Bridge Health Condition Research Articles

Recurrent Neural Network for Quantitative Time Series Predictions of Bridge Condition Ratings

Traditional forecasting models for bridge conditions, such as ARIMA and Markov chains, often fail to adequately capture nonlinear and dynamic relationships among critical variables like age, traffic patterns, and environmental factors, leading to suboptimal maintenance decisions, increased long-term maintenance costs, and heightened safety risks. This study addresses these limitations by developing recurrent neural network (RNN) models utilizing Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures with a TimeDistributed output layer. This novel approach enables accurate forecasting of the Bridge Health Index (BHI) and condition ratings for key components—deck, superstructure, and substructure—while effectively modeling temporal dependencies. Applied to bridge data from Georgia, USA, the regression models (BHI) achieved R2 values exceeding 0.84, while the classification models (components condition ratings) demonstrated accuracy between 84.78% and 87.54%. By modeling complex temporal trends in bridge deterioration, our method processes time-dependent data from multiple bridges simultaneously, revealing intricate relationships that influence bridge performance within a state’s inventory. These results provide actionable insights for maintenance planning, optimized resource allocation, and reduced risks of unexpected failures. This research establishes a robust framework for bridge performance prediction, ensuring improved infrastructure safety and resilience amid aging assets and constrained maintenance budgets.

Crowdsensing-based automatic bridge health condition assessment using drive-by measurements and deep learning

In recent decades, assessing the structural health conditions of aging bridges has emerged as a significant concern. A recent drive-by measurement method has attracted substantial attention, in which only several sensors are installed on crowdsensing vehicles rather than bridges, providing a more economical and convenient solution. This paper proposes an automatic bridge condition assessment framework incorporating drive-by measurements and deep learning techniques. The methodology involves collecting and segmenting accelerations from a vehicle passing a healthy bridge into short-time overlapped frames. Over multiple vehicular passes, all frames are then transformed into frequency-domain responses, forming the input for training an unsupervised deep learning model. The model is then trained to reconstruct the input using these frequency-domain responses. In assessing the bridge with an unknown health state, the trained model is employed to reconstruct the passing vehicle’s new short-time frames, and the response construction error automatically determines the bridge’s health condition. Experimental validation utilizing a laboratory bridge and scaled truck demonstrated that the trained model could consistently identify a healthy bridge during passages, with larger reconstruction errors indicating that the bridge was damaged. The innovative framework showcased promise for efficient and reliable bridge health condition assessment.

Automated intelligent measurement of cracks on bridge piers using a ring-climbing vision scanning operation robot

Detecting cracks on the surface of bridge piers is critical to the health condition of bridges. Aiming at the limitations of existing unmanned aerial vehicles (UAVs) and climbing robots, this research proposes a ring-climbing visual scanning operation robotic disease acquisition system, which achieves entire region, high-definition, and fast acquisition of cracks on bridge piers surfaces. In addition, a crack segmentation network based on an efficient self-attention mechanism and a refined segmentation algorithm are proposed to achieve accurate detection and quantification of cracks on bridge piers. Finally, an experimental prototype was built, and experiments were conducted. The results show that the maximum error of crack quantification is within 0.1 mm. The designed ring-climbing visual scanning operation robotic disease acquisition system can be applied to the surface of any pier with a 1.2 to 1.5 m diameter, which is of great significance for the automatic detection of the health condition of bridge piers.

Intelligent identification of moving forces based on visual perception

The task of identifying moving forces presents a challenging inverse problem for bridge health monitoring and condition assessment. Existing methods for identifying moving loads rely on complex structural response measurement equipment, resulting in inefficiency and elevated costs. To address these challenges, this study introduces an innovative intelligent identification method for moving forces on bridges using visual perception techniques. The proposed method utilizes cameras to capture displacement changes at specific points on the bridge surface to reconstruct moving forces in the time domain. Initially, numerical simulations were conducted to ascertain the feasibility and robustness of identifying moving forces based solely on the structural displacement response. This phase also investigates the influence of different measurement point combinations on identification accuracy. Subsequently, the accuracy of the proposed method in measuring the dynamic displacement response of the structure was carefully evaluated by an outdoor shaking table test. Furthermore, a meticulously designed simply supported beam model was fabricated, followed by the execution of precise vehicle-bridge coupling dynamic experiments. This phase rigorously validates the effectiveness and accuracy of the proposed moving force identification method at varying vehicle speeds. The obtained results substantiate the proposed approach's capability not only to comprehensively capture bridge response data for full-area monitoring but also to consistently and reliably identify information on moving vehicle forces. This study underscores a pioneering application of intelligent visual perception technology in the field of identifying moving forces. The introduced noncontact intelligent identification method is an effective solution for monitoring moving forces on bridges, which has a wide range of applications in the future.

Quantifying the Impact of Environment Loads on Displacements in a Suspension Bridge with a Data-Driven Approach.

Long-span bridges are susceptible to damage, aging, and deformation in harsh environments for a long time. Therefore, structural health monitoring (SHM) systems need to be used for reasonable monitoring and maintenance. Among various indicators, bridge displacement is a crucial parameter reflecting the bridge's health condition. Due to the simultaneous bearing of multiple environmental loads on suspension bridges, determining the impact of different loads on displacement is beneficial for the better understanding of the health conditions of the bridges. Considering the fact that extreme gradient boosting (XGBoost) has higher prediction performance and robustness, the authors of this paper have developed a data-driven approach based on the XGBoost model to quantify the impact between different environmental loads and the displacement of a suspension bridge. Simultaneously, this study combined wavelet threshold (WT) denoising and the variational mode decomposition (VMD) method to conduct a modal decomposition of three-dimensional (3D) displacement, further investigating the interrelationships between different loads and bridge displacements. This model links wind speed, temperature, air pressure, and humidity with the 3D displacement response of the span using the bridge monitoring data provided by the GNSS and Earth Observation for Structural Health Monitoring (GeoSHM) system of the Forth Road Bridge (FRB) in the United Kingdom (UK), thus eliminating the temperature time-lag effect on displacement data. The effects of the different loads on the displacement are quantified individually with partial dependence plots (PDPs). Employing testing, it was found that the XGBoost model has a high predictive effect on the target variable of displacement. The analysis of quantification and correlation reveals that lateral displacement is primarily affected by same-direction wind, showing a clear positive correlation, and vertical displacement is mainly influenced by temperature and exhibits a negative correlation. Longitudinal displacement is jointly influenced by various environmental loads, showing a positive correlation with atmospheric pressure, temperature, and vertical wind and a negative correlation with longitudinal wind, lateral wind, and humidity. The results can guide bridge structural health monitoring in extreme weather to avoid accidents.

Monitoring bearing damage in bridges using accelerations from a fleet of vehicles, without prior bridge or vehicle information

This paper describes a novel method for detecting bridge damage that uses a partially instrumented vehicle fleet, each vehicle being instrumented with just one accelerometer. Importantly, no prior knowledge of the bridge or individual vehicle properties is required. Firstly, a model simplification concept is proposed to calculate the displacement under the vehicle wheel from single acceleration measurements on a half-car model. Then, optimisation is used to find individual vehicle properties using simulated noisy measurements from a fleet of vehicles. Finally, accelerations from the fleet are used to find the ‘apparent profile difference’, which contains bridge deflection data. The difference is found to be independent of surface profile but dependent on vehicle axle weight differences and a moving reference influence function (MRIF). When the axle spacings and the relative axle weights are reasonably consistent in a subset of the fleet, the MRIF can be simplified into a compound MRIF. Even when the MRIF and individual axle weights are not available on-site, the shape of the compound MRIF can be determined through an iterative process and used to monitor bridge health condition. Bearing damage is represented in this paper as an increase of rotational resistance of the bearings. The numerical results show that the damage severity and location can be identified.

AI-enhanced digital inspection of bridges

Civil infrastructure inspection -and consequently maintenance- is carried out primarily through visual inspections. AI-enhanced (Artificial Intelligence) digital inspection methods, integrated with risk-based probabilistic approaches, have been promoted to keep existing structures, especially infrastructures, safe and predictable. Drones are used to obtain a significant number of images to cover the surface of a bridge, which are further integrated into a digital 3D (three-dimensional) model. According to the IFC standards (Industry Foundation Class), this 3D model is GPS-positioned (Global Positioning System) and connected to BIM (Building Information Modelling). Post-processing the accumulated data volume of all digital images is very time-consuming. For this reason, appropriate AI-based algorithms streamline this process significantly, enabling partially automated damage detection and assessment. To this end, images of various types of damage on different bridges are used to train and test the AI-enhanced models. In addition, damage identification and classification are developed. Six visually detectable defects can be identified, and theoretical models estimate the associated structural diseases. Finally, a probability-based risk assessment presents the basis for defining the criticality of the structure. With the help of digital images, it is possible to create a high-fidelity digital model and quantitative surface and spatial data records of the structural health condition of bridges and other infrastructures.

Havacılık Kompozit Malzemelerinde Mikroskobik Teknikler Kullanılarak Yapısal Sağlık İzleme Uygulamaları

Structural Health Monitoring (SHM) is a process that involves the observation and analysis of a system over time using periodically sampled response measurements to monitor changes to the material and geometric properties of engineering structures such as bridges, buildings, and aerospace composite structures. The goal of SHM is to detect changes in the structural behavior or condition that may indicate damage or degradation before a catastrophic failure occurs. SHM involves the implementation of damage detection strategies for structures of high importance. It is commonly used in civil engineering, aerospace engineering, and mechanical engineering applications to ensure the safety and reliability of structures. It improves the safety of aerospace composite structures by detecting damage at an early stage, preventing damage from occurring, improving reliability, and extending the life of the structure. SHM applications enable aircraft to spend less time on the ground and carry more passengers and cargo, thereby reducing operational costs. It can be utilized in various fields such as monitoring the health condition of aircraft tail and wing areas in the aviation industry, preventing damage and deterioration of car parts and components under operating conditions in the automotive sector, monitoring the health condition of bridges and tunnels in the transportation sector, and monitoring the health condition of wind turbines and other structures in the energy sector. Aerospace composite structures can suffer from several complex nonlinear damage modes, including impact damage, delamination, matrix cracking, fiber breakage, and voids. This study provides general and useful information on how structural health applications of aviation composites can be supported by microscopic techniques. In order to better understand the subject, an example aircraft composite structural component containing impact damage, which was mentioned above, was examined using microscopic techniques. In this investigation conducted using Stereo and Scanning Electron Microscopes (SEM), the identification of potential damage sources and the assessment of damage severity are explained in detail.

Drive‐by frequencies extraction by means of synchrosqueezed wavelet transform

AbstractBridges and viaducts are facing growing traffic, increasing loads as well as ageing and deterioration. Nowadays, vibration‐based Structural Health Monitoring (SHM) represents an effective solution to extract quantitative information regarding bridge structural condition. Bridge frequencies are fundamental parameters capable to reflect and summarize bridge dynamics and health condition. Typically, their identification is performed by direct approaches, which rely on the use of sensors installed on the structure under analysis. A cost‐efficient, movable, and flexible alternative is offered by drive‐by methods, consisting in the use of instrumented vehicles to extract bridge frequencies. This paper presents an experimental campaign carried out on a multiple‐span mixed railroad bridge, with the aim to identify its frequencies through onboard measurements. A set of MEMS wireless accelerometers is deployed on the vehicle, firstly allowing for vehicle pitch component mitigation. Vehicle accelerations were then used to extract bridge frequencies, by means of a Most Probable Modal Frequencies approach, relying on synchrosqueezed wavelet transform. At a cruise speed of 30 km/h promising results in terms of indirect frequency estimation were found, with no traffic disruption.

Extracting Bridge Frequencies from The Dynamic Responses of Moving and Non-moving Vehicles

Bridges can continuously suffer from structural deterioration due to inclement environmental and operational effects, making a timely inspection necessary to ensure the reliability and functionality of bridges. Recent progress in vehicle-bridge interactions has promoted the vehicle scanning method (VSM) for bridge frequency extraction, whereby the bridge frequency is typically identified from the dynamic response of a passing vehicle to reflect the bridge's health condition. Despite numerous endeavors, the low-speed limitation of the moving test vehicle and the adverse influence of road roughness still hinder the general application of VSM. In this regard, this paper presents a novel VSM for bridge frequency extraction by integrating moving and non-moving vehicles. By introducing the novel non-moving vehicle, the bridge vibration content becomes more obvious in the dynamic response of the moving vehicle, which is beneficial to the associated indirect bridge frequency extraction. Moreover, the non-moving vehicle is nearly free from the influence of road roughness, such that the performance of VSM for bridge frequency extraction can be enhanced against noisy real-world environments. To understand the inherent mechanism of the proposed method, a vehicle-bridge coupling system with moving and non-moving vehicles is theoretically formulated, and the analytical solutions of the coupled system are derived and numerically validated. Furthermore, several case studies are presented to comprehensively investigate key factors affecting the performance of bridge frequency extraction through the proposed method. The results indicate that incorporating a non-moving vehicle can significantly increase the extractability of bridge frequencies in vehicle responses. It becomes possible to accurately identify the first four-order bridge frequencies of a simply supported bridge (rather than the first two-order bridge frequencies using a moving vehicle exclusively) from the vehicle response after introducing a non-moving vehicle. More importantly, the adverse effect of the high-speed moving test vehicle and road roughness can be significantly alleviated by the non-moving vehicle, and therefore the proposed method becomes more robust in actual applications. Besides, further insights are provided in terms of the implementation strategies of the proposed method.

Power Self-Sustained Wireless Bridge Deformation Monitoring System Based on Solar Photovoltaic

Bridges are critical elements of contemporary civil infrastructure. The operational and environmental factors can cause inevitable impacts on the serviceability and safety of a bridge. This paper has developed a wireless bridge deformation measurement system to monitor the bridge health condition in real-time, which achieves wireless connectivity for communication. Meanwhile, a self-sustained power supply is designed based on a solar photovoltaic (PV) system, removing the conventional power cables or the frequent battery replacement operation, which reduces the installation and maintenance cost and enables a long-term 24 hours × 7 days uninterrupted operation. The detailed power supply design procedure is provided, including the selection of the solar panel and battery, as well as the design of the dc-dc converter for the constant-current (CC) and constant-voltage (CV) charging of a lithium battery. Experiments validate the effectiveness of the developed wireless bridge deformation monitoring system and the designed power supply. It is shown that without using the PV system, the bridge deformation monitoring system can last for 24 days, which helps the system to survive extreme weather conditions. With the help of the PV system, the battery is always maintained at a fully charged condition, validating the self-sustainability of the designed power supply.

LSTM approach for condition assessment of suspension bridges based on time-series deflection and temperature data

Deflection data provides important information about the mechanical characteristics and structural health condition of bridges. The study presented here pertains to development of a deep learning based approach for structural health monitoring by employing the bridge deflections. The method presented herein uses the long short-term memory (LSTM) framework in detecting the state of damage by tracking the feature changes of time-series deflection and temperature data. Deflection and temperature data of Chongqing Egongyan Rail Transit Suspension Bridge was employed over a period of 15 months to develop the proposed method. The concept of square error index (SE) is introduced as an assessment tool for estimation of the bridge damage level. Results from the present study indicated that the statistical characteristics of SE index are proportional to the level of damage, and are only sensitive to abnormal changes in deflection. Structural health monitoring data over the period of 15 months indicated that the proposed approach has the capability to detect cable damages as low as 0.5%.

Long‐term bridge performance assessment using clustering and Bayesian linear regression for vehicle load and strain mapping model

The weigh-in-motion (WIM) system and the structural health monitoring (SHM) system have been used as two separate modules playing different roles in bridge operation and providing different information for bridge maintenance. This study proposes a novel bridge safety condition assessment method that utilizes long-term monitoring data from the WIM system and the SHM system. The method uses the slope of the established vehicle load and vehicle-induced strain mapping model as the evaluation indicator for bridge condition assessment and early warning by clustering and Bayesian linear regression. The proposed method is verified with the continuous monitoring data of a concrete box girder bridge. The results show that the slope indicator of the mapping model changes with the variation of bridge performance, which is stable and can reflect the bridge state in time. The evaluation method can integrate the WIM system with the SHM system and evaluate the bridge health condition based on the correspondence between the two systems, which can make full use of the data.

Techniques for Processing Experimental Data for Structural Health Monitoring of Bridges

Reliability of transport artificial structures and transit of trains at sanctioned speed should be provided with the necessary and sufficient load-bearing capacity, strength, rigidity, and stability of engineering structures.The objective of this work was to substantiate the possibility of using well-known methods for controlling the stress-strain state of structures using automated systems of structural health monitoring of bridge spans.It is extremely important regarding operation of transport artificial structures designed according to the standards of the first half of the 20th century.Under these conditions, the experimental determination of the stress-strain state of bearing structures of bridges becomes the most important component of the task of a comprehensive assessment of physical wear and tear as well as of operational reliability of the structures. Monitoring the structural health and technical condition of bridges and planning of timely measures aimed at the repair, strengthening or reconstruction of spans will extend their service life and ensure safety during operation.Maximum permissible deflections of spans under a movable temporary vertical load have been revealed since to ensure smooth movement of vehicles it is necessary to control horizontal longitudinal and transverse displacements of the top of the bridge piers, as well as vertical settlements.The paper suggests methods of interpreting data measured by inclinometers and electric strain gauges, tensiometers to use them in an automated system for monitoring the structural health of railway bridges. The method of strain measurement is described in detail in the proposed options for installing resistance strain gauges on structures to measure tensile-compression stresses and longitudinal forces due to a temporary vertical load.Monitoring the technical condition of bridge structures, using the methods for measuring deflections and deformations proposed by the authors in this article, will make it possible to assess the change in bearing capacity of the structure over the entire period of operation. The study used regulations and experience of the Russian Federation and the Republic of Kazakhstan.

Noise Reduction for Improvement of Ultrasonic Monitoring Using Coda Wave Interferometry on a Real Bridge

Reinforced concrete bridges are iconic parts of modern infrastructure. They are designed for a minimum service life of 100 years. However, environmental factors and/or inappropriate use might cause overload and accelerate the deterioration of bridges. In extreme cases, bridges could collapse when necessary maintenance lacks. Thus, the permanent monitoring for structure health assessment has been proposed, which is the aim of structural health monitoring (SHM). Studies in laboratories have shown that ultrasonic (US) coda wave interferometry (CWI) using diffuse waves has high sensitivity and reliability to detect subtle changes in concrete structures. The creation of micro-cracks might be recognized at an early stage. Moreover, large-volume structures can be monitored with a relatively small number of US transducers. However, it is still a challenge to implement the CWI method in real SHM practical applications in an outdoor environment because of the complex external factors, such as various noise sources that interfere with the recorded signals. In this paper, monitoring data from a 36-m long bridge girder in Gliwice, Poland, instrumented with embedded US transducers, thermistors, and vibrating wire strain gauges, is presented. Noise estimation and reduction methods are discussed, and the influence of traffic, as well as temperature variation, are studied. As a result, the relative velocity variation of US waves following the temperature change with a very high precision of 10^{-4} % is shown, and a good bridge health condition is inferred. The influence of lightweight real traffic is negligible. The study verified the feasibility of the implementation of the CWI method on real bridge structures.

A New Insight to Vibration Characteristics of Spans under Random Moving Load: Case Study of 38 Bridges in Ho Chi Minh City, Vietnam

We propose a novel representative power spectrum density as a specific characteristic for showing responses of spans during a long operational period. The idea behind this method is to use the representative power spectrum density as a powerful tool to evaluate the stiffness decline of spans during their operation period. In addition, a new measurement method has been introduced to replace the traditional method of monitoring the health conditions of bridges through a periodic measurement technique. This helps to reduce costs when carrying out testing bridges. Besides, the proposed approach can be widely applied not only in Vietnam but also in many other underprivileged countries around the world. Obtained results show that, during the operational process of spans, there is not only a pure vibration evaluation such as bending vibration and torsion vibration tests but also a combination of various vibration types including bending-torsion vibration or high-level vibrations like first-mode bending and first-mode torsion. Depending on each type of structure and material properties, different types of vibrations will appear more or less during the operational process of spans under a random moving load. Furthermore, the representative power spectrum density is also suitable for evaluating and determining many different fundamental vibrations through the same measurement time as well as various measurement times.

Continuous measurement of tire deformation using long-gauge strain sensors

Measurement of tire deformation is a hot spot in the research of intelligent tire, which not only provides deep insights into the mechanism of generating tire forces and moments, but also has a significant influence on assessing the health condition of bridges. This paper proposed a tire deformation measurement method by monitoring tire hoop strain with long-gauge Fiber Bragg Grating (FBG) sensors, which can achieve real-time continuous measurement of the tire deformation by the modified conjugate beam method. Taking advantage of the FBG sensor’s high sensitivity, high durability and macro–micro, the modified conjugate beam method transforms the problem of solving the tire deformation into a more convenient solution to the bending moment of the conjugate structure. Intelligent bridge impact vehicle experiments and high-speed experiment were carried out to validate the proposed method, from which the estimated tire deformations under different wheel loads and tire pressures show good agreements with reference measurements.

Agent based routing approach to support structural health monitoring-informed, intelligent transportation system

In structural health monitoring (SHM)-informed intelligent transportation systems (ITS) system, SHM sensors can provide data on a bridge health condition for ITS applications. Where ITS uses this bridge health condition information for real-time traffic management and monitoring. Most of the SHM-informed ITS use wireless sensor network (WSN) to allow devices to coordinate and collaborate to effectively measure a structure, whether the goal is to improve spatial resolution, structural resilience, bridge traffic, or perform advanced in-situ analysis. The WSN suffers from high power consumption, yet they are generally equipped with a limited power supply and in most cases AAA batteries. Even under the most stringent power management, the sensor nodes have an unattended life of approximately a few months to a year. Towards this end, the paper proposes a multi-agent based system to augment the life time of WSN supporting SHM-informed ITS systems. The proposed agent based routing (ABR) approach consists of a mobile agent that is able to traverse the network, i.e., sensor nodes, mounted onto a bridge using multi-hop communication; collecting and aggregate the data, thus eliminating the two major causes of power consumption. These include (a) the direct transmission/broadcast from each sensor node to the sink and (b) redundant sensory data. In addition, ABR reduce much of the communication overhead and hence prolong the operational lifetime of SHM-informed ITS. Our experiment conducted on an open source simulator shows that the proposed ABR is 30% more energy efficient in comparison to the baseline, i.e., direct transmission to the sink.

Long-term health monitoring for deteriorated bridge structures based on Copula theory

Maintenance of deteriorated bridge structures has always been one of the challenging issues in developing countries as it is directly related to daily life of people including trade and economy. An effective maintenance strategy is highly dependent on timely inspections on the bridge health condition. This study is intended to investigate an approach for detecting bridge damage for the long-term health monitoring by use of copula theory. Long-term measured data for the seven-span plate-Gerber bridge is investigated. Autoregressive time series models constructed for the observed accelerations taken from the bridge are utilized for the computation of damage indicator for the bridge. The copula model is used to analyze the statistical changes associated with the modal parameters. The changes in the modal parameters with the time are identified by the copula statistical properties. Applicability of the proposed method is also discussed based on a comparison study among other approaches.

Software Agents to Support Structural Health Monitoring (SHM)-Informed Intelligent Transportation System (ITS) for Bridge Condition Assessment

In Structural Health Monitoring (SHM)-informed Intelligent Transportation Systems (ITS) system, SHM sensors can provide data on a bridge health condition for ITS applications. Where ITS uses this bridge health condition information for real-time traffic management and monitoring. Most of the SHM-informed ITS use wireless sensor network (WSN) to allow devices to coordinate and collaborate to effectively measure a structure, whether the goal is to improve spatial resolution, structural resilience, bridge traffic, or perform advanced in-situ analysis. The WSN suffers from high power consumption, yet they are generally equipped with a limited power supply and in most cases AAA batteries. Even under the most stringent power management, the sensor nodes have an unattended life of approximately a few months to a year. Towards this end, the paper proposes a multi-agent based system to augment the life time of WSN supporting SHM-informed ITS systems. The proposed agent based routing (ABR) approach consists of a mobile agent (MA) that is able to traverse the network, i.e., sensor nodes, mounted onto a bridge using multi-hop communication; collecting and aggregate the data, thus eliminating the two major causes of power consumption. These include (a) the direct transmission/broadcast from each sensor node to the sink and (b) redundant sensory data. In addition, ABR reduce much of the communication overhead and hence prolong the operational lifetime of SHM-informed ITS. Our experiment conducted on an open source simulator shows that the proposed ABR is 30% more energy efficient in comparison to the baseline, i.e., direct transmission (DT) to the sink.