Research on internal and external defect identification of drill pipe based on weak magnetic inspection

Yilai, Ma; Li, Lin

doi:10.1784/insi.2014.56.1.31

Cited by 16 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the input end, mosaic data enhancement [24] is adopted to splice the input images by random scaling, cropping, arrangement, etc, to enrich the dataset and improve the robustness of the network. The backbone network [25] is composed of a focused slice structure, a CSP structure [26] and a pyramid pool structure (SPP). The focus structure adopts a slicing operation to expand the channel of the original input image and improve the computing power without information loss [27].…”

Section: The Main Structure Of the Yolov5 Algorithmmentioning

confidence: 99%

A global centralized magnetic flux leakage small defect detection network

Chen,

Lang,

Liu

2024

Eng. Res. Express

View full text Add to dashboard Cite

To solve the problem that magnetic-flux-leakage (MFL) small defects are difficult to accurately detect by machine learning methods, a global centralized magnetic flux leakage small defect detection network (RCFPNet) is proposed. RCFPNet consists of simulation data enhancement, improved feature extraction (backbone), an improved centralized feature pyramid (CFP) and a detection head network. The MFL defect data of various scales and shapes are simulated by ANSYS simulation software and superimposed with the actual detected MFL defects to expand the dataset. The Repvgg module is used to replace the 3*3 convolution of the backbone to improve the detection speed. An improved spatially explicit vision center scheme (EVC) and a global centralized regulation rule (GCR) for feature fusion networks are proposed for feature fusion networks. RCFPNet is based on an improvement of the YOLOv5 network. Experiments have proven that RCFPNet has improved detection speed and accuracy and has achieved good results in the detection of magnetic leakage small defects. Experiments show that when the IOU=0.5, the accuracy rate of this algorithm is 96.1%, and the reasoning time is 8.9 ms.

show abstract

Section: The Main Structure Of the Yolov5 Algorithmmentioning

confidence: 99%

A global centralized magnetic flux leakage small defect detection network

Chen,

Lang,

Liu

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…internal [1][2][3][4][5][6][7] inner/inside [8,9], near-side/surface [10][11][12][13], top [14][15][16], front [17], front-side [18,19] external [1][2][3][4][5][6][7], outer/outside [8,20], far-side/surface [10][11][12][13]21], bottom [14][15][16]22], back [17], back-side [18,19,[23][24][25][26], opposite-side [27], sub-surface [28] side' are probably most unequivocal and universal, so these two terms are generally used in the rest of this article.…”

Section: Terms Describing Defectsmentioning

confidence: 99%

A Comparative Study on Methods of Distinction Between Near- and Far-Side Defects as Techniques Used Alongside with the Magnetic Flux Leakage Testing

2022

View full text Add to dashboard Cite

Results of the finite element analysis show that a far-side defect in a steel plate, with the depth greater by 10% of the plate thickness than a near-side defect, can produce a very similar magnetic flux leakage (MFL) signal. Due to the fact that a measurement of MFL itself can lead to misclassification of a far-side defect as a near-side one, and thus to underestimation of its depth, a comparative study of three complementary magnetic techniques was performed. The following techniques were studied: surface topology air-gap reluctance system (STARS), residual magnetic flux leakage (RMFL) and stray magnetic flux leakage (SMFL). Numerical results showed that in the case of the STARS and SMFL, defect signatures in signals were observed for investigated near-side defects, but not for far-side defects. The signature of the far-side defect in the RMFL was observed, however its peak-to-peak value was only about 8% of the value corresponding to the near-side defect.

show abstract

“…During the detection process, a sensor is used to detect several points, and the corresponding value of each detection point has a significant magnetic susceptibility. Therefore, the data obtained after the detection can be represented by a matrix [12] .…”

Section: System Measurement Principlementioning

confidence: 99%

The Analysis of Weak Magnetic Inspection of Standard Test Block Defects

Yuelin¹,

Zou²,

Zhang³

et al. 2018

Proceedings of the 2018 7th International Conference on Energy and Environmental Protection (ICEEP 2018)

View full text Add to dashboard Cite

The evaluation of standard test blocks plays an important role in nondestructive test, quality of which influences the inspection and production activities. The weak magnetic inspection is adopted, which direct at the common defections including wracks and holes to achieve the quantitative analysis of standard test block, regarding the split test plate as the detected objects. The standard test block is scanned horizontally and respectively by single detector, dual detector and triple detector. The collected data is analyzed and the experimental results are compared. The result shows that the method not only can probe out the location of defects, but also can take the quantitative analysis of those defections within a given range of error.

show abstract

Research on internal and external defect identification of drill pipe based on weak magnetic inspection

Cited by 16 publications

References 8 publications

A global centralized magnetic flux leakage small defect detection network

A global centralized magnetic flux leakage small defect detection network

A Comparative Study on Methods of Distinction Between Near- and Far-Side Defects as Techniques Used Alongside with the Magnetic Flux Leakage Testing

The Analysis of Weak Magnetic Inspection of Standard Test Block Defects

Contact Info

Product

Resources

About