共查询到20条相似文献，搜索用时 24 毫秒
1.
应用人工神经网络技术的大型斜拉桥子结构损伤识别研究 总被引：12，自引：0，他引：12
本文应用人工神经网络技术对大型斜拉桥结构进行了子结构损伤识别研究。文中首先介绍了子结构损伤识别的基本方法，然后应用自组织竞争神经网络建立了对于大型桥梁结构识别子结构损伤情况的子结构损伤识别方法，并且应用BP网络进一步建立了大型桥梁结构各子结构内部的损伤位置和损伤程度的识别方法，数值模拟了一大跨度斜拉桥子结构损伤以及子结构内部损伤的识别过程，最后得出结论：(1)基于自组织竞争网络的子结构损伤识别方法能迅速准确地识别大型结构的损伤情况；(2)基于BP网络所建立的结构损伤识别方法，能对子结构中结构损伤的位置和程度进行进一步的识别；(3)基于人工神经网络技术的结构损伤识别方法是大型土木工程结构损伤识别的有效方法，可在工程结构损伤识别中广泛应用。 相似文献
2.
结构健康监测的一个重要目的是实现结构损伤识别与定位,文章将结构监测数据的时间序列模型与机器学习中的核岭回归相结合,提出了一种新的结构损伤定位方法.先定义结构损伤识别矩阵,推导出结构损伤系数向量与损伤结构和未损伤结构的自回归系数向量差值的关联关系,结构的损伤识别矩阵可以通过机器学习中的核岭回归算法获得.对比其他回归算法,核岭回归的正则化、核函数特性可以大幅提高模型的拟合性能与泛化性能,更好地应用于结构损伤识别.然后通过一混凝土框架数值模型对该方法进行验证.结果表明该方法对结构的单损伤、多损伤均可进行有效识别,准确率较高. 相似文献
3.
针对结构损伤检测中损伤的识别、定位以及程度的标定这三个独立并按一定先后顺序进行的检测过程,提出了一种能将以上三者同时进行的联合检测方法。该方法首先利用经验模态分解(EMD)方法将三层钢筋混凝土剪切型结构在各种损伤工况下的顶层地震作用加速度响应分解为若干固有模态函数(IMF)分量,然后以此IMF分量和未经EMD分解的原始加速度响应数据来构造损伤标识量,作为特征参数依次输入到径向基函数神经网络(RBFNN)中进行损伤检测。给出了应用此方法的具体步骤,通过仿真实验证明了利用该方法进行结构损伤一次检测的可行性和有效性,结果表明,由加速度响应经EMD分解而得到的IMF分量输入到RBFNN中能够更为精确地一次检测出结构所有损伤信息,并且RBFNN在结构损伤损度大时具有更好的检测效果。 相似文献
4.
Introduction As we well know, the hazard of earthquake is very wide especially in cities. The conventionalmethods to investigate the damage are difficult to meet the requirements in applications. In recentyears, with the rapid development of remote sensing, especially the successful launch and applica-tion of high-resolution commercial remote sensing satellite, it has become possible to recognize andextract damage information by using remote sensing. The researchers at home and abroad hav… 相似文献
5.
近断层地震动对地表结构物造成严重的破坏，它具有明显的方向性和脉冲型特征. 在速度时程中含有大幅值、长周期的脉冲波，对结构响应影响很大. 为简化计算和分析的需要，在既有的等效速度脉冲模型的基础上，建议了较为合理等效速度脉冲模型. 在充分收集脉冲型近断层地震记录的基础上，对等效速度脉冲模型的脉冲周期、脉冲强度及卓越脉冲数等参数进行了研究，并与以往研究者的结果进行比较，以利于近断层区结构的抗震设计. 相似文献
6.
传统的利用震后单幅合成孔径雷达(SAR)影像对建筑物的震害特征分析大多基于街区范围, 很少基于其成像几何结构． 本文基于高分辨率SAR影像上的建筑物成像几何结构, 分析了建筑物单体的震害特点, 建立了利用距离向线性灰度累加的方法提取规则未倒塌建筑物的叠掩区和阴影区及倒塌建筑物的倒塌区, 并在此基础上进行各几何特征区域的纹理特征, 如同质度、 不相似度和熵的计算及其组合特征分析, 由此建立了基于SAR影像建筑物成像几何结构的震害分析方法． 采用该方法对2010年玉树MS7.1地震震后玉树县城区的高分辨率SAR影像进行分析, 结果表明: 叠掩、 阴影和二次散射亮线是进行建筑物震害解译的有效几何结构特征, 其中叠掩区和阴影区的影像纹理特征具有较好的震害识别能力; 与传统的简单特征统计方法相比, 考虑建筑物SAR影像成像几何结构的特征统计法, 可以显著提高建筑物的震害识别能力. 相似文献
7.
概率神经网络(PNN)以贝叶斯概率的方法描述测量数据,因而PNN在有噪声条件下的结构损伤检测方面具有巨大潜力。与此同时,PNN的网络规模随着训练样本的增加而增大,这极大地降低了网络运行速度。基于此,本文提出了基于主组分分析(PCA)的PNN损伤定位方法,分别用传统PNN(TPNN)、主组分分析PNN(PCAPNN)和自适应PNN(APNN)三种模型进行了悬索桥的损伤定位研究。研究发现,APNN的识别精度最好,PCAPNN次之,TPNN最差。但APNN需要很长的训练时间,网络规模较大;其他两个网络几乎不需要训练时间,且PCAPNN网络规模较其他两个网络减少了1／3～1／4。在低噪声情况下,PCAPNN的识别效果基本上等同于APNN。 相似文献
8.
《地震工程与工程振动(英文版)》2021,20(3)
An innovative damage identification method using the nearest neighbor search method to assess 3 D structures is presented. The frequency response function was employed as the input parameters to detect the severity and place of damage in 3 D spaces since it includes the most dynamic characteristics of the structures. Two-dimensional principal component analysis was utilized to reduce the size of the frequency response function data. The nearest neighbor search method was employed to detect the severity and location of damage in different damage scenarios. The accuracy of the approach was verified using measured data from an experimental test; moreover, two asymmetric 3 D numerical examples were considered as the numerical study. The superiority of the method was demonstrated through comparison with the results of damage identification by using artificial neural network. Different levels of white Gaussian noise were used for polluting the frequency response function data to investigate the robustness of the methods against noise-polluted data. The results indicate that both methods can efficiently detect the damage properties including its severity and location with high accuracy in the absence of noise, but the nearest neighbor search method is more robust against noisy data than the artificial neural network. 相似文献
9.
As urban systems become more highly sophisticated and interdependent, their vulnerability to earthquake events exhibits a significant level of uncertainties. Thus, community-level seismic risk assessments are indispensable to facilitate decision making for effective hazard mitigation and disaster responses. To this end, new frameworks for pre- and post-earthquake regional loss assessments are proposed using deep learning methods. First, to improve the accuracy of the response prediction of individual structures during the pre-earthquake loss assessment, a widely used nonlinear static procedure is replaced by the recently developed probabilistic deep neural network model. The variabilities of the nonlinear responses of a structural system given the seismic intensity can be quantified during the loss assessment process. Second, to facilitate near-real-time post-earthquake loss assessments, an adaptive algorithm, which identifies the optimal number and locations of sensors in a given urban area, is proposed. Using a deep neural network that estimates area-wide structural damage given the spatial distribution of the seismic intensity levels as a surrogate model, the algorithm adaptively places additional sensors at property lots at which errors from surrogate estimations of the structural damage are the greatest. Note that the surrogate model is constructed before earthquake events using simulated datasets. To test and demonstrate the proposed frameworks, the paper introduces thorough numerical investigations of two hypothetical urban communities. The proposed frameworks using the deep learning methods are expected to make critical advances in pre- and post-earthquake regional loss assessments. 相似文献
10.
对损伤部位向量(DLV)法作了简单介绍,并用该方法对钢框架进行了损伤识别和损伤定位。该方法假定结构损伤前后为线性,对结构损伤前后柔度矩阵差进行奇异值分解,将奇异值为零所对应的向量,作为静荷载施加在无损结构的测点位置,则应力为零的单元为可能损伤的单元。对3种不同工况的钢框架进行了振动模态试验,用前3阶模态参数构造框架的柔度矩阵,按照DLV法对其进行了损伤识别,识别结果与已知损伤情况相一致。从测试自由度不完备、噪声和振型质量归一化系数这3个方面对识别效果进行了分析,结果表明:当损伤使结构动力特性有微小改变时,使用该方法不易定位损伤,应结合局部损伤识别方法进行判定;当损伤使结构动力特性有较大改变时,该方法能有效识别损伤的单元。DLV方法概念简单,理论明确,不受结构类型的限制,不需要结构的数学模型和模型缩聚或扩展技术,只需获得结构损伤前后的前几个低阶模态参数,即可识别结构一处或多处损伤,实际应用时可操作性强。 相似文献
11.
Evaggelos Ntotsios Costas Papadimitriou Panagiotis Panetsos Grigorios Karaiskos Kyriakos Perros Philip C. Perdikaris 《Bulletin of Earthquake Engineering》2009,7(2):469-483
A bridge health monitoring system is presented based on vibration measurements collected from a network of acceleration sensors.
Sophisticated structural identification methods, combining information from the sensor network with the theoretical information
built into a finite element model for simulating bridge behavior, are incorporated into the system in order to monitor structural
condition, track structural changes and identify the location, type and extent of damage. This work starts with a brief overview
of the modal and model identification algorithms and software incorporated into the monitoring system and then presents details
on a Bayesian inference framework for the identification of the location and the severity of damage using measured modal characteristics.
The methodology for damage detection combines the information contained in a set of measurement modal data with the information
provided by a family of competitive, parameterized, finite element model classes simulating plausible damage scenarios in
the structure. The effectiveness of the damage detection algorithm is demonstrated and validated using simulated modal data
from an instrumented R/C bridge of the Egnatia Odos motorway, as well as using experimental vibration data from a laboratory
small-scaled bridge section. 相似文献
12.
Charles G. Sammis Ares J. Rosakis Harsha S. Bhat 《Pure and Applied Geophysics》2009,166(10-11):1629-1648
We review the results of a recent series of papers in which the interaction between a dynamic mode II fracture on a fault plane and off-fault damage has been studied using high-speed photography. In these experiments, fracture damage was created in photoelastic Homalite plates by thermal shock in liquid nitrogen and rupture velocities were measured by imaging fringes at the tips. In this paper we review these experiments and discuss how they might be scaled from lab to field using a recent theoretical model for dynamic rupture propagation. Three experimental configurations were investigated: An interface between two damaged Homalite plates, an interface between damaged and undamaged Homalite plates, and the interface between damaged Homalite and undamaged polycarbonate plates. In each case, the velocity was compared with that on a fault between the equivalent undamaged plates at the same load. Ruptures on the interface between two damaged Homalite plates travel at sub-Rayleigh velocities indicating that sliding on off-fault fractures dissipates energy, even though no new damage is created. Propagation on the interface between damaged and undamaged Homalite is asymmetric. Ruptures propagating in the direction for which the compressional lobe of their crack-tip stress field is in the damage (which we term the ‘C’ direction) are unaffected by the damage. In the opposite ‘T’ direction, the rupture velocity is significantly slower than the velocity in undamaged plates at the same load. Specifically, transitions to supershear observed using undamaged plates are not observed in the ‘T’ direction. Propagation on the interface between damaged Homalite and undamaged polycarbonate exhibits the same asymmetry, even though the elastically “favored” ‘+’ direction coincides with the ‘T’ direction in this case. The scaling properties of the interaction between the crack-tip field and pre-existing off-fault damage (i.e., no new damage is created) are explored using an analytic model for a nonsingular slip-weakening shear slip-pulse and verified using the velocity history of a slip pulse measured in the laboratory and a direct laboratory measurement of the interaction range using damage zones of various widths adjacent to the fault. 相似文献
13.
14.
多层及高层框架结构地震损伤诊断的神经网络方法 总被引：12，自引：4，他引：12
本文提出了强震后多层及高层框架结构地震损伤诊断的神经网络方法。文中在提出有结点损伤的梁柱有限元刚度矩阵的基础上，建立了有结点损伤框架结构的有限元模型。通过完好结构和有损伤结构的有限元分析，获取二者应变模态差值作为损伤标识量，并输入径向基（RBF）神经网络进行训练，得到了框架结构结点损伤诊断的神经网络系统。数值仿真分析结果表明，此神经网络可以对多层及高层框架结构结点各种程度的损伤做出成功诊断。 相似文献
15.
16.
为高效准确识别桥梁结构损伤,将深度学习与结构动力特性相结合,提出基于双层深度置信网络的桥梁结构损伤识别方法。首先取结构前3阶竖向振动频率和跨中节点前3阶竖向振动模态位移为参数,将其共同作为首层深度置信网络(DBN)的输入数据对结构的损伤位置进行识别;然后以1阶竖向振动的模态位移差作为参数,基于二层DBN对结构损伤程度进行预测;最后以郑许市域铁路桥梁为例进行验证。计算结果显示,当不考虑误差时,基于双层深度置信网络的结构损伤方法进行识别且结果精确;当噪声程度不超过10%时,定位识别结果准确率达100%;当噪声程度不超过15%时,定量识别结果最大绝对误差限不超过1.15%,识别结果准确;与传统的BP神经网络方法相比,本方法识别精度更高,抗噪性更强。 相似文献
17.
土木工程结构健康诊断中的统计识别方法综述 总被引：11，自引：1，他引：11
本文对土木工程结构健康诊断中的统计识别方法进行了综述。对统计识别中的统计系统识别方法(Bayes模型修正、随机有限元模型修正)、统计模式识别方法和概率神经网络方法的基本理论及其在土木工程结构健康诊断中的研究现状进行了论述，在此基础上提出了土木工程结构健康诊断中统计识别方法需要解决的关键问题和研究发展方向。 相似文献
18.
地震震相拾取是地震数据自动处理的首要环节,包括了信号检测、到时估计和震相识别等过程,震相拾取的准确性直接影响到后续事件关联处理的性能,影响观测报告的质量.为了提高震相拾取的准确性,进而提高观测报告质量,本文采用深度卷积神经网络方法来解决震相拾取问题,构建了多任务卷积神经网络模型,设计了分类和回归的联合损失函数,定义了基于加权的分类损失函数,以三分量地震台站的波形数据作为输入,同时实现对震相的检测识别和到时的精确估计.利用美国南加州地震台网的200万条震相和噪声数据对模型进行训练、验证和测试,对于测试集中直达波P、S震相识别的查全率达到98%以上,到时估计的标准偏差分别为0.067s,0.082s.利用迁移学习和数据增强,将模型用于对我国东北地区台网的6个台站13000条数据的训练、验证和测试中,对该数据集P、S震相查全率分别达到91.21%、85.65%.基于迁移训练后的模型,设计了用于连续数据的震相拾取方法,利用连续的地震数据对该算法进行了实际应用测试,并与国家数据中心和中国地震局的观测报告进行比对,该方法的震相检测识别率平均可达84.5%,验证了该方法在实际应用中的有效性.本文所提出的方法展示了深度神经网络在地震震相拾取中的优异性能,为地震震相和事件的检测识别提供了新的思路. 相似文献
19.
This work presents a novel procedure for identifying the dynamic characteristics of a building and diagnosing whether the building has been damaged by earthquakes, using a back‐propagation neural network approach. The dynamic characteristics are directly evaluated from the weighting matrices of the neural network trained by observed acceleration responses and input base excitations. Whether the building is damaged under a large earthquake is assessed by comparing the modal parameters and responses for this large earthquake with those for a small earthquake that has not caused this building any damage. The feasibility of the approach is demonstrated through processing the dynamic responses of a five‐storey steel frame, subjected to different strengths of the Kobe earthquake, in shaking table tests. Copyright © 2002 John Wiley & Sons, Ltd. 相似文献
20.
A neural network approach for the real-time detection of faults 总被引：2，自引：2，他引：0
Fault detection is an essential part of the operation of any chemical plant. Early detection of faults is important in chemical
industry since a lot of damage and loss can result before a fault present in the system is detected. Even though fault detection
algorithms are designed and implemented for quickly detecting incidents, most these algorithms do not have an optimal property
in terms of detection delay with respect to false alarm rate. Based on the optimization property of cumulative sum (CUSUM),
a real-time system for detecting changes in dynamic systems is designed in this paper. This work is motivated by combining
two fault detection (FD) strategies; a simplified procedure of the incident detection problem is formulated by using both
the artificial neural networks (ANN) and the CUSUM statistical test (Page–Hinkley test). The design of a model-based residual
generator is intended to reveal any drift from the normal behavior of the process. In order to obtain a reliable model for
the normal process dynamics, the neural black-box modeling by means of a nonlinear auto-regressive with eXogenous input (NARX)
model has been chosen in this study. This paper also shows the choice and the performance of the neural network in the training
and test phases. After describing the system architecture and the proposed methodology of the fault detection, we present
a realistic application in order to show the technique’s potential. The purpose is to develop and test the fault detection
method on a real incident data, to detect the change presence, and pinpoint the moment it occurred. The experimental results
demonstrate the robustness of the FD method. 相似文献