Structure-Aware Compressive Sensing for Magnetic Flux Leakage Detectors: Theory and Experimental Validation

Najafabadi, Hamid Esmaeili; Leung, Henry; Guo, Jian; Hu, Tiehua; Chang, Guang Hui; Gao, Wenshen

doi:10.1109/tim.2020.3047503

Cited by 3 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compressed sensing (CS) is a signal processing technique that achieves efficient compression by quickly and effectively acquiring sparse representations of signals. Compared to traditional signal compression methods, CS can capture the main features of a signal with a small number of random measurements during signal acquisition, greatly improving the efficiency of information collection; thus, CS has been used to improve the sampling performance of detectors [18,19]. In addition, CS uses sparse sampling combined with density detection algorithms to achieve higher data compression rates with minimal loss of signal information.…”

Section: B Image Data Enhancementmentioning

confidence: 99%

Adaptive Compressive Sensing: An Optimization Method for Pipeline Magnetic Flux Leakage Detection

Zhang,

Liu,

Zhang

2023

Sustainability

View full text Add to dashboard Cite

Leakage from a submarine oil pipeline would have a great impact on the environment and ecological balance. Accurate detection of pipeline defects can ensure safety in the transportation of oil resources. The traditional detection optimization algorithm may lead to the absence of effective features. An adaptive compressive sensing image data augmentation method that analyzes the pixel distribution of small defect features has been proposed to solve these issues. On the basis of Focal-EIoU, a new box loss of Focal-GIoU is proposed which is suitable for pipeline defect detection. Furthermore, the incorporation of bi-level routing attention diminishes the reliance of Yolov5 on specific inputs effectively, thereby enhancing the generalization ability of the detection model. Comparative experiments show that compared with the conventional Yolov5 model, this method improves mAP50 and mAP50:95 by 6.4% and 15.1%, respectively, with mAP50 reaching 91.5% and mAP50:95 reaching 52.9%.

show abstract

Section: B Image Data Enhancementmentioning

confidence: 99%

Adaptive Compressive Sensing: An Optimization Method for Pipeline Magnetic Flux Leakage Detection

Zhang,

Liu,

Zhang

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…The cracking of circumferential welds in oil and gas pipelines is characterized by easy propagation and a high risk of explosion after initiation [7][8][9][10] . Once a circumferential weld failure occurs, it poses a severe threat to individuals and the environment along the pipeline route, leading to substantial economic losses [11][12][13][14][15] .…”

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

“…Sub-Nyquist sampling and data compression lead to significant time-saving results in fault-detection applications like belts [4], bearing [5], composite materials [6], etc. It can also reduces the hardware requirements for monitoring applications like pipelines [7,8]. The flexible measurement rate enables robustness to partial data loss in harsh environments like nuclear sites.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Chen,

Song,

Zeng

et al. 2023

Entropy

View full text Add to dashboard Cite

Compressed sensing (CS) is a popular data compression theory for many computer vision tasks, but the high reconstruction complexity for images prevents it from being used in many real-world applications. Existing end-to-end learning methods achieved real time sensing but lack theory guarantee for robust reconstruction results. This paper proposes a neural network called RootsNet, which integrates the CS mechanism into the network to prevent error propagation. So, RootsNet knows what will happen if some modules in the network go wrong. It also implements real-time and successfully reconstructed extremely low measurement rates that are impossible for traditional optimization-theory-based methods. For qualitative validation, RootsNet is implemented in two real-world measurement applications, i.e., a near-field microwave imaging system and a pipeline inspection system, where RootsNet easily saves 60% more measurement time and 95% more data compared with the state-of-the-art optimization-theory-based reconstruction methods. Without losing generality, comprehensive experiments are performed on general datasets, including evaluating the key components in RootsNet, the reconstruction uncertainty, quality, and efficiency. RootsNet has the best uncertainty performance and efficiency, and achieves the best reconstruction quality under super low-measurement rates.

show abstract

Structure-Aware Compressive Sensing for Magnetic Flux Leakage Detectors: Theory and Experimental Validation

Cited by 3 publications

References 56 publications

Adaptive Compressive Sensing: An Optimization Method for Pipeline Magnetic Flux Leakage Detection

Adaptive Compressive Sensing: An Optimization Method for Pipeline Magnetic Flux Leakage Detection

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

A Real-Time and Robust Neural Network Model for Low-Measurement-Rate Compressed-Sensing Image Reconstruction

Contact Info

Product

Resources

About