Identification Of Two-phase Flow Research Articles

Liqnet: A real-time monitoring network for two-phase flow patterns

Real-time identification of gas-liquid two-phase flow can help fluid systems maintain safe operating conditions. A flow pattern identification method based on a convolutional neural network (CNN) algorithm (after this referred to as liqnet) is proposed in this paper to realize automatic detection and real-time identification of two-phase flow patterns. This paper mainly focuses on solving two problems of CNN algorithm flow pattern identification (1): the experimental samples for two-phase flow classification are few, and (2): the existing methods do not fully consider the real-time nature of two-phase flow identification. Therefore, this paper constructs a two-phase flow database containing 6242 images using data enhancement, proposes a lightweight network liqnet, and compares it with six mainstream CNN models. The results show that liqnet can achieve the highest accuracy (98.65%), has the least amount of parameters (1.3708 M), and can achieve the purpose of real-time prediction (32.11FPS).

Oil-in-Water Two-Phase Flow Pattern Identification From Experimental Snapshots Using Convolutional Neural Network

The flow pattern is one of the most significant parameters in modeling the oil–water two-phase system. How to extract efficient and objective features to precisely identify the oil–water two-phase flow patterns is still a significant issue. Inspired by the deep learning hierarchically feature extraction way, we, in this paper, employ convolutional neural networks (CNNs) to identify oil–water two-phase flow patterns. First, we carry out oil–water two-phase flow experiment and collect different oil–water flow pattern images. Then, we propose an image segment algorithm based on the minimum gray level to obtain the interest region that reflects the flow pattern characteristics. Finally, we employ three frequently used CNNs, LeNet-5, AlexNet, and VGG-16 net, to extract the image features and identify typical oil–water two-phase flow patterns. The results show that networks with more deep structures preserve relatively high flow pattern recognition accuracy. This paper provides a novel application of the deep learning method for the oil–water two-phase flow identification.

Classification of two-phase flow regimes via image analysis and a neuro-wavelet approach

A non-intrusive method of two-phase flow identification is investigated in this paper. It is based on image processing of data obtained partly from dynamic neutron radiography recordings of real two-phase flow in a heated metal channel, and partly by visible light from a two-component mixture of water and air. Classification of the flow regime types is performed by an artificial neural network (ANN) algorithm. The input data to the ANN are some statistical moments of the wavelet pre-processed pixel intensity data of the images. The pre-processing used in this paper consists of a one-step multiresolution analysis of the 2-D image data. The investigations of the neutron radiography images, where all four flow regimes are represented, show that bubbly and annular flows can be identified with a high confidence, but slug and churn-turbulent flows are more often mixed up in between themselves. The reason for the faulty identifications, at least partially, lies in the insufficient quality of these images. In the measurements with air-water two-component mixture, only bubbly and slug flow regimes were available, and these were identified with nearly 100% success ratio. The maximum success ratio attainable was approximately the same whether the raw data was used without wavelet preprocessing or with a wavelet preprocessing of the input data. However, the use of wavelet preprocessing decreased the training time (number of epochs) with about a factor 100.

Vertical two-phase flow identification using advanced instrumentation and neural networks

Most two-phase flow measurements, including void fraction measurements, depend on correct flow regime identification. There are two steps taken towards the successful identification of flow regimes: first, develop a non-intrusive instrument to demonstrate area-averaged void fluctuations and second, develop a non-linear mapping approach to perform objective identification of flow regimes. In this paper, an advanced non-intrusive impedance void-meter provides input signals to neural networks which are used to identify flow regimes. After training, both supervised and self-organizing neural network learning paradigms performed flow regime identification successfully. The methodology presented holds considerable promise for multiphase flow diagnostic and measurement applications.

Statistical properties of pressure drop fluctuations and flow patterns in horizontal gas-liquid two-phase flow.

Statistical characteristics of pressure drop fluctuations have been investigated experimentally in order to obtain fundamental data for flow pattern identification of two-phase flow in a horizontal pipe. The experimental results show that the horizontal flow of nitrogen gas (or air) -water mixtures exhibits peculiar features of statistical properties (PDF, PSD), that its flow patterns can be classified by using the statistical features, and that the pressure drop fluctuations measured at a short interval of pipe have high sensitivity to flow change. The results suggest that it is possible to identify the flow patterns of horizontal two-phase flow on the basis of the features of statistical parameters (standard deviation and coefficients of skewness and excess).

Two-phase flow identification by correlation techniques

It is suggested that the one-time spatial correlation function of density fluctuations can be used for two-phase flow identification. The correlation function of density fluctuations is assumed locally isotropic for most flow regimes with a correlation distance which is small compared to the system dimensions. A new procedure, based on the cross-correlation of radiation attenuation signals, is proposed by which the local spatial correlation function can be measured at any point of a propagating two-phase medium. The method is also suitable for determining local vapour velocity and local average void fraction.

Cross-sectional identification of two-phase flow by correlation techniques

A new method, based on the cross-correlation of two radiation attenuation signals, has been recently proposed for two-phase flow diagnostics. The method determines the local one-time correlation function of density fluctuations and appears to be applicable for flow regime identification as well as quantitative estimation of flow parameters such as average local void fraction, void-fluid interfacial velocity and local correlation length. This paper gives a summary of the principles of the method and presents a thorough numerical testing of the quantitative applicability of the method. A bubbly flow regime is simulated by Monte Carlo techniques which makes it possible to calculate all pertinent quantities by digital data processing methods. Performance of the proposed method was found rather satisfactory in the cases investigated.