Search

Defect depth is an essential indicator in magnetic flux leakage (MFL) detection and estimation. The quantification errors for defect depth are closely related to length and width errors, and this feature has always been used to support the operator's judgment in defect identification. However, the existing defect quantification algorithms based on shallow and deep neural networks only employed simple general network structures inspired by the field of artificial intelligence; consequently, these network structures lack the support of physical concepts and result in large quantification errors regarding defect size, especially depth. In this article, to describe and integrate the above theory into a deep neural network, we propose a physics-informed doubly fed cross-residual network (DfedResNet) suitable for MFL defect detection based on deep learning. Physics-based MFL defect quantification theory is studied and integrated into loss functions during the neural network training. DfedResNet quantifies defects in MFL data and automatically extracts deep features of defects. The experimental results show that it effectively achieves high-precision quantification of defect length, width, and depth simultaneously, especially defect depth. Moreover, it considers data from all three dimensions during network training, and use the originally measured magnetic signal data in place of recognized images to avoid defect information loss and further improve the quantification accuracy. The deep DfedResNet model proposed in this article reduces defect length and width quantification errors to within 0.3 mm and defect depth quantification errors to within 0.4% t. In addition, compared with other network structures and traditional algorithms, DfedResNet improves defect quantification accuracy by 1–2 orders of magnitude and thus achieves a high quantification performance. [ABSTRACT FROM AUTHOR]

Magnetic flux leakage (MFL) testing is widely used to detect and estimate defect in ferromagnetic materials. The lift-off of sensors caused the weakening of the detected signal inevitably. Therefore, it is necessary to correct lift-off for the detected MFL signal. In this article, we analyze the approximate negative exponential relationship between the three components of MFL signal of the defect and the lift-off based on magnetic dipole analytical method and establish a simplified numerical calculation model of MFL signal based on the lift-off. A lift-off correction method is also proposed to revise the three components of the MFL signal at a suitable range of lift-off efficiently. In this method, an exponential function compensation is introduced and only the lift-off correction value is concerned. The validity of the correction method is verified by the 3-D MFL testing experiment for the ferromagnetic pipeline defects. The results demonstrate that the corrected MFL signals match the experimental signals well. [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]

For in-line inspection of ferromagnetic materials, magnetic flux leakage (MFL) detection is one of the most common nondestructive testing methods. In practical applications of conventional MFL inspection, random mechanical vibration can cause the detection gesture of the probe, in particular, the lift-off and tilt detection angle, to continuously fluctuate throughout the inspection process, which introduces measurement errors to MFL signals. To address the problem and realize ultra-high-definition MFL detection, this paper proposed a new type of probe with dual diagonal distributed magnetic sensors for MFL detection. Based on the dual magnetic sensor probe structure and magnetic dipole model, this paper further developed analytical solutions of the real-time sensor lift-off, tilt detection angle, and defect depth. Additionally, this paper presented a compensation algorithm for MFL measurement errors caused by random lift-off and tilt detection angles. A practical implementation for the dual magnetic sensor probe in the actual MFL testing tool was given. The finite element simulation and physical experiments were designed to verify the feasibility of probe gesture compensation algorithm. Even under abnormal probe detection gesture case, MFL signals measured and compensated by the dual magnetic sensor probe were also in line with the engineering application, and measurement errors of MFL signals were reduced from more than 30 % to less than 10 %, which is conducive to the realization of ultra-high-definition MFL testing. [ABSTRACT FROM AUTHOR]

The defect opening profile recognition is of great concern in the magnetic flux leakage (MFL) measurement technique. The detected spatial MFL signal has three components: horizontal, vertical, and normal components. Horizontal and normal component signals are commonly used to estimate the defect profile, while the vertical component has always been neglected. With the development of the high resolution and the 3-D MFL testing techniques, the vertical component signal is becoming more available. This paper analyzes the essential right-angle features of the vertical component signal, which is useful for the defect opening profile recognition. After obtaining the initial profile from the horizontal or normal component, the types of the right angle is identified from the vertical component, and the opening profile is further optimized based on these right-angle features. The opening profile recognition method is put forward in this paper to improve the accuracy of the recognition result of the defect. Both simulation and experimental tests are conducted to verify the good performance of the proposed method. Compared with the opening profiles recognized merely by the horizontal component signal, the proposed method shows better recognition results, which also validates that the vertical component signal can also be a useful information for the defect estimation. [ABSTRACT FROM AUTHOR]