Two novel fast consensus algorithms based on local information of first-order discrete multi-agent systems under a directed network are proposed in this paper. By applying matrix theory and the frequency-domain analysis methods, two sufficient conditions about the convergence rate of the systems are presented, respectively, where the proportional-like gain feedback and incremental proportional–integral–differential gains feedback only with local information are added. Finally, a numerical example is given to show the double gains regulation algorithm proposed in this paper has much faster consensus rate compared with the classical consensus algorithm in the same condition for its two-degree freedom parameters.
© 2016 Informa UK Limited, trading as Taylor & Francis Group.

设计实现了一套涡流热成像无损检测系统,对试件进行涡流加热,使用热像仪进行探测,以热图像的形式展示试件温度变化情况来表征试件的损伤特征,并使用基于深度学习网络的智能识别方法诊断试件的损伤程度。该无损探伤方法使用卷积神经网络逐层挖掘可疑缺陷区域的本质特征。实验结果表明:该系统对金属板材试件损伤程度识别的准确率能达到97.3%,证明该系统具有较高的准确率和较好的适应性。

This article proposes a novel simplified model that describes the real part (in-phase component) of the difference in pickup coil voltage when an eddy current (EC) sensor consisting of two coils (excitation and pickup coils) is placed above the titanium (Ti) alloy sheet. A parameter that encapsulates the coil geometry factors is integrated into the classical Dodd-Deeds model, and then, the model is simplified by combining with the electromagnetic properties of Ti alloy. The use of the simplified model provides a thickness measurement method for Ti alloy sheets. The measured thickness can be calculated directly from the calibration signal by using the model, without the need to predict response by solving the forward model in advance. Experimental measurements were conducted on TC4 (Ti-6Al-4V) Ti alloy sheets of different thicknesses with a developed EC sensor and measurement system. The experiment verified the proposed model and measurement method. The experimental results shown that the maximum measurement error is less than 2.86%, which is greatly lower than the permissible error of the current industry standard. This study provides a theoretical basis and a fast method for EC thickness measurement of Ti alloy.
© 1963-2012 IEEE.

针对单向碳纤维复合材料平板缺陷远场涡流检测存在的伪峰干扰问题,在分析远场涡流检测信号伪峰产生机理及伪峰特征的基础上,提出了利用对称双检测线圈构成远场涡流检测探头进行伪峰识别的方法,建立了利用该探头对单向碳纤维复合材料平板缺陷进行远场涡流检测的仿真模型,借助有限元方法进行仿真计算,得到了五组不同间距缺陷的检测信号,并利用所提出的伪峰识别方法对仿真计算获得的检测信号峰值进行分析识别,结果表明所提出的伪峰识别方法在不同的缺陷分布情况下都可以准确识别出伪峰和实际缺陷对应的真实峰值,从而验证了所提出的伪峰识别方法的有效性及准确性,为单向碳纤维复合材料平板缺陷远场涡流检测的伪峰消除问题提供了解决思路,有效提高了单向碳纤维复合材料平板缺陷远场涡流检测的准确性。

Titanium (Ti) is an ideal structural material whose use is gradually emerging in civil engineering. Regular defect evaluation is indispensable during the long-term use of Ti sheets, which can be performed effectively using eddy current (EC) imaging, a method of visualizing defects that is convenient for inspectors. However, as EC scan images contain abundant information and have discrepancies in terms of their quality, it is difficult to extract effective features, thus affecting the evaluation results. In this article, we propose a method that combines the EC imaging technology with a quantitative evaluation method for Ti sheet defects based on the deep belief network (DBN) and least squares support vector machine (LSSVM). A multilayer DBN is constructed to extract the effective features from EC scan images for Ti sheet defects. Based on the extracted feature vectors, a multi-objective regression model of defect dimensions is established using the LSSVM algorithm. Then, the dimensions of Ti sheet defects such as length, diameter, and depth are quantitatively evaluated by the effective features and the efficient regression model. The experimental results show that the evaluation errors for the defect lengths and depths tested are less than 3 and 5%, respectively, confirming the validity of the proposed method.
© Copyright © 2020 Bao, Ye, Wang and Wu.

针对单向碳纤维复合材料分层缺陷难以检测的问题,设计了一个共面三矩形线圈探头,建立了利用该探头进行单向碳纤维复合材料分层缺陷垂直涡流检测的有限元模型,并利用该模型仿真计算了存在不同厚度分层缺陷时垂直涡流检测探头输出的感应电压信号变化情况。仿真结果表明,所设计的探头可灵敏地检测出单向碳纤维复合材料分层缺陷,并且在探头扫描检测分层缺陷的过程中,探头输出的感应电压虚部会出现成对的峰值和次峰值,峰值与分层厚度成正比,次峰值对的出现位置对应于分层缺陷边缘的位置,通过对峰值大小和次峰值对的出现位置进行分析,可以实现单向碳纤维复合材料分层缺陷厚度和范围的定量化评估,为实际工程应用提供了有价值的参考。

由于边缘效应的影响,TA2钛板涡流C扫描图像中缺陷区域与背景区域混杂,边缘对比度低,难以实现缺陷区域定量化评估。针对以上问题,提出了一种基于简单线性代聚类（SLIC）超像素算法和密度聚类算法的涡流C扫描图像分割方法。首先对TA2钛板进行涡流无损检测,获得包含有TA2钛板表面缺陷的涡流C扫描图像;然后利用SLIC超像素算法将获得的C扫描图像预分割成若干小区域;最后通过密度聚类算法对预分割后的C扫描图像进行区域合并,得到受检测TA2钛板C扫描图像中的缺陷区域,通过对缺陷区域进行细化处理和轮廓跟踪可以得到TA2钛板缺陷区域的估计长度,实现对TA2钛板表面缺陷的定量化评估研究。实验结果表明,该方法能够有效地实现受检测的TA2钛板表面缺陷的可视化、定量化分析,与传统的图像分割方法相比分割效果更优、准确性更高。

In eddy current testing, the trajectory of the impedance data due to a defect is presented as a Lissajous curve (LC) in the complex plane. This paper proposes a novel analytical model for describing a LC. Further, a new feature extraction method is implemented which automatically computes four geometric features (amplitude, width, angle and symmetry) from Lissajous figures. In addition, six machine learning-based classifiers are used for automatic defect identification based on these features. High detection rates are achieved for both the simulated and experimental data, which demonstrates the flexibility of the analytical model and the validity of the methodology.
© 2019 Elsevier Ltd

钛板电涡流成像检测易受工业现场中的噪声影响,包含噪声的检测图像往往难以提取较好的特征,从而影响分类识别精度。针对以上问题,提出了一种基于栈式稀疏降噪自编码（SSDAE）深度神经网络的钛板缺陷电涡流检测图像分类方法。将稀疏性限制引入降噪自编码器并进行逐层无监督自学习,然后将自编码器栈式组合后添加逻辑识别（LR）层,构建出SSDAE深度神经网络,网络在有监督微调后可实现钛板缺陷电涡流图像特征自动提取与分类识别。稀疏性限制的引入提高了特征学习能力,降噪自编码器的栈式组合提高了深度网络的鲁棒性。实验结果表明,相比其他常规方法,所提出方法不仅在理想环境下有更高的分类准确率,且该方法能有效抵抗噪声,在复杂工况下能更有效地对钛板缺陷进行分类识别。

Eddy current testing technology is widely used in the defect detection of metal components and the integrity evaluation of critical components. However, at present, the evaluation and analysis of defect signals are still mostly based on artificial evaluation. Therefore, the evaluation of defects is often subjectively affected by human factors, which may lead to a lack in objectivity, accuracy, and reliability. In this paper, the feature extraction of non-linear signals is carried out. First, using the kernel-based principal component analysis (KPCA) algorithm. Secondly, based on the feature vectors of defects, the classification of an extreme learning machine (ELM) for different defects is studied. Compared with traditional classifiers, such as artificial neural network (ANN) and support vector machine (SVM), the accuracy and rapidity of ELM are more advantageous. Based on the accurate classification of defects, the linear least-squares fitting is used to further quantitatively evaluate the defects. Finally, the experimental results have verified the effectiveness of the proposed method, which involves automatic defect classification and quantitative analysis.