Bridge Management Research Articles

A New Framework for Condition and Risk Assessment for Sustainable Management of PT Bridges

A New Framework for Condition and Risk Assessment for Sustainable Management of PT Bridges

Deep learning-based automated identification on vortex-induced vibration of long suspenders for the suspension bridge

Large amplitude vortex-induced vibration (VIV) of long suspenders, caused by vortex-shedding and wake flow, will decrease the service life of high-strength wires and its anchorage systems, hence listed as an essential monitoring indicator of the structural health monitoring system in the suspension bridges. Traditionally, a static vibration amplitude limitation is usually predefined and used to identify VIV from continuously monitored acceleration data of bridge suspenders. Due to the complexity of the starting vibration of the suspenders, it may not be able to flexibly adapt to the suspenders VIV under different conditions. In addition, transient but significant vibration events may not be captured since it relies only on static vibration amplitude limits without considering the temporal information of vibration. To address the above-mentioned issues, a novel framework to autonomously identify the suspenders VIV is proposed using the multimodal fusion techniques with deep neural networks. The main contributions of the methodology are: i) by calculating the wind field and vibration characteristic, two vibration response parameters are identified as indexes for the identification of suspenders VIV based on the significant difference method of big data analysis; ii) Two different modal information of time history images and power spectral density (PSD) sequences are used as inputs to the convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) to extract the suspenders vibration response features from the time and frequency domain perspectives, respectively; and iii) The multimodal information is concentrated and enhanced by the multi-head attention (MHA) mechanism to achieve automated identification of the suspenders VIV. The proposed framework is validated with data collected from a full-scale long-span suspension bridge in comparison with the base model. The results show that the proposed framework can efficiently identify the full-cycle development process of the suspenders VIV. This study provides a convenient strategy for suspenders VIV identification, which can be used for bridge management and vibration mitigation device design.

Enhanced Multi‐Objective Optimization Model for Bridge Performance Assessment and Prediction, Based on Improved PCA, K‐Means Clustering, and Kaplan–Meier Survival Algorithm

ABSTRACTThe research proposes a hybrid algorithm model that combines model‐driven and data‐driven approaches for the direct application of bridge health monitoring technology in bridge management. This comprehensive study encompasses a series of analytical techniques and methodologies to build a multi‐objective optimization model for bridge performance assessment and prediction. It focuses on the processing of multi‐source heterogeneous data, selection of key sub‐parameters using Principal Component Analysis (PCA), enhanced K‐means clustering analysis, determination of structural component target thresholds, time‐dependent survival probability analysis, regression fitting, and timing prediction of the bridge system for both the components of double‐layer truss arch bridge and the bridge system. The initial phase of the study concentrates on the diversification and decentralization of monitored data from various sources, integrating and cleaning data obtained from different sources to ensure data quality and consistency. PCA technique is applied to identify key sub‐parameters that have significant impacts on the performance of structural components. Enhanced K‐means clustering analysis is carried out to effectively group and classify the identified key sub‐parameters. Numerical simulations, including structural nonlinear analysis, are conducted to determine the target thresholds of bridge structure, providing important benchmarks for performance evaluation. Finally, a multi‐parameter regression model is used to evaluate and update the performance of the bridge structure, taking into account survival probability (using the Kaplan–Meier method), maintenance history, and material deterioration to estimate the most critical time for the bridge system. A case study is conducted to validate the suggested comprehensive algorithms for a double‐layer truss arch combination bridge, which contributes to enhancing performance evaluation and predicting the most critical time for structural components and bridge system in the bridge management and maintenance practices. It should not be ignored that, the accuracy and reasonability of bridge structure system performance evaluation and prediction depend largely on the selection of target thresholds.

Comprehensive durability assessment of in-service concrete bridges based on combination weighting and extenics cloud model

In recent years, with the continuous development of urban transportation, the durability of concrete bridge structures has become increasingly prominent. Many in-service concrete bridges exhibit issues such as cracks, excessive deflection, and a significant reduction in load-bearing capacity during their service life. To meet the requirements of sustainable development, it is urgent to assess the durability of bridges accurately. Therefore, this paper establishes a scientific and reliable evaluation index system for the durability of in-service concrete bridges. Based on a review of the literature and relevant standards and specifications, this paper establishes an evaluation index system for the durability of in-service concrete bridges and calculates the weights using a combination weighting method. The durability of the bridges is assessed using the extension cloud model theory, and MATLAB is utilized for efficient and accurate computation and analysis, ultimately determining the durability grades of the bridges. The method was applied to the durability assessment of five in-service concrete bridges, and the results were in high agreement with the measured data, proving its effectiveness and accuracy. The research results provide a scientific basis for the management and maintenance of concrete bridges, which can help extend their service life. Future studies will expand the sample to cover more bridge types to comprehensively assess and enhance the durability of bridges.

A machine learning-based probabilistic wind speed prediction model with multi-resolution data, quantile regression and bound estimation

Wind speed prediction can be important for management of long-span cross-sea bridges, and probabilistic prediction models are needed to take uncertainty of future wind speed into consideration. However, there are two shortcomings of existing models. One is the lack of supplementary input of detailed fluctuations of wind speed, and the other is that fixed quantiles are usually selected when the predicted probability distribution is converted into a confidence interval. To this end, we propose a novel machine learning-based probabilistic model with multi-resolution data, quantile regression and bound estimation. The proposed model is composed of the distribution prediction part and the interval prediction part. In the distribution prediction part, we employ multi-resolution data as input, which can complement details of fluctuations of wind speed to reduce uncertainty. The interval prediction part employs the lower upper bound estimation method to postprocess predicted quantiles and output a superior interval than selecting fixed quantiles. The proposed model is validated on the monitoring wind speed data of two long-span cross-sea bridges, where the superiority of the distribution part and the effectiveness of the interval part are demonstrated.

Implementation of High-Precision Life Cycle Cost Analysis (HP-LCCA) on Indonesian Bridge Management System

Life Cycle Cost Analysis (LCCA) is a method used to determine the preservation costs required for an object, in this case, a bridge, throughout its service life. This method has been implemented in several advanced countries, including Japan. The LCCA calculation concept in Japan differs from those in other countries, as it involves a detailed segmentation of structural elements of bridges, making the model unique and highly detailed. This model is known as High-Precision Life Cycle Cost Analysis (HP-LCCA) and will be tested for application in Bridge Management Systems (BMS) in Indonesia. Implementing this model requires several adjustments, including aligning perceptions of visual inspection results and adapting the assessment concepts for each element based on research interpretations. Additionally, the difference between non-physical and physical condition assessment models presents a challenge for adopting this calculation model. The research shows a similar pattern and positive correlation between non-physical and physical assessment models. Furthermore, factors influencing LCC calculations include bridge age and the number of segments in structural elements. This research aims to provide optimal LCC calculations and facilitate their application in BMS in Indonesia.

Hyperparameter Tuning Technique to Improve the Accuracy of Bridge Damage Identification Model

In recent years, active research has been conducted using deep learning to evaluate damage to aging bridges. However, this method is inappropriate for practical use because its performance deteriorates owing to numerous classifications, and it does not use photos of actual sites. To this end, this study used image data from an actual bridge management system as training data and employed a combined learning model for each member among various instance segmentation models, including YOLO, Mask R-CNN, and BlendMask. Meanwhile, techniques such as hyperparameter tuning are widely used to improve the accuracy of deep learning, and this study aimed to improve the accuracy of the existing model through this. The hyperparameters optimized in this study are DEPTH, learning rate (LR), and iterations (ITER) of the neural network. This technique can improve the accuracy by tuning only the hyperparameters while using the existing model for bridge damage identification as it is. As a result of the experiment, when DEPTH, LR, and ITER were set to the optimal values, mAP was improved by approximately 2.9% compared to the existing model.

State-of-art review of resilience of bridges and bridge networks

In recent years, many attempts have been made to incorporate resilience frameworks into decision making, establish the best use of available resources and reduce the impact of hazards on bridges and bridge networks. However, scholarly research in this area is still in its early phases, with minimal exploration of research gaps and future prospects. A state-of-the-art review of bridge and bridge network resilience studies using a science mapping approach is presented here. Research on the topic was obtained from the Scopus literature database. The literature database was then analysed using VOSviewer and Nvivo tools to display the domain-specific body of knowledge. The study then focused on the most prolific researchers and disaster types, bridge resilience assessment approaches, current research trends, future directions and theoretical and practical implications. The research paradigm on the resilience of bridges and bridge networks is changing toward the usage of digital tools and technologies. In this context, a framework id proposed by integrating building information modelling/geographic information systems and digital twin models. The proposed framework can aid bridge owners in accumulating iterative data, creating multi-hazard disaster preparedness policies and designing and enhancing life-cycle management and maintenance tasks of bridges and bridge networks.

Anomaly detection of cracks in synthetic masonry arch bridge point clouds using fast point feature histograms and PatchCore

Management of ageing masonry arch bridges entails periodic site inspections to identify signs of potential structural degradation. Previous research has focused on detecting surface cracks from images. This paper develops an alternative approach where cracks are identified from point clouds via geometric distortions. An image-based anomaly detection method called PatchCore is customized for 3D applications for this purpose. First, Fast Point Feature Histograms (FPFH) are used to extract geometric features. Then PatchCore is applied on synthetic point clouds with crack labels, generated using 3D finite element modelling (FEM) and graphical modelling. Results show that the proposed method can capture surface and internal cracks in arches. Analyses show that the method is robust against measurement noise, initial damage and masonry surface roughness, and can be applied to other bridge components. Limitations of the method in detecting small changes in curvature and in-plane geometric distortions are highlighted for further improvements.

Network-level optimisation approach for bridge interventions scheduling

This paper introduces a novel extension of the multi-system optimisation method, known as the 3C concept, tailored for optimising budget allocation for bridge interventions at the network level. This extended methodology accounts for the interdependencies among bridges due to their spatial proximity within the network. It incorporates direct and user costs, bridge performance indicators, and a bridge deterioration model. A real-world case study involving a portfolio of 555 bridges demonstrates the practicality of the methodology, efficiently determining the optimal intervention sequence. Over an 18-year analysis period, the proposed methodology achieved a 23% reduction in total costs by combining repairs for bridges with high to severe damage and maintenance for the others. This represents a significant improvement compared to the traditional approach, used by bridge management agencies, which relies exclusively on maintenance. The optimised procedure outperforms human intuition in managing complex bridge networks, particularly over extended periods. This methodology can assist transportation agencies in implementing and exploring various scenarios by adjusting the time between consecutive interventions and budget constraints, supporting comprehensive analysis and informed decision-making.

Technologies and Platforms for Remote and Autonomous Bridge Inspection – Review

Recent scientific and technological advancements have enabled a more efficient structural condition assessment of bridges, mainly through the implementation of intelligent inspection strategies. These intelligent strategies can provide early identification of critically damaged components before failure, and will therefore play a key role in extending the life of infrastructure. The latest inspection technologies can provide inspection plans with damage conditions, create a damage report as well as provide statistics and comparisons to the previous inspection findings. The new and existing inspection technologies are directed to help with the digitalization of the Bridge Management System (BMS). The complexity of maintenance/inspection requires organized, automated, open and transparent digital processes, which should consider both—structure and asset management data. Further, the inspection/monitoring findings serve as a source for decision-making models. The digitalized aspects of autonomous inspection provide better performance prediction models and guarantee safety for the users. This paper presents the latest findings in the field of remote inspection of bridges. In particular, the main technologies for inspection and geometrical assessment are depicted, especially those based on computer vision systems installed in UAVs and robots, LiDAR, radar, satellites and other non-contact systems including on-board monitoring. The accompanying article entitled: “Methodologies for remote bridge inspection” deals with the methodologies used for data processing based on Artificial Intelligence (AI).

Parametric modeling and engineering application of the high-speed continuous beam bridge based on Building Information Modeling.

To improve the informatization and intelligence level of high-speed railway (HSR) bridge construction, a parametric modeling method for continuous beam bridges based on Building Information Modeling (BIM) is proposed in this study. By this method, the parametric families of continuous beam components and key construction machinery are established, and the rapid modeling of overall continuous beam bridge and the simulation of critical construction process are realized as well. Taking the Caoxian-Shangqiu bridge of Xiong'an-Shangqiu HSR as a case study, the parametric modeling method is applied to conduct the engineering application on the prestressed duct layout and rebar clash detection. The results indicate that the modeling efficiencies of HSR continuous beam bridge and construction machinery are significantly increased by the established parametric modeling method. Based on the BIM model of continuous beam bridge, the improvement in the precision of prestressed duct layout and the elimination of rebar clash points can be achieved. The research achievement can guide the visualization of construction disclosure, enhance construction efficiency, and provide reference and technical support for the construction management and control of HSR continuous beam bridges.

Editorial: Inaugural Issue of the International Journal of Bridge Engineering, Management and Research (IJBEMR)

It is my pleasure to share with you the inaugural issue of the newly established International Journal of Bridge Engineering, Management and Research. The International Journal of Bridge Engineering, Management and Research (BER) is a fully open access online-only journal. It serves as a forum for the publication of scientific and technical papers related to all aspects of bridge engineering and management, including structural, seismic, hydraulic and geotechnical risk analysis, structural health monitoring, static and dynamic assessments, structural retrofitting, and resiliency enhancement. The journal also publishes research papers on tunnels focusing on the areas mentioned above. Technical research papers and case studies dealing with innovative technological or computational solutions to bridges and tunnels, as well as experimental methods and novel design and theoretical analysis procedures are strong candidates for publication in the journal. This inaugural issue features five high quality papers in bridge engineering. Through this issue, I am also inviting you to register with the journal and submit your research manuscripts to the journal. We are committed to expedited and thorough peer review and publication of your research.

Probabilistic pre-estimation of life-cycle costs of road bridges using dynamic Bayesian networks

Proper life-cycle cost (LCC) estimation of vital transportation network assets, such as road bridges, is crucial for cost-efficient projects. This study presents a probabilistic framework for the LCC estimation of concrete bridges based on Dynamic Bayesian Network (DBN) modelling that stakeholders can consult in projects’ preliminary stages for suitable decision-making. The proposed model consists of two separate modules. The first accounts for the probabilistic estimation of material quantities and their relative costs during the construction phase, specifically for the bridge’s superstructure and foundation. The second one refers to the operational phase of the bridge’s components. For illustrative purposes, the maintenance costs of deck expansion joints are presented, as they are regarded as vulnerable bridge components with regular repairs. The suggested DBN includes time-dependent and continuous variables thoroughly documented over multiple time stages. The DBN is formulated using actual records of 78 concrete bridges’ construction, deterioration, inspections and maintenance from the Egnatia Odos motorway in Greece. The presented approach is an effective tool for bridge management enhancement owing to stochastic dynamic interdependencies among parameters and continuous information updating.

Bridge Safety Assessment and Management Strategies Under Long-Term Operating Conditions

Bridge Safety Assessment and Management Strategies Under Long-Term Operating Conditions

Inspection data‐based prediction on fatigue crack of orthotropic steel deck using interpretable machine learning method

AbstractThe prediction of fatigue cracks on orthotropic steel decks is of great significance to the maintenance of bridges. However, fatigue cracks are affected by various uncertainties in reality, which encourages a data‐driven study for the sake of reliability and accuracy of predictions. Based on the crack inspection data from orthotropic steel decks on actual bridges in China, the feature engineering is conducted considering fatigue crack behaviors, and the machine learning models are trained and tested for predicting cracks, including XGBoost, random forest, and multiple decision trees. According to the receiver operating characteristic curves of the three models, the XGBoost model has the best performance, whereas the average AUC is about 0.75, limited by the insufficient data volume of positive samples. With the SHAP values of all features, the interpretation of the machine learning model is presented, indicating that the global effects, that is, the longitudinal position, the loading condition, and the bridge age, are always influential factors for fatigue cracks. The local features concerning the interactions between cracks have an effect on crack behaviors to a certain extent, but less important. Accordingly, the interpretable machine learning model can provide conservative predictions in a rather transparent way on this issue, which can benefit decision‐making in bridge designs, maintenance, and management.

Enhancing pier local scour prediction in the presence of floating debris

AbstractLocal scour poses a grave threat to bridge foundations, potentially causing catastrophic collapses. This study uses FLOW-3D with the Reynolds-Averaged Navier-Stokes model to analyze pier scour and dune formation under bridges. It focuses on submerged debris shapes near the water's surface. Results closely match experiments when specific conditions are met. The study introduces an innovative approach to debris impact assessment. Instead of traditional methods, it proposes a novel equation accounting for debris's effective area and elevation. This enhances reliability by over 20%, improving scour depth assessment in debris-laden scenarios. This advances the understanding of debris's role in local scour, benefiting bridge design and management practices.

Framework for rational decision-making in bridge maintenance

Bridges are deteriorating, and their safety must be continuously assessed. Efficient management of bridges is essentially about making decisions on maintenance activities in line with the decision maker’s preferences. In other words, structural safety should be ensured while optimally allocating resources. In theory, methods are available for solving this complex task; however, they have not yet been implemented by bridge owners. In this study, the implementation into practice is facilitated by presenting a consistent framework for rational decision-making. It is argued that structural assessment is a decision problem that infrastructure owners are obliged to take responsibility for. Bayesian decision theory is presented as the theoretically ideal decision-making framework. The main components of the framework—representations of structural reliability and failure consequences—are discussed in detail, and human safety constraints are integrated. For demonstration purposes, the decision-making framework is applied to two case studies. In addition, it is parameterised by the relative cost of the intervention to failure and the current failure probability to be applicable for any assessment situation. In that way, this study contributes to more efficient maintenance of single bridges and the development of generally applicable structural codes for assessing existing structures.

Analysis of Detection and Monitoring Technology in the Construction and Maintenance of Large Bridges

Currently, there is significant attention placed on the construction, management, and maintenance of large service bridges. Within the realm of bridge maintenance management, the utilization of detection and monitoring technology is indispensable. By employing these technologies, we can effectively identify any structural defects within the bridge, promptly uncover unknown risks, proactively establish maintenance strategies, and prevent the rapid deterioration of bridge conditions. This article aims to explore the advantages of applying bridge monitoring and testing technology and to discuss various methods for implementing detection and monitoring technology throughout the construction, management, and maintenance phases of large bridges. Ultimately, this will contribute to ensuring the safe operation of large bridges.

Refinement and Validation of the Minimal Information Data-Modelling (MID) Method for Bridge Management.

Various approaches have been proposed for bridge structural health monitoring. One of the earliest approaches proposed was tracking a bridge's natural frequency over time to look for abnormal shifts in frequency that might indicate a change in stiffness. However, bridge frequencies change naturally as the structure's temperature changes. Data models can be used to overcome this problem by predicting normal changes to a structure's natural frequency and comparing it to the historical normal behaviour of the bridge and, therefore, identifying abnormal behaviour. Most of the proposed data modelling work has been from long-span bridges where you generally have large datasets to work with. A more limited body of research has been conducted where there is a sparse amount of data, but even this has only been demonstrated on single bridges. Therefore, the novelty of this work is that it expands on previous work using sparse instrumentation across a network of bridges. The data collected from four in-operation bridges were used to validate data models and test the capabilities of the data models across a range of bridge types/sizes. The MID approach was found to be able to detect an average frequency shift of 0.021 Hz across all of the data models. The significance of this demonstration across different bridge types is the practical utility of these data models to be used across entire bridge networks, enabling accurate and informed decision making in bridge maintenance and management.