Search

The parts of working machinery have always suffered from various working conditions in the process of use (e.g., high temperature, high humidity, and high pressure) that may generate flaws, pitting, thermal fatigue crack and other types of defects on the surface or inside. Because these tiny defects carry big safety risks, regular detection is necessary to ensure the reliability of the production equipment. [ABSTRACT FROM AUTHOR]

In this paper, an improved generative adversarial network (GAN) is proposed for the crack detection problem in electromagnetic nondestructive testing (NDT). To enhance the contrast ratio of the generated image, two additional regulation terms are introduced in the loss function of the underlying GAN. By applying an appropriate threshold to the segmentation of the generated image, the real crack areas and the fake crack areas (which are affected by the noises) are accurately distinguished. Experiments are carried out to show the superiority of the improved GAN over the original one on crack detection tasks, where a real-world NDT dataset is exploited that consists of magnetic optical images obtained using the electromagnetic NDT technique. [ABSTRACT FROM AUTHOR]

The first step to quantifying complex defects is knowing its geometry, shape, and orientation. This is evidently challenging in electromagnetic nondestructive testing (ENDT), especially for subsurface complex defect detection, in cases where no information about defect or material is known or given. In this article, we propose a heuristic approach for the visualization, verification, and validation of complex defects in magnetic flux leakage (MFL) testing. This method is based on MFL experiment using magneto-optical images (MOIs) that are obtained from four different magnetization patterns. Using the proposed magnetization patterns, images of complex defect are captured with the aid of a charge-coupled device (CCD) camera, based on the interaction of magnetic field distribution and detected defects, from different angles and directions. An enhanced ant colony algorithm (EACA) is then used to reconstruct complex defect shapes from captured images using a mean image approach. The reconstructed image (mean image) reveals the defect shape with high precision for which the EACA is able to extract important defect features such as specific edges that might be hidden or blurred. This approach based on results has proved to provide promising solution to visually verifying complex defects in MFL, leading to a more simplified and faster way to characterize these defects as compared with conventional methods, using their shapes and orientation. [ABSTRACT FROM AUTHOR]

Abstract Magnetic flux leakage (MFL) techniques are widely used for nondestructive testing of ferromagnetic materials. An analytical model of the MFL field is essential for precise determination and reconstruction of defects. In this paper, we proposed a solenoid model based on magnetization mechanisms of the magnetic medium to explain the MFL principle and simulate the MFL field. By introducing the interaction of solenoids and the Jiles–Atherton model, this model can accurately calculate the MFL field of complex defects, particularly the field distortion caused by the coupling of the defect's components. The solenoid model was experimentally demonstrated with a Z-shaped defect in the specimen and proved to be valid for precise calculation of the magneto-optical image. This work reveals the MFL testing principle from the viewpoint of the magnetic medium and thus helps elucidate and eradicate the simulation errors. The more accurate simulation than the common magnetic dipole model facilitates the inverse calculation of defects, even if field distortion is involved. [ABSTRACT FROM AUTHOR]

On the basis of the Faraday Magneto-optical Effect (FMoE) method, that the polarized light would rotate its polarizing direction when there is the magnetic in its moving direction, a NDT method based on Magnetic optic imaging (MOI) is proposed to detect and identify the crack. In order to identify the crack, the pulsed-couple neural network (PCNN) model based this method is developed and improved to select the threshold dynamically. The output image of the PCNN model is pulsed image and this kind of image is processed by the magnetic domain spots filter. This kind of filter is based on the connection law which can detect the crack in the pulsed image. The detecting system could be used to identify the crack accurate by the above two steps, which would be confirmed by the results. [ABSTRACT FROM AUTHOR]

This paper proposes a new method to detect crack in metals by utilizing the magnetic optical image (MOI) method. MOI detection is one of a nondestructive testing method, which is based on the Faraday magneto-optical effect. The artificial neural network (ANN) approach is applied to identify the crack, according to the dynamically threshold selection. There are two kinds of threshold vectors that are proposed by the ANN algorithm. A good threshold can be obtained from the vectors using a law. The new image acquired is processed by a magnetic domain spots filter. This filtering method is based on the connection law who holds good ability to process the spots in the MOI image. Based on these methods, the detecting system can recognize the crack clearly and the results would confirm it. [ABSTRACT FROM AUTHOR]

Eddy current pulsed thermography (ECPT) is an emerging nondestructive testing and evaluation (NDT&E) technique and has been applied for a wide range of conductive materials. In this paper, a single-channel blind source separation is proposed to process the ECPT image sequences. The proposed method enables: 1) automatically extract valuable spatial and time patterns according to the whole transient response behavior without any training knowledge, 2) automatically identify defect patterns and quantify the defects, and 3) to provide guidelines of choosing the optimal contrast functions that can improve the separation results. In this paper, both mathematical and physical models are discussed and linked. The basis of the selection of separated spatial and time patterns is also presented. In addition, an artificial slot and a thermal fatigue natural crack are applied to validate the proposed method. [ABSTRACT FROM PUBLISHER]