共查询到20条相似文献，搜索用时 15 毫秒
1.
An earlier paper introduced a dataset of Coriolis meter mass flow and density errors, induced by the effects of two-phase (gas/liquid) flow, as a benchmark for which various error correction strategies might be developed. That paper further presented a series of error correction models based on neural nets. The current paper presents an alternative analysis of the same data set, using a support vector machine (SVM) approach. The analysis demonstrates that, for the benchmark data set, more accurate models are generated than those developed using neural nets. More specifically, it is found that a linear SVM model provides better performance than non-linear SVM. This improved performance may arise from over-fitting by both non-linear SVM and neural nets on this relatively small data set. 相似文献
2.
3.
Multiphase flow rate metering is a challenging problem, specially for flow patterns other than wet-gas. This paper brings forward a new comparative analysis of three differential pressure calibration models suited for liquid dominated two-phase flows, in a total of seven model configurations. First, the models are compared theoretically and classified in terms of the type of input data required. Then, experimental data of over 300 horizontal air–water experiments, for ” and ” pipe diameters, supports quantitative analyses of the prediction accuracies and sensitivity of the superficial velocities of gas and liquid to measurement errors in the model input variables. Finally, a method for assessing the decoupled measurement errors for the void fraction and gas velocity is shown, as these variables are typically subject to higher uncertainties. It results that, though the void fraction is shown to be systematically under evaluated in more than 10%, the total mass flow rate is estimated through the Paz et al. (2010) model with an overall root mean squared deviation (RMSD) of 5.75% for the ” data. Also, the use of gas velocity measurements, even if subject to considerable errors, decreased the RMSD for the gas superficial velocity by more than half for the ” data. 相似文献
4.
R. V. Raikar D. Nagesh Kumar Subhasish Dey 《Flow Measurement and Instrumentation》2004,15(5-6):285-293
The paper presents the application of artificial neural network (ANN) to determine the end-depth-ratio (EDR) for a smooth inverted semicircular channel in all flow regimes (subcritical and supercritical). The experimental data were used to train and validate the network. In subcritical flow, the end depth is related to the critical depth, and the value of EDR is found to be 0.705 for a critical depth–diameter ratio up to 0.40, which agrees closely with the value of 0.695 given by Dey [Flow Meas. Instrum. 12 (4) (2001) 253]. On the other hand, in supercritical flow, the empirical relationships for EDR and non-dimensional discharge with the non-dimensional streamwise slope of the channel are established. 相似文献
5.
Despite the intricacy, inline metering of two-phase flow has a significant impact in multitudinous applications including fusion reactors, oil, nuclear, and other cryogenic systems. Since measurement of individual flow rate is prominent in various systems, it warrants the establishment of a flow meter system that can monitor the mass flow rates of liquid. In this regard, an approach was taken towards the development of a two-phase flow meter system in the present study. The concept involves two-phase flow through narrow parallel rectangular channels resulting in laminar, stratified flow with a slope at the liquid-vapor interface. The height of the liquid column at specific channel locations is measured for determining the flow rate. However, the geometric configurations of the channels and fluid properties are pivotal in ensuring accurate measurement. Consequently, theoretical and experimental studies are performed to investigate the correspondence between flow rate and change in liquid height. Based on the governing equations, a theoretical model is established using MATLAB®. The model investigated the intricate influence of various flow and fluid properties in the estimation of the mass flow rate. The experimental investigation was done with various conditions under different liquid and vapor volume flow rates for validating the proposed supposition and the theoretical model. Both the theoretical and experimental analyses showed fair correspondence. The proposed system estimated the mass flow rate within a tolerance of ±10% and showed potential towards the development of the cryogenic two-phase flow meter. 相似文献
6.
Measuring fluid flow rate passing through pipelines is a basic strategy for developing the infrastructure of fluid-dependent industries. It is a challenging issue for trade, transportation, and reservoir management purposes. Predicting the flow rate of fluid is also regarded as one of the crucial steps for the development of oil fields. In this study, a novel deep machine learning model, convolutional neural network (CNN), was developed to predict oil flow rate through orifice plate (Qo) from seven input variables, including fluid temperature (Tf), upstream pressure (Pu), root differential pressure (√ΔP), percentage of base sediment and water (BS&W%), oil specific gravity (SG), kinematic viscosity (ν), and beta ratio (β, the ratio of pipe diameter to orifice diameter). Due to the absence of accurate and credible methods for determining Qo, deep learning can be a useful alternative to traditional machine learning methods. Justifying the promising performance of the developed CNN model over conventional machine learning models, three different machine learning algorithms, including radial basis function (RBF), least absolute shrinkage and selection operator (LASSO), and support vector machine (SVM), were also developed and their prediction performance was compared with that of the CNN model. A sensitivity analysis was also performed on the influence degree of each input variable on the output variable (Qo). The study outcomes indicate that the CNN model provided the highest Qo prediction accuracy among all the four models developed by presenting a root mean squared error (RMSE) of 0.0341 m3/s and a coefficient of determination (R2) of 0.9999, when applied to the dataset of 3303 data records compiled from oil fields around Iran. The Spearman correlation coefficient analysis results display that √ΔP, Pu, and Tf were the most influential variables on the oil flow rate in respect of the large dataset evaluated. 相似文献
7.
Wet gas metering is becoming an increasingly important problem to the Oil and Gas Industry. The Venturi meter is a favoured device for the metering of the unprocessed wet natural gas production flows. Wet gas is defined here as a two-phase flow with up to 50% of the mass flowing being in the liquid phase. Metering the gas flowrate in a wet gas flow with use of a Venturi meter requires a correction of the meter reading to account for the liquids effect. Currently, most correlations in existence were created for Orifice Plate Meters and are for general two-phase flow. However, due to no Venturi meter correlation being published before 1997 industry was traditionally forced to use these Orifice Plate Meter correlations when faced with a Venturi metering wet gas flows. This paper lists seven correlations, two recent wet gas Venturi correlations and five older Orifice Plate general two-phase flow correlations and compares their performance with new independent data from the NEL Wet Gas Loop with an ISA Controls Ltd. Standard specification six inch Venturi meter of 0.55 beta ratio installed. Finally, a new correlation is offered. 相似文献
8.
Cavitating venturis (CVs) are simple devices which can be used in different industrial applications to passively control the flow rate of fluids. In this research the operation of small-sized CVs is characterized and their capabilities in regulating the mass flow rate were experimentally and numerically investigated. The effect of upstream and downstream pressures, as well as geometrical parameters such as the throat diameter, throat length, and diffuser angle on the mass flow rate and critical pressure ratio were studied. For experimental data acquisition, three CVs with throat diameters of 0.7, 1 and 1.5 mm were manufactured and tested. The fabricated CVs were tested at different upstream and downstream pressures in order to measure their output mass flow rate and to obtain their characteristic curves. The flow inside the CVs was also simulated by computational fluid dynamics. The numerical results showed agreement with the experimental data by a maximum deviation of 5–10% and confirmed that the numerical approach can be used to predict the critical pressure ratio and mass flow rate at cavitaing condition. It is found that despite the small size of venturis, they are capable of controlling the mass flow rate and exhibit the normal characteristics. By decreasing the throat diameter, their cavitating mode became more limited. Results also show that increasing the diffuser angle and throat length leads to a decrease in critical pressure ratio. 相似文献
10.
Up until now, different methods, including; flow pressure signal, ultrasonic, gamma-ray and combination of them with the neural network approach have been proposed for multiphase flow measurement. More sophisticated techniques such as ultrasonic waves and electricity, as well as high-cost procedures such as gamma waves gradually, can be replaced by simple methods. In this research, only flow parameters such as temperature, viscosity, pressure signals, standard deviation and coefficients of kurtosis and skewness are used as inputs of an artificial neural network to determine the three phase flow rates. The model is validated by the field data which were obtained from separators of two oil fields and 6 wells over ten-month with 8 h interval (totally 5400 sets of data). A linear relation can be observed between the actual data and the predictions which were obtained from separators and neural network approach, respectively. Furthermore, it is shown that using feed forward neural network with Levenberg–Marquardt algorithm which has two hidden layers is sufficient to determine the flow rates. Also, it is tried to see the effect of flow regimes on the results of neural network approach by determining kurtosis and skewness coefficients for different flow regimes in a horizontal pipeline. 相似文献
11.
12.
整体式翅片管换热器的精度自校正模型 总被引：1，自引：0，他引：1
为提高换热器性能的计算精度和速度,建立了整体式翅片管式换热器的精度自校正模型。该模型中带了两个神经网络,一个用于补偿简化模型与分布参数模型的差异,另一个则用于自适应地学习试验结果,提高模型的精度。用该模型计算整体式翅片管冷凝器和蒸发器性能,并与试验结果相对照。对于冷凝器,换热量误差的平均值和最大值分别为0.63％和1.72％,过冷度误差的平均值和最大值则为0.9℃和3.2℃。对于蒸发器,换热量误差的平均值和最大值分别为1.56％和11.0％,过热度误差的平均值和最大值则为1.5℃和9.8℃。对于冷凝器和蒸发器,计算速度较分布参数模型均提高两个数量级。 相似文献
13.
In multiphase flow measurement, one of the most challenging issues is to define an adequate technology for a specific scenario, taking into account the measurement accuracy, implementation feasibility and costs. The electromagnetic technology based on resonant cavities is often employed in water-cut meters to measure two-phase flows such as water/oil and water/gas mixtures. The main disadvantage of this technology is the electromagnetic signal attenuation that occurs as the water content decreases. This undesirable behavior is amplified due to the impedance mismatch between the sensor ports and the transmitter/receiver modules. This paper presents a study to implement an impedance matching network in order to improve the instrument performance. Impedance matching networks were built, taking into account the matching for a 100%, 50% and, also, for the worst case of 0% of water fraction where there is a significant signal attenuation. The implemented networks improved the signal amplitude ratio between the first resonant mode and the other modes, increasing the identification accuracy of the first resonance peak. 相似文献
14.
Shankar Chakraborty Arit Basu 《The International Journal of Advanced Manufacturing Technology》2006,27(7-8):781-787
The integration of design and manufacturing has been the subject of much debate and discussion over a long period of time.
Recognition of feature patterns and the retrieval of necessary machining information from those patterns play vital roles
in this process of integration, as they facilitate the selection of the necessary manufacturing parameters required to transform
the designed product into a final physical entity. Although the problem of recognising features from a solid model has been
exclusively studied, most existing product models are expressed as engineering drawings. Moreover, the solid model can only
provide complete 3D topological and geometrical data and some of the essential machining information cannot be retrieved.
In this paper, an approach for defining engineering features, like slots, steps and circular pockets is proposed using binary
strings. Two artificial neural networks, one for slots and steps and the other for circular pockets, are designed and developed.
These neural networks take the binary strings as inputs and give the relevant machining information as outputs. The networks
are trained with non-interacting features and after training, those will become capable of providing the necessary machining
information for both non-interacting and interacting features in the domains of slots, steps and circular pockets. This novel
approach can further be extended to other features for retrieving relevant machining information and thus facilitating the
effective integration of design and manufacturing. 相似文献
15.
Environmental studies on fish require measurements of highly turbulent flows in both the laboratory and in the field. A fish-shaped bioinspired flow measuring device is applied in conjunction with data processing workflow which leverages the interactions between the body and the surrounding flow field for velocity estimation in turbulent flows. Our objective is to develop a robust velocity estimation methodology relevant for studies of fish behavior using a bioinspired fish-shaped artificial lateral line probe (LLP). We show that the device is capable of covering the range of flow velocities from 0 to 1.5 m/s. Three different sets of experiments performed in a closed flow tunnel, a model vertical slot fishway and laboratory open channel flume were collected and combined to provide time-averaged flow velocity and LLP measurements under fully turbulent flow conditions. Based on the experimental results, a signal processing workflow using Pearson product-moment correlation coefficient (PCC) features in conjunction with an artificial neural network (ANN) is presented. Using PCC features provides a simple data fusion methodology exploiting the use of the LLP's as a simultaneous collocated sensing array. In this work we show that (1) the PCC-ANN workflow provides the first LLP velocity estimator without repeated calibration across the full span of 0–1.5 m/s, (2) using all pressure sensors results in the best performance with R2=0.917, but requires a PCC feature matrix of 55 dimensions and (3) a stepwise reduction of the PCC feature matrix allows for the use of as few as 11 dimensions, and results in R2=0.911, indicating that a modest reduction in LLP velocity estimation performance can be gained by a large reduction in dimensionality. A surprising finding was that after stepwise reduction, the best performing sensor pair combinations were not the expected pitot-like anteroposterior couples spanning from nose to body. Instead, it was found that optimal velocity estimation using the LLP exploited a network of sensor pairs. It is shown that the LLP can be implemented similar to an ADV for highly turbulent flows over the range of 0–1.5 m/s, and in addition provides body-centric pressure distributions which may aid in the interpretation of fish hydrodynamic preferences in future environmental studies. 相似文献
16.
This main aim of this study is to generate an intensive artificial neural network model (ANN) based on FORTRAN language to develop a physical equation for oil rate prediction in wells lifted by ESP pumps. The backpropagation algorithm (BP) is selected in this study as a learning algorithm with its sigmoid curve based on the comparison performed against scaled conjugate gradient (SCG) and one-step secant (OSS) algorithms.300 data points are collected from 2 fields in Gulf of Suez Egypt used in the ANN model. The results show that the optimum distribution for the collected data is of 70% and 30% for training and testing processes, respectively. This distribution yields the highest R2 of 0.988 and lowest mean square error of 0.025. Furthermore, based on the statistical analysis presented in this study, it has been found that the optimum number of hidden layers and neuron are one layer and two neuros, respectively.The newly ANN and correlation can predict the oil rate at the surface with accuracy exceeding 96% and that is extremely efficient. A comparison is conducted between the presented correlation in this study and other published correlations (Gilbert and Ros correlations) based on R2 value and mean square error. The results show that the new correlation has the highest R2 value with the lowest mean square error. 相似文献
17.
Taking the Huaidian Sluice on the Shaying River in China as an example, this paper establishes the calculation model of the free flow based on artificial neural network and regression analysis. Four forms of discharge coefficient calculation equations were obtained by regression analysis, and three neural network models were established. The model is fully verified by using the measured data. The experimental results show that the third-order polynomial and multilayer perceptron neural network have better adaptability. The advantages and disadvantages of the different methods are analyzed and the cause of the error is identified. It provides a theoretical basis for dealing with the discharge calculation of small and medium dam. 相似文献
18.
The purpose of the present study was to investigate the performance and flow structure of an airlift pump-bubble generator during the lifting of gas-water-solid particles three-phase flow experimentally. Here, a mechanistic model was also developed to predict the performance of an airlift pump bubble-generator on the basis of power balance. In the experimental part, the flow structure was analyzed visually, and taken from the extraction of the differential pressure signal at both the bottom and top test sections. Time series of differential pressure normalization was analyzed by using wavelet transform to determine the wavelet energy distribution. The wavelet energy was used as input the artificial neural network method to clustering the flow regime.The results indicate that under a constant of superficial gas velocity, the discharged both the water and particle increase with the submergence ratio (SR). SR is defined as the ratio of the distance from the injector to the water surface and the distance from the injector to the outlet side. Next, under a constant gas superficial velocity, the increase of SR will increase the solid fraction, but the fractions of both gas and water will decrease. The flow patterns were classified in the clustered bubble, homogeneous bubble, cap bubble, bubbly-stable slug, bubble unstable slug, and slug churn. Furthermore, the bubble flow is indicated by the peak wavelet energy on an eighth-level decomposition of approximation signal (a8), and the energy of the fourth-level decomposition of detail signal (d4) closes to the energy of the fifth-level decomposition (d5). The wavelet energy concentrated on the seventh and/or eighth level decomposition of detail signal (d7 and/or d8) is the indicator of slug flow in the riser pipe. The clustering flow patterns by using the ANN with input from wavelet energy gives a better approach than that of stochastic parameters of time series of the pressure differential. Moreover, the developed mechanistic model shows a good agreement with the experimental data. 相似文献
19.
GMAW焊接过程监测Kohonen神经网络系统 总被引：11，自引：3，他引：8
实时测量熔化极气体保护焊（ＧＭＡＷ）焊接过程中的电参数,研制自组织特征映射神经网络（Ｋｏｈｏｎｅｎ神经网络）,直接依据不同焊接工艺条件下焊接电压的概率密度分布曲线（ＰＤＤ）以及短路过渡时间的频数分布曲线（ＣＦＤ）,自动识别出焊接过程中的各种干扰信号。 相似文献