4.6 Article

Estimation of forced heat convection in a rectangular channel with curved-winglet vortex generator: A machine learning approach

Related references

Note: Only part of the references are listed.
Article Thermodynamics

Numerical investigation on turbulent flow and heat transfer characteristics of ferro-nanofluid flowing in dimpled tube under magnetic field effect

Mehmet Gurdal et al.

Summary: This study is the first numerical study to comprehensively determine the effect of using nanofluid, MagnetoHydroDynamic (MHD), and dimpled fins tube together. The results show that the Nusselt number increases with increasing Reynolds number and decreasing pitch ratio, with the dimple geometry type of P/d = 7.50 being the most efficient type. The highest Nusselt number increment has been obtained for the highest magnetic field intensity and the highest PEC value was obtained for specific parameters, indicating the potential for highly efficient thermal energy storage devices.

APPLIED THERMAL ENGINEERING (2022)

Article Thermodynamics

Novel self-join winglet vortex generators for enhanced heat transfer of turbulent airflow in round tubes

Nianben Zheng et al.

Summary: Novel self-join winglet vortex generators were proposed for enhanced heat transfer of turbulent airflow in round tubes, generating longitudinal swirl flows to improve air mixing and reduce thermal field interactions. Experimental tests showed high capability in enhancing heat transfer, albeit with accompanying pressure loss. By adjusting the winglets' included angle and height ratio, thermal performance can be optimized.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2022)

Article Thermodynamics

Consolidated modeling and prediction of heat transfer coefficients for saturated flow boiling in mini/micro-channels using machine learning methods

Ari Bard et al.

Summary: This study accurately predicts the heat transfer coefficient during flow boiling in mini/micro-channels using data science methods. Feature analysis and machine learning algorithms are utilized to select and combine appropriate input values, and compared with existing correlations. The results show that the support vector machine model performs the best.

APPLIED THERMAL ENGINEERING (2022)

Article Thermodynamics

Experimental study on the heat transfer enhancement in a rectangular channel with curved winglets

Adnan Berber et al.

Summary: The use of curved winglet vortex generator inserts (CWVGs) in a rectangular channel significantly increases the Nusselt number while also increasing friction factor. The heat transfer enhancement is more noticeable with larger attack angles of the CWVG inserts. Performance evaluation criteria (PEC) also increase with higher attack angles.

EXPERIMENTAL HEAT TRANSFER (2022)

Article Thermodynamics

Flow and thermal characteristics produced by a curved rectangular winglet vortex generator in a channel

Hemant Naik et al.

Summary: Three-dimensional numerical computations were conducted to investigate the performance of curved winglets mounted on a rectangular channel. The study examined the influence of arc angle variation on flow and thermal characteristics, as well as the heat transfer enhancement and pressure loss of the curved winglets. The overall thermohydraulic performance was assessed using various parameters, including the surface-averaged Nusselt number and thermal performance factor. Additionally, investigations of secondary flow intensity provided valuable insights into the heat transfer mechanism.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2022)

Article Thermodynamics

Implementation of hybrid nanofluid flowing in dimpled tube subjected to magnetic field

Mehmet Gurdal et al.

Summary: This study investigated the effect of hybrid nanofluid flow in a dimpled tube under the influence of a magnetic field on convective heat transfer. It is concluded that implementing a magnetic field enhances the Nusselt number and friction factor in the flow. The results show that the hybrid nanofluid flow in the dimpled tube with a magnetic field of 0.3 T can increase the Nusselt number by 11.87% and the friction factor by 6.19% numerically, and by 174.65% and 169.4% experimentally compared to the case without a magnetic field.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2022)

Article Thermodynamics

A Comparative Study of Multiple Regression and Machine Learning Techniques for Prediction of Nanofluid Heat Transfer

Eyup Kocak et al.

Summary: This article introduces and discusses the prediction power of multiple regression, artificial neural network (ANN), and adaptive neuro-fuzzy interface system (ANFIS) methods in predicting the forced convection heat transfer characteristics of a turbulent nanofluid flow. The results show that ANFIS is a powerful tool with a prediction accuracy of R-2=0.9987.

JOURNAL OF THERMAL SCIENCE AND ENGINEERING APPLICATIONS (2022)

Article Thermodynamics

Inverse artificial neural network control design for a double tube heat exchanger

J. Garcia-Morales et al.

Summary: This work focused on a novel non-linear control approach for regulating the output cold water temperature of a double tube heat exchanger. The approach utilizes an inverse artificial neural network (ANNi) and an integral control law to achieve temperature regulation. Experimental results demonstrated that the proposed control scheme exhibits good reference tracking, fast settling time, and low overshoot.

CASE STUDIES IN THERMAL ENGINEERING (2022)

Article Engineering, Multidisciplinary

Investigation on two-phase fluid mixture flow, heat transfer and entropy generation of a non-Newtonian water-CMC/CuO nanofluid inside a twisted tube with variable twist pitch: Numerical and evolutionary machine learning simulation

Amin Shahsavar et al.

Summary: A 3-D numerical investigation was conducted to assess the hydrothermal behavior and entropy generation features of a non-Newtonian water-CMC/CuO nanofluid flow in a twisted tube with a square cross-section. The effect of variable twist pitch on the overall performance of the nanofluid was evaluated, and a gene expression programming approach was used to simulate the performance under different twist pitches.

ENGINEERING ANALYSIS WITH BOUNDARY ELEMENTS (2022)

Article Nanoscience & Nanotechnology

A Smart Model for the Prediction of Heat Transfer Coefficient during Flow Boiling of Nanofluids in Horizontal Tube

A. Bouali et al.

Summary: This study aimed to improve the accuracy and validity of predicting the heat transfer coefficient in flow boiling of different water-based nanofluids in a horizontal tube. An artificial neural network model was developed and validated using experimental data, showing better accuracy than existing correlations.

NANO HYBRIDS AND COMPOSITES (2022)

Article Thermodynamics

A deep learning method for estimating thermal boundary condition parameters in transient inverse heat transfer problem

Feiding Zhu et al.

Summary: This study proposed a simple method based on deep learning to estimate thermal boundary condition parameters in the transient inverse heat transfer problem. By combining convolutional neural network (CNN) and long short-term memory networks (LSTM), real-time prediction of multiple time-varying parameters can be achieved. Experimental results showed that the proposed model outperformed standalone models in estimating multiple time-varying parameters.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2022)

Proceedings Paper Materials Science, Multidisciplinary

Artificial neural network (ANN) modelling for the thermal performance of bio fluids

S. Selvalakshmi et al.

Summary: This study uses Artificial Neural Network modelling to predict the thermal characteristics of bio fluids and compares five different learning algorithms. The results suggest that the ANN model constructed using the LM approach is one of the most accurate for projecting bio fluid thermal performance.

MATERIALS TODAY-PROCEEDINGS (2022)

Article Green & Sustainable Science & Technology

Recent trends on nanofluid heat transfer machine learning research applied to renewable energy

Ting Ma et al.

Summary: Nanofluids have been gaining attention in the research and development of renewable and sustainable energy systems, as the addition of solid nanoparticles with high thermal conductivity can enhance heat transfer. However, the complex nature of nanofluids, including nonlinear effects and contradictory results, presents challenges. Machine learning methods show promise in predicting thermophysical properties and evaluating performance in heat transfer research.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Engineering, Chemical

A unique thermal conductivity model (ANN) for nanofluid based on experimental study

Ashutosh Pare et al.

Summary: The study utilized artificial neural networks to simulate and predict the effects of nanoparticle concentration and temperature on the thermal conductivity of nanofluids, with the final results showing good agreement with experimental data.

POWDER TECHNOLOGY (2021)

Article Thermodynamics

Effect of shape and distribution of pin-fins on the flow and heat transfer characteristics in the rectangular cooling channel

Wei Jin et al.

Summary: Numerical studies revealed that teardrop and NACA pin-fins exhibit better performance in heat transfer enhancement for turbine blade trailing edge compared to circular, elliptic, oblong, and lancet pin-fins. Under certain spanwise and streamwise spacings, NACA pin-fins show superior cooling effects in the trailing edge of turbine blades.

INTERNATIONAL JOURNAL OF THERMAL SCIENCES (2021)

Article Automation & Control Systems

A physics-informed machine learning approach for solving heat transfer equation in advanced manufacturing and engineering applications

Navid Zobeiry et al.

Summary: A physics-informed neural network is developed to solve conductive heat transfer PDEs with convective boundary conditions, improving the speed and accuracy of thermal analysis in manufacturing and engineering applications. By using physics-informed activation functions, heat transfer beyond training zone can be accurately predicted, making it a useful tool for real-time evaluation of thermal responses in a wide range of scenarios.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2021)

Article Engineering, Chemical

A machine learning approach to the prediction of transport and thermodynamic processes in multiphysics systems-heat transfer in a hybrid nanofluid flow in porous media

Rasool Alizadeh et al.

Summary: This paper presents a novel approach based on machine learning techniques for predicting transport behaviors of complex multiphysics systems, resulting in significant reductions in computational time and cost. The study focuses on a hybrid nanofluid flow over a blunt object in porous media, including mixed convection, entropy generation, local thermal non-equilibrium, and nonlinear thermal radiation. The SVR model is used to approximate various functions, while the PSO meta-heuristic algorithm is applied for proposing correlations, allowing for quantitative evaluation of variables' contributions.

JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS (2021)

Article Thermodynamics

Prediction of heat transfer enhancement of delta-wing tape inserts using artificial neural network

Mohammed Zafar Ali Khan et al.

Summary: The study uses artificial neural networks to predict the efficiency of a double-pipe heat exchanger, showing that the model can accurately predict experimental data with a low mean square error. The neural network method is also effective in predicting thermal parameters with low variability and high precision.

CASE STUDIES IN THERMAL ENGINEERING (2021)

Article Thermodynamics

Characterization of heat transfer and artificial neural networks prediction on overall performance index of a channel installed with arc-shaped baffle turbulators

P. Promvonge et al.

Summary: The influences of baffle pitch ratio (p/w) and attached angle of arc-shaped baffles (AB) on the overall performance index (OPI) of a channel were carefully studied, with significant impact observed. Additionally, an artificial neural network (ANN) model proved to be effective in predicting the OPI of the channel.

CASE STUDIES IN THERMAL ENGINEERING (2021)

Article Energy & Fuels

A novel comparative investigation of the effect of the number of neurons on the predictive performance of the artificial neural network: An experimental study on the thermal conductivity of ZrO2 nanofluid

Andac Batur Colak

Summary: This study investigated the impact of the number of neurons on the predictive performance of artificial neural networks using experimental data. The results showed that increasing the number of neurons could improve performance, but adding too many neurons does not necessarily enhance predictive capabilities.

INTERNATIONAL JOURNAL OF ENERGY RESEARCH (2021)

Article Engineering, Chemical

Experimental studies and ANN predictions on the thermal properties of TiO2-Ag hybrid nanofluids: Consideration of temperature, particle loading, ultrasonication and storage time

Weikai Ji et al.

Summary: The preparation, stability, thermal properties, and prediction of TiO2-Ag hybrid nanofluids were studied in this research. Ultrasonication treatment was found to alleviate the sedimentation of nanofluids, and artificial neural networks were established to effectively predict the thermal properties of nanofluids, saving experiment time and cost.

POWDER TECHNOLOGY (2021)

Article Energy & Fuels

Experimentally validated 3D simulation and performance optimization of a solar air duct with modified conical vortex generators

Parag Jyoti Bezbaruah et al.

Summary: The study focuses on optimizing the geometrical parameters of a solar air heater with modified conical vortex generators, aiming to enhance the thermohydraulic performance. Experimentally validated numerical simulations were utilized to optimize the parameters of the vortex generators, resulting in the development of correlation equations for Nusselt number and friction factor. The maximum Nusselt number of 142.4 was observed for a relative pitch ratio of 8 and a relative vortex generator height ratio of 0.34.

SOLAR ENERGY (2021)

Article Thermodynamics

EXPERIMENTAL ANALYSIS WITH SPECIFIC HEAT OF WATER-BASED ZIRCONIUM OXIDE NANOFLUID ON THE EFFECT OF TRAINING ALGORITHM ON PREDICTIVE PERFORMANCE OF ARTIFICIAL NEURAL NETWORK

Andac Batur Colak

Summary: This study investigated the impact of different training algorithms on the prediction performance of artificial neural networks, finding that the network designed with Bayesian regularization had the highest performance, while the one developed with scaled conjugate gradient had the lowest.

HEAT TRANSFER RESEARCH (2021)

Article Thermodynamics

Machine learning for heat transfer correlations

Beomjin Kwon et al.

INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER (2020)

Article Thermodynamics

Numerical simulation on heat transfer characteristics of rectangular vortex generators with a hole

Zhimin Han et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2018)

Article Thermodynamics

Magnetic field effect on the nanofluids convective heat transfer and pressure drop in the spirally coiled tubes

P. Naphon et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2017)

Article Thermodynamics

Designing artificial neural network on thermal conductivity of Al2O3-water-EG (60-40%) nanofluid using experimental data

Mohammad Hemmat Esfe et al.

JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY (2016)

Article Computer Science, Interdisciplinary Applications

Control of secondary flow loss in turbine cascade by streamwise vortex

Qi Lei et al.

COMPUTERS & FLUIDS (2012)

Article Thermodynamics

Modeling of heat transfer coefficient in the furnace of CFB boilers by artificial neural network approach

Jaroslaw Krzywanski et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2012)

Article Thermodynamics

Experimental investigation of performance of hot cascade type Ranque-Hilsch vortex tube and exergy analysis

K. Dincer et al.

INTERNATIONAL JOURNAL OF REFRIGERATION-REVUE INTERNATIONALE DU FROID (2011)

Article Computer Science, Artificial Intelligence

Using the artificial neural network model for modeling the performance of the counter flow vortex tube

Onuralp Uluer et al.

EXPERT SYSTEMS WITH APPLICATIONS (2009)

Article Energy & Fuels

ANN modeling of compact heat exchangers

Kemal Ermis

INTERNATIONAL JOURNAL OF ENERGY RESEARCH (2008)

Article Thermodynamics

Correlating heat transfer and friction in helically-finned tubes using artificial neural networks

Gregory J. Zdaniuk et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2007)

Article Thermodynamics

Dynamic prediction and control of heat exchangers using artificial neural networks

G Díaz et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2001)

Article Thermodynamics

Neural network analysis of fin-tube refrigerating heat exchanger with limited experimental data

A Pacheco-Vega et al.

INTERNATIONAL JOURNAL OF HEAT AND MASS TRANSFER (2001)