Search

It is challenging to apply deep learning in professional fields that lack big data support, especially in industrial structure health assessments using ultrasonic guided wave nondestructive testing (NDT) method. To solve this problem, one feasible solution is to introduce the concept of NDT physics into a deep neural network to compensate for the network's poor predictive abilities when trained on small datasets. Therefore, we propose a physics-informed deep neural network, named GuwNet, based on a unidirectional oblique-focusing (UOF) high-frequency, high-order shear horizontal guided wave electromagnetic acoustic transducer (EMAT) to quantify microcrack defects more accurately. First, the designed focused-transmission omnidirectional-reception UOF-EMAT can produce pure high-frequency, high-order guided waves. Through a circumferential arrangement of multiple receiving transducers, the maximum amount of information can be obtained regarding the reflected waves of the defect. This method solves the inherent problems of an EMAT (i.e., low energy conversion efficiency) and achieves effective detection of microcrack defects. Second, we study the quantification principle of microcrack defects suitable for UOF-EMAT, and propose a deep neural network using physical knowledge regarding this theory. We rationally design the network structure based on the quantitative principles and logic obtained from this article. In addition, feedback and feedforward loss functions suitable for evaluating different forms of variables are proposed to integrate the physical concepts of ultrasonic guided wave testing into the neural network training. Finally, we verify the performance of the proposed GuwNet based on the UOF-EMAT. Compared with traditional nonphysics-informed methods, the length, depth, and direction of the quantification errors are reduced to 0.127 mm, 0.279% dt, and 1.843°, respectively, and the average quantification error is reduced by more than 80%. [ABSTRACT FROM AUTHOR]

To overcome the shortcomings of low energy conversion efficiency of electromagnetic acoustic transducers (EMATs), point-focusing shear horizontal (PFSH) wave EMAT is used to focus the wave energy into a specific area. Many factors will affect the capability of the focusing transducer, and in addition to considering the signal intensity, the detection accuracy is also required to be investigated. Specifically, to simplify the test process, we use the orthogonal test method to study the effect of different influence parameters on signal intensity and focal area dimensions. Seven factors are selected, and three results are determined in the test. Range analysis shows that for signal amplitude $M$ , the top three impact factors are the coil width $w$ , coil turns $n$ , and focal length lF (equal to bandwidth factor $\alpha $). Moreover, magnet number $m$ and frequency $f_{c}$ dominate the effective focal length $l_{\text {fd}}$ , and aperture angle $\theta $ determines the effective focal width $w_{\text {fd}}$. To enable higher signal intensity and smaller focal area dimensions, it is necessary to consider various factors on the PFSH-EMAT focusing performance. The test’s signal intensity with optimized parameters’ combination at the focal point is nearly 144.42% higher than the average of all the tests, $l_{\text {fd}}$ decreased by 37.84%, and $w_{\text {fd}}$ decreased by 50.59%. The experiment also verified that focusing EMAT with optimized parameters has a better focusing performance. [ABSTRACT FROM AUTHOR]

As a kind of nondestructive testing (NDT) method, shear-horizontal (SH)-guided wave detection technology is widely used on an electromagnetic acoustic transducer (EMAT). Although ultrasonic-guided waves perform well in defect location, it is difficult to obtain detailed information about defects, and the low efficiency of EMAT energy conversion still reduces the EMAT’s performance. Therefore, in this work, the defect detection method of different shapes and sizes by point-focusing shear-horizontal (PFSH)-guided wave EMAT with the use of periodic permanent magnet (PPM) is investigated through simulation and experiment. For the purpose of defect classification and quantification, the extraction principles of defect features are obtained through simulation based on the circumferential scatter diagrams, and the neural network (NN) is used to process the features extracted from the experimental data. The results show that by extracting effective defect features from the scatter diagram, high-accuracy classification and high-precision quantification of defects under the influence of the focusing transducer can be achieved. [ABSTRACT FROM AUTHOR]

Ultrasonic guided wave testing technology is currently widely used in industrial nondestructive testing (NDT), including defect detection in the floors of large tanks and oil pipelines. However, in addition to noise, practical scenarios of signal detection also present mode aliasing problems, which make it difficult to accurately identify and locate defects. In this paper, we propose an improved shear horizontal guided wave mode identification method using a variational mode decomposition (VMD) algorithm and a time-of-flight (TOF) extraction method using the synchrosqueezed wavelet transform (SSWT) algorithm. Moreover, we use the wavelet denoising method to denoise the original signal before applying VMD. The results show that the TOF errors obtained by the VMD method are all less than 5% and that the wavelet denoising of the original guided wave data can further reduce the errors (to less than 2%). In addition, the SSWT can modify the time-frequency analysis results of intrinsic mode functions obtained by the VMD method and provides accurate TOF data for different modes. Therefore, the proposed ultrasonic guided wave signal method is helpful for improving the defect detection sensitivity and accuracy of SH waves. [ABSTRACT FROM AUTHOR]

We realized a phase-coherent oblique point-focusing shear-horizontal (SH) guided-wave electro- magnetic acoustic transducer (EMAT) composed of variable-spacing periodic permanent magnets (PPMs) and racetrack coils. For traditional focusing transducers, the necessary focal position adjustment in defect detection requires a redesign of the coil structure. More conveniently, this new transducer structure arrangement can achieve wave focusing and focal position change by rationally adjusting the layout of the PPM without changing the coil structure. Simulation results show that this newly designed transducer has good focusing performance: it can successfully focus the signal to a preset point, and the signal amplitude is nearly double that of the nonfocusing side. In addition, the focusing performance optimization of the transducer has been studied. The experimental results agree well with the actual location and size of a defect, which verifies the effectiveness of the newly designed focusing transducer in defect detection. [ABSTRACT FROM AUTHOR]

As a class of devices used in sound detection, electromagnetic acoustic transducers (EMATs) have been widely used in the field of nondestructive testing (NDT) owing to their advantages such as contact-free operation, wide applicability, and high performance. However, their low energy-conversion efficiency is the main drawback that limits usage in industrial testing. In this work, we report the effect of different parameters of the point-focusing shear-horizontal EMAT (PFSH-EMAT) on the signal intensity of the receiving transducer. The impact factors of the focusing transducer are as follows: number of magnets in a row m, fan-shaped periodic permanent magnet (FPPM) remanence magnetization ${B}_{{\text {r}}}$ , coil width w, coil winding number n, aperture angle $\theta $ , focal length ${l}_{{\text {F}}}$ , lift-off distance ${h}_{\text {l}}$ , excitation current frequency ${f}_{{\text {c}}}$ , and current amplitude ${I}_{{\text {c}}}$. To improve the analysis efficiency, an ${L}_{{{32}}}$ (49) orthogonal table is used to investigate the nine different factors at four levels, which can be calculated through finite element simulations. The effect of each factor on the signal intensity is obtained by range analysis, and the optimal combination of these impact factors can be achieved by reasonable level selection. Through range analysis, the influence degree of each factor is obtained, and the parameter combination is optimized by analyzing the test results to improve the PFSH-EMAT’s performance. The experimental results show that the optimized PFSH-EMAT is 170% more efficient than the average of the top-three signal intensities in the orthogonal test, which proves the effectiveness of the proposed optimization method. [ABSTRACT FROM AUTHOR]