Fluorescent Magnetic Particle Research Articles

Automated crack detection of train rivets using fluorescent magnetic particle inspection and instance segmentation

The railway rivet is one of the most important and easily damaged parts of the connection. If rivets develop cracks during the production process, their load-bearing capacity will be reduced, thereby increasing the risk of failure. Fluorescent magnetic particle flaw detection (FMPFD) is a widely used inspection method for train fasteners. Manual inspection is not only time-consuming but also prone to miss detection, therefore intelligent detection system has important application value. However, the fluorescent crack images obtained by FMPFD present challenges for intelligent detection, such as the dense, multi-scaled and uninstantiated cracks. In addition, there is limited research on fluorescent rivet crack detection. This paper adopts instance segmentation to achieve automatic cracks detection of rivets. A decentralized target center and low overlap rate labeling method is proposed, and a Gaussian-weighted correction post-processing method is introduced to improve the recall rate in the areas of dense cracks. An efficient channel spatial attention mechanism for feature extraction is proposed in order to enhance the detection of multi-scale cracks. For uninstantiated cracks, an improvement of crack detection in uninstantiated regions based on multi task feature learning is proposed, thoroughly utilizing the semantic and spatial features of the fluorescent cracks. The experimental results show that the improved methods are better than the baseline and some cutting-edge algorithms, achieving a recall rate and mAP0.5 of 86.4% and 90.3%. In addition, a single coil non-contact train rivet composite magnetization device is built for rivets that can magnetize different shapes of rivets and has universality.

Crack identification method for magnetic particle inspection of bearing rings based on improved Yolov5

The fluorescent magnetic particle inspection technique is often used for surface crack detection of bearing rings due to its advantages of simple operation and high sensitivity. With the development of computer vision technology, more and more visual algorithms are used in magnetic particle inspection for defect detection. However, most of these current algorithm models have low detection accuracy and poor efficiency, making it difficult to meet the precision requirements of production testing and affecting the overall pace of production processes. To address this problem, this paper proposes an improved algorithm model based on Yolov5. Firstly, MobileNetV3-small is utilized to construct the backbone feature extraction network, reducing the network’s parameter count and enhancing its detection speed. In addition, Bidirectional Feature Pyramid Network is implemented to facilitate swift and efficient multi-scale feature fusion, while the C3 module in the neck is replaced with C2f to enhance detection precision. Finally, Focal-Loss EIoU is adopted as the loss function to improve the model’s accuracy in positioning the crack borders. Experimental results demonstrate that the precision of this model in detecting surface cracks in bearing rings achieves an impressive 95.1%, while the recall reaches 90.4%. The mAP stands at 0.946. When compared to the original Yolov5s network, this model showcases a reduction in network parameters by 32.1% and a significant increase in frames per second by 40.0%. These improvements effectively fulfill the production process’s demands for crack detection tasks, providing a balance between accuracy and efficiency.

Surface defects 3D localization for fluorescent magnetic particle inspection via regional reconstruction and partial-in-complete point clouds registration

Accurate three-dimensional localization of defects plays a crucial role in the automated defect marking and grinding process. However, this task becomes increasingly intricate when precisely recovering the three-dimensional information of small defects due to the presence of noise and damage in point clouds generated through three-dimensional reconstruction. Simultaneously, separately reconstructing defects at different locations on the component would significantly impact efficiency. This study focuses on fluorescent magnetic particle inspection, with the aim of enhancing the accuracy of fine crack localization and multi-defects reconstruction efficiency. Its basic idea is to align the precise complete point cloud with the regionally reconstructed noisy point cloud of a component, achieving its spatial positioning within the visual system while eliminating noise and imperfections. We commence by discussing various methods for acquiring offline complete point clouds and their respective advantages and disadvantages. To enhance flexibility and minimize regional reconstruction noise, we have devised a multi-camera vision system and optimized a multi-view stereo reconstruction algorithm. We introduce a filtering function for culling back-facing points during the sparse point cloud projection process. The feasibility of our approach is empirically validated, with a particular focus on its precision and efficiency. Experimental results indicate that our method can execute within 5 s, with a relative error of less than 2 millimeters for 95% of the points and a root mean square error less than 1 millimeter. Our approach exhibits significant advantages in addressing noise issues associated with point cloud data generated through image-based 3D reconstruction processes.

Adaptive receptive field based on multi-size convolution kernel for micro-defect detection of turbine blades

Because turbine blades are essential parts of aircraft engines, micro-defects on the surface of turbine blades induce accidents in aircraft crashes. The detection of micro-defects in aerospace turbine blades is achieved within the realm of non-destructive evaluation. Given that most of the defects are tiny and spread randomly on a curved surface, which cannot be completely detected by current target detection methods, it is feasible for micro-defects to be effectively detected by the fluorescent magnetic particle method. In this paper, we propose a Defect Classification (DCLS)-Deformable Detection Transformer (DETR) model to inspect micro-defects in an automatic fluorescent magnetic particle inspection system. In the DCLS-Deformable DETR model, an adaptive receptive field (ARF) attention module is designed, which considers the interdependencies between the channel features of different feature maps. The weights between the channels of each feature map were also considered, while adaptively adjusting the receptive field according to the detection target size. The DCLS-Deformable DETR model with ARF increased the AP from 63.4% to 64% and AP50 from 95.2% to 97.2%, compared to the Deformable DETR. Turbine blades include three typical defects: linear cracks, reticular cracks, and pitting corrosion. Compared with the original model, the proposed model enhances the AP of three defect types by 1.8%, 2% and 4.7% respectively. The DCLS-Deformable DETR model considers the position, level information, and channel information of the input samples, which can capture micro-defects around large defects.

Study on sIgE distribution characteristics and the sensitization pattern of allergen in 1 161 patients with allergic diseases of respiratory tract in northwest China

Objective: To explore the allergen map of patients with allergic diseases in northwest China, to investigate the distribution characteristics of serum specific Immunoglobulin E (sIgE) in different ages, genders, diseases and the sensitization patterns of allergens. Methods: This study is a cross-sectional study, a total of 1 161 patients with confirmed respiratory allergic diseases were selected retrospectively from outpatient or inpatient department of Gansu Provincial People's Hospital, Gansu Provincial Maternity and Child Care Hospital, General Hospital of Ningxia Medical University, Yinchuan Maternal and Child Health Care Hospital, Xijing Hospital, Air Force Military Medical University and Tumor Hospital of Inner Mongolia Autonomous Region from June 2019 to October 2022. HAIKE ALLEOS 2000 fluorescent magnetic particle chemiluminescence method was used to quantify their serum for 12 inhaled allergen-specific IgE. Chi square test or Fisher's exact test were used for comparison between count data groups (Bonferroni correction was used for further pairwise comparison in multiple groups, two-sided P<0.05/3=0.017 considered that the difference was statistically significant). Pearson correlation analysis was used for correlation of continuous numerical variables. Results: The positive detection rate of sIgE in 1 161 patients was 66.8%(776/1 161). The three highest positive rate of inhaled allergen were mugwort(599/1 161, 51.6%), French chrysanthemum(565/1 161, 48.7%) and dandelion(412/1 161, 35.5%). In different age groups, the highest positive rate of sIgE was 7-18 age group(379/513, 73.9%) while the lowest positive rate was 4-6 age group(222/370, 60.0%), the difference between groups was statistically significant(χ2=21.177, P<0.001). The sensitization peak of mugwort, French chrysanthemum, plantain, timothy, birch, dermatophagoides pteronyssinus, dermatophagoides farinae, cat epithelium, dog epithelium and German cockroach appeared in 7-18 age group. In different disease groups, the highest positive rate of sIgE was allergic rhinitis with asthma group (500/717, 69.7%) while the lowest positive rate was asthma group (76/144, 52.8%), the difference between groups was statistically significant(χ2=15.563, P<0.001). In different gender groups, the positive rate of sIgE in male (503/711, 70.7%) was higher than in female (273/450, 60.7%), the difference between groups was statistically significant(χ2=12.630, P<0.001). The multiple-sensitization rate was 86.9%(674/776) and the double-sensitization rate was 16.8%(130/776) in sIgE positive patients. Pearson correlation results showed that there was an extremely strong correlation between dandelion and French chrysanthemum(r=0.93,P<0.001). There was a strong correlation between mugwort and French chrysanthemum(r=0.64,P<0.001). In the co-sensitization analysis, the number of patients sensitized by mugwort, French chrysanthemum, dandelion, plantain and timothy accounted for 25.2%(170/674)of the total number of multiple sensitization. The number of patients sensitized by mugwort, French chrysanthemum and dandelion accounted for 58.3%(393/674)of the total number of multiple sensitization. The number of patients sensitized by mugwort, French chrysanthemum, dandelion and plantain accounted for 35.6%(240/674) of the total number of multiple sensitization. Conclusion: Mugwort, French chrysanthemum, dandelion are the major inhaled allergens in northwest China. The positive rate of sIgE was different in different ages, diseases and genders. The multiple-sensitization rate of allergen was high and there was a certain positive correlation between pollen allergen-specific IgE pairwise, suggesting that there may exist co-sensitization or cross-reactions among allergens.

Failure analysis of inner wall of X-10 brake discs for urban rail vehicles

Some X-10 type brake discs for urban rail vehicles were examined by fluorescent magnetic particle inspection test, and the magnetic trace accumulation was observed at the root of the connecting claw of the brake discs. In this work, the causes of failure for the brake discs are analyzed and discussed. The chemical composition, metallographic structure, and mechanical property of the failure samples were characterized by means of X-ray energy dispersive spectrometry, metallographic microscope, scanning electron microscopy, and an electronic universal material-testing machine. At the same time, the stress and crack propagation states were analyzed by numerical simulation, braking dynamic and fatigue tests, respectively. Based on the fracture mechanics theory, the residual fatigue life was also predicted. The failure reason of the inner wall of brake disc was that the fatigue crack occurred at the root of the connecting claw of the brake disc body, and the crack source was taken from graphite sheets exposed on the surface of the grey cast iron matrix. The results of the numerical simulation showed that the larger thermal stress acted on the graphite sheets at the root of the connecting claw, and promoted the crack to expand along the path of the graphite sheets. The results of the braking force and fatigue tests showed that there was stability propagation of the crack. Finally, some suggestions and prevention for brake discs are provided.

A learning-based crack defect detection and 3D localization framework for automated fluorescent magnetic particle inspection

With the rapid development of deep learning, target detection and segmentation in dirty backgrounds have been readily available. Fluorescent magnetic particle inspection (MPI) based on such technology will be a promising alternative for automated crack defect inspection. Most previous studies in MPI have focused only on crack detection. Instead, we frame it as a crack 3D localization problem, since cracks on non-machined surfaces of metal parts need to be polished and re-inspected, which relies on their 3D positions. Although good results were obtained in defect detection, it is still challenging to perform pixel-level segmentation of micro-cracks from the large background to obtain crack 2D pixels for 3D reconstruction. This paper proposes a two-stage convolutional neural network (CNN) method for metal parts crack defect detection and segmentation at the image-pixel level. The first stage detects and crops the potential cracks to a small area, and the second stage can learn the context of cracks in the detected patches. A window-based stereo matching method is then used to find matching pixels of cracks and to map crack image plane points to the 3D world points. We also illustrate the entire system’s model deployment and signaling work to apply these methods. Both computational and experimental results based on the system are presented for validation. The training precision of target detection reaches 96.3%, its average precision reaches 85.4%, and the average precision reaches 98.3% when the Intersection-over-Union (IoU) threshold is 0.5. The Dice score reaches 94% in pixel-level segmentation, and the average precision is 99.3% when the probability threshold is set to 0.5. The corresponding efficiency reaches 19 FPS and 18 FPS, and the mean absolute errors of 3D coordinates of reconstructed crack defects are all within 1 mm in X-, Y- and Z- directions.

A Novel Reticular Retained Austenite on the Weld Fusion Line of Low Carbon Martensitic Stainless Steel 06Cr13Ni4Mo and the Influence on the Mechanical Properties

When performing fluorescent magnetic particle testing in steel welding-repaired zones, as traditional viewpoint usually ascribes magnetic particle indications to discontinuous welding defects such as cracks, incomplete fusion, etc., welding-repaired zones showing indications of these defects are always judged to be unqualified. In this study, a novel reticular phase was identified on the weld fusion line of 06Cr13Ni4Mo. By selected area electron diffraction, it was proved to be an austenite. By roasting test, it was proved to be induced by the thermal effect of welding. Non-ferromagnetic reticular austenite reduces the overall magnetic permeability, leading to the presence of fluorescent magnetic particle indication. Though the mechanical properties of the welding repaired zone are changed by the reticular austenite with the yield strength, tensile strength, and microhardness decreasing to 571 MPa, 752 MPa, and 279, respectively, they still exceed the required values of standard specifications. 06Cr13Ni4Mo welding-repaired zones showing magnetic particle indications induced by reticular austenite are qualified and should be accepted.

Automatic Defect Identification Method for Magnetic Particle Inspection of Bearing Rings Based on Visual Characteristics and High-Level Features

Fluorescent magnetic particle inspection (MPI) is a conventional non-destructive testing process for railway bearing rings that still needs to be completed manually. Due to the complexity of bearing ring surfaces in inspection, automatic detection for bearing rings based on image processing is difficult to apply. Therefore, we proposed a bearing ring defect identification method based on visual characteristics and high-level features. Inspired by the mechanism of human visual perception, defects can be identified from the complex background conveniently by human eyes. According to the linear structure characteristics and greyscale distribution characteristics of cracks in the acquired images, we introduce the centerline extraction and Gaussian similarity measure to reduce background noise and obtain the crack candidate regions. Then, an improved MobileNetV3 is used to extract high-level features of the candidate regions and determine whether they are defective, which uses a new attention module, Coordinate Attention (CA), to substitute the Squeeze-and-Excitation (SE) attention to improve the performance. The experimental results show that the detection accuracy rate of the proposed method is 96.5%. Compared with traditional methods, the proposed method can efficiently extract crack defects in a complex textured background and shows high-quality performance in recall and precision.

Intelligent Detection Method of Forgings Defects Detection Based on Improved EfficientNet and Memetic Algorithm

In the process of production, automobile steel forgings are prone to various cracks, which affect the product quality. At present, forgings defects are mainly detected by fluorescent magnetic particle inspection and manual inspection. Aiming at the problems of low detection accuracy and efficiency in this method, an improved convolutional neural network model is proposed. The fluorescent magnetic particle inspection images of two typical forgings were intelligently inspected. Firstly, a deep learning model with EfficientNet as the backbone and Feature Pyramid Network (FPN) as the fusion layer is constructed. Secondly, In order to improve the convergence speed and detection accuracy, the calculation method of intersection over union is improved, and the network is improved by using the Attention Mechanism. Finally, Particle Swarm Optimization algorithm (PSO) with adaptive parameters is introduced to optimize the hyperparameters of neural network, and a fluorescent magnetic particle inspection image acquisition platform is built for verification. The mean Average Precision (mAP) of the best model of EfficientNet-PSO on the validation set is 95.69%. F1 score is 0.94 and FLOPs is 1.86B. Compared with other five deep learning neural network models, this method effectively improves the defect detection efficiency and accuracy of flange plate and cylinder head, which can meet the defect detection requirements.

An experimental study on the use of iron oxide magnetic nanoparticles synthesized through watermelon rind extracts for industrial applications

In this study, an easy and eco-friendly way for the synthesis of magnetic nanoparticles was investigated and mainly focused on its use on magnetic particle inspection (MPI) as a fluorescent magnetic particle. For this purpose, iron oxide magnetic nanoparticles (Fe3O4 MNPs) were prepared via rapid and green route using watermelon rinds extract (WRE). The synthesized WRE@Fe3O4 MNPs have been characterized by Scanning electron microscopy (SEM), Energy dispersive spectroscopy (EDS) and Dynamic light scattering (DLS). From the SEM images of the WRE@Fe3O4 MNPs, it has been shown that particle size was ranging from 50 nm to 100 nm. EDS spectrum indeed confirmed the presence of significant amounts of Fe and O. The average particle size was found to be 554.8 nm by DLS method. The magnetic property of WRE@Fe3O4 MNPs was analyzed by Vibrating sample magnetometer (VSM). The analysis of synthesized nanoparticles showed an amount of 24.35 emu/g for magnetic saturation. All of the results, the green synthesized WRE@Fe3O4 MNPs demonstrated good potential for identifying cracks in the test block during MPI testing. Thus, the cracks between 1.29 and 1.55 mm in the test block were successfully identified.

Research and analysis of fluorescent magnetic particle inspection of steam turbine rotor blade

The operating conditions of turbine rotor blades are complex and changeable, and the probability of defects is high, which puts forward higher requirements for the professionalism, safety, stability and convenience of magnetic particle inspection personnel. How to find the deficiencies in the magnetic particle inspection of blades and improve it to better adapt to the field inspection has become the focus of attention. This paper mainly describes the process of fluorescent magnetic particle inspection, compares the similarities and differences of magnetization specifications in three domestic standards, analyzes the problems found in the process of fluorescent magnetic particle inspection and makes corresponding improvement, and adopts reasonable optimization scheme to improve the reliability of fluorescent magnetic particle inspection. After demonstration test and field application, the improved fluorescent magnetic particle inspection can give full play to its advantages, achieve the purpose of rapid, accurate inspection and continuous improvement; on this basis, different inspection platforms can be established to inspect different parts, improve the universality and inspection efficiency of magnetic particle inspection, which is conducive to the promotion and application of magnetic particle inspection in the field of nuclear power.

Liquid Metal Embrittlement Cracking During Resistance Spot Welding of Galvanized Q&amp;P980 Steel

Resistance spot-welded galvanized ultrahigh-strength steels are sensitive to liquid metal embrittlement (LME), which is manifested by surface cracks on the joints. LME occurs when a solid metal contacts a liquid metal under tensile stress, and the phenomenon has not been fully understood until now, especially for resistance spot welding. In this study, the susceptibility of hot-dipped galvanized Q&P980 steel to LME cracking during resistance spot welding was systematically investigated by an orthogonal experiment. Cracks were detected by fluorescent magnetic particle testing and cross-sectional microscopic observation. Cracks were mostly located at the indentation edge and slope, and a few cracks were also located at the indentation center and slope periphery. The severity of the cracking increased with the increasing welding current and welding time, and the decreasing electrode force. The sequence of influence degree from high to low was welding current > electrode force > welding time. Holding time had no obvious effect. Microstructural analysis revealed that the content of martensite in areas with cracking increased, indicating that a high temperature was experienced at these locations. Zinc accumulated inside the cracks, and the cracks were intergranular, which coincides with the characteristics of LME. The LME cracking was provoked by the simultaneous occurrence of a tensile stress, an appropriate temperature and liquid metal, and the cracks were influenced by the welding parameters. Under suitable conditions, Zn diffused along the grain boundaries and weakened them, resulting in LME cracking.

Fatigue crack detection in rotating steel shafts using noncontact ultrasonic modulation measurements

In this study, a noncontact fatigue crack detection technique for rotating steel shafts is developed using air-coupled transducers (ACTs). Two ACTs are used for ultrasonic wave generation at two distinctive frequencies, and a third ACT is used for sensing. The proposed technique is based on the premise that nonlinear ultrasonic modulation appears at the sum and difference of two input frequencies in the presence of any crack due to crack opening and closing. First, the spectral correlation (SC) between ultrasonic modulation components at the sum and difference of two input frequencies is computed. Next, an outlier analysis is performed on spectral correlations obtained from different input frequency combinations for automated crack diagnosis. To the best of the authors’ knowledge, this is the first study in which a sub-millimeter fatigue crack is detected in a rotating steel shaft using noncontact transducers. In this study, real fatigue cracks on half-scale and full-scale steel shafts used in automobile assembly lines are produced through cyclic loading tests, and the performance of the proposed technique is experimentally validated using ultrasonic response data obtained from the half-scale and full-scale steel shaft specimens. The formation of fatigue cracks is confirmed using fluorescent magnetic particle inspection (MPI), fluorescent penetrant inspection (FPI), and metallographic analysis.

Preparation of RE(DBM)3·Phen (RE=Eu3+,Tb3+) Plate-Loading Fe3O4 Nanospheres and their Magnetic-Optic Bifunctional Property

A facile wet chemical method has been used to synthesize bifunctional core-shell nanoparticles of Fe3O4@RE(DBM)3·Phen (RE=Eu3+,Tb3+) showing an interesting combination of magnetic and luminescent properties. This method is convenient, cheap, and efficient. The morphology, structure, luminescent, and magnetic properties of the nanoparticles were investigated by X-ray diffraction (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM), UV-vis absorption, fluorescence emission, and superconducting quantum interference device magnetometer (SQUID-VSM). The maximum emission peaks of novel Eu3+ and Tb3+ nanocomposites are at 618 nm and at 514 nm, respectively. And their corresponding special saturation magnetization Ms. are 25.853 emu/g and 24.015 emu/g, respectively. For the nanoparticles, it is shown that there have better magnetic behavior and they may act as red- and green-emitting material with potential application for fluorescent magnetic particle testing. Moreover, this chemical route could be used to obtain the development of several bifunctional systems of other rare earth ions for practical application.

Stress corrosion crack evaluation of super 13Cr tubing in high-temperature and high-pressure gas wells

Abstract Super 13Cr is widely used for oil country tubular goods (OCTG) in wet CO2 environments with small amounts of H2S. This paper presents a case study of super 13Cr tubing that failed due to stress corrosion cracking (SCC). X-ray diffraction (XRD), energy dispersive spectrometry (EDS), scanning electron microscopy (SEM), optical microscopy (OM), and fluorescent magnetic particle inspection were used to investigate the failure mechanism. The results show that the inclusions, metallographic structure, yield strength, and tensile strength of the tubing meet the standard requirements. Furthermore, cracking analysis of the tubing shows that both secondary cracks propagating along grain boundaries and tree root branching were sunlight readable. Finally, failure was attributed to stress corrosion cracking (SCC). We concluded that the mechanism leading to stress corrosion cracking was corrosion product film breaking.

Study on crack features in images of fluorescent magnetic particle inspection for railway wheelsets

Study on crack features in images of fluorescent magnetic particle inspection for railway wheelsets

Crack detection algorithm for fluorescent magnetic particle inspection based on shape and texture features

Crack detection algorithm for fluorescent magnetic particle inspection based on shape and texture features

Failure Investigation of High Temperature Stud

The premature failure in a high-temperature stud is investigated in this article. The visual examination, dimensional measurement, and wet fluorescent magnetic particle, and chemical compositions are carried out as part of preliminary investigation. Apart from these tests, microstructural examination, tensile, impact and fractographic analyses are also conducted as part of the investigation. Finally, it has been concluded that the failure of the stud is caused because of the presence of severe localized, elongated, and oriented inclusions along the thread profile, particularly near the thread-root region. The inclusions may act as stress inducers under service load and facilitate initiation of cracks. The cracks are further propagated, finally leading to premature failure of the stud.

The Hardware Design and Implement of an Image Information Collection System

It introduces the hardware design and implement of the image information collection system which is one part of Fluorescent magnetic particle nondestructive detection system of Cannonball. The image information collection system includes Open collecting card model Initialize collection card modelApply for EMS memory modelCollecting image modelWrite bitmap information head model Show pictures modeClose collection card model. Through collecting image information to the EMS memory and then processing the image information, the magnetic images on the cannonball are showed clearly on computer, and cracks on the cannonball can easily to be judged. The software of the image information collection system is developed by Visual C++.