Vertical co-current two-phase flow regime identification using fuzzy C-means clustering algorithm and ReliefF attribute weighting technique

Pan, Liang‐ming; Zhang, Muhao; Ju, Peng; He, Hui; Ishii, Mamoru

doi:10.1016/j.ijheatmasstransfer.2015.11.081

Cited by 37 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The applicability of an ANN for the identification of a two-phase flow regime has been investigated by various researchers [9,10]. Pan et al [10] developed a fuzzy C-means (FCM) clustering algorithm to create a flow regime identification map for a co-current air-water two-phase flow in the vertical direction. They conducted several experiments to build a suitable database.…”

Section: R407cmentioning

confidence: 99%

Prediction and optimization of condensation heat transfer coefficients and pressure drops of R134a inside an inclined smooth tube

Abadi

Mehrabi

Meyer

2018

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

In this study, an adaptive neuro-fuzzy inference system (ANFIS) is proposed for the prediction and optimization of condensation heat transfer coefficient and pressure drops along an inclined smooth tube. The performance of three ANFIS structure identification methods, grid partitioning (GP), a subtractive clustering method (SCM), and fuzzy C-means (FCM) clustering, were examined. For training the proposed ANFIS model, an in-house experimental database was utilised. Three statistical criteria, the mean absolute error (MAE), mean relative error and root mean square error were used to evaluate the accuracy of each method. The results indicate that the GP structure identification method has the lowest number of training errors for both the pressure drop, i.e., MAE = 6.4%, and condensation heat transfer coefficient, i.e., MAE = 2.3%, models. In addition to the ANFIS model, numerical simulations were also conducted to assess the accuracy and capability of the proposed model. The comparison shows that the CFD simulation results have better accuracy for the specified operating conditions. However, the errors of both the CFD and ANFIS methods were within the uncertainties of the experimental data. It was therefore concluded that the ANFIS model is useful in obtaining faster and reliable results. Finally, the optimization results showed a possible optimum point at a mass flux of 100 kg/m 2 s, saturation temperature of 36.2 °C, downward inclination angle of-15° and a vapour quality of 0.48. At this condition the pressure drop is almost zero.

show abstract

Section: R407cmentioning

confidence: 99%

Prediction and optimization of condensation heat transfer coefficients and pressure drops of R134a inside an inclined smooth tube

Abadi

Mehrabi

Meyer

2018

International Journal of Heat and Mass Transfer

View full text Add to dashboard Cite

show abstract

“…The electrical impedance void meter is based on the impedance difference between liquid and gas, which consists of electrodes on the surface of the flow channel. Moreover, many types of impedance void meter have been developed and applied in research on two-phase flow, such as the double ring type [24] in pipes, face-to-face plates [21], and quadrant arcs [25] in rod bundles. It should be noted that, in some way, the SCVS [5,19,20] could also be considered as one type of electrical impedance void meter.…”

Section: Electrical Impedance Void Metermentioning

confidence: 99%

“…Moreover, the 12 strip electrodes are divided into two groups, as shown in figure 1: the six dark electrodes serve as the emitter electrode while the six light electrodes serve as the receiver electrode. The working principle of the subchannel impedance meter is similar to the impedance void meter applied in the pipe [24], which is based on the conductance differences between gas and liquid. As the void fraction increases in the subchannel, the conductance of the gas liquid mixture decreases between the emitter and receiver electrode, which results in a voltage change between the two electrodes.…”

Section: Scivmmentioning

confidence: 99%

Measurement of subchannel void fraction in 5 × 5 rod bundles using an impedance void meter

Ren

Pan

Zhou

et al. 2018

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

In order to improve the ability to predict nuclear reactor behaviour, reliable measurement of the void fraction in a subchannel is essential. A subchannel impedance void meter (SCIVM) is developed and applied in air-water two-phase flow in 5 × 5 rod bundles, which consists of a six-strip emitter electrode and six-strip receiver electrode to cover the whole subchannel. Because of the lack of accurate void fraction calculation in the subchannel, the developed impedance void meter is calibrated by a four-sensor conductivity probe with a quartic polynomial function. The void fractions in different subchannels are measured with a sampling frequency of 10 kHz to capture the dynamic features of the rapidly changing phase distribution in two-phase flow. The phase distributions in rod bundles are discussed based on the void fractions measured in different subchannels, and among all flow regimes, the cap turbulent flow has the largest void fraction differences between the inner, side and corner subchannel on the same cross-section due to the effect of the casing tube. Moreover, the dynamic features of the subchannel void fraction are analysed for different flow regimes, including bubbly, cap bubbly, cap turbulent, churn turbulent, and annular flow. It is demonstrated that the newly designed subchannel impedance void sensor is an effective tool to measure the void fraction in the subchannel and figure out its dynamic features. Highlights• A novel SCIVM is designed to measure the void fraction in the subchannel.• The measured subchannel void fraction is calibrated with a four-sensor conductivity probe and verified with empirical drift-flux correlations. • The differences in void fraction are discussed for different subchannels on the same cross-section.• The dynamic features of the subchannel void fraction are analysed for different flow regimes.

show abstract

“…Based on the above discussion, due to the complexity of gas-liquid two-phase countercurrent flow in the vertical annulus, its detection signal features have high dimensions. In order to avoid the subjective factors introduced in the process of artificial flow regime recognition, many unsupervised machine learning classification methods are applied in the field of gas-liquid two-phase flow regime identification, such as K-means [29,41] , Fuzzy C -means [42] , Selforganizing maps (SOM) [43] , Expectation maximization (EM) [44] etc., It does not rely on a priori information such as flow labels, and only relies on the distance measurement between test samples to achieve the classification of flow regimes, and then realizes the correspondence between classification and flow regimes through the comparison of classification features. This research will be carried out according to this idea.…”

Section: Introductionmentioning

confidence: 99%

Flow regime identification of air-water two-phase counter-current flow in vertical annulus and eccentricity effect analysis：a machine learning approach

Cao,

Dang,

Dang

et al. 2023

Preprint

View full text Add to dashboard Cite

Gas-liquid two-phase counter-current flow has been involved in many industrial fields, due to the existence of the inner pipe and the variation of the eccentricity of the inner and outer pipes, the flow regimes are difficult to be visual identification. To solve this problem, a vertical annulus with adjustable eccentricity was designed. Experiments were carried out under different combination of gas-liquid flowrate and eccentricity. The feature vector was formed by PDF and principal components of PSD of two differential pressure signals. The clustering algorithm CFDP based on local density was used to cluster the experimental data, results show that this method can realize the identification of flow regimes without prior information, and the flow regime transition boundary agrees with the experimental results. The influence of pipe eccentricity on the flow regime transition is analyzed. The results show that, in most cases, pipe eccentricity has no obvious influence on the flow regimes. However, in the flow regime transition region, such as the bubbly flow to slug flow transition region, when the eccentricity is at a medium value, that is, e = 0.25,0.5,0.75, the flow is more likely to transit to slug flow, however, when e = 0,1. The flow tends to remain bubbly flow.

show abstract

Vertical co-current two-phase flow regime identification using fuzzy C-means clustering algorithm and ReliefF attribute weighting technique

Cited by 37 publications

References 32 publications

Prediction and optimization of condensation heat transfer coefficients and pressure drops of R134a inside an inclined smooth tube

Prediction and optimization of condensation heat transfer coefficients and pressure drops of R134a inside an inclined smooth tube

Measurement of subchannel void fraction in 5 × 5 rod bundles using an impedance void meter

Flow regime identification of air-water two-phase counter-current flow in vertical annulus and eccentricity effect analysis：a machine learning approach

Contact Info

Product

Resources

About