Gas-liquid vertical pipe flow patterns convolutional neural network classification using experimental advanced wire mesh sensor images

Brantson, Eric Thompson; Abdulkadir, M.; Akwensi, Perpetual Hope; Osei, Harrison; Appiah, Titus Fiifi; Assie, Konan Roger; Samuel, Sibil

doi:10.1016/j.jngse.2021.104406

Cited by 8 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bubble' image analysis via CNNs also enables identication of the ow patterns. 90,91 High-speed cameras are widely used to capture cavitation bubbles, but the resulting images are oen of a low quality. Machine learning can also be used to improve defects of input images.…”

Section: Cavitation Bubbles' Analysismentioning

confidence: 99%

Machine learning for soft and liquid molecular materials

et al. 2023

View full text Add to dashboard Cite

show abstract

Section: Cavitation Bubbles' Analysismentioning

confidence: 99%

Machine learning for soft and liquid molecular materials

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The resulting output y is obtained by applying the activation function f elementwise to the output of the convolutional operation and the index l represents the layer in the convolutional neural network on which the operation is being performed. The pooling layer is employed to reduce the dimensions of the feature maps to maintain relevant information of the cross-sectional frame images obtained from the convolutional layer [35]. In this regression problem, the pooling layer can be applied after the convolutional layer.…”

Section: B Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Evaluation of the nominal thickness of pipelines using neural networks through the dispersion curves drawn with the SAFE method

Boechat,

Lavor,

Sesini

et al. 2023

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Inspection through non-destructive testing is important for the analysis of oil well structures in different phases of the project, whether during execution, during the production period, or at closure. In this context, the propagation of ultrasonic waves is an important ally to assessing the integrity of structural components, through the tracing of dispersion curves, which show the pair frequency x wavelength for a specific waveguide. This study presents a neural network framework for estimating the percentage of nominal pipeline thickness. The neural network inputs are dispersion curves obtained by simulation, using the semi-analytical finite element method (SAFE), that presents a computational cost reduced compared with the totally numerical simulation. In this way, 100 samples were generated. The case studied consists of a hollow cylinder with different thickness sizes. From the results, it is concluded that the adopted methodology is efficient to predict the percentage of nominal pipeline thickness.

show abstract

“…CNNs have been implemented to analyze two-phase flow in some limited cases; they have been used to study bubbly flow [28,29] and as a tool for the analysis of complex flow characteristics [30], but the use of these networks as image-based classifiers of flow regime has been limited. Branston et al [31] achieved good results in image-based vertical flow regime classification by using a CNN to classify cross-sectional images of the flow channel, produced by an advanced wire-mesh sensor. A study by Du et al [32] compared three CNN-based architectures for their ability to classify the vertical flow regime of a given input image, captured from the observation section of a flow channel using a camera.…”

Section: Introductionmentioning

confidence: 99%

Computer Vision-Based Classification of Flow Regime and Vapor Quality in Vertical Two-Phase Flow

Kadish

Schmid

Son

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper presents a method to classify flow regime and vapor quality in vertical two-phase (vapor-liquid) flow, using a video of the flow as the input; this represents the first high-performing and entirely camera image-based method for the classification of a vertical flow regime (which is effective across a wide range of regimes) and the first image-based tool for estimating vapor quality. The approach makes use of computer vision techniques and deep learning to train a convolutional neural network (CNN), which is used for individual frame classification and image feature extraction, and a deep long short-term memory (LSTM) network, used to capture temporal information present in a sequence of image feature sets and to make a final vapor quality or flow regime classification. This novel architecture for two-phase flow studies achieves accurate flow regime and vapor quality classifications in a practical application to two-phase CO2 flow in vertical tubes, based on offline data and an online prototype implementation, developed as a proof of concept for the use of these models within a feedback control loop. The use of automatically selected image features, produced by a CNN architecture in three distinct tasks comprising flow-image classification, flow-regime classification, and vapor quality prediction, confirms that these features are robust and useful, and offer a viable alternative to manually extracting image features for image-based flow studies. The successful application of the LSTM network reveals the significance of temporal information for image-based studies of two-phase flow.

show abstract

Gas-liquid vertical pipe flow patterns convolutional neural network classification using experimental advanced wire mesh sensor images

Cited by 8 publications

References 61 publications

Machine learning for soft and liquid molecular materials

Machine learning for soft and liquid molecular materials

Evaluation of the nominal thickness of pipelines using neural networks through the dispersion curves drawn with the SAFE method

Computer Vision-Based Classification of Flow Regime and Vapor Quality in Vertical Two-Phase Flow

Contact Info

Product

Resources

About