模态应变能在复合材料机翼结构损伤检测中的应用

以复合材料机翼结构为研究对象，采用单元模态应变能改变率作为结构损伤标识量，对损伤结构进行损伤识别仿真。应用NASTRAN有限元程序对模型进行模态分析，模态分析的结果表明，单元模态应变能改变率对不同位置和不同程度损伤都具有较强的敏感性。应用神经网络成功识别了损伤的位置和程度，指出其可行性。     

基于低秩与稀疏分解的层合板损伤定位

针对基于结构振型参数的损伤定位方法抗噪性差、对微小损伤不敏感以及对多损伤识别性能低等问题,基于振型低秩性与损伤分布稀疏性提出了一种复合材料层合板多损伤识别方法。首先,使用高斯?拉普拉斯算子（Laplacian of Gaussian,简称LoG）求解曲率模态;其次,利用鲁棒主成分分析提取曲率模态中损伤诱导产生的奇异值进行损伤定位;然后,提出了一个鲁棒损伤定位指标用于融合多个曲率模态的损伤信息;最后,使用带损伤复合材料层合板数值模拟与实验数据验证了方法的有效性。结果表明,该方法无需无损结构参考信息,便可准确地定位复合材料层合板中多个小面积损伤。     

应变模态在框架结构节点损伤诊断中的应用研究

通过对某7层钢制框架结构节点损伤的数值模拟和模型试验，利用应变模态在结构损伤前后的相对变化进行框架结构节点损伤的诊断。结果表明，一阶应变振型对损伤及其位置敏感，高阶应变振型节点的存在使得依据高阶应变模态进行损伤诊断时容易造成误判。因此，利用一阶应变振型在损伤前后的相对变化可以对框架结构节点的损伤进行诊断。     

复合材料层合板侵彻行为的计算机模拟

本文以复合材料层合板抗侵彻性能分析为目的,采用ABAQUS/Explicit建立了纤维增强复合材料层合板高速冲击有限元分析模型,结合Hashin失效准则进行损伤识别,给出了层合板在球形弹头冲击下的侵彻破坏特征和模态,获得了弹道极限速度。模拟结果与理论计算结果和已有实验结果吻合良好,证明了该方法合理有效,探讨了弹头形状、冲击速度和入射角等因素对层合板损伤的影响规律,获得了一些有价值的结论,可以为工程实际提供参考。     

基于模态应变能比与神经网络的复合材料结构损伤辨识

从结构动力学特性入手，以模态应变能比作为表征结构损伤的标识量，对含损伤的复合材料机翼结构进行损伤辨识仿真，通过神经网络建立起损伤标识量和损伤状态之间的映射模型。仿真结果表明，模态应变能比对结构损伤位置和损伤程度都比较敏感，是一种有效的损伤标识量。神经网络可准确地识别出结构的损伤位置和损伤程度，应用于损伤识别是有效的。     

基于曲率模态的复合材料层合板分层损伤检测方法研究

基于振动信号应用曲率模态方法对复合材料层合板分层损伤进行损伤检测。首先由数值模拟所得不同状态下损伤以及未损伤层合板振动特性参数计算其振型曲率和均布载荷曲面值曲率;然后基于损伤与未损伤层合板曲率值的差分值建立损伤识别指标进行分层损伤检测。最后,为解决差分算法对结构未损伤模型参数的依赖性问题,引用曲面光滑算法和曲率模态变化率法直接对损伤结构进行损伤提取。结果表明,运用曲率参数差分法可以很好地识别各类损伤,且对于多层层合板来说损伤所处层的位置会影响损伤指标值的大小。曲面光滑算法和曲率模态变化率法均可不依赖于未损伤结构参数识别各类损伤,且曲面模态变化率法的检测效果优于曲面光滑算法。     

基于加速模态差值法的桁架结构早期损伤识别研究

针对起重机械的桁架结构,分析了损伤的严重后果,提出了用加速模态差值法识别早期损伤.首先建立有限元模型,随机选取一根杆件,通过降低其刚度来模拟早期损伤;然后对未损桁架和损伤桁架分别进行模态分析,并提取两者的模态振型数据,通过计算机处理得到损伤前后的加速模态振型,然后进行对比分析,找出加速模态振型变化最大的节点,即为损伤节点,进而找到损伤杆件.实例分析表明,提出的方法合理可行.     

基于Hamilton体系的能量释放率分析

基于Hamilton体系半解析法的分离合并技术,建立了脱层损伤层合板的半解析模型,具体分析了脱层损伤层合板结构脱层前缘节点的应力、位移及其分布规律,并进一步详细地研究了各种脱层损伤情况的能量释放率,本文的数值结果与Abaqus的数值结果进行了比较,证明了本文方法的正确性。     

基于深度学习的分布式光纤损伤识别方法

航空航天复合材料结构服役环境恶劣,为保证结构安全运行需要发展结构健康监测技术,基于背向瑞利散射的分布式光纤传感器因其便于埋入、抗干扰能力强等优点被广泛应用于结构健康监测领域。如何从复杂的光纤数据中识别结构损伤是健康监测的研究难点之一,基于此问题提出一种用于损伤识别的深度学习方法,采用一维卷积神经网络对复合材料层合板中的脱粘和裂纹损伤进行识别。为了验证方法的可靠性,设置预制损伤的酚醛树脂层合板的悬臂加载试验,其埋入的分布式光纤传感器很好地监测到了损伤区域的应变变化特征,采用试验数据对网络结构进行参数调整,最终确定卷积核大小和卷积层数目。试验结果表明,训练后的一维卷积神经网络能够从复杂的应变曲线中识别出损伤特征,并对损伤特征进行准确定位。在目前的研究中,该方法能够准确识别3 cm2的脱粘损伤和20 mm长的裂纹损伤,同时定位精度小于4 mm。     

复合材料层合板阻尼特性有限元数值模拟

应用耗散能原理建立了复合材料层合板的阻尼预测分析模型,对复合材料层合板进行三维有限元模态分析,求出各个模态下的应力、应变分量。根据模态分析结果,从单向复合材料的阻尼性能参数出发,利用层合板应变能、耗散能和结构模态阻尼的关系求出各个模态对应的模态阻尼损耗因子。利用该方法,分别计算了单向层合板和对称层合板的结构模态阻尼损耗因子。数值计算结果与已有的理论分析和试验结果相比吻合较好,从而验证了该方法的合理性,该方法还可以比较三维应力分量对阻尼的贡献。     

基于神经网络的壳体结构损伤诊断研究

神经网络输入参数的选择将直接影响工程结构损伤识别的精度和准确性。本文提出以反映结构损伤位置和程度的固有频率与频率下降率的组合作为神经网络输入的特征参数，以增加对损务程度敏感的参数项，克服单独使用某种参数的缺陷。针对使用BP算法的多层感知器中存在的网络收敛速度慢，容易陷入局部极小点等问题，采用一个改进算法。并以门座起重机筒形支柱－－圆柱壳结构损伤为例，进行计算分析，从中可以看出，采用此组合特征参数和改进算法提高了诊断的精度，加快了网络收敛的程度。     

一种基于模型修改的结构多点损伤识别方法

可用于结构损伤识别的方法很多。一般来讲正向方法直接利用结构模态参数的变化，逆向方法则利用模态参数变化反演结构物理参数变化，还有些方法利用了神经网络和模式识别技术。文中利用模型修改的思想，通过逆向方法计算结构单元刚度变化系数来对结构的多点损伤进行识别。以一个七自由度弹簧阻尼质量系统作为研究对象，用数值模拟方法及特征系统实现算法计算系统的模态参数，并用这些模态参数验证所提出方法的可行性，结果表明该方法对多点损伤的识别是简单而可行的。     

Computationally efficient delamination detection in composite beams using Haar wavelets

The paper presents an integrated vibration-based method for delaminations detection in homogeneous and composite beams. The method is based on Haar wavelets and artificial neural networks (ANNs). Firstly, scaled modal responses of the structure are expanded into Haar series by Chen-Hsiao method (CHM), and a delamination feature index is constructed. The database of 68 datasets built on Haar wavelet and frequency-based approaches was utilized by different ANNs to establish the mapping relationship between the delamination status and the delamination feature index or frequencies. The results are compared to each other. The simulations show the proposed complex method with delamination index detects the location of delaminations and identifies the delamination extent with high precision (>90%); the approach requires less computations and processing time than the frequency-based approach.     

LS-SVM在基于小波变换的模态分析中端部效应的应用

系统地阐述了运用改进的Morlet小波进行模态参数识别的方法。运用小波熵对小波参数进行了优化选择从而可以进行密频模态的识别,针对小波分析时产生的端部效应问题,提出了运用最小二乘支持向量机（LS-SVM）对小波骨架进行预测延拓的方法,经预测分析后可获取较准确的模态参数。通过仿真及实验信号的验证分析,表明基于LS-SVM方法可以有效地消除端部效应,且其准确效果优于基于RBF的神经网络和时变自回归的预测方法。     

Modal characteristics of symmetrically laminated composite plates flexibly restrained at different locations

A method for determining modal characteristics (natural frequencies and mode shapes) of symmetrically laminated composite plates restrained by elastic supports at different locations in the interior and on the edges of the plates is presented. The classical lamination theory together with an appropriate set of characteristic functions are used in the Rayleigh-Ritz method to formulate the eigenvalue problem for determining the modal characteristics of the flexibly supported laminated composite plates. Sweep-sine vibration testing of several laminated composite plates flexibly restrained at different locations on the plates is performed to measure their natural frequencies. The close agreement between the experimental and theoretical natural frequencies of the plates has verified the accuracy of the proposed method. The effects of elastic restraint locations on the modal characteristics of flexibly supported laminated composite plates with different lamination arrangements and aspect ratios are studied using the present method. The usefulness of the results obtained for predicting sound radiation behavior of flexibly supported laminated composite plates is discussed.     

On-line fan blade damage detection using neural networks

This paper presents a methodology for monitoring the on-line condition of axial-flow fan blades with the use of neural networks. In developing this methodology, the first stage was to utilise neural networks trained on features extracted from on-line blade vibration signals measured on an experimental test structure. Results from a stationary experimental modal analysis of the structure were used for identifying global blade mode shapes and their corresponding frequencies. These in turn were used to assist in identifying vibration-related features suitable for neural network training. The features were extracted from on-line blade vibration and strain signals which were measured using a number of sensors.The second stage in the development of the methodology entails utilising neural networks trained on numerical Frequency Response Function (FRF) features obtained from a Finite Element Model (FEM) of the test structure. Frequency domain features obtained from on-line experimental measurements were used to normalise the numerical FRF features prior to neural network training. Following training, the networks were tested using experimental frequency domain features. This approach makes it unnecessary to damage the structure in order to train the neural networks.The paper shows that it is possible to classify damage for several fan blades by using neural networks with on-line vibration measurements from sensors not necessarily installed on the damaged blades themselves. The significance of this is that it proves the possibility to perform on-line fan blade damage classification using less than one sensor per blade. Even more significant is the demonstration that an on-line damage detection system for a fan can be developed without having to damage the actual structure.     

Prediction of friction coefficient of treated betelnut fibre reinforced polyester (T-BFRP) composite using artificial neural networks

The current work is an attempt of using artificial neural network configuration to predict frictional performance of treated betelnut fibre reinforced polyester (T-BFRP) composite. Experimental dataset at different applied loads (5-30 N) and sliding distances (0-6.72 km) was used to train the ANN configuration with a large volume of experimental data (492 sets) where three different fibre mat orientations were considered (anti parallel, parallel and normal orientations). Results obtained from the developed ANN model were compared with experimental results. It is found that the experimental and numerical results showed good accuracy when the developed ANN model was trained with Levenberg-Marqurdt training function.     

胶囊内窥镜无线遥测定位的校正

为了进一步提高采用交流励磁定位无线跟踪胶囊内窥镜的定位精度,减小系统误差,提出了改进的神经网络定位校正方法。首先,设计了适应于胶囊内窥镜定位校正的神经网络结构;然后,采用Levenberg-Marquart算法结合贝叶斯正则化方法改进校正网络,抑制校正网络的过拟合。通过定位实验平台,建立了定位目标的跟踪位置与实际位置的样本对照数据表,并应用校正网络对定位数据进行校正。定位校正实验表明,改进的神经网络校正法可进一步减小定位误差,校正后的X,Y,Z,α,β分量的平均误差分别减小至8.7 mm,10.1 mm,7.3 mm,0.086 rad和0.081 rad。与基本BP算法相比,采用Levenberg-Marquart贝叶斯正则化的改进算法有效提高了定位校正网络的泛化能力和收敛精度。