Prediction Of Pressure Drop Research Articles

Modelling and optimization study to improve the filtration performance of fibrous filter

Fibrous filter made up of non-woven material was utilized in many industrial applications for increasing the collection efficiency and the quality factor. But there exists a competing effect among the fibre diameter, filtration efficiency, pressure drop, and sometime type of aerosol (liquid or solid) plays a crucial role in the performance of the fibrous filter. To avoid overdesigning of the filter along with better performance, optimum set of parameters are to be decided before the manufacturing process. In the current effort, the desirability approach and along with the “Response Surface Methodology (RSM)” were considered to optimize filtration efficiency and pressure drop simultaneously. In this perspective, the impact of Filtration velocity (v), Basis weight (φ), Particle diameter (dp), and Packing fraction (α) on filtration efficiency (η) and pressure drop (Pd) was studied. Based on the outcome, the predicted values lie within experimental data through smart agreement. The maximum percentage (%) error was only 3% and 6% filtration efficiency (η) and pressure drop (Pd), which determine the effectiveness of this useful model. The most dominant factor which affects the filtration efficiency (η) was found to be the Basis weight (φ), followed by packing fraction. However, in the case of pressure drop, the most dominant factors were filtration speed followed by the pachining fraction. Moreover, artificial neural network (ANN) models are developed for the prediction of filtration efficiency and pressure drop. The model accuracy has been estimated by calculating “Mean Square Error (MSE), Mean Absolute Error (MAE), and coefficient of determination (R2)”. Both models show promising results when compared with experimental data with the R2 value of 98.50–99.86. The optimized values of the maximum filtration efficiency and minimum pressure drop simultaneously were obtained for v = 5, φ = 59.60, dp = 52.23, α = 0.24 according to desirability approach.

A hybrid CFD – Deep learning methodology for improving the accuracy of pressure drop prediction in cyclone separators

Cyclone separators are widely used in many industries to separate solid particles from the fluid flow. As same as separation efficiency, pressure drop is considered as a primary parameter to evaluate performance of cyclone separators. Computational Fluid Dynamics (CFD) is a powerful method to predict the pressure drop of cyclone separators. However, it is indisputable that CFD technique is mathematically complicated and computationally expensive. This study has proposed a more accurate, computationally efficient hybrid method to predict cyclone pressure drop by merging CFD and Deep Learning algorithms. Its generalization has been validated by k-fold cross validation. The proposed hybrid method has also been proved to be more superior than the DNN regression method. The results verify that the proposed method not only predicts cyclone pressure drop accurately (with a maximum error less than 5% in comparison with experimental data), but also requires less computational time than traditional CFD. In other words, it leverages the potential of novel approaches to decrease CFD computational cost while increasing the accuracy level.

An improved pressure drop correlation for modeling localized effects in a pebble bed reactor

Advances in the development of pebble bed reactors (PBRs) has created a desire for accurate and cost-effective simulation tools for design scoping studies and safety analysis. The current state-of-the-art for these simulations is the use of porous media models, although these models rely on correlations to capture the effects of flow features that are not explicitly modeled. One of the areas where correlation accuracy is currently lacking is in the near-wall region of the bed. In this region, the presence of the wall causes the pebbles to pack more orderly, drastically changing the geometry and flow behavior in this region.This work presents a new generalized pressure drop correlation for PBRs based on the KTA equation. A high-to-low methodology is applied, where large eddy simulation (LES) is performed on two beds of 1568 and 1700 pebbles to generate a high-fidelity dataset. The flow fields are then averaged in time and separated into concentric rings of 0.05 Dpeb width. Average porosity, velocity, and pressure drop are extracted for each ring and the friction and form losses are calculated. The Reynolds number range for this study is 625–10,000, and thus the form losses are dominant over the friction losses. The form losses across the rings are investigated, and a correction term for the form loss calculation is determined and applied to the KTA equation to drastically improve the capability of modeling localized porosity effects in a porous media code. The improved correlation reduces near-wall velocity prediction error from over 50% with the KTA correlation to around 5%. Agreement in pressure drop prediction between LES and porous media simulations is also improved.

Experimental Investigation on Effects of Flow Orientation on Interfacial Structure of Air–Water Two-Phase Flow

This study focusses on investigating the effect of flow orientation on global and local two-phase flow parameters under two-phase flow conditions. Flow visualization, pressure measurement, and conductivity probe measurements are performed in a test facility made of 50.8 mm inner diameter acrylic pipes with flow visualization, pressure measurement, and conductivity probe measurement. Characteristics of flow regimes and interfacial structures, and frictional pressure drop prediction in the vertical upward and vertical downward two-phase flows are compared and analyzed. The results show that unique coring phenomenon and slug bubbles with off-centered noses appear in the vertical downward flow. The flow regime transition boundaries shift to the lower gas superficial velocities in the vertical downward flow compared to that in the vertical upward flow. Furthermore, the distribution and one-dimensional transport of the void fraction, interfacial area concentration, bubble velocity, bubble Sauter-mean diameter, and bubble frequency are acquired and compared to study the effect of flow orientation on interfacial structures. The interfacial structure and its development are found to be mainly affected by the lift force and the turbulence related bubble interactions. The frictional pressure drop is acquired and modeled by the Lockhart–Martinelli correlation. The frictional pressure drop is found to be larger in the vertical upward flow than that in the vertical downward flow. The recommended C value for both vertical upward and vertical downward flows are proposed.

Predicting pressure-drop for pseudo-homogeneous slurry flows using the mixture model at high solids concentrations

The main contribution of this paper is applying computational fluid dynamics (CFD) using the two-phase mixture model with algebraic slip, and turbulent dispersion to the slurry flow experiment of Kaushal et al. (2012). The results obtained were compared to the experimental results and numerical results reported by the same authors who used the mixture model as well as a more advanced Eulerian granular flow model. The authors reported that the mixture model predicted the pressure drops with very high errors, especially for the highest solids loading simulated with errors as high as 400% compared to their experimental data. They conclude that the mixture model cannot be used to predict the pressure drop of the slurry flow investigated at higher concentrations (30-50% solid fraction). In contrast to this, the pressure-drop predictions of the two-phase mixture model with algebraic slip and turbulent dispersion used in this study were in good agreement with the measured values. This calls the conclusion of Kaushal et al. (2012). to question, because they did not present any justification for 3-4 times higher pressure drop observed in their study using the mixture model in combination with the fact that no anomalies in particle concentration profiles were observed by them for the mixture model. A comparison between the two mixture models reveals that although they differ in some details, the basic structure of the models is the same. We conclude that the mixture model with algebraic slip, turbulent dispersion, and a suspension viscosity model can be used for pressure drop predictions for the slurry flow investigated even for high solids fraction. We also demonstrate that the laterally averaged solids concentration profiles are not predicted very accurately by the mixture model as well as the more complex granular model. The concentration profiles predicted by the mixture model is easily understood in contrast to the profiles predicted by the granular flow model. From an engineering viewpoint, preference should be given to a simpler model, as was used in this study which can predict pressure drop with similar accuracy compared to a more complex approach with a larger number of uncertainty parameters. Further research is necessary to correctly predict the solids concentration profile for slurry flow in pipelines.

Experimental analysis of high temperature flow boiling of zeotropic mixture R134a/R245fa in a plate heat exchanger

The potential to improve the performance of organic Rankine cycle systems by using zeotropic mixtures as working fluids has been demonstrated in the open literature. However, there are very few research works in the open literature studying the mixture flow boiling in plate heat exchangers, and none of the existing works address high temperature boiling, which is the prevailing working condition in the evaporator of organic Rankine cycle systems. This paper presents an experimental study of high temperature flow boiling of zeotropic mixtures of R134a/R245fa in a plate heat exchanger. Five compositions were tested at the reduced pressures 0.45, 0.55 and 0.65 and various heat fluxes and mass fluxes. In addition, the predictive performance of several existing prediction methods for the heat transfer coefficient and pressure drop were evaluated, and based on the results, new heat transfer and pressure drop prediction methods were developed. The experimental results suggest that the heat transfer is dominated by the nucleate boiling. The mixture having a 0.427/0.573 mass composition presents the largest heat transfer degradation, up to 42 %, compared with the pure fluids. As far as the pressure drop is concerned, the results suggest that the zeotropic mixtures have the same pressure drop characteristics as the pure fluids, and the five mixtures have almost the same frictional pressure drop due to their similar thermo-physical properties. Existing methods provide a good prediction of the heat transfer data. The new heat transfer correlations enable an even better predictive performance than those available in the literature, however, it remains to evaluate the predictive performance of the new correlation for other working fluids, plate heat exchanger geometries and working conditions than those considered in the paper.

Frictional Pressure Drop for Gas–Liquid Two-Phase Flow in Coiled Tubing

Coiled tubing (CT) is widely used in drilling, workover, completion, fracturing and stimulation in the field of oil and gas exploration and development. During CT operation, the tubing will present a gas–liquid two-phase flow state. The prediction of frictional pressure drop for fluid in the tube is an important part of hydraulic design, and its accuracy directly affects the success of the CT technique. In this study, we analyzed the effects of the gas void fraction, curvature ratio and fluid inlet velocity on frictional pressure drop in CT, numerically. Experimental data verified simulated results. Flow friction sensitivity analysis shows the frictional pressure drop reaches its peak at a gas void fraction of 0.8. The frictional pressure gradient increases with the increase in curvature ratio. As the strength of secondary flow increases with the increase in inlet velocity, the increased trend of gas–liquid two-phase flow friction is aggravated. The correlation of friction factor for gas–liquid two-phase flow in coiled tubing is developed by regression analysis of simulation results. The research results can support high quality CT hydraulics design, through which the success of CT operations can be guaranteed.

Influence of pleated geometry on the pressure drop of filters during dust loading process: experimental and modelling study

In this study, a pressure drop model was developed through numerical simulation and experimentation for optimizing the design of the pleated structure of the filter media to extend the service life of the filter and reduce the ventilation energy consumption. The effect of the Stokes number on the dust deposition on the pleated filter media was revealed through numerical simulation. On this basis, a pressure drop model during dust loading was developed. The model suggests that under the same mass of dust deposition per unit area (W), the greater the pleat ratio (α), the greater the dust cake thickness and the effective filtration velocity in the effective filtration area. In addition, for V-shaped and U-shaped filters, the relative mean deviations between experimental and modeling total pressure drops are 3.68% and 4.82%, respectively. In other words, the proposed model accurately predicts pressure drop during dust loading. Furthermore, under the same α and W, the total pressure drop of the U-shaped filter is lower than that of the V-shaped filter, demonstrating the superior filtration performance of the U-shaped filter.

Numerical Investigation of Flow Characteristics for Gas–Liquid Two–Phase Flow in Coiled Tubing

Coiled tubing (CT) is widely used for horizontal well fracturing, squeeze cementing, and sand and solid washing in the oil and gas industry. During CT operation, a gas–liquid two-phase flow state appears in the tubing. Due to the secondary flow, this state produces a more extensive flow-friction pressure loss, which limits its application. It is crucial to understand the gas–liquid flow behavior in a spiral tube for frictional pressure drop predictions in the CT technique. In this study, we numerically investigated the velocity distribution and phase distribution of a gas–liquid flow in CT. A comparison of experimental data and simulated results show that the maximum average error is 2.14%, verifying the accuracy of the numerical model. The gas and liquid velocities decrease first and then rise along the axial direction due to the effect of gravity. Due to the difference in the gas and liquid viscosity, i.e., the flow resistance of the gas and liquid is different, the gas–liquid slip velocity ratio is always greater than 1. The liquid velocity exhibits a D-shaped step distribution at different cross-sections of spiral tubing. The secondary-flow intensity, caused by radial velocity, increases along the tubing. Due to the secondary-flow effect, the zone of the maximum cross-section velocity is off-center and closer to the outside of the tube. However, under the combined action of centrifugal force and the density difference between gas and liquid, the variation in the gas void fraction along the tubing is relatively stable. These research results are helpful in understanding the complex flow behavior of gas–liquid two-phase flow in CT.

Developing an adaptive catalyst for an FCC reactor using a CFD RSM, CFD DPM, and CFD DDPM–EM approach

Cyclone separators, which have an important role in the recovery of catalysts, constituted one of the aims of the study. In the work to be done, the pressure drop occurring during the fcc reaction is also calculated using the Ergun equation and it is aimed to provide the same value in a cyclone separator. In this study, which was presented for the first time in the literature, the best working conditions were determined by simulating the pressure drop in the cyclone separator modeled by using the various catalyst types namely NiMo/ASA–Al2O3, NiMo/p–Al2O3, NiMo/Y–Al2O3, Co-Mo, HZSM-5 zeolite, HY zeolite, pAl2O3, ASA-Al2O3, Y-Al2O3 determined from the literature in the Ergun equation. Among them, NiMo/ASA Al2O3, Co-Mo, HY zeolite, and ASA-Al2O3 were determined as the best catalyst for producing diesel from high oil fractions. Unlike previous studies, the condition that the cyclone separator modeled cleans the catalyst with maximum efficiency also determines the condition that provides low catalyst porosity in the determination of the catalyst type to be determined in diesel production. Due to the accuracy between the calculated and the predicted pressure drop results (about 1,8%), HY zeolite is the best catalyst for cyclone separator geometry. It is widely used to convert high molecular weight hydrocarbon fractions, the high boiling point of petroleum crude oils into olefinic gases, more valuable gasoline, and other products. The purpose of the FCC unit is to increase the refinery conversion and white product yield by converting heavy vacuum gas oil (HVGO) into light hydrocarbons at high temperatures with the aid of fluid catalysis. These two zones (reactor and regenerator) are placed as two different pressure vessels. For these two different systems to work in harmony with each other, unlike in previous studies, the “dense discreet phase-Eularian” approach was used in the modeling of the catalytic unit and the “discreet phase” approach was used in the modeling of the cyclone separator. The values required for both processes to work together have been determined approximately.

Two-layer hydrodynamic network model for redox flow battery stack with flow field design

A two-layer hydrodynamic network model is proposed to analyze the electrolyte distribution within a redox flow battery (RFB). The proposed model consists of a channel, a porous electrode, and an interconnection part through which the electrolyte flows through the channel and porous electrode. The flow rate and pressure drop of each network component are calculated using the Hardy-Cross method. The predicted pressure drop is consistent with experimental and three-dimensional computational fluid dynamics (CFD) results. The velocity and pressure distributions are also in good agreement with CFD results. Furthermore, the proposed model analyzes the flow distribution of cells in RFB stacks with different flow field designs. The results show that the flow rate difference between the first and last cells of the RFB stack with an interdigitated flow field is 20 times higher than that of a flow-through-type.

Numerical Simulation of Critical Production Pressure Drop of Injection and Production Wells in Gas Storage Based on Gas-Solid Coupling

The periodic injection-production process of natural gas in underground gas storage make the rock bear alternating load under the gas-solid coupling. The alternating load changes the physical properties of rock, and then influence the critical production pressure drop of injection-production wells in gas storage. In the case of gas-solid coupling, the decisive factors affecting the alternating load are the number of injection-production cycles and the injection-production differential pressure. Therefore, a discrete element numerical simulation model is established to simulate the gas-solid coupling process of gas storage wells under different injection-production cycle and differential pressure. The influence mechanism of injection-production cycle and differential pressure on particle cementation and primary crack is analyzed microscopically and also the influence law of injection-production cycle and differential pressure on rock mechanical properties is analyzed from the macroscopic. Finally, the influence law of injection-production cycle and differential pressure on the critical production pressure drop of injection-production wells due to gas-solid coupling can be obtained. The results show that under the influence of gas-solid coupling, the number of bonded contact cracks and micro cracks in the model increase gradually, both the elastic modulus ratio and the cohesion ratio decrease gradually with the increase of injection-production cycle and the higher the injection-production differential pressure, the greater the decline range. Then, with the injection-production cycle increasing the Poisson’s ratio increases gradually and the higher the injection-production differential pressure, the greater the increase range. Finally, the internal friction angle ratio increases greatly in the initial stage, after that decreases and then shows a linear increase. According to the influence law, the relationship model between the critical production pressure drop of injection-production wells in gas storage and the injection-production cycle and differential pressure under the gas-solid coupling will be established, which is used for the dynamic prediction of the critical production pressure drop of injection-production wells in the whole life cycle of gas storage.

Machine-learning-aided design optimization of internal flow channel cross-sections

• Artificial neural network-based models are developed for prediction of nusselt number and friction factor. • The predictions apply for fully developed laminar flow in constant cross-section ducts of different cross section shapes. • The machine learning (ML) model predictions are validated and compared against numerical simulations. • Use of ML models in shape optimization of channel cross section for different objective functions is demonstrated. • Guidelines for usage of the developed ML models are discussed. The design optimization of various thermal management components such as cold plates, heat sinks, and heat exchangers relies on accurate prediction of flow heat transfer and pressure drop. During the iterative design process, the heat transfer and pressure drop is typically either computed numerically or obtained using geometry-specific correlations for Nusselt number and friction factor. Numerical approaches are accurate for evaluation of a single design but become computationally expensive if many design iterations are required (such as during formal optimization processes). Correlation-based approaches restrict the design space to a specific set of geometries for which correlations are available. Surrogate models for the Nusselt number and friction factor, which are more universally applicable to all geometries than traditional correlations, would enable flexible and computationally inexpensive design optimization. The current work develops machine-learning-based surrogate models for predicting the Nusselt number and friction factor under fully developed internal flow in channels of arbitrary cross section and demonstrates use of these models for optimization of the cross-sectional channel shape. The predictive performance and generality of the machine learning surrogate models is first verified on various shapes outside the training dataset, and then the models are used in the design optimization of flow cross sections based on performance metrics that weigh both heat transfer and pressure drop. The optimization process leads to novel shapes outside the training data, and so numerical simulations are carried out on these optimized shapes to compare with the surrogate model predictions and show their performance is at least as good as that of shapes with known correlations available. A three-lobed shape was found to reduce friction factor, whereas a pentagon with rounded corners and an ice cream cone-shaped duct, both found using different performance metrics. Although the ML model predictions lose accuracy outside the training set for these novel shapes, the predictions follow the correct trends with parametric variations of the shape and therefore successfully direct the search toward optimized shapes.

Prediction of flow regime boundary and pressure drop for hexagonal wire-wrapped rod bundles using artificial neural networks

This study used an artificial neural network (ANN) regression model in wire-wrapped fuel assemblies to estimate the transition-to-turbulence flow regime boundary (RebT) and friction factor. The ANN models were trained and validated using existing experimental datasets. The bundle dataset comprised several design parameters, such as the number of rods, rod diameter, wire diameter, lattice pitch, edge pitch, and wire helical pitch. The log–log scale Reynolds number and linearity characteristics of the friction coefficient were used to over-sample the friction factor in the laminar and turbulent regimes for resolving the data imbalance. Three-quarters of the entire dataset was used for training, while the remainder was used for validation. The Levenberg–Marquardt approach with the Gauss–Newton approximation for the Hessian of the training cost function was used for training the model. The number of hidden layers for RebT was selected based on the minimum validation error. The pin number effect was additionally considered for the friction factor while selecting the number of hidden layers. The ANN model predicted using the oversampled data set had a 50% reduction in the root mean square error (RMSE) than the model predicted using the original data set. Compared to previous correlations, the prediction of ANN models for the friction factor demonstrated significantly low errors (0.10% mean error and 7.36% RMSE of 142 bundle data).

Research on a New Drag Force Model for Cylindrical Particles in Fixed Bed Reactors

Fixed bed reactors play an important role in converting solid wastes to high-quality products. The solid wastes, as well as the corresponding catalysts, are often made into cylindrical particles. However, research on the drag force for cylindrical particles is still rarely reported. In this work, the fixed bed porosity was firstly predicted with the unresolved CFD-DEM method and validated against experimental data. Then, the Ergun model, Di Felice model, and Ganser model were evaluated against the reported pressure drop data for both the spherical and cylindrical particles, so that a more solid drag force theory could be selected as a candidate for cylindrical particles. Finally, a new Ganser model was proposed for cylindrical particle drag force prediction based on the reported experimental results and validated by other experimental data. It was found that, for the spherical particle bed, the relative prediction errors of the Di Felice model are approximately 10%, while those of the Ergun model are approximately 15%. For the cylindrical particle bed, the relative prediction errors of the Ganser model are approximately 10%, while those of the Di Felice model are much higher than 10%. With the new Ganser model proposed in this work, the maximum error between the predicted pressure drop and the experimental data can be lowered to approximately 5%. The research is of reference value for drag force model selection when simulating similar FBRs with cylindrical particles.

Improvement of two-phase closure models in CTF using Bayesian inference

Under the Consortium for Advanced Simulation of Light Water Reactors (CASL) program, extensive capabilities have been developed in CTF to analyze light-water reactors (LWRs) for normal operating conditions, departure from nucleate boiling (DNB), and system transients. However, further improvements are required in the modeling and simulation of boiling water reactors (BWRs), which is a focus of the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program. In this work, CTF validation results were used to optimize selected modeling coefficients by calibrating to experimental data using a Bayesian inference approach. Calibration studies were conducted to improve (vapor) void fraction prediction without worsening the two-phase pressure drop prediction, as well as to improve the two-phase pressure drop prediction. Calibration was performed for interfacial drag and wall shear models. Surrogates were developed to alleviate the computational expense required for sampling the parameter space using Markov chain Monte Carlo (MCMC). An assessment performed with calibrated models demonstrated an improvement of CTF in its prediction of key parameters such as void fraction and two-phase pressure drop.

Prioritizing pressure drop research in nuclear thermal hydraulics

Prediction of pressure drop by wall friction and at geometric discontinuities is important in nuclear thermal hydraulics simulation. Pressure-drop models were established and upgraded for decades; however, errors in predictions of experimental data are up to 40%, namely in low flow and two-phase conditions and particularly at geometric discontinuities. In order to clarify the impact in situations of interest for nuclear reactors, noticeably accident scenarios investigated in scaled experimental facilities, we propose a virtual benchmark on Reverse Natural Circulation (RNC) in the PKL test facility.

CFD simulation of gas–solid fluidized bed hydrodynamics; prediction accuracy study

Abstract The present study aims at increasing the prediction accuracy of simulating gas–solid fluidized bed hydrodynamics. Two simulation packages, Fluent and MFIX, were used to predict the pressure drop, voidage, and solid-phase velocities by solving mass, momentum, and energy balance equations. A 2D multi-fluid Eulerian model with the kinetic theory of granular flow (KTGF) was applied to simulate the process by considering two different drag models. The same comparative criterion of average absolute relative deviation (AARD%) was considered to compare the present simulation with the previous works. Compared to the prior works, the minimum decrease in error (AARD% of 5.91%) was 3.17% related to the estimation of the time-averaged voidage by applying the Gidaspow model, while the maximum reduction in error (ARRD% of 5.88%) was 17.35% attributed to the prediction of pressure drop by employing the Syamlal-O’Brien model, both in Fluent software. However, MFIX software was the best CFD tool in predicting time-averaged voidage by AARD% values less than 9% under all conditions. Furthermore, similar patterns in contours were observed for solid-phase volume fraction and gas/solid phase velocities in both simulation tools, which are compatible with results from the literature without any significant difference.

CFD Modeling of Pressure Drop through an OCP Server for Data Center Applications

Modeling IT equipment is of critical importance for the simulations of flow and thermal structures in air cooled data centers. Turbulent flow undergoes a significant pressure drop through the server due to the energy losses originating from the internal components. Therefore, there is an urgent need to develop a fast and an accurate method for the calculation of pressure losses inside server components for data center applications. In this study, high resolution numerical simulations were performed on an OCP (Open Compute Project) server under various inlet flow rates for inactive and active conditions. Meanwhile, one key challenge of modeling complete geometry of the server results from using an intense mesh even for a single server. To address this challenge, the server was modeled as a porous zone to mimic inertia and viscous resistance in a realistic way. Comparison of the results of porous and complete models showed that the proposed model could calculate pressure drop accurately even when the number of cells in the server was reduced to 0.3% of the complete model. Porosity coefficients were determined from the numerical simulations conducted in a broad range of air discharge for both active and inactive conditions. Errors in the calculation of pressure drop may result in a significant deviation in the prediction of the temperature rise over the server. Thus, the present model can effectively be used for the fast and accurate prediction of pressure drop inside a server component rather than solving internal flow on an intense mesh, while simulating airflow inside an air-cooled data center, which is crucial for the design safety of data centers. Finally, calculated porosity coefficients can be used for the prediction of the pressure drop in a server, while designing data centers based on numerical simulations.

Prediction of heat transfer coefficient, pressure drop, and overall cost of double-pipe heat exchangers using the artificial neural network

Typically, success in the estimation of machine learning is expected to rise with increasing input parameters, whereas the noise issue may rarely arise owing to redundant input factors undesirably influencing the learning algorithm. The parameters such as overall heat transfer coefficient, pressure drop, and overall cost have been determined by two different artificial neural networks evaluated by a multi-layer perceptron model. Using the Levenberg-Marquardt training algorithm, in the first model input layer, a total of 10 input parameters ρ, np, k1, Re1, fi, Re2, fo, ns, P1 and P2 have been defined, while the second involves 8 input parameters by subtracting pumping powers from the first one, thus the noise issue has been investigated using unnecessary input parameters. Overall heat transfer coefficient, tube/annulus sides pressure drops, and overall cost have been estimated with deviations of 0.16%, 0.23%, 0.02%, and 0.003% via Model 1, 0.02%, 0.18%, 0.16%, and 0.15% via Model 2, respectively. Moreover, Model 1 results in the best mean squared errors for annulus side pressure drop and overall cost with the values of 2.54E-04 and 1.93E-04, correspondingly, whereas Model 2 yields the best values of 1.11E-04 and 1.90E-04 for overall heat transfer coefficient and tube side pressure drop, sequentially.