小波包分析在结构损伤监测中的应用

小波分析具有良好的时频局部化性质,特别适合于分析和处理突变信号。在获得结构的动力响应的基础上,对结构响应信号做小波包分解。根据各种响应信号对损伤的灵敏度,选择损伤特征,通过捕捉结构出现损伤的时刻,实现对结构损伤时刻监控。为模拟测试实际结构响应噪声的影响,在第一层加速响应信号中加入信噪比为5:1的白噪声,运用小波包消噪后再运用小波包分解识别结构的损伤时刻。     

小波神经网络在大坝变形监测中的应用

本文就小波神经网络的模型建立的方法进行了介绍,通过编制MATLAB小波神经网络程序,用一组变形监测实数据对变形结果进行了仿真试验,仿真的结果精度很高,能够用于变形分析预报.     

神经网络在结构工程健康监测中的应用探讨

建立结构损伤诊断子系统是建立大型工程结构智能健康监测专家系统的核心问题。人工神经网络技术可以实现结构损伤的自动识别与定位,具有广阔的应用前景。本文介绍基于人工神经网络的两级损伤识别策略,并对采用人工神经网络进行结构损伤诊断的网络输入参数与网络结构选择等关键问题进行了探讨。     

建筑结构损伤神经网络识别方法

结构健康监测是土木工程研究的新课题。随着结构健康监测系统的发展,基于健康监测数据对结构损伤的识别显得很重要,以确保结构不突然破坏。介绍了用于结构损伤识别的BP神经网络法、概率神经网络法,为结构健康监测提供了有效依据。     

基于小波分析的结构损伤检测

介绍了结构损伤的定义及发展,对损伤识别工作要解决的问题和常用的结构损伤诊断方法进行了分析,阐述了将小波分析与人工神经网络结合起来进行结构损伤检测的方法,并通过算例与传统BP神经网络作比较,以推广其应用。     

神经网络在结构损伤检测中的应用

对传统损伤检测方法的不足进行了分析，简要介绍了神经网络的基本原理及特点，并以实例说明了应用神经网络进行损伤检测的大致步骤，证明了该技术的可行性。     

神经网络在结构损伤识别中的应用

探讨了用神经网络对混凝土结构裂缝进行损伤识别和定位的方法,以一矩形截面悬臂梁为研究对象,通过完好结构和损伤结构的有限元分析,并进行了单处损伤和多处损伤的定位研究,数值仿真结果表明,该方法对于实际工程结构的损伤识别具有一定的指导意义。     

多小波神经网络在变形预测中的应用

将多小波与神经网络结合提出一种新的变形预测方法——多小波神经网络预测法,通过理论分析和它在变形预测中的应用分析表明,该方法较其他预测方法具有更高的精度,更快的速度,值得推广。     

小波分析在结构损伤判别中的应用及试验研究

随着大型土木工程的兴建,采用先进的仪器和科学的方法来进行在线监测和诊断对结构健康状况的评估起着越来越重要的作用.但无论是基于固有频率变化,还是振型变化,以及基于柔度或刚度变化的测量方法,都存在着一个共同的局限性,就是对微小损伤和疲劳损伤的识别,由于其探测灵敏度不够,显得力不从心,因此需要寻找一种更有效的损伤检测手段.小波变换作为一种新的信号处理方法,综合了时域分析方法和频域分析方法的优点,属于多分辨率的时频分析方法,具有伸缩、平移和放大功能,可以用不同的尺度或分辨率来观察信号,实现既在时域又在频域的高分辨局部定位,对于非平稳信号的处理是非常适合和必要的,正是结构损伤检测的基本要求.给出了结构整体进行损伤判别的方法,将各层能量在各频段进行分解,通过能量变化情况给出了结构损伤程度的判定方法,并且在三层钢筋混凝土框架结构的损伤判别试验中得到应用,试验结果与理论分析吻合较好,从而证明了提出的损伤判别方法的可行性与准确性.     

卷积神经网络在结构损伤诊断中的应用

对卷积神经网络(CNN)在工程结构损伤诊断中的应用进行了深入探讨; 以多层框架结构节点损伤位置的识别问题为研究对象,构建了可以直接从结构动力反应信号中进行学习并完成分类诊断的基于原始信号和傅里叶频域信息的一维卷积神经网络模型和基于小波变换数据的二维卷积神经网络模型; 从输入数据样本类别、训练时间、预测准确率、浅层与深层卷积神经网络以及不同损伤程度的影响等多方面进行了研究。结果表明:卷积神经网络能从结构动力反应信息中有效提取结构的损伤特征,且具有很高的识别精度; 相比直接用加速度反应样本,使用傅里叶变换后的频域数据作为训练样本能使CNN的收敛速度更快、更稳定,并且深层CNN的性能要好于浅层CNN; 将卷积神经网络用于工程结构损伤诊断具有可行性,特别是在大数据处理和解决复杂问题能力方面与其他传统诊断方法相比有很大优势,应用前景广阔。     

基于遗传算法与神经网络的桥梁结构健康监测系统研究初探

在前人研究工作的基础上，根据遗传算法和神经网络在处理复杂非线性问题时的各自特点，分别将其用于桥梁结构健康监测系统的不同部分，提出了建立基于遗传算法与神经网络的桥梁结构健康监测系统的基本设想。由于该项研究工作刚刚起步，文中的有些部分已经经过试验验证，而有些部分则尚处于理论研究阶段，需通过试验进一步证实。     

基于径向基神经网络的桥梁有限元模型修正

基于某预应力混凝土大跨刚构-连续梁桥的ANSYS有限元模型,提出一种基于径向基神经网络的有限元模型修正方法。该方法以不同设计参数条件下有限元模型模态分析频率作为输入向量,以对应的桥面单元、中墩、边墩的弹性模量、密度等设计参数修正值作为输出向量,利用径向基神经网络来逼近两者之间的非线性映射关系。结合该桥梁结构健康监测系统中加速度传感器监测的桥梁结构动力反应的加速度数据,利用神经网络的泛化特性,直接计算出有限元模型设计参数的修正值。研究结果表明:修正后的有限元模型能更真实地反映结构的物理状态,较好地反映该桥梁结构的真实动力特性。     

Neural network method based on a new damage signature for structural health monitoring

Adopting wide-band Lamb wave based active monitoring technology, this study focuses on a neural network method based on a new damage signature for on-line damage detection applied to thin-walled composite structures. Honeycomb sandwich and carbon fiber composite structures are studied. Two kinds of damage are considered: delamination and impact damage. A new damage signature is introduced to determine the presence and extent of damage in composites, while eliminating the influence of different distances between the actuator and sensor. Neural network method is researched to take advantage of this new damage signature combined with several other signatures to decide the damage mode. Kohonen neural network is developed. The proposed method is shown to be effective, reliable, and straightforward for the specimens considered in the present study, which are composed of different materials and suffer various levels of damage.     

Structural health monitoring of a cable-stayed bridge with Bayesian neural networks

In recent years, there has been an increasing interest in permanent observation of the dynamic behaviour of bridges for long-term monitoring purpose. This is due not only to the ageing of a lot of structures, but also for dealing with the increasing complexity of new bridges. The long-term monitoring of bridges produces a huge quantity of data that need to be effectively processed. For this purpose, there has been a growing interest on the application of soft computing methods. In particular, this work deals with the applicability of Bayesian neural networks for the identification of damage of a cable-stayed bridge. The selected structure is a real bridge proposed as benchmark problem by the Asian-Pacific Network of Centers for Research in Smart Structure Technology (ANCRiSST). They shared data coming from the long-term monitoring of the bridge with the structural health monitoring community in order to assess the current progress on damage detection and identification methods with a full-scale example. The data set includes vibration data before and after the bridge was damaged, so they are useful for testing new approaches for damage detection. In the first part of the paper, the Bayesian neural network model is discussed; then in the second part, a Bayesian neural network procedure for damage detection has been tested. The proposed method is able to detect anomalies on the behaviour of the structure, which can be related to the presence of damage. In order to obtain a confirmation of the obtained results, in the last part of the paper, they are compared with those obtained by using a traditional approach for vibration-based structural identification.     

Development of temperature-robust damage factor based on sensor fusion for a wind turbine structure

Wind power systems have gained much attention due to the relatively high reliability, maturity in technology and cost competitiveness compared to other renewable alternatives. Advances have been made to increase the power efficiency of the wind turbines while less attention has been focused on structural integrity assessment of the structural systems. Vibration-based damage detection has widely been researched to identify damages on a structure based on change in dynamic characteristics. Widely spread methods are natural frequency-based, mode shape-based, and curvature mode shape-based methods. The natural frequency-based methods are convenient but vulnerable to environmental temperature variation which degrades damage detection capability; mode shapes are less influenced by temperature variation and able to locate damage but requires extensive sensor instrumentation which is costly and vulnerable to signal noises. This study proposes novelty of damage factor based on sensor fusion to exclude effect of temperature variation. The combined use of an accelerometer and an inclinometer was considered and damage factor was defined as a change in relationship between those two measurements. The advantages of the proposed method are: 1) requirement of small number of sensor, 2) robustness to change in temperature and signal noise and 3) ability to roughly locate damage. Validation of the proposed method is carried out through numerical simulation on a simplified 5 MW wind turbine model.     

健康监测的发展动态

首先介绍了桥梁健康监测的概况,接着论述了桥梁健康监测系统的组成,然后阐述了桥梁健康监测系统在国内外的应用,最后对桥梁健康监测进行了展望,从而进一步改进桥梁健康监测技术。     

Damage tracking and hysteresis-based evaluation of seismic-excited RC shear wall using monitoring data

Reinforced concrete (RC) shear walls play an important role as the seismic resisting system in tall buildings. Yet, assessing the seismic damage of real-world shear walls remains a challenging task. In this study, a damage index that relies on the vibration data measured by the sensors embedded in the structure is proposed to evaluate the damage condition of shear walls. The damage index is formed by the linear combination of two normalized terms, which, respectively, characterize the peak and the cumulative damages of the shear walls with little knowledge of real-life structural hysteresis. The damage tracking and evaluation based on the substructure level and the story level are discussed. The damage indices evaluated using the hysteretic loops made by the shear and bending information of the shear wall are further compared. The feasibility of the proposed damage index is examined using a numerically simulated 12-story coupled shear wall structure. It is then applied to analyze the experiments regarding the damage condition of RC shear walls under earthquakes. Results show that the proposed damage index can track the damage states of RC shear walls under seismic excitations. Analysis suggests that the proposed damage index could trace and distinguish the progression of shear and flexural damages, which potentially supports the post-earthquake structural safety management.     

改进遗传神经网络的大坝渗流监测模型

在对遗传算法的适应度函数改进并修改选择方法的基础上,用改进的遗传算法优化BP神经网络权值,提出一种改进遗传神经网络的大坝渗流监测模型。结合实例分析表明:预测模型合理,训练精度与检测性能得到提高。     

A neuro-wavelet technique for seismic damage identification of cantilever structures

A method based on artificial neural networks and wavelet transform is proposed for identifying seismic-induced damage of cantilever structures. In the proposed method, response accelerations are measured at strategically selected locations. To extract damage-induced sharp transitions from the measured signals, they are decomposed by continuous wavelet transform. The size of the decomposed signals is reduced by principal component analysis (PCA). Principal components obtained from PCA are fed to a set of neural networks to identify damage. The proposed algorithm is applied to a tall airport traffic control tower by means of numerical simulations. The obtained results show that the proposed method effectively identifies seismic-induced damage, and the noise intensity has a negligible effect on the predicted results. Moreover, the trained neural network system is able to predict the seismic-induced damage of unseen samples well.