Automatic defects classification — a contribution

The objective of this work is to provide a contribution to defect classification. More precisely, we try to prove that it is possible to identify and classify defects of different types using the pulse-echo technique. The classification process makes use of the time and frequency domain responses of the ultrasonic echo signals acquired from different specimens simulating defects with three different shapes (cylindrical, spherical and planar with rectangular cross-section) and sizes. Although the final goal is the characterisation of practical defects (for instance, voids, cracks, delaminations, and so on) appearing in composite materials during manufacturing and in service, we first use the already mentioned reflectors for simplicity reasons. In these experiments 66 reflectors are used with water as matrix material. The inclusion (reflector) materials are brass, copper, steel and polystyrene. From the time domain signals we extract three features, namely, pulse duration, pulse decay rate and peak-to-peak relative amplitude of the third cycle. From the spectra of the echoes we extract the frequency for maximum amplitude and the standard error estimate from the deconvolved spectrum responses.All experimental signals were obtained using only one normal incident ultrasonic transducer aligned to maximise the direct reflected signal. In spite of the fact that this kind of configuration does not provide complete information about the characteristics of the geometries being studied, all the extracted features proved to be important discriminating factors of the geometrical classes considered, as will be demonstrated by making use of a pattern recognition technique for classification.     

基于PSO-SVM的FPC焊盘表面缺陷检测研究

针对柔性线路板(FPC)焊盘表面的缺陷检测,建立了一种利用粒子群算法(PSO)进行参数寻优的PSO-SVM分类识别模型。首先通过OTSU法将焊盘从原始图像中分割出来,然后对其5种表面缺陷从形状、灰度、纹理三个方面提取了14维特征,接着用粒子群算法方法对支持向量机的参数优化以获得较高的识别准确率,最后对缺陷样本进行分类识别,并将其与GS-SVM和BP神经网络分类性能进行对比。实验证明了该方法可以对焊盘缺陷进行准确的分类识别。     

高强钢焊接缺陷磁光成像分形特征检测

研究一种基于磁光成像原理的焊接缺陷无损检测新方法.以高强钢表面微小焊接缺陷为例,采用分形维数对焊缝磁光图像进行特征识别并估计最优尺度,根据Adabost分类算法对提取的焊接缺陷特征进行分析和训练,构建焊接缺陷特征量并对高强钢表面缺陷磁光图像进行自动识别.结果表明,运用磁光成像方法可以获取高强钢焊接缺陷特征,并通过图像分形维数分析可识别焊缝缺陷的位置、形状和类别.     

Pattern recognition of weld defects detected by radiographic test

In recent years there has been a marked advance in the research for the development of an automatized system to analyze weld defects detected by radiographs. This work describes a study of nonlinear pattern classifiers, implemented by artificial neural networks, to classify weld defects existent in radiographic weld beads, aiming principally to increase the percentage of defect recognition success obtained with the linear classifiers. Radiographic patterns from International Institute of Welding (IIW) were used. Geometric features of defect classes were used as input data of the classifiers. Using a novel approach for this area of research, a criterion of neural relevance was applied to evaluate the discrimination capacity of the classes studied by the features used, aiming to prove that the quality of the features is more important than the quantity of features used. Well known for other applications, but still not exploited in weld defect recognition, the analytical techniques of the principal nonlinear discrimination components, also developed by neural networks, are presented to show the classification problem in two dimensions, as well as evaluating the classification performance obtained with these techniques. The results prove the efficiency of the techniques for the data used.     

基于神经网络的磁瓦表面缺陷检测识别

目的针对传统算法提取磁瓦表面缺陷的局限性,以及通过人为选择缺陷特征进而判断缺陷种类的方法精度不足等问题,结合改进的UNet模型和一个分类神经网络提出一种磁瓦缺陷检测识别算法。方法改进的UNet模型用于提取缺陷,而分类神经网络则用于对所提取的缺陷区域进行分类识别。为了提高模型的分类精度,使用空洞卷积对UNet模型部分卷积层和池化层进行替代,以减少多次池化带来的细节丢失的问题,同时,增加多次跳跃连接,使UNet模型能够融合更多的卷积特征。结果经实验验证表明,改进UNet模型对缺陷区域的预测精度可达到93%。根据预测结果使用分类神经网络对缺陷进行分类,经实验验证,分类的精度可达94%,满足工业要求。结论改进的UNet模型对磁瓦缺陷提取精度有所提高,分类神经网络的缺陷分类精度较高。结合改进的UNet模型和分类神经网络能同时并有效地实现缺陷提取和分类识别,为磁瓦质量检测和性能评估打下基础。     

焊缝表面缺陷激光视觉传感HOG-SVM的检测方法

为了实现对焊缝表面缺陷的自动检测与分类,研究一种有效识别焊缝表面缺陷的激光视觉检测方法.通过激光视觉传感器采集焊缝图像并进行预处理,包括图像分割,灰度化,平滑去噪以及焊缝轮廓提取.采用方向梯度直方图(Histogram of Oriented Gradient, HOG)提取焊缝激光条纹轮廓图像的特征向量.其次,基于5折-交叉验证网格搜索方法进行模型参数寻优,最终建立了支持向量机(Support Vector Machine, SVM)智能模型识别与分类焊缝表面缺陷.通过调整焊缝轮廓提取算法、HOG特征维度得到不同特征数据并进行对比、分析焊缝缺陷的识别效果.在相同试验条件下,发现支持向量机比随机森林分类器、K最近邻分类器以及朴素贝叶斯分类器的识别率更高,达到97.86%.基于HOG-SVM的焊缝表面缺陷智能识别方法可有效提高焊缝缺陷(气孔、凹陷、咬边)及无缺陷的分类精度.     

基于时频判别特征的焊缝超声检测缺陷分类

根据超声检测信号的瞬变特性,针对焊缝检测的缺陷分类问题,提出用判别追踪算法提取缺陷信号的局部时频判别特征,并结合概率神经网络实现了焊缝超声检测信号的缺陷分类.在提取时频判别特征时,提出考虑新选原子与已选原子的相关性的判别基提取方案,以降低特征之间的冗余,使提取出的特征能更有效地鉴别不同类别的缺陷.用该方法对一电子束焊缝试块中的缺陷进行了分类,结果表明,时频判别特征适合超声信号的缺陷分类,并能有效地抑制晶粒噪声的影响,考虑判别原子间相关性后可获得更高的分类正确率.     

An adaptive-network-based fuzzy inference system for classification of welding defects

In this paper, we describe an adaptive-network-based fuzzy inference system to recognise welding defects in radiographic images. In a first stage, image processing techniques, including noise reduction, contrast enhancement, thresholding and labelling, were implemented to help in the recognition of weld regions and the detection of weld defects. In a second stage, a set of 12 geometrical features which characterise the defect shape and orientation was proposed and extracted between defect candidates. In a third stage, an adaptive-network-based fuzzy inference system (ANFIS) for weld defect classification was used. With the aim of obtaining the best performance to automate the process of the classification of defects, of all possible combinations without repetition of the 12 features chosen, four were used as input for the ANFIS. The results were compared with the aim to know the features that allow the best classification. The correlation coefficients were determined obtaining a minimum value of 0.84. The accuracy or the proportion of the total number of predictions that were correct was determined obtaining a value of 82.6%.     

����KPCA�İ�������ȱ��ʶ�𷽷�

引入核方法分析研究了现有的板坯表面缺陷识别方法,提出了一种新的核函数,并将其应用到板坯表面缺陷特征提取中,用传统的支持向量机对图像进行分类,试验结果表明,新核函数提取的特征识别效果最好,识别率达到了91.55%。     

Intelligent pattern recognition and diagnosis of ultrasonic inspection of welding defects based on neural network and information fusion

Abstract

The detection of defects in real manual metal arc welds using ultrasonic non-destructive testing has been investigated. Twenty-six features, extracted from three domains, were applied for recognition of defect type. To increase the reliability and accuracy of identification and classification, statistical analysis was used to evaluate the features extracted from ultrasonic defect echoes. The subset of optimum feature was then selected using the method of discriminant analysis. An intelligent defect evaluation method derived from the study is presented. The results show that statistical analysis is an effective method for feature evaluation. The uncertainty of defect diagnosis can be decreased by the information fusion method, and for three specific defect types, defects were correctly identified in approximately 93% of cases.     

MFL signals and artificial neural networks applied to detection and classification of pipe weld defects

This work evaluates the use of artificial neural networks (ANNs) for pattern recognition of magnetic flux leakage (MFL) signals in weld joints of pipelines obtained by intelligent pig. Initially the ANNs were used to distinguish the pattern signals with non-defect (ND) and signals with defects (D) along of the weld bead. In the next step the ANNs were applied to classify signal patterns with three types of defects in the weld joint: external corrosion (EC), internal corrosion (IC) and lack of penetration (LP). The defects were intentionally inserted in the weld bead of a pipeline of API 5L-X65 steel with an outer diameter of 304.8 mm. In this way, the MFL signal itself, digitized with 1025 points, was used as the ANN input. Initially the signals were used as inputs for the neural network without any type of pre-processing, later four types of pre-processing were applied to the signals: Fourier analysis, Moving-average filter, Wavelet analysis and Savitzky–Golay filter. Signal processing techniques were employed to improve the performance of the neural networks in distinguishing between the defect classes.

The results showed that it is possible to classify signals of classes D and ND using ANN with very efficient results (94.2%), as well as for corrosion (CO) and LP signals (92.5%). Also it is possible to classify the defect pattern signals: EC, IC and LP using neural networks with an average rate of success of 71.7% for the validation set.     

基于优化Gabor滤波器的铸坏表面缺陷检测应用研究

目的提高金属铸坯表面缺陷检测精度。方法由于金属铸坯表面上存在鱼鳞状构造,其亮度和背景区域纹理特征不一致,而且有缺陷和无缺陷的区域的灰度值极其相似,使得缺陷非常难以准确检测出来。为解决上述问题,以便更有效地检测表面缺陷,通过详细分析金属铸坯表面缺陷特征,将该类零件表面缺陷分为两种类型,提出一种基于优化Gabor滤波器的金属表面缺陷检测算法,该算法通过设计两种评价函数,利用评价函数最大限度地提高无缺陷和缺陷区域之间的能量差,以选取Gabor滤波器四个最佳参数,同时使用双阈值滤波方法,以减少由于噪声和伪缺陷引起的测量误差。结果利用3种滤波算法对四十幅带有缺陷的图像进行试验,实验表明该算法在角部裂纹、细裂纹和伪裂纹检测精度分别达到92.50%、92.50%和95.50%。结论 Opt-Gabor算法能根据已分类的两种不同类型的裂纹较为准确地检测出铸坏表面缺陷,在测量精度上略优于其他几种算法。     

Time frequency and wavelet transform applied to selected problems in ultrasonics NDE

In this paper, we contribute by the development of some signal processing in order to enhance the sensibility of flaw detection, to measure thin materials thickness and to characterize defects in nature (planar or volumetric). Features for discrimination of detected echos are extracted in time domain, spectral domain and discrete wavelet representation. Compact feature vector obtained is then classified by different methods: K nearest neighbour algorithm, statistical Bayesian algorithm and artificial neural network. Mallat decomposition algorithm is also developed in order to enhance flaw detectability. Finally, time frequency algorithms based on STFT, Wigner–Ville, Gabor transform are developed and applied to thickness measurements of materials with small thickness.     

Automatic identification of different types of welding defects in radiographic images

Radiographic testing is a well-established non-destructive testing method to detect subsurface welding defects. In this paper, an automatic computer-aided identification system was implemented to recognize different types of welding defects in radiographic images. Image-processing techniques such as background subtraction and histogram thresholding were implemented to separate defects from the background. Twelve numeric features were extracted to represent each defect instance. The extracted feature values are subsequently used to classify welding flaws into different types by using two well-known classifiers: fuzzy k-nearest neighbor and multi-layer perceptron neural networks classifiers. Their performances are tested and compared using the bootstrap method.     

偏置量对固结磨料小工具头抛光面形收敛效率的影响

目的 解决自由曲面磨抛面形收敛困难的问题,提高抛光小工具头的抛光效率.方法 提出一种偏置式固结磨料小工具头,基于固结磨料小工具头的结构特征参数,建立抛光小工具头的去除函数理论模型,并进行仿真分析,应用定点抛光法建立抛光小工具头去除函数实验模型,并验证抛光小工具头理论去除函数合理性,基于CCOS技术原理建立工件表面定量去除模型,通过虚拟加工实验探索偏置量对固结磨料小工具头抛光钛合金后的面形收敛效率的影响.结果 归一化理论去除函数曲线与实验曲线吻合度较高,定点抛光去除函数仿真模型能够很好地预测定点抛光斑的去除轮廓形状.抛光小工具头抛光钛合金的面形误差随偏置量增加,呈现先减小、后增大的趋势,无偏置的抛光小工具头抛光后,面形数据均方根(RMS)收敛效率为54.56％,波峰值与谷峰值之差(PV)的收敛效率为60.21％,当抛光小工具头偏置量为1.5 mm时,抛光后的RMS收敛效率达到最高,为73.83％,PV收敛效率为69.68％.结论 固结磨料小工具头去除函数理论模型可指导确定性材料去除,偏置量为1.5 mm时的抛光小工具头具有最强的修正误差能力,可以显著提高固结磨料小工具头抛光工艺的面形收敛效率.     

Estimated accuracy of classification of defects detected in welded joints by radiographic tests

Over the last two decades, there has been a considerably increase in the number of publications of research projects for the detection and classification of welding defects in radiographs using image processing and pattern recognition tools. All these research projects aim to set up an automatic or semi-automatic classification system for weld joint defects detected by the radiographic method. A classification system as such would allow a reduction in some inherent inexactnesses that occur in the conventional method, consequently increasing the precision of the report. This work is a study to estimate the accuracy of classification of the main classes of weld defects, such as: undercut, lack of penetration, porosity, slag inclusion, crack or lack of fusion. To carry out this work nonlinear pattern classifiers were developed, using neural networks. Also the largest number of radiographic patterns as possible was used as well as statistical inference techniques of random selection of data with (Bootstrap) and without repositioning in order to estimate the accuracy of the classification. The results pointed to an estimated accuracy of around 80% for the classes of defects analyzed.     

基于微元材料去除模型的单摆抛光平面度预测

为探究单摆参数对抛光工件平面度的影响,提出一种基于速度和压强分布耦合的抛光微元材料去除模型,以预测工件表面平面度。从单颗磨粒的材料去除出发,建立工件表面各微元单位时间内材料去除厚度模型,并将工件相对抛光垫速度和工件表面压强分布耦合代入模型;根据工件初始面形提取微元高度值,结合各微元材料去除的厚度,计算抛光后的工件表面平面度;试验验证平面度预测方法。结果表明：仿真与实际抛光后的面形的变化趋势相同,平面度PV₂₀值绝对偏差小于12.0%,平面度预测可靠。     

基于主成分分析的多域特征融合轴承故障诊断

针对复杂工况下难以区分轴承故障状态的问题,提出一种基于主成分分析的多域特征融合轴承故障诊断方法。采集轴承振动加速度信号,提取轴承时域新量纲一化特征、频域幅值谱特征和时频域经验模态分解特征共13维特征用于完整表征轴承状态;利用主成分分析方法对所提取特征融合与降维,降低诊断模型复杂度与数据分析难度;最后,选择合适的卷积神经网络进行分类,通过石化机组故障诊断实验平台进行验证。结果表明：多域融合特征相对于单域特征诊断效果更好,卷积神经网络分类模型相对于其他经典分类模型诊断准确率更高,融合诊断分类方法整体诊断准确率达到86%。     

基于组合矩和随机森林的转子轴心轨迹识别

针对大型旋转机械难以获得大量故障样本和不变矩识别率低的问题,提出基于组合矩和随机森林模型的转子轴心轨迹识别方法。采用实测的轴心轨迹作为样本,采用Sobel算子提取轴心轨迹的轮廓,基于轮廓的形状几何特征和不变矩构造组合矩。将不变矩和组合矩作为随机森林模型的输入进行分类,证明了组合矩的分类准确率最高。对随机森林、支持向量机和BP神经网络的分类效果进行了对比,结果表明：随机森林的分类准确率要高于支持向量机和BP神经网络,并且识别时间较短,是诊断旋转机械故障的一种新方法     

Analysis of defect mechanisms in polishing of tool steels

The polishing process in the mold and die making industries is nowadays still predominantly done manually. As a consequence of this the quality of the mold strongly depends on the worker’s skill, experience and also on his form on the day, patience and concentration. Furthermore, polishing is in most cases the last manufacturing step of the process chain and occurring surface defects are critical and often a “knock-out-criterion”. Until now there exists no systematical acquisition or explanation for the appearance of this polishing defects. This paper shows the results of experiments describing the polishing process and defect mechanisms in order to generate process strategies for manufacturing “defect-free” high-gloss polished tool steel surfaces. Ten different steel grades were analyzed in order to see how the final surface quality is influenced by e.g. the polishing system, the degree of purity or the microstructure. The surface quality is represented by roughness values and SEM-images. It could be concluded that the degree of purity and the homogeneity of the steel material are crucial to the final surface quality. The lower the amount of inclusions, the better the surface quality. Furthermore, a classification of the occurred defects during the polishing process is shown in this paper.