Intelligent Diagnosis of Highway Bridge Technical Condition Based on Defect Information

In the bridge technical condition assessment standards,the evaluation of bridge conditions primarily relies on the defects identified through manual inspections,which are determined using the comprehensive hierarchical analysis method.However,the relationship between the defects and the technical condition of the bridges warrants further exploration.To address this situation,this paper proposes a machine learning-based intelligent diagnosis model for the technical condition of highway bridges.Firstly,collect the inspection records of highway bridges in a certain region of China,then standardize the severity of diverse defects in accordance with relevant specifications.Secondly,in order to enhance the independence between the defects,the key defect indicators were screened using Principal Component Analysis(PCA)in combination with the weights of the building blocks.Based on this,an enhanced Naive Bayesian Classification(NBC)algorithm is established for the intelligent diagnosis of technical conditions of highway bridges,juxtaposed with four other algorithms for comparison.Finally,key defect variables that affect changes in bridge grades are discussed.The results showed that the technical condition level of the superstructure had the highest correlation with cracks;the PCA-NBC algorithm achieved an accuracy of 93.50%of the predicted values,which was the highest improvement of 19.43%over other methods.The purpose of this paper is to provide inspectors with a convenient and predictive information-rich method to intelligently diagnose the technical condition of bridges based on bridge defects.The results of this research can help bridge inspectors and even non-specialists to better understand the condition of bridge defects.

Dynamic behavior of bridge-erecting machine subjected to moving mass suspended by wire ropes

The dynamic behavior of a bridge-erecting machine, carrying a moving mass suspended by a wire rope, is investigated. The bridge-erecting machine is modelled by a simply supported uniform beam, and a massless equivalent ＂spring-damper＂ system with an effective spring constant and an effective damping coefficient is used to model the moving mass suspended by the wire rope. The suddenly applied load is represented by a unitary Dirac Delta function. With the expansion method, a simple closed-form solution for the equation of motion with the replaced spring-damper-mass system is formulated. The characters of the rope are included in the derivation of the differential equation of motion for the system. The numerical examples show that the effects of the damping coefficient and the spring constant of the rope on the deflection have significant variations with the loading frequency. The effects of the damping coefficient and the spring constant under different beam lengths are also examined. The obtained results validate the presented approach, and provide significant references in the design process of bridgeerecting machines.

Seismic fragility analysis of bridges by relevance vector machine based demand prediction model

A relevance vector machine(RVM)based demand prediction model is explored for efficient seismic fragility analysis(SFA)of a bridge structure.The proposed RVM model integrates both record-to-record variations of ground motions and uncertainties of parameters characterizing the bridge model.For efficient fragility computation,ground motion intensity is included as an added dimension to the demand prediction model.To incorporate different sources of uncertainty,random realizations of different structural parameters are generated using Latin hypercube sampling technique.Mean fragility,along with its dispersions,is estimated based on the log-normal fragility model for different critical components of a bridge.The effectiveness of the proposed RVM model-based SFA of a bridge structure is elucidated numerically by comparing it with fragility results obtained by the commonly used SFA approaches,while considering the most accurate direct Monte Carlo simulation-based fragility estimates as the benchmark.The proposed RVM model provides a more accurate estimate of fragility than conventional approaches,with significantly less computational effort.In addition,the proposed model provides a measure of uncertainty in fragility estimates by constructing confidence intervals for the fragility curves.

Design and Research of Class 900 t Railway Box-girder Bridge Erecting Machine

In this article, the current railway box girder bridge erecting machines at home and abroad are briefly introduced and analyzed, the research & design situation of class 900t railway box girder bridge erecting machines is described, and also the principle for determining the overall plan and a series of issues much concerning the design of key components of class 900t railway box girder bridge erecting machines are described.

Structural Damage Identification System Suitable for Old Arch Bridge in Rural Regions: Random Forest Approach

A huge number of old arch bridges located in rural regions are at the peak of maintenance.The health monitoring technology of the long-span bridge is hardly applicable to the small-span bridge,owing to the absence of technical resources and sufficient funds in rural regions.There is an urgent need for an economical,fast,and accurate damage identification solution.The authors proposed a damage identification system of an old arch bridge implemented with amachine learning algorithm,which took the vehicle-induced response as the excitation.A damage index was defined based on wavelet packet theory,and a machine learning sample database collecting the denoised response was constructed.Through comparing three machine learning algorithms:Back-Propagation Neural Network(BPNN),Support Vector Machine(SVM),and Random Forest(R.F.),the R.F.damage identification model were found to have a better recognition ability.Finally,the Particle Swarm Optimization(PSO)algorithm was used to optimize the number of subtrees and split features of the R.F.model.The PSO optimized R.F.model was capable of the identification of different damage levels of old arch bridges with sensitive damage index.The proposed framework is practical and promising for the old bridge’s structural damage identification in rural regions.

ML and CFD Simulation of Flow Structure around Tandem Bridge Piers in Pressurized Flow

Various regions are becoming increasingly vulnerable to the increased frequency of floods due to the recent changes in climate and precipitation patterns throughout the world.As a result,specific infrastructures,notably bridges,would experience significant flooding for which they were not intended and would be submerged.The flow field and shear stress distribution around tandem bridge piers under pressurized flow conditions for various bridge deck widths are examined using a series of three-dimensional(3D)simulations.It is indicated that scenarios with a deck width to pier diameter(Ld/p)ratio of 3 experience the highest levels of turbulent disturbance.In addition,maximum velocity and shear stresses occur in cases with Ld/p equal to 6.Results indicate that increasing the number of piers from 1 to 2 and 3 results in the increase of bed shear stress by 24%and 20%respectively.Finally,five machine learning algorithms,including Decision Trees(DT),Feed Forward Neural Networks(FFNN),and three Ensemble models,are implemented to estimate the flow field and the turbulent structure.Results indicated that the highest accuracy for estimation of U,and W,were obtained using AdaBoost ensemble with R2=0.946 and 0.951,respectively.Besides,the Random Forest algorithm outperformed AdaBoost slightly in the estimation of V and turbulent kinetic energy(TKE)with R2=0.894 and 0.951,respectively.

A Novel Half-Bridge Power Supply for High Speed Drilling Electrical Discharge Machining

High Speed Drilling Electrical Discharge Machining (HSDEDM) uses controlled electric sparks to erode the metal in a work-piece. Through the years, HSDEDM process has widely been used in high speed drilling and in manufacturing large aspect ratio holes for hard-to-machine material. The power supplies of HSDEDM providing high power applica-tions can have different topologies. In this paper, a novel Pulsed-Width-Modulated (PWM) half-bridge HSDEDM power supply that achieves Zero-Voltage-Switching (ZVS) for switches and Zero-Current-Switching (ZCS) for the dis-charge gap has been developed. This power supply has excellent features that include minimal component count and inherent protection under short circuit conditions. This topology has an energy conservation feature and removes the need for output bulk capacitors and resistances. Energy used in the erosion process will be controlled by the switched IGBTs in the half-bridge network and be transferred to the gap between the tool and work-piece. The relative tool wear and machining speed of our proposed topology have been compared with that of a normal power supply with current limiting resistances.

Experimental investigation of damage identification for continuous railway bridges

Considering the issue of misjudgment in railway bridge damage identification, a method combining the step- by-step damage detection method with the statistical pattern recognition is proposed to detect the structural damage of a railway continuous girder bridge. The whole process of damage identification is divided into three identification sub- steps, namely, damage early warning, damage location, and damage extent identification. The multi-class pattern clas- sification algorithm of C-support vector machine and the regression algorithm of c-support vector machine are engagedto identify the damage location and damage extent, respectively. For verifying the proposed method, both of the pro- posed method and the optimization method are used to deal with the measured data obtained from a specific railway continuous girder model bridge. The results show that the proposed method can not only identify the damage location correctly, but also obtain the damage extent which is consistent with the experimental results accurately. By uncou- pling finite element analysis and damage identification, normalizing the index, and seeking the separation hyper plane with maximum margin, the proposed method has more favorable advantages in generalization and anti-noise. As a re- sult, it has the ability to identify the damage location and extent, and can be applied to the damage identification in real bridge structures.

跨线转体桥施工抗倾覆技术研究现状及展望

在我国交通强国战略背景下,伴随公共交通建设力度的进一步提升,交叉线路变得越来越频繁。在跨越既有铁路开展桥梁工程建设时,为不影响铁路线路的正常运营,大多选用桥梁转体施工方案。为保障转体桥梁施工的安全,亟需系统梳理和总结桥梁转体施工抗倾覆难点及现有抗倾覆关键技术。通过调研国内外平转型转体桥工程实例及对相关文献进行分析与研究,分别从桥梁结构不平衡因素、转体结构所受外荷载影响及转体桥梁的施工工艺三方面进行研究,分析现有跨线转体桥梁施工技术抗倾覆难点,结合当前最新研究成果及较为先进的施工工法,总结专家学者提出的桥梁转体施工抗倾覆关键技术。最后对桥梁转体施工抗倾覆新技术进行展望,提出基于北斗技术下桥梁转体姿态实时动态监测技术与基于机器学习算法下,对转体桥梁的动态位移及结构损伤快速且精确识别的构思,为平转型桥梁转体施工抗倾覆研究的进一步发展提供了一定的研究思路,对平转型桥梁转体工程建设抗倾覆具有一定参考与借鉴意义。

基于声发射的钢桥面板焊接气孔缺陷在线识别

为实现正交异性钢桥面板机器人智能化焊接过程中缺陷的在线监测,提出了一种基于快速傅里叶变换和支持向量机的气孔缺陷声发射识别方法.通过开展机器人焊接实验,揭示了钢桥面板焊接及缺陷产生过程的声发射特征.无损伤与气孔缺陷2种工况信号的幅值、振铃计数、峰值频率和中心频率等参数重叠交叉严重、相关性不显著,而气孔缺陷信号的傅里叶频谱存在更多高频能量分布,因此以频谱为输入建立2种工况的径向基核支持向量机模型.实验结果表明,与朴素贝叶斯、随机森林和线性核支持向量机模型相比,径向基核支持向量机模型拥有更高的正确率(95.4%)和召回率(94.3%),能够用于焊接过程气孔缺陷的在线识别,具有较强的鲁棒性和实用性.

基于改进PSO-SVM法的斜拉桥可靠度分析

对于斜拉桥结构体系复杂、结构功能函数难以显现等问题导致实际应用中往往难以准确、高效地评估斜拉桥的可靠性,本文提出了基于改进PSO-SVM(particle swarm optimization-support vector machine)的可靠度分析方法。该方法通过引入非线性递减惯性权值和异步线性变化的学习因子2种策略的粒子群算法,其目的在于提高全局的搜索能力并对支持向量机参数进行优化,从而得到挠度钢混组合梁跨中位移超限失效和单根斜拉索强度失效的隐式功能函数代理模型,结合Monte-Carlo对其抽样获取概率分布及统计参数,并进一步求解可靠度指标。通过算例比较,该方法在整体计算时长和精度方面表现出较好的效果,相比于传统方法有明显的优势。采用该方法对银洲湖大桥进行可靠度分析,结果显示:在汽车荷载作用下,主梁跨中位移超限失效的斜拉桥可靠度指标为4.203,各个斜拉索强度失效的可靠度指标为4.623~5.812,均满足规范要求;斜拉索的弹性模量和容重分别对跨中位移超限失效和斜拉索强度失效的斜拉桥可靠度指标影响最大,并且它们的变量均值与可靠度指标基本呈线性正相关。主梁跨中位移超限失效的斜拉桥可靠度指标随着斜拉索弹性模量均值系数的增大而降低、斜拉索41#强度失效的斜拉桥可靠度指标随着斜拉索容重均值系数的增大而下降。

基于异构集成模型的连续刚构桥预拱度预测

预拱度在大跨度悬臂桥梁的施工线形监控中扮演着重要角色,提高预测精度能够确保施工阶段和成桥状态的线形尽可能符合设计要求。为获得更好的预测性能,本文提出了一种基于自适应集合加权的SSA-BPNN-RF(sparrow search algorithm-back propagation neural network-random forest)异构集成模型。该模型利用不同算法之间的协作来提高预测性能,为了验证该模型的可行性,将训练好的模型应用于湖南某连续刚构桥预拱度预测,并与BPNN、RF、BPNN-RF、SSA-BPNN和SSA-RF 5种预测模型进行对比。研究结果表明:SSA-BPNN-RF异构集成模型在平均绝对误差、均方根误差和拟合度等评价指标上表现最佳。此外,BPNN-RF集成和SSA分别对BPNN和RF都有积极的影响,进一步验证了异构集成的有效性。因此,SSA-BPNN-RF异构集成模型具有高精度和更好的适应性,在工程实践中具有重要的指导意义。

基于机器学习的堵漏颗粒粒径推荐方法

井漏是油气勘探领域的重大技术难题。桥接堵漏是最常用的堵漏技术手段,其中架桥颗粒粒径是关键参数,直接影响堵漏成败,目前架桥颗粒粒径的选择主要依赖经验,缺乏科学有效的方法。研究了一种基于机器学习算法的堵漏颗粒粒径推荐方法。该方法基础数据为塔里木盆地库车山前区域126口完钻井的测井、录井及防漏堵漏施工数据,其输入层为基于皮尔森算法筛选出的23项主要参数,输出层为0~750μm、750~1 500μm、1 500~4 000μm、4 000μm以上等4个架桥颗粒粒径区间。训练测试了10种常用的机器学习算法在测井数据、录井数据及测井+录井数据等三类数据集上的准确率,测井+录井数据集上各算法得分普遍高于测井和录井数据集。在测井+录井数据集上,支持向量机和极限随机树算法的F1得分最高,达到0.9以上。基于支持向量机和极限随机树算法的架桥颗粒粒径推荐模型在库车山前一口井上验证2井次,两种算法模型的架桥颗粒粒径预测结果与现场实际堵漏效果一致,在桥堵粒径级配科学优选上具有良好的应用前景。

超宽公路架桥机优化设计与应用:以贵州省新平河特大桥为例

针对在超宽梁架设过程中,由于桥墩的墩顶直径较小,使得前支腿间距过窄,横梁会与架桥机前支腿产生干涉,并且现有架桥机无法满足喂梁和架设要求这一问题,提出了超宽公路架桥机前支腿内收开合的设计方案。通过理论分析,三维建模以及有限元分析的方法,提出了架桥机双前支腿独立运动方案,将架桥机前支腿由传统的纯箱式结构改造为具有主支腿,液压升降支腿,副支腿的新型前支腿结构,通过前支腿的内收可以使架桥机前支腿架设在普通直径的桥墩上;通过前支腿开合结构设计,可以使超宽梁通过前支腿,不造成干涉。成功解决贵州省钢-混桥梁实际施工建设中的技术难点,实现了超宽连续超宽钢主梁的整孔高效架设,并以贵州省都匀—安顺高速公路新平河特大桥铺设为例,进行了有限元分析与现场应力、挠度监测,验证了所提出架桥机的结构安全性能,为超宽公路架桥的应用提供参考。

基于域矩阵因子分解机的点击通过率预估增强网络

有效的特征交互,对于工业推荐系统中点击通过率(click-through-rate,CTR)预估的准确性起着至关重要的作用。以往并行结构的CTR预估模型通过将独立的浅层模型和深层模型并行连接,以此来学习特征的低阶交互和高阶交互。但是,这些模型存在浅层模型准确性低、未考虑特征交互时的多语义问题、参数过多、深层模型过度泛化等问题。基于上述问题,提出了一种基于域矩阵因子分解机的点击通过率预估增强网络,通过引入域矩阵优化浅层模型中的交互,提高运算效率,并在深层模型的DNN层与层之间增加了桥接模块,在每层高阶交互后增强对原始特征的记忆能力,将浅层模型和深层模型的结果相加并归一化得到预测值。该模型在Criteo、KKBox、Frappe和MovieLens数据集上进行了大量实验,展现了优秀的预测能力。

基于机器学习的砂浆流变特性预测

砂浆流变性除了与混合料成分特性和配合比设计相关外,还随胶凝材料混合时间的长短而发生改变。为研究上述因素对砂浆流变性能的影响,采用流变仪获得4个不同时段、30种不同配合比下砂浆的塑性黏度与屈服应力,并对得到的120组流变性能数据进行数据清洗等处理分析工作。接着通过支持向量回归、K-邻近回归和随机森林回归3种机器学习算法,以水泥含量、机制砂、粉煤灰、石灰石矿粉、减水剂、水、砂浆混合后时间、水灰比、骨胶比以及水胶比等参数作为自变量,塑性黏度与屈服应力作为因变量,对砂浆的流动性能进行学习预测。最终结果是支持向量回归算法对砂浆的塑性黏度与屈服应力预测准确率最高,预测结果的平均绝对误差、均方根误差、平均绝对百分比误差以及决定系数均优于其他模型,拥有更好的泛化能力,在预测领域中具有良好的适用性。通过时间效应分析,得到了不同组分对水泥砂浆流变性能的重要系数,其中减水剂、水泥、砂、水对于砂浆的流变性能影响比较显著。最后使用支持向量回归对具有较大特征重要性的变量(水泥、机制砂以及减水剂)进行单一特征分析,通过改变单一变量得到了该变量对砂浆流变性能的影响曲线。

基于高光谱成像的桥梁混凝土表面露筋病害识别

桥梁作为交通关键节点,承担与日俱增的交通流量压力,相当一部分桥梁尚未达到设计使用年限就出现较多的病害,技术状况不容乐观。高光谱成像运用光电技术检测物体对光谱波段信号的辐射和吸收情况,将该信号转换成图像和图形,可基于吸收峰的位置和强度分析被测物体的物理性质和物质组成,因此本文提出基于高光谱成像的桥梁混凝土表面露筋病害识别方法。利用线阵高光谱相机集成匀速步进滑轨装置,形成高光谱成像测试系统,采集桥梁混凝土表面露筋病害图像;基于桥梁露筋病害高光谱图像谱线与空间特征,结合预处理——平滑滤波-多元散射校准(Savizky-Golay-Multivariate scattering calibration,SG-MSC)、特征空间变换——光谱导数法(First derivative,FD)、特征变量选择算法——竞争自适应重加权抽样(Competitiveadapativereweighted sampling,CARS),将原始光谱曲线数据经特征空间转换提取相应特征值并显示波段;以光谱曲线特征向量构建数据集,基于支持向量机形成露筋病害识别预测模型。以某跨江大桥为例,以高光谱成像测试系统对实际桥梁混凝土露筋病害进行识别,将原始光谱数据经平滑特征空间变换与特征提取后放大差异,将254个波段数据维度降低到23个波段数据,模型预测精度达到94.6%,对比可见光成像高光谱成像具有更高维度信息可有效表征物质属性,表明高光谱成像对复杂表面环境下的桥梁病害识别具有可行性和广泛应用前景。

桥梁面相学及其研究进展

为了探索更加实效、经济、便捷、可信的桥梁安全状态检(监)测新方法,受中医望、闻、问、切诊断人体健康状态理念启迪,提出了依据桥梁外观形态变化来获知结构近期安全状态的桥梁面相学;总结了10多年来基于桥梁面相学的桥梁安全状态检(监)研究进展;介绍了基于定点相机平转+竖转拍摄的桥梁动静影像全息性态监测系统、基于激光雷达+全景数码相机拍摄的WWWQ-G桥梁安全巡检车、基于普通摄像头拍摄的常规跨径桥梁安全监测系统和基于定点旋转测量装置的拉索性态远距全域视频检测系统的构成理论,以及各系统应用于桥梁构件损伤检测的试验研究案例和实际工程应用案例;展望了融合“测点传感器+机器视觉”实现桥梁结构状态的“精+密”监测方法及其应用前景。

蜂窝梁一体化架桥机力学性能研究

蜂窝梁一体化架桥机作为全预制装配式桥梁的重要施工机械,使用期间结构的静动力性能是影响一体化安装施工的重要因素.为揭示其静动力性能,分别采用了应变传感器,基于数字图像相关(DIC)技术的光电图像测量仪对关键截面的应变、挠度进行监测,并对结构的强度、刚度进行分析评估.采用简单移动平均法提取结构的动位移,并进行动力特性分析.此外,建立了结构主梁的有限元模型,并将其分析结果与监测结果进行对比.研究结果表明:有限元分析结果与实测结果一致,验证了有限元分析的准确性,两者均证明了其强度及刚度满足规范要求.基于动位移数据采用峰值拾取法能够有效识别架桥机的自振频率,有限元计算的一阶自振频率为4.08 Hz,相对于实测分析结果的最大误差仅为0.73%.

基于机器视觉的大跨长联桥上无缝线路小阻力扣件纵向服役状态监测研究

以福厦高铁渔溪特大桥为例,提出一种基于机器视觉的小阻力扣件纵向服役状态监测方案,以获取大跨长联桥上无缝线路钢轨纵向变形与复合垫板窜出的时变特征;同时,结合梁轨温度与梁端位移测试结果,分析梁体温度、钢轨温度、梁端累积位移、梁轨相对位移与垫板窜出量之间的相关性。研究结果表明:根据图像识别结果,钢轨在监测阶段将随温度变化产生不同方向的伸缩,且钢轨位移略大于垫板窜出量。钢轨昼夜温差要显著大于桥面气温以及连续梁梁内气温、顶板温度、腹板温度,且梁体温度变化幅度显著比钢轨的小,其原因在于钢轨的比热容较小,在同等热量输入输出时产生的温度变化幅度较大。梁端纵向位移随温度变化幅度较小,最大日位移为0.15 mm;在监测周期内,梁端累积位移呈波动减小趋势,即梁体发生了缓慢收缩,其原因在于夏季到秋季时气温逐渐降低,且最大平均位移变化速率为0.09 mm/d。梁体温度、钢轨温度、梁端累积位移、梁轨累积相对位移和垫板窜出量之间的相关系数均大于0.8,说明其相关性较大,且均呈较好的正相关关系。通过基于机器视觉的小阻力扣件状态监测方法,可见小阻力扣件在福厦高铁渔溪特大桥区段具有较好的纵向服役状态,且监测周期内线路状态均正常,验证了此类方案在小阻力扣件现场监测中的适用性。