Multi-frequency fusion ultrasonic tomography for gas–liquid two-phase distribution imaging

Líu, Hao; Tan, Chao

doi:10.1088/1361-6501/abbebd

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rapid and accurate reconstruction of multiphase distribution is of great significance for optimal control, state monitoring and fault prediction of industrial processes. The tomography techniques, such as electrical resistance tomography (ERT) [6,7], electrical capacitance tomography (ECT) [8,9], magnetic inductance tomography (MIT) [10,11] and ultrasonic transmission tomography (UTT) [12,13], etc, have been developed and widely used in multiphase distribution imaging. When only two media distribution visualization is considered, the traditional single-modality tomography technique can achieve the purpose of media differentiation.…”

Section: Introductionmentioning

confidence: 99%

Coplanar electrical/ultrasonic dual-modality tomography for water continuous gas/oil/water three-phase distribution imaging

Liang

Ren

Dong

2021

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Multiphase distributions are common in industrial processes, such as the gas/oil/water three-phase flow, where the visualization of three media is of great significance for state monitoring and fault prediction of industrial production processes. Industrial process tomography possesses unique advantages of non-invasive, non-radiation, and low-cost in multiphase distribution imaging, attracting more and more attention. Due to the complexity of the physical parameters of gas/oil/water three media, traditional single-modality tomography technology is usually difficult to reconstruct and distinguish three media simultaneously. To overcome this problem, an electrical/ultrasonic dual-modality tomography method is proposed, where a coplanar dual-modality sensor is designed to obtain electrical and ultrasonic measurement data. To achieve image fusion, the same mesh model is used in electrical resistance tomography (ERT) and ultrasonic transmission tomography (UTT) inverse problems. The logistic regression and two-dimensional wavelet-transform fusion methods are proposed to fuse the ERT and UTT reconstructed images and visualize the gas/oil/water three media. Numerical and experimental tests are conducted, and image reconstruction results show that the proposed coplanar electrical/ultrasonic dual-modality tomography method can simultaneously reconstruct and distinguish three media in water continuous gas/oil/water three-phase distribution. Especially, the proposed logistic regression and two-dimensional wavelet-transform fusion methods can also improve the imaging quality compared with the traditional single-modality and weighted-average fusion methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Coplanar electrical/ultrasonic dual-modality tomography for water continuous gas/oil/water three-phase distribution imaging

Liang

Ren

Dong

2021

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

Classification of damage types in liquid-filled buried pipes based on deep learning

ma¹,

Du²,

Yu³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

In long-distance pipelines, the type of local damage can lead to different forms of damage. Ultrasound-guided wave technology can detect channel damage at a distance and reduce the workforce and material resources. Deep learning has the advantages of high efficiency and accuracy for pipeline damage classification and identification. This study proposes a classification method that combines ultrasound-guided waves with deep residual neural networks. First, the time series data of the defect echoes are encoded into different types of images using the glare angular field matrix (GAF); then, the features of the generated images are extracted using ResNet. Finally, it is put into Faster-RCNN for training, validation, and defect type recognition. Finite element models containing cracked, square and circular defects were built to verify the effectiveness of method. The network models were trained for classification, testing, and validation using pipes with broken defects. Finite element analysis (FEA) results show that the network model classifies cracked, square and circular defects with different damage levels with accuracy, recall and F1-score indices close to 90%, and the experimental results show that the network model has an identification accuracy of approximately 90%. Furthermore, the results show that the Faster-RCNN-ResNet model is more accurate in identifying complex pipeline defect types than machine learning and other deep learning methods. The model showed good feasibility and effectiveness in classifying the damage types of long transmission buried pipelines.

show abstract

Multi-frequency fusion ultrasonic tomography for gas–liquid two-phase distribution imaging

Cited by 2 publications

References 34 publications

Coplanar electrical/ultrasonic dual-modality tomography for water continuous gas/oil/water three-phase distribution imaging

Coplanar electrical/ultrasonic dual-modality tomography for water continuous gas/oil/water three-phase distribution imaging

Classification of damage types in liquid-filled buried pipes based on deep learning

Contact Info

Product

Resources

About