On the application of self-organizing neural networks in gas-liquid and gas-solid flow regime identification

Barbosa, Paulo Roberto; Crivelaro, Kelen Cristina Oliveira; Seleghim, Paulo

doi:10.1590/s1678-58782010000100003

Cited by 17 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In forced convection flow the motion of electrolyte bulk exert drag force on the bubbles which is summed to buoyancy force to overcome the interfacial tension force at the vicinity of electrode-gas interphase 95 (b) Flow regime of gas-liquid phase in horizontal flow. 96 and lift force tries to push the bubble away from the electrode surface. The growing bubbles on the electrode surface more likely move from the nucleation vicinity along the electrode surface until they coalesce/collide with another bubble, at which time the volume of the collided bubbles reaches the critical diameter.…”

Section: Effect Of Bulk Flow On Bubblesmentioning

confidence: 99%

See 1 more Smart Citation

Review—Physicochemical Hydrodynamics of Gas Bubbles in Two Phase Electrochemical Systems

Taqieddin

Nazari

Rajić

et al. 2017

J. Electrochem. Soc.

View full text Add to dashboard Cite

Electrochemical systems suffer from poor management of evolving gas bubbles. Improved understanding of bubbles behavior helps to reduce overpotential, save energy and enhance the mass transfer during chemical reactions. This work investigates and reviews the gas bubbles hydrodynamics, behavior, and management in electrochemical cells. Although the rate of bubble growth over the electrode surface is well understood, there is no reliable prediction of bubbles break-off diameter from the electrode surface because of the complexity of bubbles motion near the electrode surface. Particle Image Velocimetry (PIV) and Laser Doppler Anemometry (LDA) are the most common experimental techniques to measure bubble dynamics. Although the PIV is faster than LDA, both techniques are considered expensive and time-consuming. This encourages adapting Computational Fluid Dynamics (CFD) methods as an alternative to study bubbles behavior. However, further development of CFD methods is required to include coalescence and break-up of bubbles for better understanding and accuracy. The disadvantages of CFD methods can be overcome by using hybrid methods. The behavior of bubbles in electrochemical systems is still a complex challenging topic which requires a better understanding of the gas bubbles hydrodynamics and their interactions with the electrode surface and bulk liquid, as well as between the bubbles itself.

show abstract

Section: Effect Of Bulk Flow On Bubblesmentioning

confidence: 99%

“…Figure 5. Flow patterns: (a) Flow regime of gas-liquid phases in vertical flow,95 (b) Flow regime of gas-liquid phase in horizontal flow 96. …”

mentioning

confidence: 99%

Review—Physicochemical Hydrodynamics of Gas Bubbles in Two Phase Electrochemical Systems

Taqieddin

Nazari

Rajić

et al. 2017

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…When an input pattern is presented to the network, the best-matching node (winner node) is found by the ED estimation. The weights of the winner have a chance to adjust in a gradient step [19][20][21]30]. After 600 training iterations, it takes 15.67 s to cluster the 50 training patterns into 5 Classes.…”

Section: Learning Performancesmentioning

confidence: 99%

Multiple harmonic-source classification using a Self-Organization Feature Map network with voltage–current wavelet transformation patterns

Huang

Lin

2015

Applied Mathematical Modelling

View full text Add to dashboard Cite

a b s t r a c tThis paper proposes multiple harmonic-source classification using a Self-Organization Feature Map (SOFM) network with voltage (V)-current (I) wavelet transformation patterns. Using the V-I wavelet transformation (WT) patterns, a SOFM network is employed to separate non-harmonic loads from non-linear loads in a distribution system. Morlet wavelet functions are used as feature extractors to extract the features from voltage and current signals. These features are constructed from various V-I WT patterns, and can vary with different dilation and translation parameters. Therefore, the selectable features are relatively broad for real-time applications. Two-dimensional (2-D) patterns appear in different harmonic fluctuations with various harmonic orders, load levels, and power factors. A SOFM network is employed to classify the various V-I WT patterns, including non-linear electronic devices, AC/DC motors, and Electric Arc Furnaces (EAFs). By contrast with the traditional SOFM network and the support vector machine (SVM), the testing results show that the proposed method has a fast learning process, a high accuracy, and an adaptive capability with new add-in training patterns. It can be used as an added tool for power quality (PQ) engineers and can be integrated into monitor instruments.

show abstract

“…In the oil field, machine learning has been widely used in research due to its great potential to solve problems [6][7][8][9][10]. This deep learning method has a great performance in price prediction, in which there is a study in the oil price forecast with this tool [11].…”

Section: Introductionmentioning

confidence: 99%

Initial study of application of Neural Networks to predict flow patterns in multiphase flow

Neyra

Moura

2022

Sci. Plena

View full text Add to dashboard Cite

The study of flow patterns in multiphase flow is widely used in the oil industry. Many tools are being developed to help predict these flow patterns. Artificial Intelligence is a tool with high performance and great use to characterize physical phenomena and can be used to predict these flow patterns in multiphase flow. We developed an Artificial Neural Network to recognize and predict the flow patterns of multiphase flow using an experimental database. In addition to using the neural network, data processing was also carried out to improve the tool's effectiveness. For a complete analysis, we trained the network with several combinations of the patterns, the patterns being: intermittent, annular and stratified. We did not use the bubble pattern due to the difference in the amount of data available between this and the other patterns. The net was up to 90% effective in some combinations of the analysis between flow patterns. Analyzing the 3 patterns together, the network showed an efficiency of approximately 67%. We analyzed the results of the net error behavior during its training and the hit rate after training. In this article, we used the artificial neural network as a tool to predict the flow pattern in the multiphase flow, with the maximum available flow parameters.

show abstract

On the application of self-organizing neural networks in gas-liquid and gas-solid flow regime identification

Abstract: One of the main problems associated with the transport and manipulation of multiphase

Cited by 17 publications

References 23 publications

Review—Physicochemical Hydrodynamics of Gas Bubbles in Two Phase Electrochemical Systems

Review—Physicochemical Hydrodynamics of Gas Bubbles in Two Phase Electrochemical Systems

Multiple harmonic-source classification using a Self-Organization Feature Map network with voltage–current wavelet transformation patterns

Initial study of application of Neural Networks to predict flow patterns in multiphase flow

Contact Info

Product

Resources

About