Two-phase Pressure Drop Research Articles

Experimental data for flow boiling of R450A in a horizontal tube

According to the new European policies aimed at the replacement of highly-pollutant greenhouse gases refrigerants, the scientific community has focused on new synthetic environmentally friendly substances to be employed in vapor compression cycles for the refrigeration and the air conditioning fields.On this regard, R450A is a new blend made up of R134a (42%) and R1234ze (58%), having a GWP equal to 604, and therefore represents an attractive solution as pure R134a substitute. In this paper, new flow boiling heat transfer and pressure drop data of R450A collected at the refrigeration lab of Federico II University of Naples are presented. The data refer to a horizontal stainless-steel tube having an internal diameter of 6.0 mm. The effects of mass flux (from 150 to 400 kg m−2s−1), heat flux (from 10 to 20 kW m−2) and saturation temperature (from 30 to 50 °C) are presented and discussed, together with the assessment of the most quoted two-phase heat transfer and pressure drop prediction methods.

Investigation on gas-liquid two-phase frictional pressure drop in pipeline riser

The pressure drop characteristics of gas-liquid two-phase flow in pipeline-risers are important to the design optimization of marine risers lifting oil and gas. In this study, experimental investigation on single-phase and air-water two-phase flow pressure drop characteristics in vertical and S-shaped risers have been carried out in a long-distance pipeline with the gas superficial velocities ranging from 0.03 to 6.2 m/s and the liquid superficial velocities from 0.02 to 1.3 m/s. The test loop with 50 mm i. d. Consists of a horizontal pipeline with 114 m in length, followed by a 16 m downward inclined section, and ended at a riser. The downward section is adjustable in inclination with various angle of −2°, −3°, −4° and −5° with respect to horizontal. A vertical riser and an S-shaped flexible riser were used in the experiment. The effects of flow and geometry parameters on two-phase frictional pressure drop multiplier are studied. For flow parameters, the two-phase frictional pressure drop multiplier increases with increasing the inlet gas and liquid superficial velocity. For geometric parameters, the two-phase frictional pressure drop multiplier in S-shaped riser is larger compared to that in straight vertical riser. The existing correlations reported in the literature are evaluated. A single-phase friction factor correlation and a two-phase frictional pressure drop multiplier correlation for pipeline-riser system are developed. Comparison of the predicted value and the measured results shows good agreements.

Study on Two-Phase Pressure Drop of Methane during Flow Boiling in Mini Channel

For LOX/LCH4 variable thrust rocket engine, the propellant methane is traditionally selected as the coolant in regenerative cooling channel (RCC). With the decrease of engine thrust, the mass flow rate of coolant methane decreases gradually. At low engine thrust, the coolant methane is usually in a subcritical state. The heat transfer deterioration of subcritical methane occurs in RCC, which may cause thrust chamber wall ablation. The two-phase pressure drop data of methane are crucial parameters for the design and optimization of RCC. But it is rarely to find such measured frictional pressure drop data of methane in open published literature. The two-phase pressure drop of methane during flow boiling in the single mini channels with the diameters of 2.0 mm are investigated systematically. Effects of the mass flux (582.19~1755.48 kg/m2·s), inlet pressure (0.56~3.55 MPa), heat flux (53.25~318.68 kW/m2) on the frictional pressure drop of methane are discussed. The results show that the frictional pressure drop of methane during flow boiling increases with mass flux and inlet pressure at the experimental conditions, and heat flux shows weak effect on the frictional pressure drop. The comparisons of the experimental data with the predicted value by existing six correlations are analyzed. Contrary to the conventional channels, homogeneous model yields better prediction than five separated flow models. Present experimental results can provide reference for the design and optimization of RCC in LOX/LCH4 rocket engine.

Numerical analysis of sodium-argon two-phase flow in narrow channels under severe accident conditions in pool type SFR

A two-phase flow model for sodium-argon mixture flow through the reactor vessel head penetrations under the energetic core disruptive accident in a sodium fast reactor (SFR) is presented. The model evaluates the total sodium mass in sodium-argon mixture released to the reactor containment building (RCB) through penetrations. The driving pressure at the penetration entrance is given as input. The two-phase frictional and local pressure drops, inertial and piezo-metric heads are accounted for in the model. Depending on the argon volume fraction, either a homogenous or separated flow approach is adopted to evaluate the mixture flow. Reactor-scale analysis show that the presence of argon in vessel head penetrations can significantly mitigate the total sodium release mass during the slug impact phase. Also, the two-phase frictional pressure drop plays a mitigating role and needs to be included in the model formulation to avoid overestimation of the sodium release mass. Fluid-structure interaction effects such as vessel head bending and hold-down bolt elongation have negligible influence on sodium release mass as long as the deformations are within the elastic limit. The model is conceived to be part of an integrated code system to evaluate the sodium fire and the maximum RCB pressure under severe accident conditions in a pool-type SFR.

Comprehensive study of synergistic effects of phase separation structures and electric fields for enhancing the heat transfer performance of minichannel heat sinks

In this paper, the effects of the phase separation structure on the enhanced boiling heat transfer mechanism and bubble dynamics were investigated. Two types of phase-separation structures and one type of conventional minichannel were manufactured by ultrafast laser technology. Flow boiling experiments of a glycerol-water solution were conducted under various heat flux and electric field conditions. Entropy generation analysis was employed to comprehensively analyze and assess energy losses and irreversibility within the system. Response surface analysis method was introduced to optimize operational and design parameters for achieving optimal experimental design. Moreover, the coupling effect of the phase-separation structure and electric field was observed to have a significant impact on the enhancement of heat transfer. The visualization results indicate that, compared to conventional parallel minichannels, the countercurrent minichannel with phase-separation structure leads to a gradual decrease in the aspect ratio of confined bubbles downstream (in contrast to the increasing aspect ratio of confined bubbles downstream in general minichannels), and smaller bubbles at the upstream of adjacent minichannels gradually disappear and diminish due to the condensation effect. The experimental results demonstrate that the porous phase-separation structure plays a significant role in enhancing heat transfer performance and can reduce the increase of two-phase friction pressure drop per unit length with the increase of heat flux. Under electric field-free conditions, the porous phase separation structure exhibits a maximum increase in heat transfer efficiency of 26.2% compared to conventional structures. Furthermore, the maximum reduction in two-phase frictional pressure drop per unit length reaches 19.4%. In the presence of the synergistic effect between an electric field and the phase separation structure, the maximum heat transfer efficiency is enhanced by 65.5%. The above analysis provides an effective means for investigating the comprehensive performance of phase separation structures and the bubble dynamics of confined bubbles in heat sinks.

Development of Two-Phase Frictional Pressure Gradient Correlation for Saturated Cryogenic Flow Boiling in Uniformly Heated Tubes

Experiments to determine two-phase frictional pressure drop for saturated cryogenic flow boiling in uniformly heated round tubes have been performed throughout the globe during the past sixty years for a variety of cryogens. However, the experimental data are scarce and either rarely published or published only for a few cryogens, with majority of the data remaining in the archives of authors, or in obscure technical reports of an organization or other inaccessible sources. In the present study, the Purdue University-Boiling and Two-Phase Flow Laboratory (PU-BTPFL) Cryogenic Total Pressure Drop Database is consolidated both for saturated adiabatic liquid-vapor and saturated flow boiling for cryogens from world literature dating back to 1964. With 474 total pressure drop data points for LHe, LH2, LNe, and LN2, it represents the largest total pressure drop database for cryogenic saturated two-phase flow assembled to date. Using this database, predictive accuracy of seminal frictional pressure gradient correlations employing both the Homogenous Equilibrium Model (HEM) and the Separated Flow Model (SFM) are assessed. The distinct fluid physics unique to cryogens is studied further using the database and new dimensionless criteria are developed to demarcate a dispersed flow dominant data subset from the separated flow dominant data subset, which are better represented using HEM and SFM, respectively. These criteria are subsequently used to develop a hybrid HEM-SEM frictional pressure gradient correlation for saturated cryogenic flow for the two distinct data subsets. The new hybrid correlation performs the best of all seminal correlations and provides excellent predictive agreement with the database, evidenced by a Mean Absolute Error (MAE) of 14.7 %.

Analytical modelling of the hydraulic effect of hydrate deposition on transportability and plugging location in subsea gas pipelines

Accurate prediction of the hydraulic effect of hydrate deposition and plug location is critical to the safety and operability of natural gas transport pipelines, especially for gas-dominant subsea pipelines where maintenance and intervention activities are more difficult. To achieve this, the present work improved an existing two-phase pressure drop relation due to friction, by incorporating the hydrates deposition rate into the equation. In addition, a model has been developed to predict the pipeline plugging time. The transient pressure drop predictions in the present study for all six cases at high and low velocities are within 4% mean relative error. Similar predictions by Di Lorenzo et al. are within 40% maximum relative error, while the mean relative error of the transient pressure drop predictions by Zhang et al. was 7.43%. In addition, the plugging flowtime model underpredicts the plugging time by a mean relative error of 9%.

CFD and lower order mechanistic models for gas-liquid flow in NETmix: Pressure drop and gas hold-up

This study evaluates a 2D two-phase computational fluid dynamics (CFD) model, based on the Volume-of-Fluid approach, to represent the air–water co-current downwards flow inside the micro/meso structured static mixer, NETmix. The 2D model was suitable for representing properties more reliant upon the shape and size of the bubbles, such as the gas hold-up. Additionally, it was measured the two-phase pressure drop associated with the NETmix, through which it was observed a capability of the NETmix to operate at a lower pressure drop than some common static mixers. Using both CFD and experimental measurements, a method for predicting the gas hold-up and a mechanistic model to predict the two-phase pressure drop in static mixers were proposed, both based on previous works. A maximum deviation from the reference data of 7.2% and 17.0% was found between the predictions of the proposed gas hold-up method and the two-phase pressure drop, respectively.

Multi-objective optimization of two-phase flow in the proton exchange membrane fuel cells based on a data driven surrogate model

Flooding is detrimental to Proton Exchange Membrane Fuel Cells (PEMFCs). Reducing two-phase pressure drop and flooding relief time alleviates the devastating effect of flooding. To this end, an innovative surrogate model based on Artificial Intelligence is developed for flooding conditions. Volume of Fluid is employed to capture two-phase flow during the flooding in the simulations. A dataset is generated by 3D two-phase CFD simulation. An Artificial Neural Network is developed based on the dataset to predict the dynamic behavior of two-phase during flooding in time series. Flooding criteria are formulated based on the time series. The results show that the model predicts two-phase flow behavior accurately. Low gas velocity compels small parasitic power, but flooding conditions are exacerbated by the low flow rate, especially in the geometries with corners and virtual bottlenecks. Two distinct methods are used to develop multi-objective optimization, fed by the presented formula. Features are cathode channel characteristics, and objectives are relief time and stabled two-phase pressure. The optimum case brings a time of 9.11 ms and a pressure drop of 27.44 Pa. Also, it reduces the stable pressure drop and the time by 83% and 90%, compared with the worst conditions.

Thermal-hydraulic characterization of R513A during flow boiling inside a 6.0 mm horizontal tube, comparison with R134a and development of a new correlation

This paper presents two-phase heat transfer coefficient and pressure drop data of refrigerant R513A, a new azeotropic mixture conceived as possible alternative to R134a for medium temperature small-size refrigeration systems. All the experiments were performed in a commercial horizontal stainless-steel tube having an internal diameter of 6.0 mm and an outer diameter of 8.0 mm. The channel heating was obtained through DC current and Joule effect. The effect of the main operating parameters in terms of mass flux (from 150 to 500 kg/m2s), heat flux (from 5.0 to 40 kW/m2), saturation temperature (from 30 to 50 °C) and vapor quality (from the onset of boiling up to the dry-out occurrence) was analyzed and discussed for the heat transfer coefficient values, finding that both convective and nucleate boiling were significant contributions. The same ranges of mass flux and saturation temperature were also applied to frictional pressure gradient trends with vapor quality, taken in adiabatic conditions. The thermo-hydraulic performances were then compared with those of R134a, obtaining lower heat transfer coefficients and very similar pressure gradients. Finally, the collected experiments were assessed with values predicted from the most quoted correlations available in literature. A new composite method for nucleate-dominant or convective-dominant mechanisms was proposed for the evaluation of the heat transfer coefficient, with a mean absolute error of 25.3%, whereas the frictional pressure gradient values were well predicted with the Friedel correlation, that provides a mean absolute error of 13.8%.

An experimental investigation of flow boiling instability of R245fa in a horizontal tube

Two-phase pressure drop oscillations during flow boiling of pure fluid R245fa in a horizontal microchannel with a diameter of 0.9 mm were experimentally investigated. Three mass fluxes G = 400, 630, and 1100 kg/m2 s with three different heat fluxes q = 40, 50, and 55 kW/m2 were tested under the inlet pressure of 211.72 kPa and inlet subcooling of 17 K. Flow instabilities were analyzed based on images and temporal oscillation results of two-phase mass flux (G), pressure drop (ΔP), and inlet pressure (Pin). Four types of high-amplitude/low-frequency are identified, the main reasons for which are found to be flow patterns in the test section and upstream compressible volume of vapor. The inlet pressure oscillation is attributed to the mixture between expansion vapor and subcooled liquid in the inlet plenum. Effects of mass flux and heat flux on the pressure drop oscillation are also discussed through the variation trends on ΔP vs q/G and the fast Fourier transform.

Pressure drop and bubble length prediction for gas-non-newtonian fluid two-phase flow in a curved microchannel

The control mechanism of the pressure drop and bubble size has a guiding significance for selecting the micropump, the pressure resistance design, and the precise control of the microfluidics. In this study, single-phase flows and gas-non-Newtonian fluid two-phase flows are studied in a microchannel containing curved structures. Sodium carboxymethyl cellulose solutions are used as the non-Newtonian fluids; water and nitrogen are used as Newtonian fluid and gas phases, respectively. The pressure drop and the bubble length are measured. The influences of operating conditions are discussed. The non-Newtonian properties of the solutions are found to affect the parameters measured significantly. The experimental results are compared with the existing models, and the fanning friction factor is used to evaluate the pressure drop. The two-phase flow pressure drop can be predicted by the Lockhart-Martinelli method with a newly developed C-coefficient as a function of the fluid characteristic parameters and microchannel structure parameters. The new correlation for two-phase pressure drop prediction has an error within 18%, smaller than existing models. A new prediction method for the dimensionless bubble length containing the two-phase friction multiplier is also given with an error of 16%.

FRICTIONAL PRESSURE DROP DURING CONDENSING FLOW INSIDE MINI/MICRO-CHANNELS: PREDICTIVE TOOLS ASSESSMENT AND DATA TREATMENT

A total of 1210 new condensation friction pressure gradient points (database) is collected from 12 open articles on mini/micro-channels literature. The database covered a wide range of thermophysical properties associated with low-GWP refrigerants, physical dimension, mass velocity and vapor quality. A comparison of the experimental database against eleven two-phase flow frictional pressure drop prediction tools is carried out. Based on that, the mini/micro-channel developed by Xu and Fang exhibited the best ability to capture the tendency of the database with a mean absolute relative deviation of (36.59%) for all data. Keywords: Two-phase flow frictional pressure gradient; Mini/micro-channels; Condensing flow; New refrigerant fluid; Heat transfer; Collect database.

Condensation of R290 + R13I1 zeotropic mixture in a plate heat exchanger with offset-strip fin geometry

Energy-efficient refrigerants with a low global-warming potential (GWP) is becoming increasingly popular, particularly in the automobile sector. In this sense, despite its higher flammability, R290 can meet environmental regulations with outstanding thermal properties. Studies have been conducted to reduce the flammability of R290 by combining it with flame retarding agents, and it has been discovered that the use of R13I1 has good control over R290's flammability and offering good thermal performance. However, research into the two-phase behavior of R290 + R13I1 combinations is extremely important for building compact heat-pumps. Therefore, this study experimentally investigated the condensation behavior of a new low-GWP R290 + R13I1 refrigerant mixture in a plate heat exchanger with an offset-strip fin flow passage. The effects of the heat flux (HF), mean vapor quality (xm), saturation temperature (Ts), and mass flux (MF) on the condensation heat transfer coefficient (HTC) and two-phase frictional pressure drop were explored. The results show that the peak condensation HTC increased by 66.2% and 19.7% with an increase in HF and MF, respectively, although it deteriorated by 26.7% in the case of Ts. Moreover, the dominance of the mass transfer resistance (MTR) and surface tension was observed at lower xm values, whereas the shear force dominated at higher xm values. The MTR was estimated with Silver–Bell–Ghaly (SBG) approximation, and the values were in the range of 0.0000342 K.m−2.W−1 and 0.000067 K.m−2.W−1. Moreover, the Nusselt number (Nu) predicted using the SBG approximation correlations was lower than the experimental value. Hence, two types of new Nu correlation were made with and without SBG approximation, and they showed reasonably good Nu prediction with 9.6% and 10.8% mean absolute deviation.

An Experimental Investigation of Two-Phase Frictional Pressure Drop in Straight-Tube Steam Generator Used in SFR

Due to the presence of sodium, it is a challenging task to achieve the reliable and safe operation of steam generators in a sodium-cooled fast reactor (SFR). Water flow oscillations in a two-phase flow system worsen the tube integrity. An accurate prediction of two-phase pressure drop is essential in designing steam generators to operate in a stable regime. Toward this, experiments have been carried out on an industrial-size 19-tube model sodium-heated steam generator of 5.5-MW capacity to understand two-phase pressure drop characteristics at various operating conditions. The measured data are used to estimate the two-phase frictional pressure drop. The concept of a two-phase friction multiplier has been used in the present study. A significant variation in the two-phase frictional multiplier is seen with steam quality, whereas the variation of the two-phase friction multiplier is insignificant at saturated steam condition. Based on the experiments, complemented by computational model, a correlation has been developed for the two-phase frictional multiplier as a function of steam quality for sodium-heated once-through straight-tube steam generators.

Enhancing the dynamic performance of proton exchange membrane fuel cells through two-phase flow experimental investigation

Efficient water transfer is crucial for enhancing the rapid response and durability of proton exchange membrane fuel cells (PEMFCs). In this paper, ex situ observation experiments and in situ dynamic performance tests of fuel cells are conducted and correlated with each other by two-phase flow pressure drop. The experimental results show that slug flow within the cathode gas flow channels (GFCs) is unfavorable to mass transfer and results in loading failure under high current densities, as identified in Design Failure Mode and Effects Analysis (DFMEA). However, slug flow in GFCs of PEMFCs can be converted into film flow by reducing the hydraulic diameter of GFC, increasing the air stoichiometry ratio, and extending the loading resistance time to an appropriate value. This facilitates a successful and efficient load change process of PEMFCs under high current densities. This study provides a methodology, combines ex situ observation and in situ evaluations, identifying potential risks, which can shed light on improving the dynamic performance and development process of PEMFCs.

Irregular-shaped nucleated bubbles induced enhancement of subcooled flow boiling heat transfer in leaf vein inspired three-tiered open microchannels (LTOMCs)

Nature is an important source of inspiration for developing desired structures for various industrial applications. The efficacy of water transport in leaf vein systems provides important insights for the structural design of microchannels. In addition, open microchannels (OMCs) have been reported to effectively reduce the two-phase pressure drop and suppress flow instabilities by providing extra space for bubble and vapor expansion. Thus, the synergistic cooperation of open microchannels with leaf-vein-like structures is expected to alter the flow patterns and improve the heat transfer performance in the flow boiling process. In this work, two leaf-vein inspired three-tiered open microchannels (LTOMC) with exactly the same structure but opposite orientations of vein-like channels, i.e., LTOMC-Ⅰ and LTOMC-Ⅱ, were manufactured, respectively. Flow boiling experiments were conducted at the inlet temperature of 25 °C under different mass fluxes. It was observed that the flow patterns of the LTOMC were divided into bubbly flow, slug flow, reverse and rewet flow; the shapes and movement trends of nucleated bubbles were mainly dominated by the vein-like structures. The required wall superheat of the onset of nucleated boiling for LTOMCs was 2–6 °C lower than ROMC; the one for LTOMC-Ⅱ was 2–3 °C lower than LTOMC-Ⅰ at various mass fluxes. The average two-phase heat transfer coefficient of LTOMC-Ⅱ was increased by 83.2% compared to ROMC at the mass flux of 234 kg/m2·s; the one of LTOMC-Ⅱ was 54.1% higher than LTOMC-Ⅰ. The pressure drop of three OMCs was comparable; however, the onset of two-phase flow instability occurred earlier for ROMC at the same heat flux. Besides, the liquid rewetting capability of ROMC was easier to get deteriorated at ultra-high heat flux. This work offers an avenue for structural optimization of microchannel heat sinks to enhance heat transfer performance without compromising the pressure loss.

Flow Pattern Study and Pressure Drop Prediction of Two-Phase Boiling Process in Different Surface Wettability Microchannel.

An experimental study of two-phase flow pressure drop using R-134a is conducted on three types of different surface wettability microchannels with superhydrophilic (contact angle of 0°), hydrophilic (contact angle of 43°) and common (contact angle of 70°, unmodified) surfaces, all with a hydraulic diameter of 0.805 mm. Experiments were conducted using a mass flux of 713-1629 kg/m2s and a heat flux of 7.0-35.1 kW/m2. Firstly, the bubble behavior during the two-phase boiling process in the superhydrophilic and common surface microchannel is studied. Through a large number of flow pattern diagrams under different working conditions, it is found that the bubble behavior shows different degrees of order in microchannels with different surface wettability. The experimental results show that the hydrophilic surface modification of microchannel is an effective method to enhance heat transfer and reduce friction pressure drop. Through the data analysis of friction pressure drop and C parameter, it is found that the three most important parameters affecting the two-phase friction pressure drop are mass flux, vapor quality, and surface wettability. Based on flow patterns and pressure drop characteristics obtained from the experiments, a new parameter, named flow order degree, is proposed to account for the overall effects of mass flux, vapor quality, and surface wettability on two-phase frictional pressure drop in microchannels, and a newly developed correlation based on the separated flow model is presented. In the superhydrophilic microchannel, the mean absolute error of the new correlation is 19.8%, which is considerably less than the error of the previous models.

Development and validation of a general two-fluid thermal-hydraulic analysis code for reactors with plate-type fuel assemblies

A general two-fluid thermal-hydraulic analysis code, TTHAC-PFA (Two-fluid Thermal-Hydraulic Analysis Code for reactors using Plate-type Fuel Assemblies), has been developed. The code was developed on basis of the fundamental governing equations. Reasonable mathematic and physical models for parallel rectangular channels and fuel plates have been built up to meet the command of the safety analysis for plate-type fuel reactors. The coolant distribution is conducted on basis of the pressure drop equation theory. Normal subchannel approach is adopted in the code. Fortran language is adopted. The RA-6 experiment is used to evaluate the heat transfer models. The max deviation of the simulations from the measured value is about 5.7 °C. Then, experiments on two-phase flow pressure drop are adopted to validate the code. Approximately 97% of the data points are within ±20% of the deviation range. In addition, CARR (China Advanced Research Reactor) is adopted as the benchmark for normal condition validation. Flow distribution validation and temperature profile validation are conducted. The flow validation presents negligible mean discrepancy and the temperature differences are within the scope of 6 °C. All validations are in good agreement, which indicates the developed code meet the requirements of analyzing thermal-hydraulic characteristics for parallel rectangular channels in reactors. Furthermore, TTHAC-PFA is applied to the investigate channel blockage accident occurred in the CARR. The mass flow is redistributed among channels due to the obstruction. In the obstructed channel and two nearby channels, the coolant temperatures increase a lot. The coolant temperature in the obstructed channel rises by 60 °C. In the rest of the channels, the coolant temperatures decrease with the increase of coolant flow. Besides, the two fuel plates, which form the blocked channel, are asymmetrically cooled due to flow maldistribution. The temperature difference between the cladding on both sides of the fuel plate can reach 40 °C. As a result of partial blockage, the cladding temperature on the side of the blocked channel rises by 63 °C. During the blockage accident, the plate temperature is under the melting temperature. The results indicate the significance of studying the effects of the adjacent channels near the obstructed channel for reactors with plate-type fuel elements.

Deep learning-based assessment of saturated flow boiling heat transfer and two-phase pressure drop for evaporating flow

This work proposes new correlations as well as deep learning based modeling of saturated flow boiling heat transfer and two-phase pressure drops for evaporating flow. First, existing saturation flow boiling heat transfer correlations are compared to experimental database (2,500 data points) of numerous refrigerants for tube diameters ranging from 1 to 7 mm. The newly developed correlation for heat transfer outperformed the existing correlations resulting in an MAE =11.28%. For two-phase pressure drop of the evaporating flow, 1,954 measurement data points of 7 refrigerants were used, for the experimental tube diameter ranged from 0.509 to 14 mm. The newly developed correlation for pressure drop outperformed the existing correlations resulting in an MAE =19.07%. An optimal deep learning model (DL) was developed that further improved the accuracy of the prediction in terms of both heat transfer and pressure drop (R2=0.984 and MAE=4.5 % in terms of heat transfer and R2=0.994 and MAE=7.39 % in terms of two-phase pressure drop). The proposed correlations and deep learning models significantly improve microchannel prediction in terms of heat transfer and two phase pressure drop. Besides, explainable artificial intelligence highlights the dependence and interaction between various features affecting the heat transfer and pressure drop.