利用深度神经网络和小波包变换进行缺陷类型分析

超声检测中对缺陷进行类型分析通常取决于操作人员对于特定专业知识的了解及检测经验,从而导致其分析结果的不稳定性和个体差异性。本文提出了一种使用小波包变换提取缺陷特征信息,并应用深度神经网络对得到的信息进行分类识别的方法。利用超声相控阵系统对于不锈钢试块上的通孔、斜通孔和平底孔进行超声检测,并对得到的超声回波波形按照新方法进行分析。实验结果表明,使用小波包变换后的数据进行分类识别能够在提高识别准确率的同时降低神经网络的学习时间,而使用深度神经网络相比通用的BP神经网络以可接受延长学习时间的代价提高了识别的准确率。采用新方法后,缺陷分类正确率提高了21.66%,而网络学习时间只延长了91.9s。在超声检测中使用小波包变换和深度神经网络来对于缺陷进行类型分析,能够排除人为干扰,增加识别准确率,对于实际应用有着极大的意义。     

基于卷积神经网络的气体绝缘组合开关盆式 绝缘子螺栓松动检测方法*

盆式绝缘子是GIS的关键绝缘器件,它与两侧气室法兰通过螺栓进行紧固连接,当螺栓松动时会导致盆式绝缘子应力分布不均,严重时会引起绝缘子破裂,从而影响GIS运行的安全性和可靠性。文章搭建了盆式绝缘子螺栓松动超声波检测系统,以获取不同螺栓不同工况下的超声信号,基于卷积神经网络对超声信号进行特征提取,并且与BP神经网络的训练结果进行对比分析。实验结果表明,卷积神经网络可以自动提取GIS盆式绝缘子螺栓松动特征量,对十种螺栓松动工况的识别准确率达到100%,相比于BP神经网络具有较高的识别准确率,该方法可以直接用于盆式绝缘子螺栓松动检测。     

Sonocatalyzed synthesis of 2-phenylvaleronitrile under controlled reaction conditions--a kinetic study

In the current study, kinetics of synthesis of 2-phenylvaleronitrile (PVN) was successfully carried out by selective C-alkylation of benzyl cyanide (BC) with n-bromopropane (BP) using aqueous KOH and catalyzed by TBAB under ultrasonic (300W) assisted organic solvent-free conditions. Selective monoalkylation of benzyl cyanide has been achieved by controlling the reaction conditions and has been followed using gas chromatogram. The effects of various parameters such as agitation speed, catalyst concentration, KOH concentration, benzyl cyanide concentration, volume of water, ultrasonic frequency and temperature were studied systematically to understand their influence on the rate of the reaction. The experimental observations are consistent with an interfacial-type process. Further the kinetic results demonstrate clearly, that ultrasonic assisted phase-transfer catalysis significantly increased the reaction rate when compared to silent reactions.     

Comparison of optical detection system ,PVDF detection system, and PVDF needle hydrophone for optoacoustic tomography

Optoacoustic tomography (PAT) is a two-dimensional medical imaging method that has the advantage of optical contrast and resolution of ultrasonic waves. The detection systems with a high sensitivity can be used for detecting small tumors, located deeply in human tissues, such as the breast. In this study, the sensitivity of existing ultrasonic detection systems has been compared experimentally with that by using thermoelastic waves as a broadband ultrasonic source. For the comparison, an optical stress transducer(OST), a polyvinylidene difluoride (PVDF) sheet and a calibrated PVDF needle hydrophone were used.To ensure all of the detection systems interrogated by the same ultrasonic field, a small optical instrument that fixed the generating laser head was constructed. The sensitivity was evaluated by measuring signalto-noise ratios (SNRs) and noise equivalent pressures (NEPs). The PVDF system, with a 4-kPa NEP has a 22 dB better performance than the OST. The OST showed nearly the same sensitivity as the hydrophone for detecting ultrasound waves at a 1-cm distance in water. PVDF detection system provides a useful tool for imaging of soft tissues because of its high sensitivity and broad detection range.     

Hidden corrosion detection in aircraft aluminum structures using laser ultrasonics and wavelet transform signal analysis

Preliminary results of hidden corrosion detection in aircraft aluminum structures using a noncontact laser based ultrasonic technique are presented. A short laser pulse focused to a line spot is used as a broadband source of ultrasonic guided waves in an aluminum 2024 sample cut from an aircraft structure and prepared with artificially corroded circular areas on its back surface. The out of plane surface displacements produced by the propagating ultrasonic waves were detected with a heterodyne Mach-Zehnder interferometer. Time-frequency analysis of the signals using a continuous wavelet transform allowed the identification of the generated Lamb modes by comparison with the calculated dispersion curves. The presence of back surface corrosion was detected by noting the loss of the S(1) mode near its cutoff frequency. This method is applicable to fast scanning inspection techniques and it is particularly suited for early corrosion detection.     

Presence detection under optimum fusion in an ultrasonic sensor system

Reliable presence detection is a requirement in energy-efficient occupancy-adaptive indoor lighting systems. A system of multiple ultrasonic sensors is considered for presence detection, and the performance gain from optimum fusion is studied. Two cases are considered wherein an individual sensor determines presence based on (i) local detection by processing echoes at its receiver, and (ii) the optimum Chair-Varshney fusion rule using multiple sensor detection results. The performance gains of using optimum fusion over local detection are characterized under different sensor system configurations and it is shown that improved detection sensitivity is obtained over a larger detection coverage region.     

An Experimental Approach for Detection of the Acoustic Radiation Induced Static Component in Solids

We propose an experimental approach to directly detect the acoustic radiation induced static component(SC)of primary longitudinal(L) wave propagation in solids using an ultrasonic pitch-catch technique,where a lowfrequency ultrasonic transducer is used to detect the SC generated by the co-propagating primary L-wave tone burst that is excited by a high-frequency ultrasonic transducer.Essentially,the experimental approach proposed uses a dynamic method to detect the SC generated.The basic requirem...     

纵向带状裂隙形貌的逆时偏移超声成像

传统的工业超声成像方法通常只能确定缺陷的位置与横向尺寸,无法获得缺陷的形貌信息.一些特殊的缺陷,如纵向裂纹,是典型的例子.基于多阵元技术,开展了固体介质缺陷逆时偏移超声成像方法的数值与实验研究.针对铝块平底纵裂纹及内部纵裂纹两种传统方法无法有效成像的缺陷,首先开展了单分量逆时偏移成像方法研究,给出了基于数值仿真的逆时偏移成像结果以及基于多阵元超声成像实验系统实验测试的逆时偏移成像结果.进一步开展了基于多分量位移检测与转换横波分离的逆时偏移成像方法研究,并提出了基于新型多分量激光干涉仪进行检测的思路.数值仿真结果证实了多分量逆时偏移图像重建结果可以克服单分量方式的缺点,得到明显优于单分量检测时的图像.     

多层介质中超声相控阵声场仿真*

由于良好的声束偏转与聚焦特性,超声相控阵已经广泛应用于多层固体介质的缺陷检测。当超声束经过多层介质时,由于反射、透射以及模式转换的存在,多种声束存在于这种结构中,使得声场分析变得复杂。为了提高多层介质检测的准确性,有必要对超声声场的分布规律进行深入地了解。该文结合高斯声束等效点源模型以及射线追踪法,给出了相控阵声源在多层固体介质中激发声场的仿真方法,并且模拟计算了一维线型相控阵在楔块-铝-黄铜-钢四层固体介质中的辐射声场。通过对不同延时法则的计算,实现了声波在这种复杂介质中的偏转与聚焦,进而研究了不同焦点处聚焦声场的分布。结果表明:相控阵方法能使聚焦点处的声场幅值增大,能量集中,提高了检测分辨率;不同聚焦点处声场聚焦效果不同,实际检测时应根据检测区域结构及位置特点,合理放置相控阵换能器。与瑞利积分法的比较表明,该文的仿真方法适用于多层介质相控阵声场的计算。     

Inspection of cracks using laser-induced ultrasound with shadow method: Modeling and validation

A numerical model based on the finite element method (FEM) is developed for crack inspection using laser-induced ultrasonic waves with the shadow method. Before the simulation, the numerical code is verified by comparing the directivity patterns of ultrasonic waves with the experiment. The use of thermo-elastically generated ultrasonic waves for crack detection and evaluation with the shadow method is investigated by simulation. The simulation is validated by comparing with the experiment.     

一种基于2D-CNN的激光超声表面缺陷检测方法

激光超声表面缺陷检测的过程中,缺陷的定量表征通常依赖于操作者的判断,易受到人为因素干扰,致使检测结果不稳定.针对这一问题,提出一种基于图像识别的二维卷积神经网络(2D-CNN)的缺陷自动分类检测方法.利用有限元方法模拟激光超声检测过程,并采集超声信号数据用于训练分类模型;使用连续小变换(CWT)处理超声信号得到小波时频...     

Location of multiple proximate flaws using perpendicular NDT ultrasonic arrays

An improved method for ultrasonic location of multiple flaws using perpendicular ultrasonic arrays, working in near-field conditions, is presented. The method uses the pulse-echo technique and is based on the processing of the information acquired by both the elemental emitting transducers and their adjacent ones. This type of processing improves the performance of a previous method that sometimes presents limitations for the detection of multiples flaws. This new method is applied to a set of ultrasonic traces, obtained with an ultrasonic prototype specifically designed for testing this method, showing the improvement obtained in imaging results.     

Measurement of hydroxyl radical production in ultrasonic aqueous solutions by a novel chemiluminescence method

Measurement methods for ultrasonic fields are important for reasons of safety. The investigation of an ultrasonic field can be performed by detecting the yield of hydroxyl radicals resulting from ultrasonic cavitations. In this paper, a novel method is introduced for detecting hydroxyl radicals by a chemiluminescence (CL) reaction of luminol-hydrogen peroxide (H2O2)-K5[Cu(HIO6)2](DPC). The yield of hydroxyl radicals is calculated directly by the relative CL intensity according to the corresponding concentration of H2O2. This proposed CL method makes it possible to perform an in-line and real-time assay of hydroxyl radicals in an ultrasonic aqueous solution. With flow injection (FI) technology, this novel CL reaction is sensitive enough to detect ultra trace amounts of H2O2 with a limit of detection (3sigma) of 4.1 x 10(-11) mol L(-1). The influences of ultrasonic output power and ultrasonic treatment time on the yield of hydroxyl radicals by an ultrasound generator were also studied. The results indicate that the amount of hydroxyl radicals increases with the increase of ultrasonic output power (< or = 15 W mL(-1)). There is a linear relationship between the time of ultrasonic treatment and the yield of H2O2. The ultrasonic field of an ultrasonic cleaning baths has been measured by calculating the yield of hydroxyl radicals.     

Fiber optic liquid leak detection technique with an ultrasonic actuator and a fiber Bragg grating

We present a technique for liquid leak detection in which ultrasonic and optical waves are introduced into a fiber simultaneously. The system is based on an ultrasonic technique using an ultrasonic actuator and a fiber Bragg grating receiver. A fiber-guided ultrasonic wave is utilized to stress the fiber Bragg grating, which is remote from the ultrasonic transmitter. When the traveling ultrasonic wave encounters a liquid, part of the wave will leak out from the fiber, which results in an ultrasonic strain decrease in the fiber Bragg grating. The ultrasonic wave and its attenuation are detected by the light variation of a narrowband laser source reflected and transmitted from the fiber Bragg grating, and the amplitude variation of the ultrasound can eventually be correlated with the fiber area coupled with the liquid.     

Internal tissue displacement measurement based on ultrasonic wave Doppler signal digital detection and its application to fetal movement monitoring

We have developed a fetal movement monitoring system based on small displacement measurement of internal tissues. When ultrasonic pulses are transmitted to the fetus, the reflected ultrasonic waves which have a Doppler frequency shift due to the fetal movements are detected by using an ultrasonic pulsed Doppler technique. In this paper, we propose a displacement measurement method for internal tissues which is based on the Doppler signal digital detection technique. In the method, the received ultrasonic RF signals are sampled with a sampling frequency of four times higher than the centre frequency of the ultrasonic waves; the Doppler frequency shift signals are derived using digital signal processing. From the detected signals, the internal displacements are estimated using the arc-tangent method. The basic algorithm of the detection method has already been used in the area of blood flow sensing, however, we apply the algorithm to the displacement measurement of internal tissues. The comparison between the proposed method and the conventional method is presented. The fetal movement quantitative monitoring system based on the method which has been constructed is shown.     

改进的Faster-RCNN算法在聚乙烯管接头内部缺陷检测中的应用

超声相控阵技术是目前聚乙烯管道热熔接头内部缺陷检测的一种主流方法。提出了基于注意力机制的改进Faster-RCNN目标检测网络用于超声相控阵D扫图聚乙烯管接头内部缺陷检测。针对聚乙烯管道热熔接头内部超声相控阵D扫图小缺陷较多、特征信息容易丢失的问题,将残差网络(ResNet50)与特征金字塔网络(FPN)相结合作为骨干网络,并引入卷积注意力模块(CBAM)自适应细化特征。将SSD网络框架和Faster-RCNN网络框架用于模型训练和测试,使用VGG16、ResNet50、ResNet50+FPN、ACBM+ResNet50+FPN作为骨干网络依次对超声相控阵聚乙烯管道热熔对接接头内部缺陷样本进行训练对比。结果表明,改进的Faster-RCNN网络模型在聚乙烯管接头内部缺陷检测和分类方面有明显改进,对小缺陷的检测性能有了显著的提高。     

A Simple Model for Nonlinear Confocal Ultrasonic Beams

A confocally and coaxially arranged pair of focused transmitter and receiver represents one of the best geometries for medical ultrasonic imaging and non-invasive detection. We develop a simple theoretical model for describing the nonlinear propagation of a confocal ultrasonic beam in biological tissues. On the basis of the parabolic approximation and quasi-linear approximation, the nonlinear Khokhlov-Zabolotskaya-Kuznetsov （KZK） equation is solved by using the angular spectrum approach. Gaussian superposition technique is applied to simplify the solution, and an analytical solution for the second harmonics in the confocal ultrasonic beam is presented. Measurements are performed to examine the validity of the theoretical model. This model provides a preliminary model for acoustic nonlinear microscopy.     

Weak guided wave signal detection using period jump of Duffing system

A potential risk in ultrasonic guided wave testing is that weak echo signals from small defects may be submerged in noisy signals, which will cause missed detection. To overcome this shortcoming, a weak guided wave signal detection method based on period jump of the Duffing system is proposed in this paper. The critical state of the system period jump can be obtained by analyzing the bifurcation characteristics of the Duffing system with the variation of the driving force amplitude. A weak ultrasonic guided wave signal with the same frequency as the driving force is added to the driving force. This is equivalent to changing the driving force amplitude, which causes the period state to jump. Consequently, the weak guided wave signals can be identified based on the period jumps. The increase or decrease in the driving force amplitude due to the interference of the guided wave signal depends on the phase difference between the intercepted signal and the periodic driving force. The conditions for increasing and decreasing the driving force amplitude are out of phase with each other.They have an approximate phase difference of π within the same period. Two detection models for small-scale periodic states(SPS) and large-scale periodic states(LPS) are constructed, and the effectiveness of the models in identifying the guided wave signal is verified numerically and experimentally. The anti-noise interference capabilities of the two models are also compared.The results show that the SPS detection model provides unique results and a strong anti-noise ability, and effectively improves the sensitivity of small defect detection using ultrasonic guided waves.     

用斜探头激发的兰姆波对三层板参数进行反演测试研究

超声无损检测中逆问题(反演)的研究在众多的工业领域有广阔的应用前景。本文利用多模式兰姆波速度测量建立了一种基于误差函数的三层板参数反演算法;结合快速傅里叶变换(FFT)及自回归(AR)模型,还提出了一种用于精确检测多模式超声波相速度的“混合”谱估计方法。实验工作由两个普通的斜探头在三层复合结构的同一面激发与接收多模式兰姆波,通过反演得到此三层结构中的多个参数(厚度及其中某层的纵横波声速),实验测试所得到的反演结果与参数的实际值符合得较好。     

核电堆内构件围板螺栓超声检测优化有限元仿真研究

围板螺栓是核电堆内构件的关键紧固部件,典型的围板螺栓主要为外六角形式。在长期辐照和震动等恶劣环境服役过程中,其断裂韧性下降,脆性增加,最终导致螺栓退化开裂或断裂脱落,需要对其进行定期无损检测。然而由于其结构的复杂性,现有超声检测方法仍难以对其进行有效检测。为进一步提高超声检测方法对于围板螺栓内部缺陷的检测能力,针对堆内构件围板螺栓典型缺陷失效形式,通过有限元数值仿真技术开展适用于围板螺栓不同区域(螺栓过渡区域、螺杆区域和螺纹区域)的超声检测方法和工艺研究,对超声探头激励频率、晶片尺寸及超声波入射角度等进行优化,实现对不同区域15%缺陷横截面积占比的检测目标。为研发具有高度匹配性和高灵敏度的堆内构件围板螺栓超声传感器、实现对围板螺栓敏感区域的高精度检测提供理论指导。