A Novel Cascaded Deep Learning Model for the Detection and Quantification of Defects in Pipelines via Magnetic Flux Leakage Signals

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

doi:10.1109/tim.2023.3272377

Cited by 9 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, those defect features are restricted in the field applications to cover all characteristics of MFL testing regarding pipeline defects. Then, artificial intelligence methods are adopted for MFL testing in support of defect quantification [19][20][21][22][23]. The study's findings demonstrate that the machine learning method (e.g.…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

Magnetic flux leakage defect size estimation method based on physics-informed neural network

Xiong,

Liu,

Hou

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Magnetic flux leakage (MFL) is a magnetic method of non-destructive testing for in-pipe defect detection and sizing. Despite the fact that recent developments in machine learning have revolutionized disciplines like MFL defect size estimation, the most current methods for quantifying pipeline defects are primarily data-driven, which may violate the underlying physical knowledge. This paper proposes a physics-informed neural network-based method for MFL defect size estimation. The training process of neural network is guided by the MFL data and the physical constraints that is mathematically represented by the magnetic dipole model. We use synthetic MFL data produced by a virtual MFL testing of pipeline defects to validate the proposed method through a comparison to purely data-driven neural networks and support vector machines. The findings imply that the physics-informed strategy can both improve predictive accuracy and mitigate physical violations in MFL testing, providing us with a better knowledge of how neural networks perform in defect size estimation. This article is part of the theme issue ‘Physics-informed machine learning and its structural integrity applications (Part 2)’.

show abstract

Section: Introductionmentioning

confidence: 94%

“…Deep learning applications in MFL testing for pipeline defect quantification have received significant research attention [22][23][24]. This work was motivated by deep learning's ability to automatically learn from data representing features.…”

Section: Introductionmentioning

confidence: 99%

Magnetic flux leakage defect size estimation method based on physics-informed neural network

Xiong,

Liu,

Hou

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

show abstract

“…Xia et al [14] used thermal imaging technology to obtain images of surface defects on steel ropes and proposed an image segmentation algorithm based on scale morphology to eliminate the influence of non-uniform heating background and visualize the defect area. Yuksel et al [15] used magnetic leakage sensors to obtain signals of internal damage in steel pipelines and combined them with an improved YOLOv5 and cross-convolutional neural network, effectively improving the accuracy of internal defect detection in steel pipes. However, this algorithm introduces the Swin Transformer module as the backbone network, which has higher complexity and is not ideal in terms of detection speed and model size.…”

Section: Introductionmentioning

confidence: 99%

FLCNet: faster and lighter cross-scale feature aggregation network for lead bar surface defect detection

Lv,

Xia,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming at the defect inspection under the characteristics of scale change, high reflection, inclined deformation of defects of lead bars and meeting the needs for faster detection, this paper proposes a faster and lighter cross-scale feature aggregation network (FLCNet). In this study, we focus on the redundancy of channel information, and design a new partial channel group convolution, based on which we design a Faster C3 module and a lightweight cross-scale feature fusion module. In addition, we design a cross-scale slim neck to reduce the redundant feature transfer of the model. Finally, we propose a uniform brightness acquisition method for lead bar sidewall image by using combined light source and construct a lead bar dataset with various complex defect samples. Experiments show that FLCNet effectively improves the detection accuracy of the surface defects of lead bars, the mAP@0.5 value reaches 97.1%, and compared with YOLOv5s, the model’s parameters reduced by 33.9%. At the same time, the detection speed reaches 114.9 FPS, which is faster than other advanced detection models.

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

A Novel Cascaded Deep Learning Model for the Detection and Quantification of Defects in Pipelines via Magnetic Flux Leakage Signals

Cited by 9 publications

References 36 publications

Magnetic flux leakage defect size estimation method based on physics-informed neural network

Magnetic flux leakage defect size estimation method based on physics-informed neural network

FLCNet: faster and lighter cross-scale feature aggregation network for lead bar surface defect detection

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

Contact Info

Product

Resources

About