Structural Condition Assessment Research Articles

A Novel Bayesian Empowered Piecewise Multi-Objective Sparse Evolution for Structural Condition Assessment

In this study, a novel Bayesian empowered piecewise multi-objective function is developed, in which a traditional objective function is applied to realize the rough optimization in the first stage to determine the approximate results. Then, a sparse Bayesian learning-based objective function is applied to realize refined optimization with the obtained approximate results in the second stage. On the other hand, considering the sparsity of the structural damage identification, two simple but effective calculation frameworks, the colony initial sparsification and elite clustering framework, are integrated into the evolution, making the algorithm adaptable to handle the defined sparse optimization problem. Therefore, the proposed calculation framework is more efficient and robust while no initial conditions are needed. We will carry out a numerical example on a truss and an experimental validation on a fixed-end beam with a single-sensor measurement system to verify the method.

Reactive UAV-based automatic tunnel surface defect inspection with a field test

This work addresses the problem of automatic tunnel surface defect inspection using unmanned aerial vehicles (UAVs). The research aims at proposing a robust and efficient monitoring method for image data acquisition and processing in complex and dark tunnel environments. A method, called Proximity Move-Pause-Photo for Surface Defect Inspection (PMPP-SDI), is proposed by combining reactive flying control strategies with a grid scanning pattern to capture high-quality image data from multiple views and angles. The image data is then used to generate a 3D point cloud model of the tunnel surface for structural condition assessment. The method is tested in a field experiment in a railway tunnel in Ireland, and the results show that it can achieve stable navigation, high-resolution reconstruction, and accurate defect detection. The paper discusses the advantages and limitations of the method, and suggests improving the control/navigation intelligence, data quality, and defect analysis as the future research directions.

Structural condition assessment with structural health monitoring systems and nonlinear simplified models

Structural condition assessment with structural health monitoring systems and nonlinear simplified models

Potential and limits using the DAD method for condition assessment of bridge structures

In the last years, the age of the bridge contingent is in all countries constantly increasing while in addition the bridges are solicited by an increased load level and an increased load frequency. This leads to an urgent need for defining efficient bridge structure condition assessment methods. Here, the Deformation Area Difference (DAD) method has already proven to be reliable and practicable. This has been shown in recent research in which it has been tested on real bridge structures using photogrammetry and compared with other highly precise measurement techniques. In order to further develop this method and to analyze the potential and limits of the DAD method in practical experiments, in the present study different parameters are varied such as e.g., the loading position along the longitudinal axis of the bridge structure, the damage position along the longitudinal axis of the bridge structure and the damage position in the cross-section. In addition, the method is analyzed on different bridge structure types. The results of the current study allow to determine set-ups for in-situ experimental investigations of existing bridge structures using the DAD method. A novel DAD Influence Line (DAD IL) is introduced to identify necessary load positions for the experiments. The Damage Detection Range depends on different damage levels, precisions, and deflection values. It is found that for local damage only one measurement line for the cross-section is not sufficient.

Vibration monitoring and acoustic emission sensing during progressive load tests of corroded reinforced concrete beams

Corrosion of reinforcement in concrete civil structures poses a significant challenge to their integrity and durability. To ensure the safety and longevity of such structures, effective monitoring strategies that can accurately detect, localise and assess the progression of damage are crucial. For most existing concrete structures, this is often challenging, as damage is already present when the monitoring campaign starts. In addition, reinforced concrete structures can be subject to a combination (or a succession) of corrosion and load-induced damage. By combining multiple measurement techniques, a more accurate and reliable condition assessment of concrete civil structures can be aimed for. This paper presents a comprehensive experimental study of the combination of vibration-based monitoring (VBM) and acoustic emission (AE) sensing techniques during progressive load tests of corroded reinforced concrete beams. Five beams were subjected to a cyclic four-point bending test, three of which were previously corroded while two beams remained undamaged prior to the mechanical loading. The influence of pre-existing corrosion damage and corresponding longitudinal concrete cracking on the modal characteristics (natural frequencies and strain mode shapes) and AE outcomes is investigated during the four-point bending test. The monitoring results obtained by both techniques are shown to be influenced by the pre-existing longitudinal concrete cracking caused by the reinforcement corrosion. Lower AE activity and a lower reduction in natural frequencies is observed for corroded RC beams during load bending tests when compared to uncorroded specimens. In addition, bending cracks occurring within the corroded zones appear to have a very limited effect on the identified strain mode shapes. These observations could possibly result in an underestimation of the damage and corresponding overestimation of the load-carrying capacity, as the corrosion damage conceals the occurrence of bending cracking on the AE and VBM outcomes.

Evaluation of Infrared Thermography Dataset for Delamination Detection in Reinforced Concrete Bridge Decks

Structural health monitoring and condition assessment of existing bridge decks is a growing challenge. Conventional manned inspections are costly, labor-intensive, and often risky to execute. Sub-surface delamination, a leading cause of deck replacement, can be autonomously and objectively detected using infrared thermography (IRT) data with developed deep learning AI models to address some of the limitations associated with manned inspection. As one of the most promising classifiers, deep convolutional neural networks (DCNNs) have not been utilized to their fullest potential for delamination detection, arguably due to the scarcity of realistic ground truth datasets. In this study, a common encoder–decoder semantic segmentation-based DCNN is adapted through domain adaptation. The model was tuned and trained on a publicly available dataset to detect subsurface delamination in IRT data collected from in-service bridge decks. The authors investigated the effect of dataset augmentation, class imbalance, the number of classes, and the effect of background removal in the training dataset, resulting in an overall number of seventy-five UNET models. Four out of five bridges were adopted for training and validation, and the fifth bridge was for testing. Most models averaged 80 iterations, and the training progress finally reached a training accuracy of 75% with a loss of about 0.6 without any overfitting. The result showed a substantial difference in the minimum and maximum values for the evaluated performance metrics (0.447 and 0.773 for global accuracy, 0.494 and 0.657 for mean accuracy, 0.239 and 0.716 for precision, 0.243 and 0.558 for true positive rate (TPR), 0.529 and 0.899 for true negative rate (TNR), 0.282 and 0.550 for F1-score. The results also indicated that the models trained on the raw annotated balanced dataset performed best for half of the metrics. In contrast, the models trained on raw data (with no dataset enhancement) performed better when only global accuracy was considered.

Online Bridge Structural Condition Assessment Based on the Gaussian Process: A Representative Data Selection and Performance Warning Strategy

Data-driven methods have now been widely used in structural health monitoring of civil infrastructures thanks to the rapid development of sensor technologies with massive structural and operational condition data. One main issue of data-driven methods is that the computational time increases with the number of monitoring data used, which limits their applications for online structural condition assessment. Focusing on bridge structural health monitoring, this paper proposes a representative data selection strategy for online performance assessment based on Gaussian process models. The proposed method can effectively reduce the required monitoring data size for training, allowing the bridge performance assessment to be conducted in a real-time manner. The method is developed in a probabilistic manner, allowing associated uncertainty of bridge monitoring data to be rigorously considered. A probabilistic warning index is proposed for bridge condition assessment and anomaly detection. The proposed method is validated using synthetic data and applied to structural condition assessment of two full-scale bridges, illustrating the feasibility for real implementations.

Image enhancement-based detection of concrete cracks under turbid water bodies

ABSTRACT Underwater concrete structure crack detection and structural health condition assessment based on image processing is challenging. The complex underwater environment and severe image degradation seriously affect the accuracy of crack detection. To solve these problems, a monocular vision and image-enhanced fractal-based fractal science based on computer vision and image processing techniques are proposed to conduct a non-contact detection study of underwater concrete cracks. This study established a four-level structural health condition to assist in underwater crack measurement and safety assessment. The box-counting method was used as a practical tool to calculate the fractal dimension. Three distances of 0.5, 0.8, and 1.2 m were set to verify the effective distance of the algorithm. The results show that the method proposed in this study can effectively detect cracks in submerged concrete members within 0.6 m and help managers correctly determine the structure's health using the fractal dimension.

Rapid full-field deformation measurements of tall buildings using UAV videos and deep learning

Full-field deformation of tall buildings is informative and imperative for structural health condition assessments. This study explores the feasibility of using videos recorded by an unmanned aerial vehicle (UAV) to measure the vibration profiles of tall buildings with the aid of deep neural networks. First, a Transformer network with a self-attention mechanism is used, and its outcome is employed for the homography transformation to minimize the drifting problems induced by the UAV. Second, a boundary-aware salient object detection network is adopted to extract the boundary of the buildings in the stabilized videos for further full-field deformation measurements. The accuracy of the proposed method is experimentally validated using a wood frame structure under harmonic excitations. Under a measuring distance of approximately 4.2 m, the proposed method achieves averages of root-mean-square-errors (RMSEs) for the displacement and rotation measurements of 2.13 mm and 1.74 × 10−3 rad, respectively, as compared to that determined by an infrared light tracking system. The study further analyzes the field-test data recorded from the vibration of a 247-m tower. Under a measuring distance of about 55 m, the proposed method is comparable to the vibration measurement at a specific story and estimates the full-field deformation within the region of interest. Overall, the proposed method with rapid UAV deployment is feasible and accurate for monitoring the full-field deformation using the UAV-recorded videos.

An modified intelligent real-time crack detection method for bridge based on improved target detection algorithm and transfer learning

The combination of UAV camera and intelligent algorithm is a promising method for non-contact bridge crack detection. In this paper, an inspection tool based on UAV Image Acquisition Technology (UAVIAT) and Improved Intelligent Target Detection Technology (IITDT) called Improved Intelligent Real-Time Crack Detection Method for Bridges (IIRTCDMB) is proposed for efficient crack detection. The contributions of this paper are (1) The Squeeze-Excitement (SE) attention module is integrated into the target detection algorithm - You Only Look Once version 7 (YOLOv7) model to improve the learning ability of the feature channel. A Focal-efficient intersection over union (Focal-EIoU) loss function is also introduced to improve the regression accuracy of the model. As a result, a new crack image detection algorithm, YOLOv7-CD, is proposed. (2) A training process based on two-stage transfer learning (TSTL) is established, and hyper-parameter optimization of YOLOv7-CD is carried out. The feasibility and excellent performance of the proposed method are verified by applying it on the Cuntan Yangtze River Bridge. The results show that the average precision (AP) of the YOLOv7-CD model is improved by 3.19% compared with the original YOLOv7 model. After TSTL and hyperparameter optimization, the AP of the YOLOv7-CD model for bridge crack detection reaches 98.01%, which is higher than that of the popular target detection models. The IIRTCDMB proposed in this paper can acquire bridge surface images more safely and efficiently, and provide inspectors with more accurate structural crack information with lower computational and hardware requirements, which can provide technical support for the assessment of structural safety conditions and the formulation of maintenance programs.

Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automated structural condition assessment in visual inspection

Efficiently monitoring the condition of civil infrastructure requires automating the structural condition assessment in visual inspection. This paper proposes an Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for automatic structural condition assessment in visual bridge inspection. AECIF-Net can simultaneously parse structural elements and segment surface defects on the elements in inspection images. It integrates two task-specific relearning subnets to extract task-specific features from an overall feature embedding. A co-interactive feature fusion module further captures the spatial correlation and facilitates information sharing between tasks. Experimental results demonstrate that the proposed AECIF-Net outperforms the current state-of-the-art approaches, achieving promising performance with 92.11% mIoU for element segmentation and 87.16% mIoU for corrosion segmentation on the test set of the new benchmark dataset Steel Bridge Condition Inspection Visual (SBCIV). An ablation study verifies the merits of the designs for AECIF-Net, and a case study demonstrates its capability to automate structural condition assessment.

Damage Detection and Condition Assessment of Civil Engineering Structures Using Structural Health Monitoring

Damage identification is critical in evaluating the condition and performance of the existing civil infrastructure. This requires not just routine or critical event-based inspections, but rather a means of continuous monitoring of a structure to provide an assessment of changes as a function of time and an early warning of an unsafe condition using real-time data. Health monitoring plays an important role in the construction and maintenance of the infrastructure. It employs in situ, continuous, or regular measurements and analyses of key structural and environmental parameters under the operating conditions to identify if a damage has occurred, define its location, and estimate its severity, evaluate its consequences on the residual life of the structure also to provide warning of impending abnormal states or accidents to avoid casualties and to inform maintenance and rehabilitation decisions. SHM takes advantage of the new technologies in sensing, instrumentation, communication, and modelling to integrate them into an intelligent system. Structural Health Monitoring for civil structures is becoming increasingly popular in Europe and worldwide because of the opportunities that it offers in the fields of construction management and maintenance. Reduction of inspection costs, research, with the possibility to better understand the behaviour of structures under dynamic loads, seismic protection, observation, in real or near real-time, of the structural response and of evolution of damage, so that it is possible to produce post-earthquake scenarios and support rescue operations, are the main advantages related to the implementation of such techniques.

Development of Rating System of Existing Railway Steel Bridges

Abstract: Railway bridges are designed to be serviceable for a long time. However, the structural conditions of railway bridges change over time due to environmental effects, fatigue and structurally unplanned modifications etc. which affect health of the structure significantly. Hence inspection and condition assessment of structure is required for their uninterrupted operation. Condition assessment is also required for maintenance and repairs of existing structures so as to avoid any mishaps and save valuable human life. Dealing with thousands of bridges and several factors that cause deterioration, makes the rating process extremely complicated. It is therefore necessary to develop a practical and accurate system, which will be capable of rating a network of railway bridges. Several bridge inspectionstandards and condition assessment practices have been developed around the globe. Some practices employ four linguistic expressions to rate bridge elements while other practices use five or six, or adopt numerical ratings such as 1 to 9. This research article introduces six colour codes in the proposed rating system for a network of railway bridges based on their current structural condition by means of visual inspection and different non-destructive evaluation techniques. The proposed rating system could provide bridge stakeholders with a rational appraising tool for condition assessment of railway bridges, allowing better allocation of budget and more precise maintenance decisions.

Automated pixel-level crack detection and quantification using deep convolutional neural networks for structural condition assessment

Crack detection is a crucial task in assessing the condition of concrete structures. Herein, a novel deep learning method based on convolutional neural networks, referred to as R-FPANet, is proposed for crack detection. The R-FPANet performs automatic segmentation and quantification of crack morphology at the pixel level. In this methodology, the modularization concept based on the following three modules is adopted: ResNet-50 is chosen as the backbone to extract features from images, the Feature Pyramid Network with Dense Block is integrated to promote the fusion of both shallow and deep features as well as enhance feature reuse, and self-attention mechanisms such as Channel Attention Module and Position Attention Module are introduced to strengthen the dependency between features. Based on the crack segmentation results, a suitably established framework is developed for quantitative analysis of the major geometric parameters, including crack area, crack length, crack mean width and crack max-width at the pixel level. To verify the effectiveness of the proposed method, a large-scale concrete crack image dataset was produced and carefully labeled at the pixel level and then utilized to train the model. Finally, our experiments reveal that the proposed approach achieves an Intersection over Union of 83.07%, further indicating that the segmentation performance of the proposed method is better than the state-of-the-art models and also confirming that the crack quantification results are close to reality. Overall, the proposed method performs well, contributing to crack detection and quantification with great potential for practical use.

Adaptive Bayesian filter with data-driven sparse state space model for seismic response estimation

The present work proposes a seismic response estimation framework for post-earthquake structural condition assessment via acceleration measurements. An augmented sparse state space model is first derived to represent the underlying governing equations of the system of interest with hysteresis nonlinearity. A Bayesian filter is then utilized to provide the displacement estimate under an earthquake excitation by fusing the identified sparse state space model with the measured system acceleration. To avoid subjective assumptions on the process and observation noises in the Bayesian filter, a double-loop process is proposed, where the inner loop is an online Bayesian filtering by the unscented Kalman filter with Robbins-Monro algorithm, while the outer loop is an offline Bayesian updating by the transitional Markov chain Monte Carlo method. The feasibility of the framework is demonstrated on a simple illustrative example and a followed engineering application to the state estimation of a bridge pier finite element model. The results indicate the capability of the framework to properly infer the system displacement, including its residual components.

A deep learning-based method for structural modal analysis using computer vision

Structural modal analysis aims to determine a structure's natural frequency, damping ratio, and mode shape, helping with structural condition assessment and maintenance. In this study, a computer vision-based framework for the identification of structural modal parameters is developed, which consists of two main procedures: First, the one-dimensional (1D) vibration signals of edge pixels on the structure in the video are extracted via edge detection and optical flow theory. Second, a 1D convolutional neural network (CNN) coupled with long short-term memory (LSTM) is generated to extract structural modal parameters from the input 1D signal. The framework's performance has been validated through comparison with baseline values, which were obtained from contact sensors. Additionally, the model's robustness and extrapolability has been analyzed. The good performance of the computer vision-based approach confirms its potential for precise and dependable contact-free modal analysis.

A Practical Data Extraction, Cleaning, and Integration Method for Structural Condition Assessment of Highway Bridges

The success of regional bridge condition assessment, a crucial component of systematic maintenance strategies, relies heavily on comprehensive, well-structured regional bridge databases. This study proposes the data extraction, cleaning, and integration method for the construction of such databases. First, this research proposes an extraction method tailored for unstructured data often present in inspection reports. Additionally, this paper meticulously outlines a cleaning procedure designed to rectify two distinct categories of typical errors that are present within the inspection data. Subsequently, this study takes a holistic approach by establishing integration rules that harmonize data from various sources, including inspection records, monitoring data, traffic statistics, as well as design and construction blueprints. The architectural framework of the regional bridge information database is then meticulously laid out. To validate and demonstrate the effectiveness of the method, this study applies them to a set of representative highway bridges situated within Shandong Province. The results show that this approach can be used to successfully establish a functional regional bridge database. The database plays a pivotal role in harnessing the latent potential of an extensive range of multi-source information and propels the field of bridge condition assessment forward by providing a solid basis for informed decision making and strategic planning in the realm of infrastructure maintenance.

EUROPEAN GROUND MOTION SERVICE FOR BRIDGE MONITORING: TEMPORAL AND THERMAL DEFORMATION CROSS-CHECK USING COSMO-SKYMED INSAR

Abstract. This paper elaborates on the potential of the deformation time-series provided by European Ground Motion Service (EGMS) data points for bridge monitoring, in terms of the response of bridge structures to temporal and thermal deformations. For this purpose, high-resolution Cosmo-SkyMed (CSK) Synthetic Aperture Radar (SAR) images have been utilized through Persistent Scatterer SAR Interferometry (PS-InSAR) to derive spatially detailed deformation time-series of two bridges located at the north of Lombardy region, Italy. Then, the Annual Displacement Velocity and Thermal Expansion Coefficient of the data points in both datasets are extracted based on the corresponding deformation time-series. The response parameters are post-processed through projection and compensation steps to become comparable. Cross-checking the results by comparing the response parameters along the bridges showed that the global (for L3 products) and local (for L2b products) differential behaviour and the variation of the values of these parameters from one side to the other side of each bridge are consistent between CSK and EGMS datasets. However, the EGMS L3 information shows a slightly lower magnitude in both displacement velocity and thermal expansion coefficient responses. According to the revealed capability of EGMS information in this work, it can be concluded that the EGMS data points, if spatially cover a bridge, can present a reasonable and sufficient insight into the temporal evolution of displacement and thermal structural response, suitable for structural health monitoring and condition assessment of bridges under operational and environmental loads.

A systematic approach to pixel-level crack detection and localization with a feature fusion attention network and 3D reconstruction

Automated detection and localization of surface cracks by using deep learning and computer vision (CV) techniques are conducive to efficient structural condition assessment. However, insufficient feature resolution in deep architecture networks leads to misclassification and inaccurate segmentation of cracks. Furthermore, accurately localizing cracks within the overall structure is crucial for understanding the extent of damage to structural safety and durability. To address these challenges, this paper proposes a systematic approach for pixel-level surface crack detection and localization. The approach is based on a novel Feature Pyramid and Attention Feature Fusion Network (FPAFFN) and 3D reconstruction techniques. Two attention mechanisms named Attention Refinement Module (ARM) and Feature Fusion Module (FFM) are embedded in FPAFFN to strengthen the extraction and fusion of semantic and detailed information. With the cracks annotated images produced by FPAFFN, COLMAP and an open Multi-View Stereo are adapted to reconstruct the 3D model of the cracked structural components. Experimental studies on benchmark datasets CRACK500 and Cracktree200 and manually captured images validate the effectiveness of FPAFFN. The ARM and FFM embedded in FPAFFN enhance the feature learning efficiency and lead to a 3 % rise in the mean intersection ratio (mIoU). FPAFFN demonstrates remarkable generalization capability in detecting images with disturbances and outperforming other well-known crack detection methods in delineating crack edges and details. A subsequent experimental study on a damaged concrete slab shows that the proposed approach is capable of systematically detecting and localizing cracks. Therefore, it is promising to apply the proposed approach to practical structural inspection.

Damage identification of long-span bridges based on the correlation of monitored global dynamic responses in high dimensional space

Structural damage identification and condition assessment is the most direct goal in structural health monitoring (SHM). Vibration-based methods (VBM) using the global dynamic responses (displacement or acceleration), including modal-based methods and statistical methods, have been comprehensively investigated in the last few decades in the SHM community. These two types of methods face challenges in practice due to the indicators being sensitive to the environment and insensitive to local damage. It is curious whether new features of data in high-dimension space can be found and the new features can be used as damage indicators. This study proposes a method based on the correlation of the global dynamic responses in high dimensional space for damage identification. It is proved that the ratio of mean square (RoMS) between any two responses (two-dimensional space) is dependent on the modal parameters of the structure only and changes only with the damage of the structures. Therefore, it can be used as a damage indicator. The proposed method is validated through a finite element numerical analysis on a cable-stayed bridge and the monitored acceleration of a real-world suspension bridge, and is further compared with the modal analysis methods. The results show that the proposed method can accurately identify the damage and is sensitive to local damage compared to modal parameters.