Estimation of Pressure Drop of Two-Phase Flow in Horizontal Long Pipes Using Artificial Neural Networks

Abstract Gas–liquid two-phase flows through long pipelines are one of the most common cases found in chemical, oil, and gas industries. In contrast to the gas/Newtonian liquid systems, the pressure drop has rarely been investigated for two-phase gas/non-Newtonian liquid systems in pipe flows. In this regard, an artificial neural networks (ANNs) model is presented by employing a large number of experimental data to predict the pressure drop for a wide range of operating conditions, pipe diameters, and fluid characteristics. Utilizing a multiple-layer perceptron neural network (MLPNN) model, the predicted pressure drop is in a good agreement with the experimental results. In most cases, the deviation of the predicted pressure drop from the experimental data does not exceed 5%. It is observed that the MLPNN provides more accurate results for horizontal pipelines in comparison with other empirical correlations that are commonly used in industrial applications.

Download Full-text

Prediction of NOx Emissions for a Range of Engine Hardware Configurations Using Artificial Neural Networks

ASME 2020 Internal Combustion Engine Division Fall Technical Conference ◽

10.1115/icef2020-2911 ◽

2020 ◽

Author(s):

Nick Papaioannou ◽

XiaoHang Fang ◽

Felix Leach ◽

Martin H. Davy

Keyword(s):

Experimental Data ◽

Neural Networks ◽

Artificial Neural Networks ◽

Operating Conditions ◽

Data Accuracy ◽

Nox Emissions ◽

Ann Model ◽

Baseline Training ◽

Wide Range ◽

Artificial Neural

Abstract The predictive ability of artificial neural networks where a large number of experimental data are available, has been studied extensively. Studies have shown that ANN models are capable of accurately predicting NOx emissions from engines under various operating conditions and different fuel types when trained well. One of the major advantages of an ANN model is its ability to relearn when new experimental data is available, thus continuously improving its accuracy. The present work explored the potential of an ANN model to predict NOx emissions for various engine configurations outside its training envelop. This work also looked into quantifying the amount of new data required to improve the accuracy of the model when exposed to unknown conditions. The chosen ANN model was constructed using data from a high-speed direct injection diesel engine and is capable of accurate NOx emissions over a wide range of operating conditions. The optimized network utilized 14 input parameters and is using 6 neurons in a single hidden layer feed-forward neural network. Experimental data from the various engine configurations tested, were then used to predict NOx from the existing ANN model. The results indicate that when the new data are within the baseline training envelop, the ANN model is capable of accurate NOx prediction even when there are substantial changes in engine configuration such as piston material. Similar results were also observed when the injector nozzle is changed. However, the model’s performance drops significantly when new data, outside the baseline training envelop, were employed indicating that additional training is required. As such, various methods for retraining the ANN model were explored with the selected method showing the best compromise between new-data accuracy and old-data accuracy retention. The retrained ANN model developed was found to be an effective tool in predicting NOx emissions for different engine configurations and operating conditions.

Download Full-text

Prediction of Pressure Drop of Various Refrigerants During Condensation in Horizontal Smooth and Micro-Fin Tubes by Means of Artificial Neural Networks

Volume 7: Fluids and Heat Transfer, Parts A, B, C, and D ◽

10.1115/imece2012-85039 ◽

2012 ◽

Author(s):

Muhammet Balcilar ◽

Ahmet Selim Dalkiliç ◽

Şevket Özgür Atayılmaz ◽

Hakan Demir ◽

Somchai Wongwises

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Pressure Drop ◽

Tube Length ◽

Two Phase ◽

Pressure Drops ◽

Data Points ◽

Artificial Neural ◽

Fin Tubes ◽

Liquid And Vapor Phases

The predictions of condensation pressure drops of R12, R22, R32, R125, R410A, R134a, R22, R502 and R507a flowing inside various horizontal smooth and micro-fin tubes are made using the numerical techniques of Artificial Neural Networks (ANNs) and non-linear least squares (NLS). The National Institute of Standards and Technology’s (NIST) experimental data and, Eckels’ and Pate’s experimental data, as presented in Choi et al.’s study provided by NIST, are used in our analyses. In their experimental setups, the horizontal test sections have 1.587 m, 3.78 m, 3.81 m and 3.97 m long countercurrent flow double tube heat exchangers with refrigerant flowing in the inner smooth (8 mm, 8.01 mm and 11.1 mm i.d.) and micro-fin (5.45 mm and 7.43 mm i.d.) copper tubes as cooling water flows in the annulus. Their test runs cover a wide range of saturation pressures from 0.9 MPa to 2.9 MPa, inlet vapor qualities range from 0.19 to 1.0 and mass fluxes are from 8 kg m−2s−1 to 791 kg m−2s−1. The condensation pressure drops are predicted using 673 measured data points, together with numerical analyses of artificial neural networks and non-linear least squares. The input of the ANNs for the best correlation are the measured and the values of the test sections are calculated, such as mass flux, tube length, inlet and outlet vapor qualities, critical pressure, latent heat of condensation, mass fraction of liquid and vapor phases, dynamic viscosities of liquid and vapor phases, hydraulic diameter, two-phase density, and the outputs of the ANNs as the experimental total pressure drops in the condensation data from independent laboratories. The total pressure drops of in-tube condensation tests are modeled using the artificial neural networks (ANNs) method of multi-layer perceptron (MLP) with a 12-40-1 architecture. The average error rate is 7.085%, considering the cross validation tests of the 867 condensation data points. A detailed model of f(MLP) is given for direct use in MATLAB. This explanation will enable users to predict the two-phase pressure drop with high accuracy. As a result of the dependency analyses, dependency of the output of the ANNs from 12 sets of input values is shown in detail, and the pressure drops of condensation in smooth and micro-fin tubes are found to be highly dependent on mass flux, all liquid Reynolds numbers, the latent heat of condensation, outlet vapor quality, critical pressure of the refrigerant, liquid dynamic viscosity, and tube length. New ANNs based empirical pressure drop correlations are developed separately for the conditions of condensation in smooth and micro-fin tubes as a result of the analyses.

Download Full-text

Estimation of pressure drop in venturi scrubbers based on annular two-phase flow model, artificial neural networks and genetic algorithm

Chemical Engineering Journal ◽

10.1016/j.cej.2008.12.011 ◽

2009 ◽

Vol 150 (1) ◽

pp. 131-138 ◽

Cited By ~ 16

Author(s):

S. Nasseh ◽

A. Mohebbi ◽

A. Sarrafi ◽

M. Taheri

Keyword(s):

Genetic Algorithm ◽

Neural Networks ◽

Artificial Neural Networks ◽

Pressure Drop ◽

Flow Model ◽

Two Phase Flow ◽

Phase Flow ◽

Two Phase ◽

Artificial Neural

Download Full-text

Identifying nonclassicality from experimental data using artificial neural networks

Physical Review Research ◽

10.1103/physrevresearch.3.023229 ◽

2021 ◽

Vol 3 (2) ◽

Author(s):

Valentin Gebhart ◽

Martin Bohmann ◽

Karsten Weiher ◽

Nicola Biagi ◽

Alessandro Zavatta ◽

...

Keyword(s):

Experimental Data ◽

Neural Networks ◽

Artificial Neural Networks ◽

Artificial Neural

Download Full-text

Improved Effort and Cost Estimation Model Using Artificial Neural Networks and Taguchi Method with Different Activation Functions

Entropy ◽

10.3390/e23070854 ◽

2021 ◽

Vol 23 (7) ◽

pp. 854

Author(s):

Nevena Rankovic ◽

Dragica Rankovic ◽

Mirjana Ivanovic ◽

Ljubomir Lazic

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Cost Estimation ◽

Time Estimation ◽

Effort Estimation ◽

Activation Functions ◽

Estimation Model ◽

Wide Range ◽

Software Product ◽

Artificial Neural

Software estimation involves meeting a huge number of different requirements, such as resource allocation, cost estimation, effort estimation, time estimation, and the changing demands of software product customers. Numerous estimation models try to solve these problems. In our experiment, a clustering method of input values to mitigate the heterogeneous nature of selected projects was used. Additionally, homogeneity of the data was achieved with the fuzzification method, and we proposed two different activation functions inside a hidden layer, during the construction of artificial neural networks (ANNs). In this research, we present an experiment that uses two different architectures of ANNs, based on Taguchi’s orthogonal vector plans, to satisfy the set conditions, with additional methods and criteria for validation of the proposed model, in this approach. The aim of this paper is the comparative analysis of the obtained results of mean magnitude relative error (MMRE) values. At the same time, our goal is also to find a relatively simple architecture that minimizes the error value while covering a wide range of different software projects. For this purpose, six different datasets are divided into four chosen clusters. The obtained results show that the estimation of diverse projects by dividing them into clusters can contribute to an efficient, reliable, and accurate software product assessment. The contribution of this paper is in the discovered solution that enables the execution of a small number of iterations, which reduces the execution time and achieves the minimum error.

Download Full-text

Performance Estimation of Direct Methanol Fuel Cell Using Artificial Neural Network

Volume 6B: Energy ◽

10.1115/imece2015-51723 ◽

2015 ◽

Cited By ~ 1

Author(s):

M. A. Rafe Biswas ◽

Melvin D. Robinson

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Networks ◽

Fuel Cell ◽

Direct Methanol Fuel Cell ◽

Cell Voltage ◽

Operating Conditions ◽

Direct Methanol ◽

Artificial Neural ◽

Methanol Fuel Cell

A direct methanol fuel cell can convert chemical energy in the form of a liquid fuel into electrical energy to power devices, while simultaneously operating at low temperatures and producing virtually no greenhouse gases. Since the direct methanol fuel cell performance characteristics are inherently nonlinear and complex, it can be postulated that artificial neural networks represent a marked improvement in performance prediction capabilities. Artificial neural networks have long been used as a tool in predictive modeling. In this work, an artificial neural network is employed to predict the performance of a direct methanol fuel cell under various operating conditions. This work on the experimental analysis of a uniquely designed fuel cell and the computational modeling of a unique algorithm has not been found in prior literature outside of the authors and their affiliations. The fuel cell input variables for the performance analysis consist not only of the methanol concentration, fuel cell temperature, and current density, but also the number of cells and anode flow rate. The addition of the two typically unconventional variables allows for a more distinctive model when compared to prior neural network models. The key performance indicator of our neural network model is the cell voltage, which is an average voltage across the stack and ranges from 0 to 0:8V. Experimental studies were carried out using DMFC stacks custom-fabricated, with a membrane electrode assembly consisting of an additional unique liquid barrier layer to minimize water loss through the cathode side to the atmosphere. To determine the best fit of the model to the experimental cell voltage data, the model is trained using two different second order training algorithms: OWO-Newton and Levenberg-Marquardt (LM). The OWO-Newton algorithm has a topology that is slightly different from the topology of the LM algorithm by the employment of bypass weights. It can be concluded that the application of artificial neural networks can rapidly construct a predictive model of the cell voltage for a wide range of operating conditions with an accuracy of 10−3 to 10−4. The results were comparable with existing literature. The added dimensionality of the number of cells provided insight into scalability where the coefficient of the determination of the results for the two multi-cell stacks using LM algorithm were up to 0:9998. The model was also evaluated with empirical data of a single-cell stack.

Download Full-text