工业CT图像亚体素表面检测算法研究

针对ICT图像序列,研究了基于Facet模型和基于矩的亚体素表面检测算法,并通过引入基于Otsu的阈值分割预处理环节,大大减少了待处理体素的数目,在很大程度上提高了原始算法的处理速度。最后在对航空发动机叶片仿真数据的实验中,对比了算法处理效果,结果表明两算法检测精度均可达1/5个像素以内,预处理环节的引入可将原始算法速度提高约4倍。     

光滑模型与尖锐边界结合的MT二维反演方法

如何得到快速稳定的反演结果和更清晰的地质体分界面等问题仍然是当前MT反演研究的一个重点.为了解决反演结果不能得到清晰的电性分界面的问题,本文在前人研究的基础上,基于OCCAM反演以及突出尖锐边界反演的思想,结合最小支撑梯度泛函,构建了新的反演目标函数,并利用共轭梯度法优化目标函数,实现了一种光滑模型与尖锐边界结合的MT二维反演方法.模型实验证明了该方法的准确性,通过与已发表的相关反演方法的结果进行比较,证明了该方法在光滑稳定的基础上可突出对尖锐电性边界的刻画.对广东徐闻地区的实测MT资料进行了处理,表明了该方法的适用性和效果.     

基于振动方法的汲水门大桥损伤检测研究

基于高精度三维有限元模型以及模态灵敏度分析结果,对汲水门大桥损伤检测进行了数值模拟研究.该研究采用三阶段层次识别策略,首先确定损伤的发生,然后,确定损伤所在的区域,最后确定具体的损伤构件及损伤程度.所获得的汲水门大桥损伤识别模拟研究结果表明了本文所采用的策略与方法的可行性与实用价值.     

利用卷积神经网络检测地震的方法与优化

本文以西昌台阵观测的8 321次近震数据为例,详细介绍了利用深度卷积神经网络检测地震的数据处理流程,包括数据预处理、模型训练、波形长度、网络层数、学习率和概率阈值等关键参数对检测结果的影响,并将训练得到的最优模型,应用于事件波形和连续波形的检测。研究表明,数据预处理和数据增强可以提升模型的检测精度和抗干扰能力。用于模型训练的波形窗口长度可近似于S-P到时差的最大值。不同网络层数(5—8层)的检测结果差别不大。对于地震检测,学习率设为10-4—10-3较为合适。卷积神经网络检测出的地震数量与选择的概率阈值有关,通过绘制精确率-召回率变化曲线,可以为选择合适的概率阈值提供参考。本文为进一步利用深度学习算法提高地震检测效果提供了参考。     

中强震下砌体结构损伤检测方法研究

当前地震记录法检测中强震下砌体结构损伤时,基于已知砌体结构地震动记录实施损伤检测存在较高的局限性。提出新的中强震下砌体结构损伤检测方法,利用DASP动态测试分析仪和891型的压电式位移传感器,检测拟静力试验后的砌体结构模型,采用参数互补校正方法得到受损砌体结构的自振频率和振型检测,通过有限元分析获取砌体结构位移,依据频率和位移采用信号匹配方法检测砌体结构损伤情况,根据墙体刚度变化检测中强震下砌体结构的损伤程度。实验证明所提方法可对中强震下砌体结构损伤情况进行准确检测。     

基于EMD方法与RBF神经网络的结构损伤检测

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。     

一种基于神经网络的探地雷达信号解释研究

运用人工神经网络理论和方法,建立了用于隧道衬砌厚度探地雷达探测信号解释的BP神经网络模型,对某公路隧道衬砌检测厚度进行了分析应用,并与钻孔取芯结果进行比较,实践证明,该方法可提高探地雷达信号解释精度和工作效率．     

综合BIM结合表面图像分析的钢结构无损检测方法

采用质量脆弱性评价方法检测地震区绿色施工建筑钢结构时,易受噪声的干扰,且检测深度较浅,未能全面检测钢结构的损坏情况。提出综合BIM结合表面图像分析的钢结构无损检测方法,使用小波分解方法对建筑钢结构的检测图像进行去噪处理,通过膨胀与腐蚀处理增强检测图像的清晰度,采用红外图像技术,依据缺陷边缘处检测图像恢复的变化率,通过旋转跟踪法依次提取缺陷边缘,构建基于BIM的地震区绿色施工建筑钢结构检测模型,全面掌控地震区绿色建筑钢结构的材料、无损检测以及管理等过程,管控建筑钢结构全寿命周期,完成建筑钢结构的无损检测。实验结果表明,所提方法有效检测率为100%,检测深度高达1 499 mm,且检测结果的相对误差仅有0.000 7%。     

三维地质建模与可视化方法研究

设计了超体元实体模型、断层数学模型及褶皱几何模型, 以表达复杂地质构造的空间几何形态; 建立了面向应用的三维地质建模的体系结构, 提出以空间数据处理为基础、以实体建模技术为核心、以模型应用为目的的设计理念, 丰富和发展了三维地质建模的理论与方法. 根据这一理论方法, 提出基于特征的驾驭式可视化设计思路, 通过将数据库、图形库、知识库与三维动态模拟的系统集成, 直观、形象、准确地把握空间地质数据的局部特征与整体构架.     

基于灵敏度分析的结构损伤识别中的传感器优化配置

本文提出了结构损伤识别中的传感器测点优化配置的方法。该方法是通过仅考虑结构刚度变化的结构特征灵敏度分析，以结构各自由度的损伤信息为条件，计算出结构的Fisher信息阵，并且考虑到Fisher信息阵的逆阵可能不存在，而将Fisher信息阵对应于每个自由度进行分解，通过计算每个分解的Fisher信息阵的迹而确定每个自由度含有的损伤信息的多少，从而从结构的全部自由度中去掉那些含损伤信息少的自由度。建立直接利用结构不完整的实测模态来定位结构的损伤，避免结构模态扩阶带来不必要的误差。最后，通过数值算例表明，该方法能有效地识别出结构的损伤。     

A method for non-parametric damage detection through the use of neural networks

A neural network-based approach is presented for the detection of changes in the characteristics of structure-unknown systems. The approach relies on the use of vibration measurements from a ‘healthy’ system to train a neural network for identification purposes. Subsequently, the trained network is fed comparable vibration measurements from the same structure under different episodes of response in order to monitor the health of the structure. The methodology is applied to actual data obtained from ambient vibration measurements on a steel building structure that was damaged under strong seismic motion during the Hyogo-Ken Nanbu Earthquake of 17 January 1995. The measurements were done before and after repairs to the damaged frame were made. A neural network is trained with data after the repairs, which represents ‘healthy’ condition of the building. The trained network, which is subsequently fed data before the repairs, successfully identified the difference between the damaged storey and the undamaged storey. Through this study, it is shown that the proposed approach has the potential of being a practical tool for a damage detection methodology applied to smart civil structures. © 1998 John Wiley & Sons, Ltd.     

A neural network approach for the real-time detection of faults

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.     

Structural damage detection using empirical-mode decomposition and vector autoregressive moving average model

A method based on empirical-mode decomposition (EMD) and vector autoregressive moving average (VARMA) model is proposed for structural damage detection. The basic idea of the method is that the structural damages can be identified as the abrupt changes in energy distribution of structural responses at high frequencies. Using the time-varying VARMA model to represent the intrinsic mode functions (IMFs) obtained from the EMD of vibration signal, we define a damage index according to the VARMA coefficients. In the two examples given, the Imperial County Services Building and the Van Nuys hotel are used as the benchmark structures to verify the effectiveness and sensitivity of the damage index in real environments with the presence of actual noise. The analysis results show that the damage index can indicate the occurrence and relative severity of structural damages at multiple locations in an efficient manner. The damage index can also be potentially used for structural health monitoring, since it is based on the time-varying VARMA coefficients. Finally, some recommendations for future research are provided.     

面向对象遥感分类方法在汶川地震震害提取中的应用

震后城市建筑物震害的自动识别与分类, 是遥感震害调查中的关键步骤, 其精度直接影响损失评估的结果. 而随着高分辨率遥感影像的发展, 传统基于像元的分类技术已不能满足需求, 引入面向对象的信息提取技术, 充分挖掘影像对象的纹理、形状和相互关系等信息, 能够有效的提高震害的分类精度. 该文阐述了面向对象的遥感震害提取思路和方法, 并应用汶川地震震后高分辨率航空遥感数据, 针对建筑物震害进行面向对象的快速提取与自动分类. 结果表明, 与基于像元分类比较, 面向对象的建筑物震害分类能够显著改善分类效果.     

Statistical damage detection method for frame structures using a confidence interval

<正>A novel damage detection method is applied to a 3-story frame structure,to obtain statistical quantification control criterion of the existence,location and identification of damage.The mean,standard deviation,and exponentially weighted moving average(EWMA) are applied to detect damage information according to statistical process control(SPC) theory.It is concluded that the detection is insignificant with the mean and EWMA because the structural response is not independent and is not a normal distribution.On the other hand,the damage information is detected well with the standard deviation because the influence of the data distribution is not pronounced with this parameter.A suitable moderate confidence level is explored for more significant damage location and quantification detection,and the impact of noise is investigated to illustrate the robustness of the method.     

New remote sensing techniques for the detection and quantification of earth surface CO2 degassing

Earth degassing specifically of carbon dioxide CO₂ is of increasing interest with respect to the global carbon budget, related climate effects, earthquake and volcano eruption mechanisms, as well as plant physiological reactions in gas-rich environments. Investigations in all of these disciplines require the detection of surface CO₂ degassing structures and quantification of their emissions. We introduce minimal thermal change detection based on infrared imaging as a new remote sensing tool for the detection of earth surface thermal anomalies suiting among others to discover earth degassing locations of any origin. The method allows for seamless areal search and monitoring of degassing structures in any terrain. As proof of concept infrared imaging measurements were performed at the Bossoleto vent on the eastern master fault of the Siena Graben (Tuscany, Italy). It is known for the migration of a large amount of CO₂-rich gas from deep geothermal reservoirs. Field data acquired confirmed the qualification of the method. Detection of CO₂ degassing locations from infrared image time series worked reliably and optimal detection conditions were identified (dry, calm, cloudless weather between dusk and dawn). A simple model of heat exchange processes involved and observed was developed. In a first attempt this model was applied to determine the gas exit temperature, the area of gas thermal reach and the gas flux from recorded image series. It is the first method that allows remote areal survey of mofette fields and the associated CO₂ flux quantification sole from infrared image time series.     

A Bayesian probabilistic approach for structure damage detection

A Bayesian probabilistic approach is presented for the damage detection of multistorey frame structures. In this paper, a Bayesian probabilistic approach is applied to identify multiple damage locations using estimated modal parameters when (1) the measurement data are potentially corrupted with noise, (2) only a small number of degrees of freedom are measured, and (3) a few fundamental modes are estimated. To reduce the potentially intensive computational cost of the proposed method, a branch-and-bound search scheme is proposed and a simplified approach for the modelling of multistorey frame structures is employed. A six-storey shear frame example and two multistorey frame examples, with multiple damage locations, are presented to illustrate the applicability of the proposed approach. © 1997 John Wiley & Sons, Ltd.     

混沌噪声背景下检测微弱信号的神经网络方法分析

地震勘探资料的噪声许多呈现混沌现象，利用传统的去噪方法效果并不理想，如何根据混沌固有的性质，对地震勘探资料中的有效信号进行提取是许多科学工作者极为关注的问题，针对这种混沌噪声下的微弱信号检测，本文提出三种神经网络方法并对此进行比较，理论分析及仿真实验表明这三种神经网络在信噪比达到—37dB时，均能检测混沌噪声背景中的微弱信号。