivers Ahr, Inde and Vicht caused by the flood of 2021

AbstractDuring the flood event in 2021 within Western Europe, many bridges were severely damaged, particularly in North Rhine‐Westphalia and Rhineland‐Palatinate in Germany. Within this study, a statistical analysis of the damages caused to bridges by the flood event was carried out. First, locations and damages of bridges along the rivers Inde, Vicht and Ahr were mapped. Based on these data, statistical correlations among the damage patterns were analyzed. Approximately 25 bridges along both rivers Inde and Vicht were damaged, while over 80 bridges along the Ahr were damaged. Notably, bridges located near residential areas suffered more severe damage than those in rural areas. In addition, the presence of debris played a significant role in damaging bridges. Although the bridge design did not emerge as the crucial factor, the bridge height could be determined as a contributing factor influencing the extent of damage along all three rivers. Also, the extent of damage increased as soon as overtopping of bridges occurred. Based on these findings, recommendations for the reconstruction of the numerous destroyed bridges could be identified which agree with existing literature. Additionally, recommendations regarding the estimation of 100‐year design floods and the implementation of clogging into flood hazard maps were derived.

A Frequency Identification Approach for Damaged Heavy-Haul Railway Bridge with Bogie Accelerations

Bridge structural health monitoring (BSHM) is extensively employed to assess whether bridge damage exceeds maintenance limits and helps maintenance decision-making. Frequency identification is an essential part of BSHM, which utilizes the first-order modal frequency as an evaluation indicator of bridge health status. This paper proposes a method for bridge damage identification based on extracting the first-order modal frequency of the bridge from dynamic responses of vehicle bogies. Firstly, the feasibility of extracting bridge modal frequency from bogie accelerations is theoretically deduced via a vehicle–bridge interaction model. The result indicates that the bogie accelerations encompass three frequency components, namely vehicle driving frequency, vehicle pitching frequency and bridge first-order modal frequency. Then, a multi-domain conjoint analysis method incorporating the time domain, frequency domain and time–frequency domain is proposed to extract the first-order frequency of damaged bridge from bogie accelerations. By defining a damage sensitivity index of the sliding window, the time-domain sensitive boundaries of bogie acceleration to bridge damage are pinpointed. Leveraging prior knowledge of the bridge modal frequency range, the frequency-domain sensitive boundaries bogie acceleration to bridge frequency are determined. On this basis, the sensitive region of bogie acceleration to bridge frequency can be precisely localized in the Hilbert Huang transform spectrum, ultimately identifying bridge frequency through searching local maximum instantaneous energy points within this region. Finally, comprehensive experiments, considering different vehicle speeds and track spectra scenarios, are carried out to investigate the effectiveness and robustness of the proposed method. The results affirm the performance of the method to accurately identify the first-order modal frequency of the damaged bridge, further underscoring the promising prospect of on-board BSHM.

Application of variational mode decomposition in vibration-based bridge damage detection

Bridges are critical infrastructure that require continuous structural health monitoring to ensure safety. Vibration-based methods use changes in dynamic response for damage detection. In this study, variational mode decomposition (VMD), a signal analysis technique, was applied to detect damage in a three-span beam bridge model subjected to moving loads. A finite-element model was developed to represent the bridge–vehicle interaction and damage was simulated by reducing the flexural stiffness of the bridge. Sensors placed on each span recorded the vibrations during vehicle passage. VMD was used to decompose the signals for analysis of damage indications. Different damage levels (30–50% stiffness reduction) and locations (each span) were evaluated. The vehicle speed was also varied to assess its effect. Damage was identified as peaks in the instantaneous energy diagrams of decomposed signals, correctly indicating the axle locations. Detection was improved with sensors nearer the damage and lower vehicle speed. The results demonstrate the ability of VMD to detect and locate damage without a baseline, indicating its potential as a non-baseline vibration-based damage detection method for bridges.

Bridge Damage Detection with Support Vector Machine in Accelerometer-Based Wireless Sensor Network

Abstract Purpose This paper proposes an in-network vibration data processing using Wireless Sensor Network (WSN) leveraging Machine Learning (ML) for damage detection and localization. The study also presents the ML algorithms comparison that is suitable to be deployed in WSN and implemented the proposed cluster-based WSN topology on the bridge simulation test. Methods The bridge vibration data was acquired using accelerometer-based wireless sensor nodes. The data collected are transformed using Fast Fourier Transform (FFT) to obtain fundamental frequencies and their corresponding amplitudes. The machine learning method i.e., Support Vector Machine (SVM) with linear and Radial Basis Function (RBF) kernel was used to analyze the vibration data collected from the WSN. In-network data processing and cluster-based WSN topology is implemented and the programmable wireless sensor nodes is utilized in this study. Results The experiments were conducted using real programmable wireless sensor nodes and developed our test bed bridge which makes this work different from the previous studies. The classification and predicting results shows 97%, 96%, 97%, and 96% for accuracy, precision, recall rate, and f1-score, respectively. Conclusion Machine learning methods can potentially be combined with the vibration WSN for bridge damage detection and localization.

Acoustic emission technology-based waveguide localization method for damaged internal tendons of in-service post-tensioned hollow slab bridges

Prestressing tendons are crucial load-bearing elements in post-tensioned hollow slab bridges. Damage to these tendons significantly reduces the safety, functionality, and longevity of the bridge. Regular monitoring of prestressing tendons is essential for bridge operation. Acoustic emission technology, known for its high accuracy and sensitivity to minor vibrations, is a key technique for monitoring bridge cables. This study proposes a novel dual-sensor acoustic emission localization method for detecting tendon damage in post-tensioned hollow slab bridges, utilizing waveguide technology. The effectiveness of this method is confirmed through hammering tests that simulate acoustic emission damage on operational hollow slab bridges. The proposed method, requiring only two sensors, offers a cost-effective alternative for monitoring the entire span of post-tensioned hollow slab bridges, so that effectively reduces the cost of bridge health monitoring and is easy to be promoted in actual engineering projects.

Smart Bridge Damage Assessment through Integrated Multi-Sensor Fusion Vehicle Monitoring

Abstract. This study explores the efficacy of vehicle-assisted monitoring for bridge damage assessment, emphasizing the integration of diverse sensor data sources. A novel method utilizing a deep neural network is proposed, enabling the fusion of fixed sensors on bridges and onboard vehicle sensors for damage assessment. The network offers scalability, robustness, and implementability, accommodating various measurement types while handling noise and dynamic loading conditions. The main novel aspect of our work is its ability to extract damage-sensitive features without signal preprocessing for future bridge health monitoring systems. Through numerical evaluations, considering realistic operational conditions, the proposed method demonstrates the capability to detect subtle damage under varying traffic conditions. Findings underscore the importance of integrating vehicle and bridge sensor data for reliable damage assessment, recommending strategies for optimal monitoring implementation by road authorities and bridge owners.

Theoretical and Experimental Investigations of Identifying Bridge Damage Using Instantaneous Amplitude Squared Extracted from Vibration Responses of a Two-Axle Passing Vehicle

Identifying bridge damage using a movable test vehicle is highly regarded for its mobility, cost-effectiveness, and broad monitoring coverage. Previous studies have shown that the residual contact-point (CP) response between connected vehicles is free of the impact of vehicle self-vibrations and road roughness, making it particularly suitable for the indirect extraction of bridge modal properties. However, most experimental campaigns regarding contact-point (CP) responses focus on a single-axle testing vehicle within a non-moving state. This study aims to theoretically and experimentally identify bridge damage using the instantaneous amplitude squared (IAS) extracted from the residual CP response of a two-axle passing vehicle. First, the closed-form solution of the residual CP acceleration was derived for a two-axle vehicle interacting with a simply supported beam. The IAS index was constructed from the driving frequency of the residual CP acceleration. Then, numerical investigations using finite element simulation were conducted to validate using the IAS index for indirect bridge damage identification. The application scope of the approach under various vehicle speeds and road roughness grades was examined. Finally, a laboratory vehicle–bridge interaction system was tested to validate the approach. Numerical studies demonstrated that bridge damage could be directly determined by observing the IAS abnormalities, which were baseline-free. The IAS from the residual CP response outperformed the IAS from CP responses in identifying bridge damage. However, it was better to use the IAS when the vehicle speed was no greater than 2 m/s and the grade of the road surface roughness was not high. Laboratory tests showed that it was possible to identify bridge damage using the IAS extracted from the residual CP acceleration under perfect road surfaces. However, it fell short under rough road surfaces. Hence, further experiments are required to fully examine the capacity of the IAS for bridge damage identification in practical applications.

Deep learning-based bridge damage cause estimation from multiple images using visual question answering

This paper presents a framework for estimating the cause of damage to bridge members by combining Structure from Motion (SfM) and Visual Question Answering (VQA) techniques. A VQA model was developed that uses bridge images for dataset creation and outputs the damage or member name and its existence based on the images and questions. In the developed model, the correct answer rate for questions requiring the member or damage name were 67.4 and 68.9%, respectively. The correct answer rate for questions requiring a yes/no answer was 99.1%. Based on the developed model, a damage cause estimation method was proposed. In the proposed method, the damage causes are narrowed down by inputting new questions to the VQA model, which are determined based on the surrounding images obtained via SfM and the results of the VQA model. Subsequently, the proposed method was then applied to an actual bridge and shown to be capable of determining damage and estimating its cause. The proposed method could be used to prevent damage causes from being overlooked, and practitioners could determine inspection focus areas, which could contribute to the improvement of maintenance techniques. In the future, it is expected to contribute to infrastructure diagnosis automation.

Cross-domain damage identification of bridge based on generative adversarial and deep adaptation networks

Model-driven bridge damage identification based on video measurement frequently encounters challenges due to low data quality, which leads to significant discrepancy between numerical model and actual bridge, exacerbating the cross-domain problem. To address this issue, the generative adversarial network (GAN) and Deep Adaptation Network (DAN) are introduced in this paper. The principles and utilizations of the two networks are introduced, while GAN is used to generate a large number of high-quality artificial samples to enhance the learning, and DAN is used to extract generic damage features to cross the source and target domains. A damage experiment of a steel truss model bridge is conducted to validate the proposed method, and the damage identification results of the proposed method and the traditional method are compared. The identification results illustrate that the proposed method can generate a substantial number of artificial samples only using a limited number of real target samples. These artificial samples facilitate the learning of cross-domain damage features, which ultimately contributes to achieving higher accuracy in damage identification.

Train-induced vibration response reconstruction for bridge damage detection with a deep learning methodology

Sensor malfunctions in bridge structural health monitoring system (BSHMS) could cause the missing of measured data, reducing the accuracy of damage detection. It is of great significance to reconstruct the data of faulty sensors with measured data of well-functioning sensors for bridge structural state assessment. In this paper, a train-induced vibration response reconstruction approach for bridge damage detection is proposed. An enhanced deep densely connected neural network (ED-DCNN) introducing a multi-head self-attention mechanism and a skip connection is designed to reconstruct the missing bridge responses, aiming to improve the vibration correlation between the faulty sensors and good sensors and benefit the learning of temporal and spatial features of responses. Then to further validate the accuracy and reliability of the ED-DCNN, an alternate down-sampling residual network (AD-ResNet) is built to identify bridge damage with the complete responses, including the reconstructed ones and the measured, which extracts the structural damage features at different scales utilizing different types of residual blocks in an alternating manner. The efficiency and robustness of the two networks are comprehensively studied using the collected acceleration data from a heavy-haul railway bridge, considering different noise levels. The results demonstrate that under various conditions, the reconstructed responses match the real responses well in time domain, with a low RMSE below 0.4% and a high correlation coefficient of 0.9744, which indicates that the incorporation of a multi-head self-attention module effectively improves the construction of correlations between responses. Additionally, the natural frequencies of bridge are accurately identified from the reconstructed responses. In terms of bridge damage detection, taking both the measured and reconstructed responses as inputs, the identification accuracy obviously improves by 33.57% compared to cases without the reconstructed responses, further emphasizing an excellent reconstruction capability of the ED-DCNN.

A novel MO-YOLOv4 for segmentation of multi-class bridge damages

Most studies of multi-class damage segmentation overlook two prominent and critical challenges: the substantial variations in damage scale and the susceptibility of network training to background interferences. As a consequence, achieving the desired performance in multi-class damage segmentation becomes a difficult task. To tackle these challenges, a novel multi-class damage segmentation method, MO-YOLOv4, is proposed based on the widely used YOLOv4 structure. MO-YOLOv4 incorporates the Multi-Scale Attention (MSA) module to greatly enhance the feature extraction ability for multi-class damages, and employs the Oriented Bounding Box (OBB)-based segmentation strategy for effectively reducing the influence of background interferences during the network training phase. The effectiveness of the MSA module and OBB-based segmentation strategy is validated through verification and ablation experiments. In the comparative study, the Mean Precision rate (MP), Mean Recall rate (MR), Mean F1-score (MF) and Mean Intersection over Union rate (MIoU) of the proposed MO-YOLOv4 reach up to 82.49%, 72.73%, 77.04% and 64.28%, respectively, indicating the superior level of segmentation performance offered by MO-YOLOv4 in comparison to the mainstream semantic segmentation methods for multi-class damages.

A novel attached-spring model for damage quantification and degradation evaluation of short/mid-span bridges

Short/mid-span bridges are the most commonly used infrastructure in highways, railways, and other transportation projects. With service time increasing, local damage and performance degradation of short/mid-span bridges are inevitable. Therefore, the assessment of the bridge condition is essential to ensure its safe operation. However, the existing methods mostly assume the damage region of the bridge as a uniform reduction in stiffness, which is not consistent with the actual bridge. Consequently, those methods can hardly achieve the evaluation of the damage. To address this issue, this paper proposes a novel attached-spring model for damage quantification and degradation evaluation of short/mid-span bridges. By assuming the damage region as a spring, an attached-spring model is proposed to describe the nonuniform local damage of the bridge. Then, the deflection influence line is used to identify the stiffness and position of the attached-spring, which achieves the damage detection and evaluation. This approach provides a general model to describe various bridge damage and evaluate the effect of the damage. Numerical simulation and experimental tests are used to verify the feasibility and accuracy of the proposed method. By comparing the results identified from the moving load test and those measured from the static test, the performance of the method is assessed.

A fast survey report about bridge damages by the 2024 Noto Peninsula Earthquake

The 2024 Noto Peninsula Earthquake was a significant seismic event that caused extensive damage across the region, characterized by a strong shake, subsequent tsunami, fires, liquefaction, and landslides. An emergency survey was conducted by our team from January 6 to January 8, 2024, focusing primarily on the impact of the earthquake on road bridges. This preliminary report includes ground motion records from the most affected areas and their response spectra, providing insights into the earthquake's intensity and characteristics. Among the key findings, substantial damage was reported to the long-span bridges connecting Noto Island to the mainland, specifically the Noto Island Ohashi Bridge and the Naka-Noto Agriculture Bridge (Twin Bridge Noto). These bridges are crucial as they serve as the sole access points to Noto Island. Additionally, the survey recorded damage to several other structures, including the Okogawa Bridges, Ouchigata Bridge, and a collapsed old wooden bridge.

Quasi-distributed optical fiber sensing for the coupled vibration analysis of high-speed train-bridge coupled system under earthquakes

Due to the extensive construction of high-speed rail lines passing through seismically active areas, the possibility of a sudden earthquake occurring during train operation is very high. Additionally, the earthquake will intensify the dynamic response of trains and bridges, causing serious bridge damage. In this work, the dynamic response behavior of the bridge structures in the coupled train-bridge system under the earthquake is investigated based on the 4-table shaking table system. Shaking table experiments are also conducted on a high-speed railroad model of simple-supported girder bridge at a scale of 1/10 with the simulated layers of China Railway Track System type II (CRTS II) ballastless track slabs. The strain responses of various components, including rails, track plates, base plates, and beams, were measured on the bridge using quasi-distributed fiber optic gratings, both with and without seismic actions. Additionally, the seismic isolation characteristics of the fasteners and the CA mortar layer were investigated. The dynamic performance of the coupled train-bridge system under earthquakes was studied in both the time and frequency domains.

Quantitative detection of typical bridge surface damages based on global attention mechanism and YOLOv7 network

Surface damages of reinforced concrete and steel bridges, for example, crack and corrosion, are usually regarded as indicators of internal structural defects, hence can be used to assess the structural health condition. Quantitative segmentation of these surface damages via computer vision is important yet challenging due to the limited accuracy of traditional semantic segmentation methods. To overcome this challenge, this study proposes a modified semantic segmentation method that can distinguish multiple surface damages, based on you only look once version 7 (YOLOv7) and global attention mechanism (GAM), namely, YOLOv7-SEG-GAM. Initially, the extended efficient layer aggregation network in the backbone network of YOLOv7 was substituted with GAM, followed by the integration of a segmentation head utilizing the three-scale feature map, thus establishing a segmentation network. Subsequently, graphical examples depicting five types of reinforced concrete and steel bridge surface damages, that is, concrete cracks, steel corrosion, exposed rebar, spalling, and efflorescence, are gathered and meticulously labeled to create a semantic segmentation dataset tailored for training the network. Afterwards, a comparative study is undertaken to analyze the effectiveness of GAM, squeeze-and-excitation networks, and convolutional block attention module in enhancing the network’s performance. Ultimately, a calibration device was developed utilizing a laser rangefinder and a smartphone to enable quantitative assessment of bridge damages in real size. Based on the identical dataset, the evaluated accuracy of YOLOv7-SEG-GAM was compared with DeepLabV3+, BiSeNet, and improved semantic segmentation networks. The results indicate that the mean pixel accuracy and mean intersection over union values achieved by YOLOv7-SEG-GAM were 0.881 and 0.782, respectively, surpassing those of DeepLabV3+ and BiSeNet. This study successfully enables pixel-level segmentation of bridge damages and offers valuable insights for quantitative segmentation.

A Two-stage Method for Damage Detection in Z24 Bridge Based on K-nearest Neighbor and Artificial Neural Network

In this paper, we propose an effective approach for identifying damages in the Z24 bridge, a large-scale bridge in Switzerland. The dataset of the Z24 bridge is evaluated as a benchmark, reflecting the behavior of a real structure that has been used for numerous studies. However, most of the previous studies have only addressed the issues of updating the model or estimating the location and severity of damages. The core idea behind our proposed approach is to leverage the strengths of two effective Machine Learning (ML) algorithms: K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN), to assess both the location and severity of damages in the Z24 bridge. First, we employ KNN, an unsupervised learning algorithm, for pinpointing the damage location. This strategy proves highly efficient, significantly reducing computation time by circumventing the need for a loss function during KNN training. By adopting this approach, KNN effectively mitigates the risk of encountering local minima in the ANN optimization process. Subsequently, we deploy ANN to determine the damage severity. When compared to previous studies on the Z24 bridge, our proposed method (KNN-ANN) exhibits promising results. Furthermore, our results illustrate that KNN-ANN consistently outperforms traditional ANN methodologies.