基于稀疏重构编码的图像检索算法

针对现有方法在哈希函数构造过程中没有考虑数据的稀疏结构,提出了一种基于稀疏重构的哈希函数学习方法。利用相似点的l_(21)范数对重构系数进行了稀疏约束,以增强局部保持映射过程中的判别性,并构建拉普拉斯矩阵进行局部邻域关系的约束,在调和协方差矩阵和最小化数据的重构误差间建立了一种平衡机制。从特征所在的空间与经映射后的汉明空间的可判别性角度出发,对哈希函数构造过程中的内在要求和约束同时进行了考虑并综合权衡。采用公共图像检索数据集Caltech-256进行实验,实验结果表明:32位编码长度时,本文算法的检索精度比其他无监督的深度哈希算法至少提高了4.69%。     

基于残余力向量法的桁架结构损伤识别

提出一种基于残余力向量理论的桁架结构损伤识别方法。先由灵敏度分析求出桁架结构刚度联系矩阵,再由刚度联系矩阵将损伤后的刚度摄动矩阵展开成对角矩阵,结合残余力向量方程得出由刚度联系矩阵表示的新的残余力向量方程。由新方程可以得到各杆单元刚度的改变量,即可识别出桁架结构的受损杆单元位置及其损伤程度。最后以某桁架结构模型进行数值仿真分析。分析结果表明,该方法具有计算简单,计算量小等优点,仅需要损伤后第一阶模态参数,就可以识别出结构的损伤情况,并且测量精度较高,对于实际工程具有一定指导意义。     

基于柔度矩阵主对角斜率的结构损伤识别方法

基于柔度矩阵的结构损伤识别指标可以有效识别结构损伤,且敏感性优于模态振型及频率类指标。本文提出基于柔度矩阵主对角元素斜率的两个新损伤识别指标:柔度矩阵斜率差(FSD)和柔度矩阵差斜率(FDS),通过提取损伤前后结构柔度矩阵主对角线斜率差值的与柔度差矩阵主对角线元素斜率差得到。通过简支梁和连续梁算例,在不同工况下对新指标识别效果进行验证。研究结果表明:FSD指标和FDS指标可以精确识别简支梁和连续梁损伤的发生,有效定位损伤,定性反映损伤程度。FDS相对于FSD识别结果更稳定,损伤识别效果更好,对快速判定损伤发生、定位最危险点具有一定优势。     

未知输入下基于响应重构的结构损伤识别

本文提出一种基于响应重构和遗传算法相结合的结构损伤识别方法,在状态空间域内,输入未知、输出数据不完整情况下对结构进行损伤位置和程度的研究。该方法直接采用结构测量动力响应作为损伤指标,利用少数已知测量响应,通过状态空间域内马尔科夫系数组成的传递矩阵来重构其他目标位置的动力响应,采用重构目标位置响应和测量响应的差值构建遗传优化算法的目标函数,对未知输入、少数测点输出情况下的结构进行损伤识别。悬臂梁的数值算例和试验结果表明,在结构单损伤、多损伤以及均匀损伤情况下,同时考虑一定测量噪音水平,该方法仍能准确重构目标位置的动力响应和识别结构的损伤位置及大小,验证了该方法的正确性和有效性。     

合成孔径压缩感知超声成像中的高效能稀疏字典设计

针对目前常见的稀疏字典缺乏针对性,在合成孔径医学超声成像中的应用效果不佳,难以在低压缩率下保证重构图像质量的问题,本文设计了一种高效能的稀疏字典。根据超声回波信号是由发射脉冲信号经过不同延时衰减后叠加的特点,利用发射脉冲作为基函数构造稀疏字典,回波信号在该稀疏字典确定的变换域中具备很好的稀疏性,理论上能使其稀疏表示系数的稀疏度等于超声阵元接收到的反射回波数。通过FieldⅡ对简单点目标和复杂目标的仿真结果表明:在相同的重构算法和压缩率下该稀疏字典重构的平均绝对误差明显小于常见的稀疏字典,其值仅为DWT的几分之一,DFT和DCT的几十分之一,能让回波信号以更低的压缩率实现相同的恢复效果。本文最后使用体模的实际采集数据对算法的实际效果进行检测,实验结果也与仿真结果基本一致。基于该稀疏字典的压缩感知算法可以进一步减少合成孔径成像所需存储的数据量、降低系统的复杂度。     

残余力向量矩阵变化率的损伤诊断法

为降低损伤诊断时模态数据不完备对损伤识别结果精度的影响,提出一种运用残余力向量矩阵变化率的损伤检测法。采用缩聚法对结构自由度进行缩减,并推导出结构自由度缩聚后的残余力向量表达式。通过利用结构损伤前、后的前几阶模态参数计算出受损结构的残余力向量变化率矩阵,取变化率矩阵每行元素最大值的绝对值作为改进的残余力向量。算例研究表明:在考虑随机噪音的影响下,无论单处损伤还是多处损伤该方法的损伤识别结果精度均高于传统的残余力向量法。验证了该方法具有良好的损伤定位性能和鲁棒性,其损伤识别结果可靠性高,具有较高的实际应用价值。     

基于时域方法的结构状态评估

应用两阶段识别方法,对结构状态进行评估。第一阶段,利用结构不完备测量信息,对结构外荷载进行识别,基于识别的外荷载重构结构时程信息。第二阶段,利用测量时程和重构时程,基于时域灵敏度方法,对结构损伤识别。应用IIRS模型缩聚方法,将8层砌体结构缩聚成8个自由度的剪切型模型。在数值仿真计算中,基于砌体结构的不完备地震时程响应记录,对地震荷载进行识别,并对结构损伤状况进行评估。结果证明,即使在有噪声的情况下,提出的结构状态方法依然能够很好的重构结构响应,并能识别地震荷载和结构损伤程度、位置,较好的计算出损伤程度。     

基于数据融合的张弦桁架损伤识别方法与试验研究

针对张弦桁架采用单损伤指标识别损伤位置易受到干扰甚至产生误判的问题,提出基于曲率模态差和模态柔度差曲率融合的损伤识别方法。基于D-S证据矩阵和加权平均两种数据融合准则,建立张弦桁架损伤识别的单次融合和两阶段融合识别流程。采用有限元软件ANSYS建立张弦桁架分析模型,利用减小构件截面积模拟弦杆损伤,分别采用非融合单损伤指标、单次数据融合和两阶段融合方法进行损伤识别分析。结果表明：单损伤识别指标的抗干扰能力较低,尤其对支座附近下弦杆的识别效果差;基于数据融合的损伤识别方法能够综合多种指标损伤识别结果,有效提高损伤位置识别的准确性;与加权平均数据融合准则相比,基于D-S证据矩阵准则的数据融合方法更能有效降低非损伤位置干扰,识别效果更好;两阶段融合方法效果优于单次融合方法,损伤位置的损伤概率愈发接近于1,非损伤位置的损伤概率愈发趋近于0。最后开展了一榀张弦桁架模型的损伤识别试验,通过试验验证了当所获取模态数据受到环境或测试噪声等因素影响下,文章提出的基于数据融合的损伤识别方法仍具有较好的鲁棒性,能够有效识别实际张弦桁架结构的损伤位置。但由于曲率模态差以及模态柔度差曲率难以识别损伤程度,因此文章方法仅能够提高损伤位置的识别精度。     

基于高频压电阻抗信号的钢制薄板损伤识别研究

为了利用机电阻抗技术(EMI)来实现结构的损伤识别,并考虑外部温度环境的影响。通过获取的压电阻抗信号并经过压电阻抗分析技术得到了结构的高频振动信息,从而达到识别结构损伤的目的。利用该技术对钢制薄板进行了损伤识别的试验研究,并采用电阻抗实部的协方差(Covariance)作为损伤指标定量地识别了损伤的严重程度和损伤的扩展。试验研究表明,利用机电阻抗技术能够很好地识别结构的损伤。进一步的研究还表明,该技术不受外部温度环境的影响,可以实现结构损伤的实时在线监测。     

基于ARMAX模型和稀疏正则化的结构损伤识别方法

结构健康监测系统对于保障工程结构安全具有重要意义,而结构损伤识别方法是结构健康监测系统的关键组成部分。本文提出一种基于时间序列ARMAX模型和稀疏正则化的结构损伤识别方法。首先,建立与结构运动方程对应的ARMAX模型,并利用模型自回归系数提取结构的固有频率和振型;然后,将提取的结构模态参数作为损伤敏感特征,构建损伤识别求解方程;最后,结合结构损伤的稀疏特性,使用稀疏正则化算法对方程进行求解,由解向量中的非零元素可得结构损伤的位置和程度。进行了一个六层集中质量剪切结构试验,试验结果表明该方法可以准确识别出结构中损伤的位置和程度,与传统损伤识别方法相比,该方法有效提高了损伤识别的精度。     

基于信号处理技术的ITS数据压缩方法与应用

当前智能交通系统(ITS)数据采集技术的飞速发展所引发的ITS数据海量特性,将严重妨碍数据在交通系统内的存储、传输和发布。在ITS数据自身特征分析的基础上,利用信号处理领域中的小波变换、离散余弦变换、量化和编码技术,通过设计适当的特征抽取阈值和量化器,提出了有限失真条件下(以一定的失真为代价)的高效ITS数据压缩与重构方法。压缩的出发点是在控制失真度的前提下,尽可能多的保留有用信息。通过对北京市三环路上的交通流数据进行测试,表明采用本文提出的数据压缩方法与常用的无损压缩方法(WinZip软件)相比,能够将文件的压缩幅度相对提高61.92%,且重构数据中与原始数据差值大于1的记录仅占1.27%,证明在有限的失真度前提下压缩效果得到明显改善。     

桁架结构损伤识别的数据融合方法研究

以数据融合技术进行桁架结构的单损伤和多损伤识别。通过研究基于频率的结构损伤理论,分析归一化的频率和损伤位置的关系;利用小波概率神经网络的算法对决策融合进行修正,建立基于小波概率神经网络的数据融合结构损伤识别模型。运用结构计算软件计算了一典型桁架结构的频率,并融合为小波概率神经网络算法的输入特征向量,并对桁架算例模型结构进行损伤识别。通过桁架不同位置的损伤情况,验证该方法的有效性,并提出工程应用中应注意的问题。研究结果表明,基于小波概率神经网络算法的数据融合技术是一种比较可靠的损伤识别方法,具有良好的工程应用前景。     

基于最小秩方法的结构损伤识别

针对结构损伤识别中的最小秩方法存在的问题,经过研究发现,对测试模态进行关于质量矩阵的正交归一化可保证反演后刚度矩阵的对称性;提出了一种迭代修正算法,可保持反演结果的稀疏性;基于模态力余量,定义了一种损伤指标来预先判定结构损伤单元的位置,并可据此选取合适的测试模态阶数进行反演计算。数值试验结果表明,改进后的方法在考虑测试模态误差的情况下可对结构的损伤进行精确的定位和标定。     

Spectral element modeling based structure piezoelectric impedance computation and damage identification

This paper presents a numerical simulation study on electromechanical impedance technique for structural damage identification. The basic principle of impedance based damage detection is structural impedance will vary with the occurrence and development of structural damage, which can be measured from electromechanical admittance curves acquired from PZT patches. Therefore, structure damage can be identified from the electromechanical admittance measurements. In this study, a model based method that can identify both location and severity of structural damage through the minimization of the deviations between structural impedance curves and numerically computed response is developed. The numerical model is set up using the spectral element method, which is promised to be of high numerical efficiency and computational accuracy in the high frequency range. An optimization procedure is then formulated to estimate the property change of structural elements from the electric admittance measurement of PZT patches. A case study on a pin-pin bar is conducted to investigate the feasibility of the proposed method. The results show that the presented method can accurately identify bar damage location and severity even when the measurements are polluted by 5% noise.     

Machine learning based novelty detection using modal analysis

Among many structural assessment methods, the change of modal characteristics is considered a well‐accepted damage detection method. However, the presence of environmental or operational variations may pollute the baseline and prevent a dependable assessment of the change. In recent years, the use of machine learning algorithms gained interest within structural health community, especially due to their ability and success in the elimination of ambient uncertainty. This paper proposes an end‐to‐end architecture to detect damage reliably by employing machine learning algorithms. The proposed approach streamlines (a) collection of structural response data, (b) modal analysis using system identification, (c) learning model, and (d) novelty detection. The proposed system aims to extract latent features of accessible modal parameters such as natural frequencies and mode shapes measured at undamaged target structure under temperature uncertainty and to reconstruct a new representation of these features that is similar to the original using well‐established machine learning methods for damage detection. The deviation between measured and reconstructed parameters, also known as novelty index, is the essential information for detecting critical changes in the system. The approach is evaluated by analyzing the structural response data obtained from finite element models and experimental structures. For the machine learning component of the approach, both principal component analysis (PCA) and autoencoder (AE) are examined. While mode shapes are known to be a well‐researched damage indicator in the literature, to our best knowledge, this research is the first time that unsupervised machine learning is applied using PCA and AE to utilize mode shapes in addition to natural frequencies for effective damage detection. The detection performance of this pipeline is compared to a similar approach where its learning model does not utilize mode shapes. The results demonstrate that the effectiveness of the damage detection under temperature variability improves significantly when mode shapes are used in the training of learning algorithm. Especially for small damages, the proposed algorithm performs better in discriminating system changes.     

A pattern recognition technique for structural identification using observed vibration signals: Linear case studies

This and the companion article summarize linear and nonlinear structural identification (SI) methods using a pattern recognition technique, support vector regression (SVR). Signal processing plays a key role in the SI field, because observed data are often incomplete and contaminated by noise. Support vector regression (SVR) is a novel data processing technique that is superior in terms of its robustness, thus it has the potential to be applied for accurate and efficient structural identification. Three SVR-based methods employing the autoregression moving average (ARMA) time series, the high-order AR model, and the sub-structuring strategy are presented for linear structural parameter identification using observed vibration data. The SVR coefficient selection and incremental training algorithm have also been presented. Numerical evaluations demonstrate that the SVR-based methods identify structural parameters accurately. A five-floor structure shaking table test has also been conducted, and the observed data are used to verify experimentally the novel SVR technique for linear structural identification.     

基于数据融合的张弦桁架多位置损伤识别与抗噪性分析

为提高张弦桁架多位置损伤识别的准确性,将数据融合方法与损伤识别指标相结合,采用D-S证据矩阵理论融合叠加曲率模态改变率和模态柔度差曲率两项指标的损伤识别结果,提出了张弦桁架多损伤的单次融合和两阶段融合识别方法。以某实际工程缩尺简化得到的张弦桁架作为研究对象,设计了两种不同的多损伤工况,通过有限元分析获取了结构损伤前后的前三阶模态数据,并进行了损伤识别分析。结果表明：基于数据融合的多损伤识别方法能够准确地识别张弦桁架多损伤,其能够综合两种单指标的识别结果,降低甚至消除非损伤位置的干扰,有效解决了单指标识别精度低、不能全面反映损伤位置的问题;两阶段融合方法通过两次融合逐步降低了非损伤位置的干扰,识别效果优于单次融合方法。此外,分析中考虑了不同水平噪声对张弦桁架多损伤识别的影响,结果表明：基于数据融合的多损伤识别方法具有较好的抗噪能力,能够降低噪声和非损伤位置的干扰,且两阶段融合方法的抗噪能力优于单次融合方法。     

基于固有模态函数振动传递率的结构损伤识别

提出了无需量测外荷载的新的结构损伤识别方法,将经验模态分解应用于结构损伤识别,通过求振动响应信号固有模态函数的振动传递率,构建结构损伤识别参数;通过对预置不同开胶损伤程度的玻璃幕墙试件进行动态测试,得到不同损伤程度下玻璃幕墙的固有模态函数振动传递率,并根据振动传递率的差别来识别和评估玻璃幕墙开胶损伤程度。研究结果表明:与传统方法相比,该方法无需量测外荷载也能精确识别结构损伤,通过损伤参数值也能判断损伤大小。     

Autoencoders for unsupervised real-time bridge health assessment

Over the last decades, the rising number of aging infrastructures has progressively fueled much interest toward the field of structural health monitoring. Following the increasing popularity of artificial intelligence algorithms, an autoencoder-based damage detection technique within the context of unsupervised learning is proposed in this paper to provide support for practical engineering applications. The developed methodology uses the autoencoder to reconstruct raw acceleration sequences of user-defined length collected from a healthy structure. To quantify the errors between the original input and the reconstructed output, which may be representative of damage occurrence, two indexes of reconstruction loss are selected as damage-sensitive features. To support damage detection, a selected number of short-time sequences are finally grouped into a unique macrosequence. The novel procedure can effectively both work at the single sensor level, as well as combine the predictive models using an ensemble learning strategy. Avoiding system identification, results obtained in the Z24 bridge demonstrate that the proposed method is quite effective for local damage detection with limited computational effort and using a limited number of sensors, thereby suitable to be easily applicable in the context of real-time bridge assessment.