Robust Re-Weighted Multi-View Feature Selection

In practical application, many objects are described by multi-view features because multiple views can provide a more informative representation than the single view. When dealing with the multi-view data, the high dimensionality is often an obstacle as it can bring the expensive time consumption and an increased chance of over-fitting. So how to identify the relevant views and features is an important issue. The matrix-based multi-view feature selection that can integrate multiple views to select relevant feature subset has aroused widely concern in recent years. The existing supervised multi-view feature selection methods usually concatenate all views into the long vectors to design the models. However, this concatenation has no physical meaning and indicates that different views play the similar roles for a specific task. In this paper, we propose a robust re-weighted multi-view feature selection method by constructing the penalty term based on the low-dimensional subspaces of each view through the least-absolute criterion. The proposed model can fully consider the complementary property of multiple views and the specificity of each view. It can not only induce robustness to mitigate the impacts of outliers, but also learn the corresponding weights adaptively for different views without any presetting parameter. In the process of optimization, the proposed model can be splitted to several small scale sub-problems. An iterative algorithm based on the iteratively re-weighted least squares is proposed to efficiently solve these sub-problems. Furthermore, the convergence of the iterative algorithm is theoretical analyzed. Extensive comparable experiments with several state-of-the-art feature selection methods verify the effectiveness of the proposed method.     

声发射测试系统的发展

综述了声发射测试系统的发展历程及现状。展望了其发展前景，给出了两种分类依据，重点介绍了几种目前先进的声发射仪．     

Acoustic Emission in Composite Laminates

The response of a laminated plate to internal acoustic emission events is examined in detail. The plate consists of four layers of a unidirectional fiber composite material arranged in a cross-ply configuration. The sources considered include a vertical line couple, a horizontal line couple and a line double couple without moment. The latter is produced by the combination of two equal and opposite line couples and may be associated with a shear dislocation in the plane of the laminate. The particular response presented here is that of the normal upper surface displacement. Four different orientations of the line sources relative to the core fiber direction are considered. The sources may be located at any depth within the plate and results are shown for three locations, namely, the upper interface, the midplane and the lower interface. The receiver is positioned on the upper surface at a known distance from the line of action of the source. When this distance is small relative to the depth of the plate, it is possible to associate some of the peaks and troughs present in the response with the arrival of individual rays. At larger distances, the disturbance arises from the propagating Rayleigh Lamb modes.     

芳纶纤维/环氧树脂复合材料损伤与断裂过程的声发射特性

研究了芳纶/环氧复合材料在承受拉伸载荷时的损伤与断裂行为.发现不同损伤类型表现出不同的声发射特性,从声发射信号的某几种关联图中可以较好地判断损伤发生的类型,并可根据某些声发射特征参量值对临界承载值进行合理的确定.     

基于声发射技术的Si-Cr-Ti高温抗氧化涂层弯曲失效机理研究

本研究借助声发射技术对铌基高温抗氧化涂层在常温下的弯曲失效过程进行了研究。利用k均值聚类方法对信号进行了分类,结合截面扫描电镜观测结果确定高温抗氧化涂层在弯曲载荷下的信号分别对应基体变形、表面垂直裂纹、滑动型界面裂纹和张开型界面裂纹,通过快速傅里叶变换得到了各类信号的主频分别为100、310、590和450 kHz,借助小波分析得到了各信号的小波能量系数。涂层弯曲失效过程主要包括四个阶段,分别为受拉侧表面垂直裂纹萌生的初始损伤阶段、表面垂直裂纹增殖阶段、两侧界面裂纹快速扩展的损伤积累阶段和受压侧涂层明显剥落的宏观剥落阶段。     

近似熵在声发射信号处理中的应用

为研究在载荷作用下,结构裂纹声发射信号的变化特征,提出了将一种最近新发展起来的度量序列复杂性的统计方法--近似熵引入到结构裂纹声发射信号的研究中.介绍了近似熵的概念及性质,并对仿真声发射信号和预制裂纹钢管在静载下的声发射实验信号进行了近似熵计算分析,结果表明,近似熵在表征信号的复杂性方面有明显的效果,从而为声发射信号分析提供了一种很有效的新方法.     

声发射技术在工程结构疲劳损伤监测中的应用和展望

疲劳失效是工程结构和材料科学研究领域都十分关注的问题。研究疲劳损伤机制对于解决工程结构疲劳失效问题是很重要的。应用断裂力学理论研究工程结构的疲劳问题已取得了显著的成果，随着声发射技术研究的深入，将二者结合起来必将成为疲劳问题研究的更有效方法之一。阐述了国内外采用声发射技术对工程结构疲劳裂纹损伤监测中的声发射源机制状况的研究，展望了声发射技术结合断裂力学在该领域的应用前景。     

Application of Acoustic Emission for Masonry Arch Bridges

Abstract:  There are over 40 000 masonry arch bridges in the UK, 60% of which are over 100 years old. The ever increasing levels of loading and volumes of traffic make it imperative that the condition, life expectancy and load capacity of such bridges are accurately assessed. Assessment procedures, however, generally rely on visual methods without giving any information on the internal condition of the structure. The acoustic emission (AE) technique has the ability to record certain types of damages anywhere within the structure before their effect becomes visible on the surface. Although AE is increasingly widely used for monitoring concrete and metallic bridges, its application for masonry bridges is currently very limited. A series of multi-ring brickwork arches have been tested as part of an extended study on fatigue performance of masonry arch bridges at the University of Salford. The present study attempts to assess the applicability of the AE technique for masonry arch bridges under static and long-term cyclic loading, to study crack propagation and failure mechanisms.     

声激励检测信号的特征分析

通过信号分析与处理的方法，提取出与金属和非金属粘接状态和粘接质量有关的特征量，对粘接结构施加微力。通过对声音信号在时域，频域上的特征分析。提取出与粘接有关的特征量。在检测到的声音信号的时域波形上，粘接的特征不强，而对声音信号作频谱分析后。能使粘接特征在频谱图上比较容易地显现，声音信号特征值的提取为进一步的模式识别工作打下了良好的基础。     

Parametric Analysis of Acoustic Emission Signals for Evaluating Damage in Composites Using a PVDF Film Sensor

With the increased utilization of advanced composites in strategic industries, the concept of Structural Health Monitoring (SHM) with its inherent advantages is gaining ground over the conventional methods of NDE and NDI. The most attractive feature of this concept is on-line evaluation using embedded sensors. Consequently, development of methodologies with identification of appropriate sensors such as PVDF films becomes the key for exploiting the new concept. And, of the methods used for on-line evaluation acoustic emission has been most effective. Thus, Acoustic Emission (AE) generated during static tensile loading of glass fiber reinforced plastic composites was monitored using a Polyvinylidene fluoride (PVDF) film sensor. The frequency response of the film sensor was obtained with pencil lead breakage tests to choose the appropriate band of operation. The specimen considered for the experiments were chosen to characterize the differences in the operation of the failure mechanisms through AE parametric analysis. The results of the investigations can be characterized using AE parameter indicating that a PVDF film sensor was effective as an AE sensor used in structural health monitoring on-line.     

Measuring Transformations of Acoustic Emission Signals

Methods are presented for the selection and measuring transformation of acoustic emission signals from materials and structures. The probabilistic characteristics of the signal are considered and algorithms are given for estimating the amplitude distribution parameters and the damping parameters of acoustic emission signal, and the errors of the estimates are also given.     

压缩载荷下陶瓷材料声发射特性的实验研究

对陶瓷材料在两种压缩加载下破坏过程中的声发射特性进行实验研究。三点弯曲和巴西劈裂实验中,采用多通道声发射系统监测了陶瓷试件的破坏过程。对声发射信号进行分析,结果表明,声发射能量数、事件数、振铃数等参数都反映了材料内部损伤演化扩展直至试件宏观断裂的过程。利用声发射参数可以定位陶瓷试件的破坏位置;试件断面的宏细观分析表明,陶瓷的脆性破坏机制主要是颗粒附近的微裂纹开裂。     

Automatic Classification of Acoustic Emission Patterns

Abstract: The problem of automatic classification of acoustic emission signals using techniques derived from pattern recognition is addressed in this paper. The data were taken from laboratory experimental work on a box girder of a bridge in which the acoustic emission (AE) generation mechanism and location were monitored. Two statistical methods and a neural network procedure have been used to classify the data into groups representing different AE generation mechanisms. The classifiers are constructed using the traditional AE features – four parameters from each burst. Principal component analysis is used to reduce the dimension of the AE data feature vectors to two dimensions, resulting in simple visualisations of the data.     

Finite Element and Plate Theory Modeling of Acoustic Emission Waveforms

A comparison was made between two approaches to predict acoustic emission waveforms in thin plates. A normal mode solution method for Mindlin plate theory was used to predict the response of the flexural plate mode to a point source, step-function load, applied on the plate surface. The second approach used a dynamic finite element method to model the problem using equations of motion based on exact linear elasticity. Calculations were made using properties for both isotropic (aluminum) and anisotropic (unidirectional graphite/epoxy composite) materials. For simulations of anisotropic plates, propagation along multiple directions was evaluated. In general, agreement between the two theoretical approaches was good. Discrepancies in the waveforms at longer times were caused by differences in reflections from the lateral plate boundaries. These differences resulted from the fact that the two methods used different boundary conditions. At shorter times in the signals, before reflections, the slight discrepancies in the waveforms were attributed to limitations of Mindlin plate theory, which is an approximate plate theory. The advantages of the finite element method are that it used the exact linear elasticity solutions, and that it can be used to model real source conditions and complicated, finite specimen geometries as well as thick plates. These advantages come at a cost of increased computational difficulty, requiring lengthy calculations on workstations or supercomputers. The Mindlin plate theory solutions, meanwhile, can be quickly generated on personal computers. Specimens with finite geometry can also be modeled. However, only limited simple geometries such as circular or rectangular plates can easily be accommodated with the normal mode solution technique. Likewise, very limited source configurations can be modeled and plate theory is applicable only to thin plates.     

声发射技术及其在锅炉"四管"检测中的应用

介绍了声发射技术的发展过程,叙述了声发射的原理以及在锅炉“四管”检测中的应用情况,并分析了声发射技术存在的问题和进一步发展的趋势。     

相关分析在特征选择中的应用

目的 研究模式识别中特征选择的理论和方法。方法 利用相关分析法实现高效率的特征选择。 结果 在4种车辆声信号特征选择的实际应用中取得了良好的效果。结论 该方法具有运算量小,所选特征识别效果好等明显优点。     

开缝衬套成形过程声发射在线监测系统设计

为提高开缝衬套的双轴柔性滚弯成形质量,设计了一套基于声发射信号和虚拟仪器的在线监测系统,该系统主要由数据采集软件、数据采集卡、声发射传感器以及信号调理电路构成,实现对双轴柔性滚弯成形过程的声发射信号进行采集、显示、分析和存储,为开缝衬套双轴柔性滚弯成形过程控制和质量预测提供数据支持.通过实验对比分析了开缝衬套的双轴柔性滚弯过程声发射信号的时域和频域特性.实验结果表明,该在线监测系统响应速度快,性能稳定,能够可靠地实现对开缝衬套双轴柔性滚弯成形过程声发射信号的在线监测.     

声发射技术在疲劳失效领域的研究进展

疲劳失效是一种具有突然性和灾难性的失效形式,因此对材料的疲劳失效进行监测显得尤为重要。与传统的疲劳裂纹检测方法相比声发射技术能够对材料的疲劳失效过程进行实时、在线监测,因此在疲劳失效监测领域得到了广泛的应用。对声发射技术进行了简要的介绍,总结了声发射技术在疲劳失效过程监测和疲劳寿命预测两方面的研究进展,指出了当前研究中存在的问题并对其下一步的发展进行了展望。     

涂层疲劳损伤声发射特征参数及损伤机理

使用超音速等离子喷涂设备在1045钢基体上制备了铁基合金涂层。以球盘式接触疲劳试验机为平台,研究了涂层接触疲劳损伤过程中声发射特征参数的变化规律,并分析了涂层的接触疲劳损伤机理。结果表明,在转速为2500r/min和应力水平为1.58GPa实验条件下,点蚀是涂层的主要失效形式,表现为在涂层磨痕轨迹范围内出现大量的点蚀坑,点蚀坑深度为20～30μm。涂层表面粗糙的微凸体与轴承球滚压接触产生黏着磨损,以及涂层、磨粒、滚动轴承三者形成三体磨料磨损是点蚀失效产生的主要原因。声发射幅值、有效值(Root Mean Square,RMS)、能量、计数和平均频率对涂层表面粗糙微凸体去除、弹塑性变形、裂纹萌生、裂纹稳定扩展和失稳扩展过程比较敏感,并且在不同的疲劳损伤阶段具有不同的信号反馈特点。     

压力容器声发射检验中信号去噪研究

压力容器作为工业系统中的重要设备,其安全运行直接影响工业生产的安全性.通过定期对压力容器进行声发射信号检测,可及早发现设备缺陷,保障安全生产.由于压力容器检验现场各种噪声普遍存在,导致采集的声发射信号严重失真甚至淹没在噪声信号中.通过研究小波阈值去噪,自适应滤波原理,采用小波-自适应联合滤波,进行含噪信号去噪处理.