基于模型试验的悬索桥结构损伤识别研究

通过整桥模型试验, 探讨了悬索桥结构损伤识别方法. 首先面向损伤识别研究设计制作了长10m的悬索桥试验模型, 并通过模型误差分析建立了相应的高精度有限元模型. 基于悬索桥结构健康监测和试验检测的主要常用参数以及这些参数对结构损伤的灵敏性和相关性研究, 确定损伤识别策略. 采用有限元模型模拟可能的损伤工况, 从而生成BP网络的训练样本数据. 再将试验模型作为“实际结构”通过损伤模拟试验生成网络测试数据. 就试验模拟的损伤情况而言, 对损伤位置的识别准确率达到了86%, 相应的损伤程度识别精度也达到可接受程度. 显示了该方法较好的应用前景, 对基于监测系统的悬索桥健康状态识别与评价具有参考意义.     

基于神经网络的SPC/EPC整合过程监测方法研究

为解决统计过程控制(SPC)/工程过程调整(EPC)整合引起的传统SPC控制图监测异常扰动效率低的问题,提出了采用神经网络技术监测SPC/EPC整合过程的策略,并对神经网络模型结构和参数设置进行分析,构建过程输入、过程输出及两者的协方差为输入参数,异常扰动发生与否为输出参数的3层神经网络模型。为验证该方法的性能,进行了大量的比较实验:即对相同的样本,分别采用Shewhar图、CUSUM图和上述神经网络模型进行监测。实验结果表明:神经网络模型能准确监测幅度大于2的阶跃扰动和大于2的过程漂移,平均运行步长(ARL)为1;传统SPC监测技术只能较准确地(监测率大于90%)监测幅度大于5的阶跃扰动和大于2的过程漂移,ARL大于2。与传统监测方法相比,该方法能快速有效地监测异常扰动的发生。     

基于自适应概率神经网络的损伤模式识别研究

在传统的概率神经网络(PNN)的基础上,提出了通过Gap-Based方法初步估算平滑因子σ,并以遗传算法优化σ参数集的自适应概率神经网络(APNN)模式分类识别方法.以桥梁健康监测委员会提出的两跨桥梁Benchmark模型为例,通过将小波包分解结构在正弦激励和交通激励载荷模型下的动力响应信号的能量特征向量作为网络的输入样本,利用APNN进行了损伤模式进行识别.结果表明, APNN不仅识别精度高和抗噪性能好,而且还能用于输入特征向量参数筛选和降维,提高学习效率和识别精度.     

基于相关函数矩阵及卷积神经网络的结构健康监测研究

环境激励下利用时域振动响应构建的内积矩阵是结构健康监测中一种较好的结构特征参数。为了提升结构健康监测方法的识别准确率,构建内积矩阵时往往需要较多的振动响应测点,这将直接影响方法的工程实用性。该文基于时域振动响应的相关性分析理论,将内积矩阵扩展到了相关函数矩阵,实现从少量的振动响应测点中获取更多的结构健康特征信息,以降低结构健康监测方法对测点数量的需求。进一步结合卷积神经网络优异的数据特征提取能力,以相关函数矩阵为输入、结构健康状态为输出,提出了基于相关函数矩阵及卷积神经网络的结构健康监测方法。典型航空加筋壁板螺栓松动监测的实验研究结果表明,仅采用结构上任意2个测点的时域振动响应,该文方法针对螺栓松动位置的识别准确率可达99%以上。     

采用BP神经网络优化的振动信号压缩感知方法

无线传感网络逐渐应用于结构健康监测,但是因能耗问题难以实现长期、高频的数据采集工作。压缩感知技术可利用少量的采样点重构原始信号,有望降低无线传感网络的能耗。实测振动信号因受到噪声干扰而导致稀疏性有限,常用于压缩感知的LASSO算法难以精确求解稀疏系数,进而影响振动信号重构效果。引入BP神经网络优化LASSO算法解得的稀疏系数,BP神经网络经ADAM优化算法训练后,可有效提升振动信号重构精度。用三层框架结构的模拟加速度数据和广州塔的监测加速度数据验证方法的有效性,并探讨了正则化参数和优化迭代次数的影响。结果表明,基于BP神经网络优化的压缩感知方法的信号重构效果在不同压缩率下均优于非优化的压缩感知方法。     

偏最小二乘回归神经网络模型在爆破振动峰值速度预测中的应用

神经网络方法是处理非线性问题的有力工具,但当输入变量较多,输入变量间存在的多重共线性性会使得网络的建模效率下降。偏最小二乘回归方法通过提取对因变量解释性较强的成分,能较好地克服变量间的多重共线性。将两种方法相结合,建立了爆破振动峰值速度的偏最小二乘回归BP神经网络预测模型。利用偏最小二乘法对影响爆破振动的因素进行分析,提取出3个新综合变量,使BP网络的输入层节点数目由9个减少到3个,简化了网络结构,提高了计算速度,增强了网络稳定性。分析结果表明,耦合模型的平均预测误差为7.62%,相较于传统的萨氏公式及标准的BP神经网络模型其预测精度有了明显提高。     

用概率社会网络进行结构损伤位置识别

在不计测量误差情况下,神经网络能够成功地识别损伤位置及其程度,但在测量噪声影响下,神经网络的损伤识别效果则比较差,考虑到基于多变量模式分类的概率神经网络具有处理受噪声污染的测试数据的能力,本文将可能的损伤位置作为模式类,利用概率神经网络的分类能力来识别结构的损,地对两个算例,一个六层框架和一个两层框架进行数值模拟分析,并将概率神经网络与BP网络进行了比较,结果表明,概率神经网络具有更好的识别效果,是一种很有潜力的结构损伤位置识别方法。     

质量缺陷生鲜品库存与筛选决策研究

针对实际生产中商品出现的质量缺陷问题,在综合考虑生鲜品腐损特征及筛选过程中存在两类错误的基础上,构建了变质率服从两参数Weibull分布,缺陷率及筛选错误发生率皆为随机变量的零售商库存模型,并对筛选过程中发生的腐损成本进行了核算。随后,基于零售商平均总成本最小化视角,运用遗传算法对零售商的库存策略与筛选策略进行规划求解。最后,灵敏度分析发现,I类错误的发生概率与变质率尺度因子对零售商库存成本的影响最为显著。因此,零售商在进行生鲜库存管理时,可通过采取相关的技术投入降低I类错误的发生概率,并维系商品变质率的稳定。     

基于BP神经网络的围岩介质爆炸峰值压力预测

基于BP(Back Propagation)神经网络法,收集对比130个公开的地下封闭爆炸数据,区分黏土、砂性土和岩石三组围岩介质,简化地下任意点爆炸围岩介质峰值力的多因素影响,分析爆炸比例距离、纵波波速、密度和饱和度等特征参数产生的权重影响,考察爆冲的输出峰值压力特征,提出土中任一点围岩介质峰值压力的简易预测方法,并通过与经验方法对比,验证简易方法的实效性。利用Matlab建立不同隐含层单元数的BP(Back-Propagation)神经网络,当隐含层分别选择6、7、6个神经元时整体网络性能最佳,该条件下对比测试样本的BP神经网络、经验公式和多元回归分析方法(MVRA)的预测效果,BP神经网络方法得到最小平均绝对误差。在各围岩介质数据的误差对比分析中,BP神经网络法得到砂性土的预测误差相对最小,相比经验公式和多元回归分析优势明显。在同一围岩介质参数的敏感度分析中,纵波波速对峰值压力产生最显著影响。将工程实例参数带入对比BP神经网络和MVRA,考虑不同介质反射系数得到峰值压力预测值和拱顶爆炸荷载峰值实测值的相对误差可小于20%。该估算方法可为类似地下结构防护设计值提供一种简化参考。     

基于BP网络的蜂窝铝芯力学性能预测与灵敏度分析

以蜂窝铝芯几何结构参数对其面内等效性能影响为研究对象,将正交试验和均匀化理论与有限元相结合来获得数据样本,建立了蜂窝铝芯几何结构参数与其等效弹性性能参数之间复杂非线性映射关系的网络模型,并利用贝叶斯正则化算法,实现了BP神经网络对蜂窝铝芯力学性能的预测。在较少样本数据的情况,可以较高精度地预测胞元结构参数对蜂窝铝芯等效性能的影响规律。提取该BP模型中各层的权值,运用Garson算法得到各结构参数对蜂窝铝芯等效力学性能影响程度的灵敏度系数,结果表明灵敏度分析可评估结构参数对等效力学性能的影响,可为蜂窝铝芯设计提供参考。     

飞机结构健康监测技术发展研究

介绍了结构健康监测技术（Structural Health Monitoring, SHM）的概念以及主动和被动损伤监测方法 的原理, 分析了飞机结构健康监测技术的国内外研究现状, 阐述了比较真空监测（Comparative Vacuum Monitoring, CVM）传感技术、智能涂层传感器技术、光纤传感技术、压电传感器（Piezoelectric Sensors, PZT）技 术和无线传感器网络（Wireless Sensor Network, WSN）等目前较为先进的传感技术的原理以及传感器技术在各类 装备上的应用情况,介绍了飞机结构健康监测技术在F-35联合攻击机（Joint Strike Fighter, JSF）上的典型应用。 指出飞机结构健康监测技术正向智能化方向发展;未来需要重点研究传感器网络的智能诊断技术、复杂环境下 的SHM技术、基于结构健康监测的健康管理技术、智能材料 / 结构健康监测技术,并将深度学习、数字孪生等 前沿技术应用于航空领域,以推动我国飞机结构健康监测技术发展。     

Optimal planning of structural performance monitoring based on reliability importance assessment

Recently, the effective use of information from structural health monitoring (SHM) has been considered as a significant tool for rational maintenance planning of deteriorating structures. Since a realistic maintenance plan for civil infrastructure has to include uncertainty, reliable information from SHM should be used systematically. Continuous monitoring over a long-term period can increase the reliability of the assessment and prediction of structural performance. However, due to limited financial resources, cost-effective SHM should be considered. This paper provides an approach for cost-effective monitoring planning of a structural system, based on a time-dependent normalized reliability importance factor (NRIF) of structural components. The reliability of the system and the NRIFs of individual components are assessed and predicted based on monitored data. The total monitoring cost for the structural system is allocated to individual components according to the NRIF. These allocated monitoring costs of individual components are used in Pareto optimization to determine the monitoring schedules (i.e., monitoring duration and prediction duration).     

Validation of HDOP Measure for Impact Detection in Sensor Network-Based Structural Health Monitoring

This paper studies the validity of horizontal dilution of precision (HDOP) measure to evaluate sensor network geometries when localizing impacts in structural health monitoring (SHM). First, HDOP is defined similarly to navigation applications. Even though several low-complexity closed-form solutions have been proposed recently, HDOP measure has been theoretically justified only for iterative least-squares approach. The localization errors of popular impact localization methods are experimentally collected and compared with HDOP data for validation. The experimental setup is also described. It is shown that HDOP, in general, correlates with the positioning error and can be used to characterize geometry.      

On the influence of moisture absorption on Lamb wave propagation and measurements in viscoelastic CFRP using surface applied piezoelectric sensors

The understanding of the impact of environmental influence factors on propagation and damping of Lamb waves in composite materials is a topic of great interest for both design and utilization of structural health monitoring (SHM) systems. In this work, the influence of humidity absorption on the dispersive behavior of Lamb waves propagating in viscoelastic composite materials is investigated. Using a transversely isotropic material model and DMA measurements, the changes in the viscoelastic material properties due to water absorption are characterized. By means of a higher order plate theory and those mechanical properties, the dispersion curves for unconditioned and hot/wet-conditioned UD reinforced CFRP plates are then predicted. Both the changes in Lamb wave velocity and Lamb wave damping are investigated and compared with experimental values. Additionally, the changes of the sensor response, which are related to both the changes of the material properties and that of the adhesive layer, are investigated. The large impact of moisture absorption on Lamb wave excitation and propagation and its relevance for structural health monitoring (SHM) applications is shown and discussed.     

An introduction to structural health monitoring

The process of implementing a damage identification strategy for aerospace, civil and mechanical engineering infrastructure is referred to as structural health monitoring (SHM). Here, damage is defined as changes to the material and/or geometric properties of these systems, including changes to the boundary conditions and system connectivity, which adversely affect the system's performance. A wide variety of highly effective local non-destructive evaluation tools are available for such monitoring. However, the majority of SHM research conducted over the last 30 years has attempted to identify damage in structures on a more global basis. The past 10 years have seen a rapid increase in the amount of research related to SHM as quantified by the significant escalation in papers published on this subject. The increased interest in SHM and its associated potential for significant life-safety and economic benefits has motivated the need for this theme issue.This introduction begins with a brief history of SHM technology development. Recent research has begun to recognize that the SHM problem is fundamentally one of the statistical pattern recognition (SPR) and a paradigm to address such a problem is described in detail herein as it forms the basis for organization of this theme issue. In the process of providing the historical overview and summarizing the SPR paradigm, the subsequent articles in this theme issue are cited in an effort to show how they fit into this overview of SHM. In conclusion, technical challenges that must be addressed if SHM is to gain wider application are discussed in a general manner.     

Double bridge circuit for self‐validated structural health monitoring strain measurements

In structural health monitoring (SHM) applications, sensor faults and structural damage need to be assuredly discriminated. A self‐diagnosis strain sensor operating in a continuous online SHM scenario is considered. The strain sensor is based on full electric resistance strain gauge Wheatstone bridges. The state of the art shows that such a sensor has not yet been developed. The loop current step response (LCSR) is a well‐known method to detect strain gauge debonding. However, applying the LCSR method to a full strain gauge Wheatstone bridge has some limitations analysed in this paper. To enable the use of the LCSR method in an online SHM scenario, the double bridge circuit is proposed in this work. Two new strain gauge debonding fault detection methods and a new debonding fault isolation method—based on the double bridge circuit measurements—are proposed and evaluated. Two new sensor fusion weighting approaches are also proposed and evaluated—to achieve strain gauge debonding fault tolerance on the double bridge circuit. The experimental results show that the proposed methods can detect, isolate, and tolerate a strain gauge grid debonding fault and can be applied in an online SHM self‐diagnosis sensor scenario.     

A nonparametric change detection approach in social networks

A network provides powerful means of representing relationships between entities in complex physical, biological, cyber, and social systems. Any phenomena in those areas may be realized as changes in the structure of the associated networks. Hence, change detection in dynamic networks is an important problem in many areas, such as fraud detection, cyber intrusion detection, and health care monitoring. This article proposes a new methodology for monitoring dynamic networks for quick detection of structural changes in network streams and also estimating the location of the change-point. The proposed methodology utilizes the eigenvalues for the adjacency matrices of network snapshots and employs a nonparametric hypothesis to test if the distribution of the eigenvalues for the current snapshot is different from those of the previous ones along a sliding window of reference networks. The statistic of the nonparametric test, energy distance among eigenvalues, is monitored using a one-sided exponentially weighted moving average control chart. Then, after an anomaly detection signal from the monitoring scheme, eigenvalues for the snapshots are employed to calculate the energy statistic at various time steps to locate the change-point. The proposed method is intended to detect two types of structural changes in the networks: (1) change in the communication rates among individuals and (2) change in the community structure of the network. The proposed methodology is applied to both simulated and real-world data. Results indicate that the proposed methodology provides a reliable tool for monitoring networks streams and also estimating change-points locations for precise assessing of the networks under investigation.     

基于Shannon 复数小波的复合材料结构时间反转聚焦多损伤成像方法

研究了一种基于压电传感器阵列和主动Lamb 波的结构损伤成像方法,有助于克服Lamb 波在板结构中、特别是在复合材料板结构中存在的频散、多种模式及模式转换的现象给结构健康监测带来的困难。分析了结构多损伤散射信号的时间反转聚焦原理,在此基础上提出了一种基于Shannon 复数小波和时间反转聚焦的信号合成成像方法。该方法中,确定Lamb 波响应信号的到达时刻是信号能够准确聚焦的关键因素之一。提出了利用Shannon 复数小波变换计算Lamb 波响应信号到达时刻的方法。在碳纤维复合材料板结构上对整套信号合成成像方法进行了验证。研究结果表明,该方法能够有效地对同一个监测区域中的多个损伤进行成像定位。相对于30 cm ×30 cm 的监测区域,定位误差不超过2 cm。该方法有助于结构健康监测技术的工程应用。      

某钢结构梁高温切割全过程的监测与分析

为保证某大型生产车间钢框架平台梁在设备荷载作用下改造过程中的安全性,采用ANSYS软件对改造方案进行了有限元分析,并采用光纤光栅传感器对其改造全过程进行了实时可视化监测。通过钢梁的有限元结构分析以及高温切割过程中钢梁温度场分析,确定了钢梁的切割方案,同时为相应高温环境下的结构实时监测方案设计、传感器的布设以及实时监测预警阀值的设定提供了依据。监测过程中实时获取了现场钢梁的工作状态,并对实时监测数据进行了快速分析和评价,从而判断钢梁的安全性,以保证钢梁切割过程的顺利进行。监测结果表明,根据监测方案可以快速评价钢梁的受力状态,为切割机的前进速度提供指导,同时表明光纤光栅应变和温度传感器完全满足高温环境下的测量要求。可视化监测方案在快速预警方面的成功应用可为类似的结构改造提供结构健康监测依据。     

损伤预警的时序方法及其在Benchmark结构试验中的应用

针对结构健康监测中如何利用在线监测数据进行损伤诊断的问题,基于时间序列分析提出了一种新的损伤预警方法。首先对所有监测数据样本建立ARMA模型,以模型中AR部分参数的主成分矩阵构建Mahalanobis距离判别函数,进而提出了一种新的结构损伤敏感特征指标DSF。然后,采用t检验考察该指标的均值在损伤前后是否存在显著性变化,从而可以实现结构的损伤预警。最后,对Benchmark结构在环境激励下的试验数据进行了损伤预警研究。结果表明:该文基于时序方法提出的DSF对结构的微小损伤具有敏感性,具备在线实时损伤预警的应用价值。