Defect Detection and Quantification from Magnetic Flux Leakage Signals Based on Deep Learning

Yuksel, Veysel; Tetik, Yusuf Engin; Basturk, Mahmut  Omer; Recepoglu, Onur; Gokce, Kursad; Cimen, Mehmet Ali

doi:10.2139/ssrn.4201045

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction2

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Other2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Planar defects, such as lack of fusion, incomplete penetration, and cracks, pose greater risks. Planar defects at the root weld are the main causes of cracking and represent a focal point in the research on non-destructive testing of circumferential weld defects [21][22][23][24][25] .…”

Section: Introductionmentioning

confidence: 99%

Mechanical structure design and simulation of multi-physical field integrated pipeline internal inspection detector

Huang,

Chen,

et al. 2024

Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024)

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Mechanical structure design and simulation of multi-physical field integrated pipeline internal inspection detector

Huang,

Chen,

et al. 2024

Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024)

View full text Add to dashboard Cite

“…Chen et al [5] developed a multi-class defect detection method based on sparsity reconstruction, which detects faults of weld lines in Xray images. In addition to the mentioned methods, deep learning algorithms are the most effective methods for autonomous defect detection, which are used vastly by researchers [6,7].…”

Section: Introductionmentioning

confidence: 99%

Autonomous inspection of steel pipe weld lines implementing frequency analysis combined with YOLOv5

Komarsofla,

Charest-Finn,

Nokleby

2023

Progress in Canadian Mechanical Engineering. Volume 6

View full text Add to dashboard Cite

In this research, autonomous inspection of steel pipe weld lines for a single class of defects is done using a frequency analysis combined YOLOv5 (You Only Look Once) model. Since steel pipes are vastly implemented in high-risk applications, it is essential to accurately inspect them for defects. A new method is presented to enhance the training process of YOLOv5 using frequency analysis. Two YOLOv5 models are trained using frequencymodified and original images, and the results and training process of these two models are compared. In order to produce frequencymodified images, the first 50 frequencies are removed from the Fourier transform, resulting in a new image set. Results revealed that removing lower frequencies leads to more smooth behavior in indices of the YOLOv5 model during different epochs and reduces training time by 15%. I.

show abstract

A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data

Chen,

Li,

et al. 2024

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

Defect Detection and Quantification from Magnetic Flux Leakage Signals Based on Deep Learning

Cited by 3 publications

References 18 publications

Mechanical structure design and simulation of multi-physical field integrated pipeline internal inspection detector

Mechanical structure design and simulation of multi-physical field integrated pipeline internal inspection detector

Autonomous inspection of steel pipe weld lines implementing frequency analysis combined with YOLOv5

A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data

Contact Info

Product

Resources

About