Magnetic Flux Leakage Research Articles

Intelligent identification of girth welds defects in pipelines using neural networks with attention modules

Girth weld defects (crack, lack of penetration, lack of fusion, and edge nibbling) can cause pipeline cracking failure accidents. Internal magnetic flux leakage (MFL) detection can successfully identify pipeline defects, while the intelligent identification of MFL signals based on deep learning can promote the accurate determination of pipeline girth weld defects. Although the YOLOv5 model can effectively identify abnormal image objects, it exhibits no attention preference during the feature extraction process, proving insufficient for small objects. This study targeted minor defects in the girth weld of the pipeline and used the Convolutional Block Attention Module (CBAM) to optimize the YOLOv5 network model structure, increasing detection network attention preference toward extracting small-target defect signals. The CBAM+YOLOv5 model improved the detection accuracy of the MFL signal of the girth weld in the pipeline from 89.33% to 98.11% and correctly identified and classified the MFL signal of the pipeline girth weld with 85% confidence, with minor anomalies. The CBAM+YOLOv5 model effectively improved the identification accuracy of the girth weld defect signal in the pipeline, providing technical support for safety grade assessment and excavation verification.

Fatigue damage evaluation and verification of steel wire rope based on magnetic flux leakage

Fatigue damage evaluation and verification of steel wire rope based on magnetic flux leakage

A Signal Filtering Method for Magnetic Flux Leakage Detection of Rail Surface Defects Based on Minimum Entropy Deconvolution

Magnetic flux leakage (MFL) detection of rail surface defects is an important research field for railway traffic safety. Due to factors such as magnetization and material, it can generate background noise and reduce detection accuracy. To improve the detection signal strength and enhance the detection rate of more minor defects, a signal filtering method based on minimum entropy deconvolution is proposed to denoise. By using the objective function method, the optimal inverse filter parameters are calculated, which are applied to the filtering detection of MFL signals of the rail surface. The detection results show that the peak-to-peak ratio of the defect signal and noise signal detected by this algorithm is 2.01, which is about 1.5 times that of the wavelet transform method and median filtering method. The defect signal is significantly enhanced, and the detection rate of minor defects on the rail surface can be effectively improved.

Enhanced defect detection in NDE using registration aided heterogeneous data fusion

The degradation of systems in service, including pipelines, over time highlights the critical need for reliable and accurate defect detection to ensure safe operations. However, single modality-based Nondestructive Evaluation (NDE) data used in practical applications often suffers from noise contamination and errors caused by various factors like lift-off/standoff distances, probe drift, scanning speed, variation in data acquisition rates, and poor sensor sensitivity. The presence of agnostic noise types poses a challenge in extracting defect signals. To address these challenges, this paper presents an automated NDE theory-based data fusion framework aimed at enhancing the detection of surface and near-surface defects in magnetizable and conductive specimens. The Magnetic Flux Leakage (MFL) and Eddy Current (EC) based NDE sensing methods demonstrate the highly heterogeneous nature of noise distributions. Given the heterogeneity of the inspection methods, a screening rule is proposed to determine the conditions under which fusion would be beneficial. An important aspect of the proposed fusion method is registration, which ensures accurate alignment of multi-sensor image data. Two registration methods are proposed in this study as performing blind fusion without registration leads to erroneous results. The first registration method is translational, whereas the second method is registration based on linear optimal transport (OT) which proves to be effective in the boundary conditions. Finally, the registered source images from the EC and MFL modalities are fused using pixel-based fusion algorithms, including transform domain and spatial domain-based methods. Qualitative and quantitative assessments demonstrate that the registered fusion results exhibit higher accuracy and reliability compared to unregistered fused results and source images. Although the fusion method is applied to MFL and EC data in this paper, it is also suitable for other NDE modalities.

Exploration and Application of Acoustic Emission Detection Technology in Leakage Detection of the Bottom Plate of Crude Oil Metal Storage Tanks

The use of acoustic emission detection technology can conduct online and non-stop detection and evaluation of crude oil metal storage tanks, achieving the integrity detection and evaluation of storage tanks. In order to explore the applicability of acoustic emission detection technology in the leakage detection of the bottom plate of crude oil metal storage tanks, this project carried out online acoustic emission detection of crude oil metal storage tanks, magnetic flux leakage detection after tank opening and cleaning, and compared and analyzed the results of two detection technologies. The adaptability of online acoustic emission detection technology was analyzed and explored. It was found that acoustic emission technology can qualitatively evaluate the corrosion of tank bottom plates, but cannot accurately locate corrosion defects. For tanks with severe corrosion that require maintenance, it is still necessary to open the tank and use magnetic flux leakage and other detection techniques to determine the location of defects. Through comparative analysis of acoustic emission testing technology and magnetic flux leakage testing technology, the results obtained from acoustic emission testing technology are conservative compared to the actual results. It is recommended to upgrade the evaluation of corrosion degree for the acoustic emission evaluation results of crude oil metal storage tanks.

SSCT-Net: A Semisupervised Circular Teacher Network for Defect Detection With Limited Labeled Multiview MFL Samples

Deep learning methods have demonstrated promising performance in magnetic flux leakage (MFL) defect detection under adequate amounts of labeled samples. However, in industrial occasions, obtaining adequate amounts of labeled samples is time-consuming and expensive, and applying only limited labeled samples can lead to unsatisfactory defect detection accuracy. To address the above issues, a defect detection method named semi-supervised circular teacher network (SSCT-Net) is proposed in this article. First, a parallel feature extraction network with hybrid attention is proposed in SSCT-Net so that the useful features of multi-view MFL signals can be extracted simultaneously. Second, semi-supervised circular learning is proposed for the first time. In semi-supervised circular learning, a distinguishable feature embedding space is constructed, and two structurally identical deep networks co-supervise and collaborate through the proposed consistent circular strategy so that the decision bias of unlabeled samples can be reduced. Finally, the trained model is applied for defect detection in practice. The proposed method can establish a potential connection between multi-view MFL signals and fully utilize labeled and unlabeled MFL signals. The experiments in simulations and real-world applications demonstrate that SSCT-Net can reach 92% detection accuracy with only 20% labeled samples, which is more effective than the state-of-the-art methods and leads to a promising practical utility of the proposed method.

Magnetic flux leakage, eddy current loss and temperature distribution for large scale winding in UHVDC converter transformer based on equivalent 2D axisymmetric model

Magnetic flux leakage, eddy current loss and temperature distribution for large scale winding in UHVDC converter transformer based on equivalent 2D axisymmetric model

Magnetic Flux Leakage Testing Method for Pipelines with Stress Corrosion Defects Based on Improved Kernel Extreme Learning Machine

This study aims to study the safety of oil and gas pipelines under stress corrosion conditions and grasp the corrosion damage situation timely and accurately. Consequently, a non-destructive testing method combining magnetic flux leakage testing technology and a kernel function extreme learning machine improved by genetic algorithm (GA-KELM) is proposed. Firstly, the variation of the corrosion defect dimension and profile with time is obtained by numerical simulation. At the same time, the distribution of the magnetic flux leakage signal under different defect conditions is analyzed and studied. Finally, feature selection is carried out on the magnetic flux leakage signal distribution curve, and GA-KELM is used to predict the depth and length of corrosion defects so as to realize the non-destructive testing of the pipeline defects. The results show that different geometric features result in different magnetic flux leakage signal distributions. There is a corresponding relationship between the defect dimension and extreme value, area, and peak width of the magnetic flux leakage signal distribution curve. The GA-KELM prediction model can effectively predict the depth and length of corrosion defects, and the prediction accuracy is better than the traditional extreme learning machine prediction model.

Design of magnetic flux leakage detector for mine wire rope

At present, the online detection technology of wire rope damage in coal mine hoisting needs to be improved. Given the large number of detection elements and high detection cost in the wire rope detection device, the magnetic flux leakage detection device of the wire rope damage detection system is designed. The magnetic sensor is selected. At the same time, in order to improve the strength of the magnetic leakage field at the defect and reduce the number of magnetic sensors, a magnetic focusing device is designed. The finite element simulation shows that the magnetic focusing device can effectively improve the sensitivity of defect detection. The above research provides the basis for the design of steel wire rope damage detection systems and is of great significance to ensure the safe and efficient operation of mine hoisting equipment.

Defect Size Quantification for Pipeline Magnetic Flux Leakage Detection System via Multilevel Knowledge-Guided Neural Network

Defect size quantification plays a vital role in pipeline magnetic flux leakage (MFL) detection system. However, most existing methods suffer from poor applicability and low precision due to complex industrial process. Moreover, they often overlooks the valuable knowledge that may be beneficial for defect size quantification. To solve this problem, a defect size quantification method based on multi-level knowledge-guided neural network (MLKG-NN) is proposed, which effectively integrates prior knowledge and specific data. First, at the feature level, a recursive residual subnet is proposed to inject the mechanism features into the network, so that the network performance can be enhanced. Second, an experience-aided subnet is proposed to incorporate expert experience at the decision level, which supervises the network training with labels, so that the network stability can be improved. Third, at the modeling level, a cascade expression subnet based on two-point representation is first proposed in the defect size quantification area, where both the value and distribution of labels are considered to boost the network precision. These three parts are jointly trained and promote each other. Finally, extensive experiments are conducted with defects from a pipeline network in northern China and the experimental results highlight the superiority of our method.

Finite element analysis of magnetomechanical coupling behaviour of perforated steel plate

In this paper, finite element analysis is carried out for the stress of a 45# steel specimen with a round hole and its correlation with a magnetic signal. The leakage magnetic field signals of the specimen under different loads are obtained. The results show that the greater the tensile stress is, the greater the stress is at 2 mm above the round hole, and the permeability first increases and then decreases with the increase in stress. The leakage magnetic field signal is correlated with permeability and the tangential component of the magnetic flux leakage signal has a trend of increasing first and then decreasing. The phenomenon of zero crossing of the normal component of the leakage magnetic field signal appears.

Research on Improving the Shielding Effect of Stacked Superconducting Bulks Based on Increasing the Gap Reluctance

Superconducting bulk has great advantages in shielding magnetic fields owing to its high critical current density. Since the shielded area is usually larger than the size of a single bulk, superconducting bulks need to be stacked together to form a shielding layer. However, bulks stacked together can cause the magnetic flux to concentrate at the gaps between bulks. In order to increase the shielding effect, multiple shielding layers are usually required. This increases the shielding cost. In this paper, a shielding structure that makes an angle between gap and external field non-parallel is explored. This structure can increase the gap reluctance and reduce the magnetic flux leakage, which provides a method to get a uniform shielding area in a relatively economical way. The shielding effects are studied by experiment and finite element calculation. The established simulation model can be used to further explore and optimize new shielding structures.

Image recognition model of pipeline magnetic flux leakage detection based on deep learning

Abstract Deep learning algorithm has a wide range of applications and excellent performance in the field of engineering image recognition. At present, the detection and recognition of buried metal pipeline defects still mainly rely on manual work, which is inefficient. In order to realize the intelligent and efficient recognition of pipeline magnetic flux leakage (MFL) inspection images, based on the actual demand of MFL inspection, this paper proposes a new object detection framework based on YOLOv5 and CNN models in deep learning. The framework first uses object detection to classify the targets in MFL images and then inputs the features containing defects into a regression model based on CNN according to the classification results. The framework integrates object detection and image regression model to realize the target classification of MFL pseudo color map and the synchronous recognition of metal loss depth. The results show that the target recognition ability of the model is good, its precision reaches 0.96, and the mean absolute error of the metal loss depth recognition result is 1.14. The framework has more efficient identification ability and adaptability and makes up for the quantification of damage depth, which can be used for further monitoring and maintenance strategies.

Defect-depth-field algorithm for simulating magnetic flux leakage signals based on discrete magnetic dipole model

Magnetic flux leakage (MFL) testing is widely used for non-destructive detection of defects in ferromagnetic materials, in which fast and accurate processing of MFL signals is critical for reconstructing and evaluating the defects. Of the detection technologies, the existing magnetic dipole model (MDM) can simulate the MFL signals with regular or limited types of defects, but not with complex defects, such as naturally occurring corrosion material losses. With the help of finite element method (FEM), MFL signals of complex defects can be analysed but demanding time-consuming calculation. In this paper, an improved MDM method, i.e., the discrete MDM (DMDM) is proposed, and an algorithm for automatic MFL signals processing is further developed based on the DMDM and the defect-depth-field concept. By comparison, the difference of the simulated MFL signals between the DMDM and the FEM is less than 3%, and the maximum discrepancy of the MFL signals between the simulated and the experimental is about 6%. In addition, the simulation with the DMDM can be thousands of times more efficient than the FEM, indicating significant advantage over the existing method in both improving the accuracy and enabling the fast signal processing of reconstruction for any types of defects in MFL testing.

Methodology for ranking internal corrosion-induced leakage susceptibility in oilfield pipelines

ABSTRACT This investigation focuses on the ranking of pipeline leakage susceptibility of two categories of pipeline systems. One consists of three oilfield water-handling pipeline systems and the other consists of five dry crude systems. Online corrosion monitoring (OCM) method was used for both systems, forthermore, in-line inspection (ILI) method, with Magnetic Flux leakage (MFL) tool, was also used for the dry crude systems. The OCM leakage susceptibility potential is derived from the combined severity of general corrosion, pitting corrosion, fluid corrosivity and sessile bacteria population density in the process streams. The ILI leakage susceptibility potential is derived from the average number of corrosion anomalies greater than 10% of the wall thickness and the maximum depth of the anomalies (as percentage of the wall thickness). In spite of such distinctions, the ranking of pipeline leakage susceptibility for the five dry crude pipeline segments turned out to be identical for the two methodologies.

Low-cost inspection tool for identifying illegal tapping

Pipelines for fuel transportation range in length from hundreds to thousands of kilometers, with part of their length underground. Due to the high cost of the fluids and products transported an increasing number of criminal activities are taking place all over the world. In addition to causing great economic and environmental losses the illegal activity brings risks to the surrounding population. For example, the accident in Tlahuelilpan, Mexico, due to illegal tapping, resulted in the tragedy of hundreds of deaths. In order to combat such activities, many efforts have been employed to early detect and locate illegal tapping in pipelines. The great challenge of such inspections is the unpredictable activity of the clandestine taps, requiring frequent inspections. Usual pipeline inspection tools, such as ultrasound or MFL (Magnetic Flux Leakage) PIG’s, are sensitive for detecting and positioning the anomalies, however, the high operating costs make the recurring application of such tools unfeasible. Focusing on these challenges, a low-cost inspection tool embedded with a minimalist eddy current instrumentation was developed. The results achieved show the capability to detect and differentiate the components existing in the pipeline and illegal taps of different diameters as well as, in a complementary way, the detection of corrosion on the internal surface of the pipelines.

Development of Non-destructive Testing Method for Tube Inspection in Fin-Fan Coolers in Kazakhstan’s Oil/Gas, Chemical and Power Industries.

Many oil/gas fields in Kazakhstan contain high levels of highly corrosive H2S and CO2, sometimes at very high pressures. The management of corrosion is essential in maintaining plant safety and integrity of the processing facility. This paper describes the development of a non-destructive testing (NDT) method that improves the reliability of air-cooled heat exchangers by reducing down-time related to corrosive and erosive failure of fin-fan tubes. The project goal was to maximize the output of oil and gas plants and refineries while reducing the plant operating cost. The work first identified those NDT requirements for air-cooled heat exchangers damage assessment that would provide the greatest economic benefit for Kazakhstan industry. The main objective was to develop a state-of-an-art NDT method for air-cooled heat exchanger tubes, capable to: a) detect any damage mechanism while testing from tube internal diameter, b) accurately determine the damage in terms of wall loss, c) perform inspection quickly and expediently, d) requires minimum tube cleaning. Consequently, the method specially adapted for Kazakhstan conditions was developed based on a combination of Magnetic Flux Leakage (MFL) technique for flaw detection and with Hall effect measurement of wall thickness and gradual corrosion in tubes. The method has been tested in both laboratory and field conditions and the results were compared with accurate but slow ultrasonic IRIS method. High correlation was obtained, which proved that the developed technology is capable to deliver similar results at the speed almost 10 times faster and less than half the cost.

Methodology for Electromagnetic Optimization of a Partially Superconducting 1.4 MW Electric Machine for Electrified Aircraft Propulsion

Large transport aircraft with electrified propulsion systems require MW-class electric machines that have higher efficiency and power-to-weight ratio than existing machines. Superconducting machines are being evaluated as potential solutions. This paper presents a method to optimize the electromagnetic design of a partially superconducting machine in terms of these metrics and the approximate fuel burn of the aircraft. The optimization is based on 2D electromagnetic finite element simulations, a prediction of the superconducting coils' critical current, and geometry relations that design the superconducting coils based on dependent variables while constraining the total cost of superconductor and ensuring adequate space for structure. The design process is completed by (1) a 3D electromagnetic finite element simulation to improve the prediction of torque and assess magnetic flux leakage, (2) refinement of the superconductor width for each individual racetrack coil, and (3) evaluating inverter-produced stator current harmonics on eddy current losses in the rotor.

Multi-Objective Optimization Analysis of Magnetic Gear With HTS Bulks and Uneven Halbach Arrays

To improve the output torque of coaxial magnetic gears, a novel coaxial magnetic gear (CMG) with high temperature superconducting (HTS) bulks and uneven Halbach arrays is proposed in this paper. The convex structure is used in the middle of inner rotor permanent magnets (PMs). The PMs of the outer rotor are arranged in a low-high-low arrangement, epoxy resin is added between the PMs of outer rotor and the outer iron yoke. At the same time, the HTS bulks replace the epoxy resin to reduce magnetic flux leakage. In addition, according to the sensitivity analysis, the structural parameters can be divided into different levels, the multi-objective optimization analysis is carried out. Finally, the optimal CMG topology with 4 inner and 17 outer pole pairs is established. The results show that the amount of PM is reduced and the output torque is effectively increased by finite element analysis (FEA).

AC-MFL testing method for surface crack on reground billets using flexible parallel-cable-based probe

Square billet is an important industrial raw material. Due to the large amount of oxidation skin on the surface after continuous casting process, it needs surface grinding treatment. Meanwhile, the billet surface is prone to stress concentrations and cracks in the crystallization zone, so it is easy to break and cause accidents in the subsequent process. However, the poor surface condition of the reground billet, such as the large roughness and fluctuations in the shape, makes it difficult to be tested by traditional methods. In this paper, the relationship between the excitation frequency of alternative current magnetic flux leakage (AC-MFL) and the fluctuation of magnetic field generated by uneven surface is studied, and the high-frequency AC leakage field formation is restated. Furthermore, a flexible probe integrating parallel cables (PC) magnetizer and receiving coils is proposed, which can realize the profiling testing and reduce the influence of the undulating surface. Finally, the wavelet transform is used to reconstruct signals, which increases the average signal-to noise ratio (SNR) from 7.25 dB to 11.89 dB.