Big Model Strategy for Bridge Structural Health Monitoring Based on Data-Driven, Adaptive Method and Convolutional Neural Network (CNN) Group

This study introduces an innovative“Big Model”strategy to enhance Bridge Structural Health Monitoring(SHM)using a Convolutional Neural Network(CNN),time-frequency analysis,and fine element analysis.Leveraging ensemble methods,collaborative learning,and distributed computing,the approach effectively manages the complexity and scale of large-scale bridge data.The CNN employs transfer learning,fine-tuning,and continuous monitoring to optimize models for adaptive and accurate structural health assessments,focusing on extracting meaningful features through time-frequency analysis.By integrating Finite Element Analysis,time-frequency analysis,and CNNs,the strategy provides a comprehensive understanding of bridge health.Utilizing diverse sensor data,sophisticated feature extraction,and advanced CNN architecture,the model is optimized through rigorous preprocessing and hyperparameter tuning.This approach significantly enhances the ability to make accurate predictions,monitor structural health,and support proactive maintenance practices,thereby ensuring the safety and longevity of critical infrastructure.

Review and Prospect of Research on Structural Health Monitoring Technology for Bridges

As a crucial infrastructure in the transport system,the safe operation of bridges is directly related to all aspects of people’s daily lives.The development of bridge structural health monitoring technology and its application play an important role in ensuring the safety and extending the service life of bridges.This paper carries out in-depth research and analysis on the related technology of bridge structural health monitoring.Firstly,the existing monitoring technologies at home and abroad are sorted out,and the advantages and problems of various methods are compared and analyzed,including nondestructive testing,stress measurement,vibration characteristic identification,and other commonly used monitoring technologies.Secondly,the key technologies and equipment in the bridge health monitoring system,such as sensor technology,data acquisition,and processing technology,are introduced in detail.Finally,the development trend in the field of bridge health monitoring is prospected from both theoretical research and technical application.In the future,with the development of emerging technologies such as big data,cloud computing,and the Internet of Things,it is expected that bridge health monitoring with intelligent and systematic features will be more widely applied to provide a stronger guarantee for the safe and efficient operation of bridges.

Operational modal identification of suspension bridge based on structural health monitoring system

An output-only modal identification method by a combination use of the peak-picking method and the cross spectrum methods are presented. Meanwhile, a novel mode shape optimum method of the deck is proposed. The methods are applied to the operational modal identification system of the Runyang Suspension Bridge, which can be used to obtain the modal parameters of the bridge from out-only data sets collected by its structural health monitoring system （SHMS）. As an example, the vibration response data of the deck, cable and tower recorded during typhoon Matsa excitation are used to illustrate the program application. Some of the modal frequencies observed from deck vibration responses are also found in the vibration responses of the cable and the tower. The results show that some modal shapes of the deck are strongly coupled with the cable and the tower. By comparing the identification results from the operational modal system with those from field measurements, a good agreement between them is achieved, but some modal frequencies identified from the operational modal identification system （OMIS）, such as L1 and L2, obviously decrease compared with those from the field measurements.

Structural health monitoring of long-span suspension bridges using wavelet packet analysis

During the service life of civil engineering structures such as long-span bridges, local damage at key positions may continually accumulate, and may finally result in their sudden failure. One core issue of global vibration-based health monitoring methods is to seek some damage indices that are sensitive to structural damage, This paper proposes an online structural health monitoring method for long-span suspension bridges using wavelet packet transform （WPT）. The WPT- based method is based on the energy variations of structural ambient vibration responses decomposed using wavelet packet analysis. The main feature of this method is that the proposed wavelet packet energy spectrum （WPES） has the ability to detect structural damage from ambient vibration tests of a long-span suspension bridge. As an example application, the WPES-based health monitoring system is used on the Runyang Suspension Bridge under daily environmental conditions. The analysis reveals that changes in environmental temperature have a long-term influence on the WPES, while the effect of traffic loadings on the measured WPES of the bridge presents instantaneous changes because of the nonstationary properties of the loadings. The condition indication indices VD reflect the influences of environmental temperature on the dynamic properties of the Runyang Suspension Bridge. The field tests demonstrate that the proposed WPES-based condition indication index VD is a good candidate index for health monitoring of long-span suspension bridges under ambient excitations.

Finite element model updating of existing steel bridge based on structural health monitoring

Based on the physical meaning of sensitivity,a new finite element(FE) model updating method was proposed. In this method,a three-dimensional FE model of the Nanjing Yangtze River Bridge(NYRB) with ANSYS program was established and updated by modifying some design parameters. To further validate the updated FE model,the analytical stress-time histories responses of main members induced by a moving train were compared with the measured ones. The results show that the relative error of maximum stress is 2.49% and the minimum relative coefficient of analytical stress-time histories responses is 0.793. The updated model has a good agreement between the calculated data and the tested data,and provides a current baseline FE model for long-term health monitoring and condition assessment of the NYRB. At the same time,the model is validated by stress-time histories responses to be feasible and practical for railway steel bridge model updating.

Fatigue damage reliability analysis for Nanjing Yangtze river bridge using structural health monitoring data

To evaluate the fatigue damage reliability of critical members of the Nanjing Yangtze river bridge, according to the stress-number curve and Miner’s rule, the corresponding expressions for calculating the structural fatigue damage reliability were derived. Fatigue damage reliability analysis of some critical members of the Nanjing Yangtze river bridge was carried out by using the strain-time histories measured by the structural health monitoring system of the bridge. The corresponding stress spectra were obtained by the real-time rain-flow counting method. Results of fatigue damage were calculated respectively by the reliability method at different reliability and compared with Miner’s rule. The results show that the fatigue damage of critical members of the Nanjing Yangtze river bridge is very small due to its low live-load stress level.

Structural condition assessment of long-span suspension bridges using long-term monitoring data

This paper focuses on developing an online structural condition assessment technique using long-term monitoring data measured by a structural health monitoring system. The seasonal correlations of frequency-temperature and beam-end displacement-temperature for the Runyang Suspension Bridge are performed, first. Then, a statistical modeling technique using a six-order polynomial is further applied to formulate the correlations of frequency-temperature and displacement-temperature, from which abnormal changes of measured frequencies and displacements are detected using the mean value control chart. Analysis results show that modal frequencies of higher vibration modes and displacements have remarkable seasonal correlations with the environmental temperature and the proposed method exhibits a good capability for detecting the micro damage-induced changes of modal frequencies and displacements. The results demonstrate that the proposed method can effectively eliminate temperature complications from frequency and displacement time series and is well suited for online condition monitoring of long-span suspension bridges.

Engineering approach to in-situ bridge health monitoring with fiber bragg gratings

In this presentation the feasibility and capability of fiber Bragg gratings （FBG） employed in bridge health monitoring are demonstrated on a real bridge. FBG＇ s wavelength shift depending on strain variance has been tested. The technique of FBG installation on bridges has been developed. 12 FBG strain sensors and 3 temperature sensors have been successfully embedded in the prestressed concrete box girder during the construction of Heilongjiang Hulan River Bridge. The prestressing tension process and quasi-static loading process of the girder were monitored with those sensors before it was installed onto the bridge. After the bridge was completed, the FBG sensors embedded have been utilized to monitor the strain shift of the beam under quasi-static load, traffic load and temperature. The results show that the traffic fluxes, possible tatigue damage and deflection of the bridge can be revealed conveniently through strain measurements with these FBG sensors, which provide key information for structural health diagnosis. The fact that the FBG strain sensors have withstood the ordeal of harsh construction process and lasted for more than one year proves that their durability and stability can satisfy the requirements for bridge health monitoring. It is also shown that the FBG strain sensor is more adaptive to long-term structural health monitoring than the electric resistance strain gauge.

Outlier Detection and Forecasting for Bridge Health Monitoring Based on Time Series Intervention Analysis

The method of time series analysis,applied by establishing appropriate mathematical models for bridge health monitoring data and making forecasts of structural future behavior,stands out as a novel and viable research direction for bridge state assessment.However,outliers inevitably exist in the monitoring data due to various interventions,which reduce the precision of model fitting and affect the forecasting results.Therefore,the identification of outliers is crucial for the accurate interpretation of the monitoring data.In this study,a time series model combined with outlier information for bridge health monitoring is established using intervention analysis theory,and the forecasting of the structural responses is carried out.There are three techniques that we focus on:(1)the modeling of seasonal autoregressive integrated moving average(SARIMA)model;(2)the methodology for outlier identification and amendment under the circumstances that the occurrence time and type of outliers are known and unknown;(3)forecasting of the model with outlier effects.The method was tested with a case study using monitoring data on a real bridge.The establishment of the original SARIMA model without considering outliers is first discussed,including the stationarity,order determination,parameter estimation and diagnostic checking of the model.Then the time-by-time iterative procedure for outlier detection,which is implemented by appropriate test statistics of the residuals,is performed.The SARIMA-outlier model is subsequently built.Finally,a comparative analysis of the forecasting performance between the original model and SARIMA-outlier model is carried out.The results demonstrate that proper time series models are effective in mining the characteristic law of bridge monitoring data.When the influence of outliers is taken into account,the fitted precision of the model is significantly improved and the accuracy and the reliability of the forecast are strengthened.

Development of IoT-Based Condition Monitoring System for Bridges

As of April 2019,India has 1,42,126 kilometres of National Highways and 67,368 kilometres of railway tracks that reach even the most remote parts of the country.Bridges are critical for both passenger and freight movement in the country.Because bridges play such an important part in the transportation system,their safety and upkeep must be prioritized.Manual Condition Monitoring has the disadvantage of being sluggish,unreliable,and inefficient.The Internet of Things has given structural monitoring a boost.Significant decreases in the cost of electronics and connection,together with the expansion of cloud platforms,have made it possible to collect large amounts of data remotely,aggregate it,and perform essential analysis to generate actionable insights.This research focuses on a scalable system for monitoring the state of bridges,such as vibration and loading,employing multimodal inputs,controllers,and Wi-Fi modules.The accelerometer and load cells were installed on the prototype,tested for a sample load(56.21 grams_(avg),590 grams_(max),and 147.66 grams_(rms))with induced vibration(5.87 m/sec^(2)_(avg),18 m/sec^(2)_(max),and 7.04 m/sec^(2)_(rms))that are processed,displayed on-board,and uploaded to ThingSpeak cloud service.This system will aid the maintenance personnel in remotely monitoring it.This system can send out notifications if any of these parameters exceeds their threshold value,allowing you to take preventive measures ahead of time.

大跨度斜拉桥模态参数长期追踪及其变异性分析

为了丰富大跨度斜拉桥模态参数的实测数据库,依托苏通大桥结构健康监测系统采集的数据,采用所建立的模态自动识别和追踪方法,获取了2010年期间该桥的模态参数值,并据此分析了在温度和风速作用下桥梁模态参数的变异性。研究结果表明,大桥主梁模态频率的变化受温度和风速共同影响,随着温度的升高而降低,随着风速的升高而增加。大桥主梁模态阻尼比的变异性显著大于模态频率,低风速下主梁一阶侧弯阻尼比在0.5%~15%之间波动,风速大于9 m/s时逐渐降低并稳定在2%左右。大桥主梁前四阶竖弯阻尼比受气动阻尼的影响较大,在风速较小时随着风速的增加略有增加。研究结果可为大桥的服役性能评估与运营管理提供参考。

基于EDA统计图量化的桥梁动态监测数据质量评估

探索性数据分析统计图在桥梁健康监测动态数据质量评估中已有广泛应用。为了减少人工观察统计图的主观性,通过近似度量方法实现统计图的量化分析,得到多个指标对监测数据进行快速质量评估。在运营环境激励作用下,桥梁结构动力响应具有短时线性平稳性,近似服从正态分布。以某大跨斜拉桥振动数据为研究对象,首先,绘制样本数据直方图和Q-Q图,通过观察数据分布特征预先判断数据质量,确定优、良和差3个等级。然后,分别通过KL散度和余弦相似度2种近似度量方法对样本数据直方图和Q-Q图进行量化,得到数据服从正态分布程度的指标;通过箱线图检测样本数据全局异常点,得到正常数据占比;统计分析得到量化值和先验质量等级的对应关系,确定以直方图KL散度和余弦相似度为主、以箱线图正常数据占比为辅的数据质量评估标准。最后,取部分数据为验证集,进一步验证所提方法各个指标的合理性,并给出该方法在实际工程上的应用结果。

基于InSAR技术的大跨桥梁温度变形监测研究

以国内某高速铁路钢拱桥为研究对象,选取2017—2018年期间59幅C波段Senti⁃nel-1号雷达卫星影像,利用PS-InSAR技术处理影像获得桥梁的视线向(Line of Sight,LOS)位移,根据SAR成像空间几何关系解算出支座的纵向位移.研究结果表明:支座纵向位移的时空特性与实际桥梁结构相符合,验证了PS-InSAR技术观测桥梁结构位移的可行性.建立支座纵向位移与温度的线性相关模型,并与结构健康监测系统的实测结果进行对比.两者吻合良好,相对误差控制在10%以内,验证了PS-InSAR测量桥梁结构位移的可靠性.利用有限元模拟温度作用下桥梁支座的位移变化,并与PS-InSAR位移时间序列进行对比.两者趋势基本一致,LOS向位移误差在[-10,10]mm,验证了PS-InSAR测量桥梁结构位移的准确性.

Vehicle-Bridge Interaction Simulation and Damage Identification of a Bridge Using Responses Measured in a Passing Vehicle by Empirical Mode Decomposition Method

To prevent early bridge failures, effective Structural Health Monitoring (SHM) is vital. Vibration-based damage assessment is a powerful tool in this regard, as it relies on changes in a structure’s dynamic characteristics as it degrades. By measuring the vibration response of a bridge due to passing vehicles, this approach can identify potential structural damage. This dissertation introduces a novel technique grounded in Vehicle-Bridge Interaction (VBI) to evaluate bridge health. It aims to detect damage by analyzing the response of passing vehicles, taking into account VBI. The theoretical foundation of this method begins with representing the bridge’s superstructure using a Finite Element Model and employing a half-car dynamic model to simulate the vehicle with suspension. Two sets of motion equations, one for the bridge and one for the vehicle are generated using the Finite Element Method, mode superposition, and D’Alembert’s principle. The combined dynamics are solved using the Newmark-beta method, accounting for road surface roughness. A new approach for damage identification based on the response of passing vehicles is proposed. The response is theoretically composed of vehicle frequency, bridge natural frequency, and a pseudo-frequency component related to vehicle speed. The Empirical Mode Decomposition (EMD) method is applied to decompose the signal into its constituent parts, and damage detection relies on the Intrinsic Mode Functions (IMFs) corresponding to the vehicle speed component. This technique effectively identifies various damage scenarios considered in the study.

基于气象大数据的大跨桥梁温度效应预测方法

为了提高结构健康监测的经济性,扩大其应用范围,提出了一种基于气象站大数据信息的大跨度桥梁结构温度场预测方法,从而实现轻量化和可持续性的桥梁温度场及温度变形计算.以某大跨钢拱桁架桥为研究对象,通过气象数据平台获取气象站大数据信息(包括天气、气温和风速信息),利用Elbadry等改进的凯尔别克辐射模型计算桥梁关键构件各表面受到的辐射强度,基于热交换传递理论计算结构热分析边界条件,结合有限元分析方法进行结构瞬态热分析,从而获得目标桥梁关键构件的时变温度场.温度场的计算结果与桥梁上实测温度在时间历程和结构竖向分布上均吻合良好,平均误差在3%以内.将计算得到的结构温度施加到桥梁结构整体有限元模型上,得到桥梁结构的温度变形,桥梁支座纵向位移的计算值与实测值吻合良好,平均误差在13 mm以内.验证了所提出的基于气象站大数据的桥梁结构温度场预测方法是可行的,利用该方法可进一步得到桥梁结构的温度变形.

Comparable study on typhoon and strong northern wind characteristics of the Runyang Suspension Bridge based on field tests

The strong wind characteristics of the Runyang Suspension Bridge（ RSB） including the wind speed and direction, the turbulence intensity, the turbulence integral length and power spectrum are analyzed based on measurement data from the wind environment monitoring subsystem of the structural health monitoring system （SHMS）of the RSB and field tests during strong winds. The differences between the typhoon and the strong northern wind are especially studied. It is found that the mean wind speed of the strong northern wind is a little smaller and the mean wind direction is more stable than that of the typhoon. The turbulence intensity of both the typhoon and the strong northern wind is greater than the values suggested in Chinese code, and the turbulence integral length difference between the typhoon and a strong northern wind is not clear. As for the along-wind turbulence power spectrum, the spectrum of the strong northern wind can fit the Kaimal spectrum better than that of the typhoon. The obtained results can provide measurement data for founding a strong wind characteristic database and determining the strong wind characteristic parameter values of the RSB.

Finite element model updating and validating of Runyang Suspension Bridge based on SHMS

Based on the finite element （FE） program ANSYS, a three-dimensional model for the Runyang Suspension Bridge （RSB） is established. The structural natural frequency, vibration mode, stress and displacement response under various load cases are given. A new method of FE model updating is presented based on the physical meaning of sensitivity and the penalty function concept. In this method, the structural model is updated by modifying the parameters of design, and validated by structural natural vibration characteristics, stress response as well as displacement response. The design parameters used for updating are bounded according to measured static response and engineering judgment. The FE model of RSB is updated and validated by the measurements coming from the structural health monitoring system （SHMS）, and the FE baseline model reflecting the current state of RSB is achieved. Both the dynamic and static results show that the method is effective in updating the FE model of long span suspension bridges. The results obtained provide an important research basis for damage alarming and health monitoring of the RSB.

Measurement of wind field characteristics at a long-span suspension bridge

In order to provide a reliable basis for wind resistant evaluation of a long-span suspension bridge, a structural health monitoring system is installed on a bridge in the East China Sea and the simultaneous wind data at the bridge deck and at the top of the bridge tower are recorded. The average wind speeds and directions, variations of wind speeds with height, turbulent characteristics, spatial correlation and characteristics of wind flow around the bridge deck are analyzed by using statistical methods and spectral analysis. It is found that the average wind speeds along the bridge girder are almost identical; however, the mean wind directions vary greatly at different locations. The dimensionless exponent decreases as the average wind speed increases. The measured turbulence intensities are greater than the recommended values, and the turbulence power spectrum can well fit the standard spectrum. However, the measured spectral values are considerably smaller in low frequency ranges. The mean wind speed of the wake flow decreases and the turbulence intensity increases significantly, and the spectral characteristics of the wake flow change obviously while the feature frequency of vortex shedding has not yet been observed.

自激非平稳振动数据驱动的拉索动力性能表征

跨海斜拉桥的拉索在非极端风环境下会产生自激振动,基于现代监测与数据分析技术可即时把握拉索自激振动的数字特征,并以此反映拉索的实时动力性能。根据某跨海大桥主航道斜拉桥拉索振动加速度长期监测数据中的共性特征,提出基于振动加速度时间序列信号上包络线高斯混合模型和频域功率谱的拉索风致自激振动非平稳段自动提取方法。提出基于各自激振动非平稳时间序列进行主导频率识别,并采用带通滤波后的最后1个下降段数据进行阻尼比识别的策略,排除了振动幅值上升段环境风自然激励带入能量对阻尼比识别的干扰。基于各自激振动非平稳段主导频率-阻尼比的识别结果,通过对频率值进行聚类,得到各阶模态对应的模态频率-阻尼比数据簇。根据阻尼比数据的离散、偏态特征提出采用对数正态分布模型的e^(μ)和其累积分布函数的分位值来描述拉索阻尼比统计规律。采用各数据簇的频率质心以及阻尼比概率特征参数作为表征拉索动力性能当前状态的指标。针对背景工程的主要结论包括:桥梁拉索振动加速度信号噪声强、干扰大,在动力特征分析时须排除类似干扰;桥梁拉索的自激振动加速度幅值最高已超过3000 mm/s^(2),振动幅度较大;桥梁拉索的阻尼比平均水平约为0.03%,与设计规范推荐值相比偏低。

高速铁路桥梁车致加速度响应监测数据分类方法研究

为提高不同列车过桥时基于车致加速度响应的桥梁结构损伤识别准确性,提出了一种基于加速度传感器的高速铁路桥梁车致加速度响应监测数据分类方法。该方法根据桥梁结构健康监测系统中加速度传感器监测数据幅值的变化趋势,在监测数据时程曲线中确定2个标记点,将标记点对应的时间分别作为列车抵达和驶离传感器的近似时间,然后通过2个不同位置加速度传感器的标记点识别出高铁列车的相对车速、行驶方向和编组数量,并据此对桥梁结构车致加速度响应监测数据进行分类。将该方法应用于商合杭客专裕溪河特大桥健康监测系统中,实现了对不同列车荷载作用下的桥梁结构车致加速度响应监测数据的程序化自动分类,识别出的列车编组数量和行驶方向与现场视频监控结果一致。