Friction Factor Correlations Research Articles

Numerical study on enhanced heat transfer and friction factor characteristics of helical bead-groove tube

The comprehensive thermo-hydraulic performance of a helical tube (HT) is improved in this study by proposing a new type of helical bead-groove tube (HBGT). The heat transfer performance and friction factor of HBGT, helical groove tube, and HT under the same conditions were compared by the numerical simulation method. The effects of different bead-groove positions, bead-groove density ratios, and depth ratios on the HBGT heat transfer and friction factor properties are analyzed. The research introduced the field synergy theory to investigate the enhanced heat transfer mechanism. The results show that the HBGT can strengthen the vortex and secondary flow intensity. Meanwhile, this structure can also reduce the average field synergy angle. Its performance evaluation criterion is increased by a maximum of 8.5% and 28.2% compared to the HBGT and the HT, respectively. Compared with the bead-groove position, the bead-groove density ratio and depth ratio have more significantly influenced the thermal performance of the HBGT. The Nusselt (Nu) and friction factor (f) correlations were calculated from simulation data with error limits of ±5% and ±10%, respectively, to forecast the Nusselt (Nu) and friction factor (f).

Laminar Flow Heat Transfer Studies in a Twisted Square Duct for Constant Wall Temperature

Abstract: Three dimensional analysis of steady fully developed laminar flow inside twisted duct of square cross section flow area is studied for Reynolds number range of 100 – 2000 using a commercially available software. Twist ratio used are 2.5, 5, 10 and 20. Heat transfer results are generated for a uniform wall temperature case for Prandtl number range of 0.7 to 20. Maximum values for the product of friction factor and Reynolds number is observed for a twist ratio of 2.5 and Reynold number of 2000. Maximum Nusselt number is observed for the same values along with Prandtl number of 20. Correlations for friction factor and Nusselt number are developed involving swirl parameter. Local distribution of friction factor ratio and Nusselt number across a cross-section is presented. Heat transfer enhancement for Reynold number of 2000 and Prandtl number of 0.7 for twist ratio of 2.5, 5, 10, and 20 are 33 %, 18 %, 10 % and 7 % respectively. The results are significant because it will contribute to development of compact heat exchanger.

Thermohydraulic performance parameter based experimental investigation of frustum shaped roughened solar air heater

An outdoor experimental investigation was conducted to explore the thermohydraulic characteristic (Nusselt no. and friction factor) of artificial roughened solar air heater (ARSAH) having frustrum shaped roughened element on absorber plate. Data were recorded and further processed to generate Nusselt number and friction factor correlation to predict the effect of flow and roughness parameter on performance of ARSAH. The investigation was conducted by varying Reynolds number in range of 2500–12,500. Dimensionless parameter for Frustrum shaped roughness was relative frustum height (e/Dh) from 0.013 to 0.054, relative frustum pitch (p/e) from 8 to 14, Relative frustum height to base diameter (e/d1) from 0.37 to 0.75, relative frustum diametral ratio (d1/d2) from 1 to 3. Maximum performance for ARSAH was obtained corresponding to the optimum value of flow and geometric parameter. The geometric orientation of the proposed roughness geometry produced tremendous rise in Nu with an acceptable rise in friction (f). Maximum enhancement in Nu for varying p/e, e/Dh, e/d1, and d1/d2 was, 4.58, 5.21, 6.62 and 6.09 times and that of friction was 5.59, 4.69, 4.92 and 4.66 times respectively over conventional SAH. Maximum Thermohydraulic performance was 3.7, 3.6, 3.9 and 3.8 at p/e = 12, e/Dh = 0.054, e/d1 = 0.75 and d1/d2 = 3.

Roughness Related to Cooling Performance of Channels Made Through Additive Manufacturing

Abstract The complex surface morphology and multiscale surface features inherent in additively manufactured (AM) components contribute to the overall flow characteristics and heat transfer of cooling passages. As the AM process and cooling data in the literature continue to evolve, so does the need for more accurate heat transfer and pressure loss correlations for AM cooling schemes. This study improves the predictability of pressure loss and heat transfer for AM cooling passages by fabricating a range of coupons and investigating samples in the literature. Twenty-seven test coupons were manufactured using direct metal laser sintering in an assortment of build directions and build locations that produced a variety of surface morphologies. Nondestructive evaluation, computed tomography scanning, was used to quantify the surface morphology as well as capture the as-built geometric dimensions of the cooling schemes. The friction factor and bulk Nusselt number of the coupons were measured using an experimental rig. Pressure loss and heat transfer correlations in the literature were compared with the experimental results from the current coupons and datasets from the literature. Arithmetic mean roughness correlations in the literature struggled to predict the cooling performance of AM channels since the bulk roughness statistic did not capture the overall form of the surface morphology. A combination of root mean square roughness and skewness of the roughness was able to best predict pressure loss and heat transfer for the present samples and those in the literature while being independent of build location, build direction, material, machine, and laser parameters. The maximum absolute error was 25% and the average absolute error was 12% for the friction factor correlation. The maximum absolute error was 39% and the average absolute error was 8% for the Nusselt Number correlation.

New pressure drop and heat transfer correlations for turbulent forced convection in internally channeled tube heat exchanger ducts

In our previous paper, a novel heat exchanger concept, the so-called internally channeled tube (ICT) was suggested, based on a tubular geometry fitted with specially designed curved channels along the tube length. The enhanced heat transfer in the ICT results from extended surface area between two contacting fluids. To facilitate industrial application, ICT design methods must be developed. This work provides new equations for thermo-hydraulic characterization of ICT under turbulent flow conditions. In particular, new friction factor and Nusselt number correlations are derived based on the validated CFD simulations performed over a wide range of Reynolds numbers and geometrical parameters.

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.

Experimental and ensemble machine learning analyses of heat transfer, friction factor and thermal performance factor of rGO/water nanofluids in a tube

This paper explains about the experimental evaluation of thermophysical properties, heat transfer coefficient, Nusselt number, friction factor, and thermal performance factor of water-based reduced graphene oxide (rGO) nanofluids passes through a tube under turbulent flow conditions. The rGO nanoparticles in this study was prepared based on the Hummer's procedure. The thermophysical properties were estimated at different volume loadings from 0.5 % to 2.0 % and at different temperatures from 20 °C to 60 °C, respectively, similarly, the heat transfer and friction factor experiments were conducted in the Reynolds number ranging from 1800 to 21,000. The obtained data of heat transfer coefficient, Nusselt number, friction factor and thermal performance factor was predicted based on the advanced machine learning algorithms of boosted regression tree (BRT), and extreme gradient boosting (XGB), respectively. Results indicated that, at 2.0 % vol. of rGO/water nanofluid the thermal conductivity is raised by 26.95 % at a temperature of 60 °C, viscosity is raised by 63.29 % at a temperature of 20 °C, over base fluid. Moreover, the results are further shown that, at 2.0 % vol. of nanofluid the Nusselt number, heat transfer coefficient, factor in friction, drop in pressure, and pumping power raise of 34.80 %, 44.19 %, 16.73 %, 10.48 %, and 4.55 % at a Reynolds number of 13,705, against water. The correlation coefficient (R2) results predicted from BRT and XGB models for Nusselt number data is 0.9831 and 0.994, respectively. It is understood that the XBG algorithm predicts very accurate values compared to BRT algorithm with a less mean square error. The overall performance of the system was raised by 1.28 -folds than water. Using the experimental data, new Nusselt number and friction factor correlations were proposed.

Hydrodynamic design of the Separate Effect test facility for Flow-Accelerated Corrosion and Erosion (SEFACE) studies in liquid lead

Flow-accelerated corrosion and erosion (FACE) phenomena can be crucial for performance of structural elements in heavy liquid metal (HLM) cooled reactor systems. Existing experimental observations indicate that turbulent flow characteristic can affect FACE, but there is no quantitative data that can be used for model development and validation. Main recirculation pump impellers, which operate at high relative velocities and rotational flow conditions can be especially vulnerable to FACE. For comparison, the core internals operate at lower velocities and in axial flow conditions, but at higher temperatures and neutron fluence. Hence, systematic experimental data is needed to improve our knowledge on FACE phenomena. The Separate Effect Test Facility for Flow-Accelerated Corrosion and Erosion (SEFACE) is designed to obtain such experimental data including high relative velocities (up 20 ms−1) and high temperatures (400 to 550 °C) of liquid lead. This article focuses on the hydrodynamic design of SEFACE. The aim of the design is to achieve well defined flow conditions for experiments and ensure safe operation of the facility. First, we examine three design concepts (i.e., forced convection loop, rotating cylinder, and rotating disk) and motivate the choice of the rotating disk approach for SEFACE. Second, we discuss different design options, i.e., a confined rotor–stator test chamber and the unconfined rotating disk configuration. We used Reynolds-Averaged Navier Stokes (RANS) calculations to identify and solve the issues stemming from the high rotational speed. These include, for instance, lead free surface deformation, radial pressure buildup, and axial bending forces due to asymmetric test chamber. The CFD-derived torque and power predictions in rotor–stator and rotating disk systems are verified with selected empirical turbulent friction factor correlations or/and DNS calculations. We demonstrate that the developed hydrodynamic design of SEFACE solves identified issues and enables obtaining experimental data under well-defined flow conditions. The findings are deemed to also be applicable to the design of rotating disk-type FACE installations for other liquid mediums.

Experimental and numerical study on thermofluidic characteristics of microchannel heat sinks with various micro pin-fin arrays arrangement patterns

Targeting at improving the comprehensive performance of microchannel heat sink, microchannel heat sinks integrated with various arrangements of micro pin-fins arrays are proposed in this paper. The thermofluidic characteristics and heat transfer enhancement mechanism of different pin-fins arrangement patterns is investigated by experimental test and numerical simulations. It is found that the partially uniform/gradient stagger pin-fins arrangement patterns present largest pressure drop with moderate heat dissipation performance, while the patterns with overall pin-fins distribution demonstrate superior heat transfer performance than all partial pin-fins distribution modes. Thus, overall gradient stagger pin-fins arrangement with moderate pressure drop yields optimal heat transfer capacity, achieving 4.8∼6.1 times enhancement than smooth channel. Furthermore, the partially uniform/gradient stagger pin-fins arrangement patterns indicate best temperature uniformity and thermal resistance with 26.2 K and 47.6% reduction than smooth channel at 80 ml/min, 100 W/cm2, respectively. The temperature trend in the longitudinal direction shows peaks and troughs for arrangements with partial pin fins distribution, while patterns of gradient pin fins distribution exhibit wavy curves of temperature rise. Additionally, the performance evaluation plot is adopted to describe the comprehensive performance of heat sinks with different pin fins patterns. It is observed that the overall gradient stagger pin-fins arrangement shows optimal comprehensive performance among all patterns, achieving heat transfer enhancement ratio greater than 4 in contrast with smooth channel. Finally, the correlations of Nusselt number and apparent friction factor for patterns are established. This study provides feasible insights on the performance improvement of microscale liquid cooling technologies for thermal management of electronic devices.

Study on the influence of circumferential shape on the performance of cross wavy primary surface heat exchanger channel

The primary surface heat exchanger can be described as a compact and highly efficient heat exchanger. In contrast, the cross wavy primary surface heat exchangers are suitable for microturbines. Based on the study of circular cross wavy channel, this study innovatively proposed the triangular cross wavy channel to improve the fluid flow conditions and the rectangular cross wavy channel to increase the overall heat exchange of the channel. The applicability domain of the three types of channels is summarized by numerical simulation. The circular cross wavy channels have the smallest irreversible loss, the triangular cross wavy channels have the highest efficiency and the rectangular channels have the largest total heat transfer. Moreover, the correlations of Nusselt number and friction factor are proposed. The correlations for the Nusselt number and friction coefficient have been validated, and the average absolute errors are 2.71 % and 7.85 % respectively. The results show that the correlation formulas can effectively predict the resistance and heat transfer performance of the cross wavy heat exchange channel.

Flow rate measurement of gas-liquid annular flow through a combined multimodal ultrasonic and differential pressure sensor

Natural gas is an important strategic reserve resource for the country, also plays an important role in energy transition. During mining and transportation, natural gas has high liquid content and high-pressure characteristics, typically exhibiting gas-liquid annular flow state. Accurate flow metering of each individual phase without separation is significant to academic research and industrial production. Therefore, a combined ultrasonic and differential pressure sensor is presented to acquire flowing information. Based on the limited flowing information (liquid film fraction and gas velocity) measured by dual mode ultrasonic sensor, a two-fluid model is established to solve liquid velocity and droplet entrainment rate for calculating phase flow rates by analyzing the momentum balance between gas and liquid phases. The pressure drop by differential pressure sensor is introduced to make this two-fluid model closed and solvable. Considering the effects of system pressure and pipe diameter on pressure drop, a closed correlation for friction factor at the gas-liquid interface is established. Furthermore, the phase flow rates are calculated by the experimental measurement values obtained by dual mode ultrasonic sensor and the two-fluid model. The relative error of total flow rate is within ±10 % and the mean absolute percentage error is 5.220 %.

Numerical modelling of stepped helical cooling channels

The automotive industry is in the midst of a radical change of propulsion technology to meet the increasingly stringent limits on emissions and fuel consumption. Electric and hybrid power-trains are progressively replacing their internal combustion counterparts, as they are more efficient, especially in transient operation. In electric and hybrid vehicles effective cooling system operation is of utmost importance as it influences directly the efficiency and power density levels achievable by the power train. Thus, accurate analyses are needed to maximize the thermal performance of these systems. In this work an electric motor cooling jacket, that features a stepped helical geometry, is studied by means of CFD, with a particular focus on the head losses. The periodicity of the cooling channels geometry along the helical development is exploited to reduce the computational domain to a basic periodic module. The flow field is determined by applying a 3D Finite Volume approach, and numerical solutions are obtained by means of a validated incompressible solver. Novel boundary conditions are purposely developed to allow for the coupling of the inlet and outlet patches, which are roto-translated with respect to each other. The sensitivity of integral results on friction losses, with respect to the number of periodic modules included in the model, is investigated. The developed numerical model is employed to obtain a suitable correlation for the equivalent Darcy friction factor as a function of the Reynolds number only. Finally, a first estimation of the total head losses is obtained by using the Darcy Weisbach formula along with the aforementioned friction factor correlation.

Influence of impingement jet designs on solar air collector performance

The present work shows the impact of jet shapes and absorber plate spacing on the performance of heat transfer and pressure drop in solar air collectors experimentally. Absorber wall temperature, outlet temperature, useful heat gain, Nusselt number, friction factor, and thermal-hydraulic performance (THP) are the parameters under investigation. The experiment is conducted at heat fluxes of 900 W/m2 and 1000 W/m2, and Reynolds numbers ranging from 3000 to 19000. The results indicate that, in comparison to the Nusselt numbers for square and triangular jets, the Nusselt number for the circular jet is greater by 11.64% and 18.94%, respectively. The average useful heat gain of the circular jet is 6.45% higher than that of the square jet and 15.19% higher than that of the triangular jet. The maximum useful heat gain is provided by lower absorber plate spacing values. When the ratio of absorber plate spacing to jet diameter is 3.3, the THP for circular and triangular jets is 0.96 and 1.04, respectively. As a function of the geometrical and flow characteristics, the jet's Nusselt number and friction factor correlations are proposed, which forecast the current experimental findings.

Experimental investigation on comprehensive thermal-hydraulic performance of supercritical CO2 in a NACA 0020 airfoil fin printed circuit heat exchanger

Printed circuit heat exchanger (PCHE) is a promising compact heat exchanger for supercritical CO2 power conversion systems. Among the channel shapes of PCHE, an airfoil fin channel was considered for the high thermal-hydraulic performance of the PCHE. However, quantitative experimental evaluation of the thermal-hydraulic performance between the optimized airfoil fin and the wavy channel (commercially utilized channel shape) has not been performed. Therefore, in this study, to compare the performance according to channel shape, experiments on the optimized arrangement of airfoil fin PCHE (NACA 0020 airfoil fin with non-dimensional arrangement parameters, staggered number 1.0, horizontal number 2.0, and vertical number 1.8) and wavy PCHE (120° bending angle) were conducted. The experimental conditions of supercritical CO2 were temperatures ranging from 70°C (inlet) to 40.5°C (outlet) with pressures varying from 7.5 to 8.5 MPa. To reflect the real etched shape of airfoil fin channel, the real shape of airfoil fin was measured by using optical 3-Dimensional scanner. And hydraulic diameter was calculated based on measured information of real etched airfoil fin shape. The pressure drop of the airfoil fin PCHE was one-fifth of that of the wavy PCHE with the same total heat transfer rate per unit volume. New empirical correlations for the friction factor and Nusselt number of the airfoil fin PCHE were proposed based on the experimental data for the precooler design in the supercritical CO2 Brayton cycle. A friction factor correlation with maximum deviations of ±5.04 % and Nusselt number correlation with maximum deviations of ±14.0 % were proposed.

Combined effects of inlet conditions and assembly accuracy on Nusselt and friction factors of plate heat exchangers

From 1920's on plate heat exchangers (PHE) became a successful industrial solution regarding energy conversion owing to their compactness and efficiency. Motivated by a well-organized assembly concept, the gasket plate heat exchanger (GPHE) grew into the most common PHE design. One century later PHE dimensioning is still a challenge: application of divergent Nusselt and friction factor correlations found in the literature yield significant differences on heat exchanger sizing and pumping power. In this work, the effects of inlet conditions and plate's features on the GPHE thermal-flow performance are investigated, since they affect the channel flow geometry. Furthermore, the effect of a modified tightening distance, which scales with typical measurement system bias, on the exchanger performance is likewise assessed. No systematic study was performed that considered the combined effects of inlet conditions and assembly accuracy on friction factors and Nusselt numbers for GPHEs. The present work aims at filling this gap. Experiments in GPHEs occurred with the inlet pressure difference between branches ranging from −1.5 to 1.5 bar, three plate thicknesses, two chevron angles, corrugation aspect ratios, plate materials and tightening distances, for Reynolds numbers ranging from 900 to 10,000.

Condensation Performance of Symmetrical and Parallel Capsule Plate Heat Exchangers

Condensation characteristics of symmetrical and parallel capsule plate heat exchangers were experimentally investigated in this article. Plate heat exchangers with parallel capsule corrugation, symmetrical capsule corrugation, and chevron-type corrugation are manufactured as the test sections, each containing 41 plates. Pure steam and water are the hot and cold fluids, respectively. The experiments covered a range of equivalent Reynolds number from 9,000 to 25,000, mass flux of condensing fluid from to 18 to 49 kg/(m2·s), liquid Prandtl number from 1.37 to 1.71, average vapor quality from 0.5 to 0.7, and condensation pressure from 110 to 240 kPa. The correlations of condensation heat transfer coefficient and friction factor of the symmetrical and parallel capsule plate heat exchangers are developed. Compared with chevron-type plate heat exchangers, capsule plate heat exchangers show low friction pressure drop, and 33% higher energy efficiency index for condensation flow and heat transfer. Specifically, the energy efficiency index of the symmetrical capsule plate heat exchanger is 8.6% higher than that of the parallel capsule plate heat exchanger, indicating the superiority of counter-rotating longitudinal vortices over co-rotating longitudinal vortices in condensation, similar to what is observed in single-phase flow and heat transfer.

Study of the Thermal-Hydraulic Characteristics of a Printed Circuit Heat Exchanger Using a Novel Iterative Inversion Method Combined with Genetic Algorithm

Printed circuit heat exchangers are getting more and more applications in various energy systems. Detailed data monitoring is essential to understand their operation situations in real time. Nevertheless, the commonly monitored parameters are inadequate to evaluate the local flow and heat transfer characteristics when the fluid undergoes an obvious property variation in the channel. In this work, a measurement system for printed circuit heat exchangers similar to those in industrial applications was set up to study the thermal-hydraulic characteristics of supercritical CO2 with non-linear physical properties. The experimental results show that the heat transfer coefficient can be increased by 82.9–109.6% when the mass flow rate increases from 0.15 to 0.42 kg/s. By comparison, the heat transfer coefficient can be increased by 70.7% when the fluid state approaches the critical point. A novel iterative inversion method was proposed to deduce the coefficients of the heat transfer and friction factor correlations based on the collected fundamental parameters. The deviations of the heat transfer rate and friction coefficient between the measured data and the predicted results by the derived correlations were both within 10%, indicating the feasibility and reliability of the inversion method.

Advances in triple tube heat exchangers regarding heat transfer characteristics of single and two-phase flows in comparison to double tube heat exchangers part 2

Abstract Triple concentric-tube heat exchangers are often used in a variety of industries, including HVAC, food and beverage manufacturing, and chemical processing. They may also be utilized in applications requiring thermal homogeneity, such as food and pharmaceutical production. They are appropriate for a number of applications since they may be constructed to withstand a range of temperatures and pressures. The purpose of this study is to examine the most current papers, covering single- and two-phase flows having pure and nanofluids with a particular emphasis on the heat transfer and hydrodynamic properties. The use of advanced surfaces improves heat transfer with respect to smooth surfaces, and the use of nanofluids has a positive influence on heat transfer characteristics with the increase in nanoparticle volume concentration since nanoparticles rise thermal conductivity, heat transfer area, and Brownian motion. The practical calculation methodologies, proposed correlations for calculating the Nusselt number and friction factor in triple ones are shown. There are insufficient studies to comment on pressure drop features, and correlations for Nusselt numbers and friction factors that are only known for single-phase flows. The research indicates that the heat transfer characteristics of triple concentric-tube heat exchangers surpass those of double tube heat exchangers. Important progress is supposed to occur for the design and utilization of triple ones as a substitute for double ones soon. Finally, there are a limited number of experimental two-phase flow studies in triple ones. It is essential to work on this topic to meet the important lack in open sources.

Model-based battery thermal parameter optimization using symbolic regression

Lithium-ion battery packs are commonly used in electromobility and distributed energy storage. However, keeping both cell temperature and inter-cell temperature differences within operating ranges is important to avoid a negative impact on performance and lifespan. For this reason, modeling the thermal behavior of battery packs in different operating conditions is crucial for both design and practical use.In this work, we optimize the parameters of a battery thermal model using a symbolic regression method based on evolutionary algorithms. We obtain power-type expressions for the drag coefficient, friction factor, and heat transfer correlation (Nusselt number), as a function of the Reynolds number and the cell spacing factor, plus the Prandtl number in the case of the Nusselt number. The model is adjusted with CFD simulations of battery modules containing up to 102 cells to obtain the steady-state temperature distribution. Compared to CFD simulations, the proposed model gets a mean absolute percentage error of 2.39 % in estimating the temperature in a 53-cell battery pack. The adjusted parametric thermal model is validated with experimental data for cooling down a battery pack and a single cell, obtaining a mean absolute percentage error of 1.26 % and 4.68 %, respectively, in estimating the dynamic temperature balance.The adjusted parametric thermal model and the mathematical expressions obtained for the drag coefficient, friction factor, and Nusselt number, can be useful for designing battery thermal management systems in electromobility and distributed energy storage.

Neural net-based surrogate square pin fin correlations for thermal-fluid design optimization under developing flow conditions

Heat exchangers and cold plates are widely used for thermal management of electronic devices and in energy storage applications. Accurate prediction of the thermal-fluid transport performance of heat transfer surfaces is crucial for design optimization of these thermal management components. Microscale pin fin structures are commonly employed for enhancement of convection heat transfer. Previous studies have focused on fully developed flow through circular and square pin fins in staggered arrangements, leaving a gap in predictive correlations available for in-line arrangements of square pin fins with consideration of hydrodynamic and thermal developing effects. This study aims to investigate and develop robust friction factor (f) and Nusselt number (Nu) correlations for developing flow through in-line square microscale pin fin structures. Traditional empirical correlations are highly geometry dependent and assume functional forms that could introduce inaccuracies. On the other hand, accurate data may be available at specific points, but continuous evaluation of the function value and derivatives as needed for design optimization processes is difficult. To overcome these limitations, artificial neural network (ANN)-based surrogate models are developed to provide accurate and continuous-valued correlations. The proposed models, trained on numerically simulated data using water as the working fluid, provide accurate predictions of f and Nu, with a near exact match to the training data as well as on unseen testing data. Furthermore, the outputs of the ANNs are inspected to propose new analytical correlations to estimate the hydrodynamic and thermal entrance lengths for flow through square pin fin arrays. The ML models are also shown to be useable for fluids other than water, employing physics-based, Prandtl-number-dependent scaling relations. These generalized ML models have promise to significantly reduce computation cost in the design optimization of thermal management components having pin fin structures for enhanced convection, but without loss in prediction accuracy associated with alternative reduced-order correlations.