• Energy Research

Mixed convection phenomenon over radiant cooled surfaces with displacement ventilation in living environments is becoming a popular issue due to the airborne viruses and energy economy. Artificial neural networks are one of the machine learning methods that are widely evaluated as an engineering tool. In the current study, heat transfer coefficients for a radiant wall cooling system coupled with mixed and forced convection have been predicted by a machine learning approach. This approach should be noted as a first experimental investigation couple with an artificial neural network analysis in the open sources in which mixed convection systems in real sized living environments is examined. Experimentally obtained heat transfer coefficients have been used in the development of the feed forward back propagation multi-layer perceptron network structure. So as to analyze the impact of the input factors on the prediction performance, two neural network structures with dissimilar input parameters such as various temperatures, velocities, and heat transfer rates have been developed. By means of feed forward back propagation multi-layer perceptron neural network algorithms, convection, radiation, and total heat transfer coefficients have been predicted using the experimentally acquired dataset including 35 data points belonging to the mixed and forced convection conditions. Training, validation, and test data groups include 70%, 15%, and 15% of the dataset, in turn. Training algorithm has been computed via LevenbergMarquardt one with 10 neurons in the hidden layer. The findings obtained from the computational solution have been evaluated as a result of the contrast with the target data with in the +/- 5% deviation band for all heat transfer coefficients. The performance factors have been computed and the estimation precision of the numerical models has been thoroughly examined.

This study examined a room with a surface of 1.8 × 1.8 × 2.85 (m) and a well-insulated floor (adiabatic condition) and examined the heat exchange from the side surfaces and ceiling. In this closed room, the heat transfer effects with radiation were investigated while bringing them to comfort conditions ranging from 30 (°C) air temperature to 20–24 (°C). A computer with a power of 25 (W) as a source of heat, a person with an average metabolic activity of 50–70 (W) and a table were found in this closed room. In this study, the cooling of the room from the floor, ceiling and air conditioner was inquired while the computer was running, in a closed area under the specified heat transfer conditions. As a scenario, the air exchange coefficient was modeled via Ansys Fluent, fed with air of 15 (°C) with 1, 3, 5, 10, 15 air. In addition, the comfort values of the human wrist (the distance of 0.1 m) and the shoulder (the distance of 1.1 m) were researched according to ASHRAE-55. The obtained results were analyzed as a comparison of ACH results, and the comfort parameter values were analyzed by reading the sections taken from the ankle shoulder level and velocity, temperature, values according to ANSI/ASHRAE-55. The relative humidity was 50% in the room, while the metabolic activity is 1.2 (met). These parameters corresponded to the sitting position; the clothing effect was found to be 0.67 (clo). The novelty of this study encourages the production of the ideal CFD analysis on the thermal comfort conditions of a cooled room, the task of engineering.

Abstract Analytical solutions may not always be applicable in the calculation of the turbulent flow convective heat transfer rate, unlike the radiative and the conductive ones. Therefore, experimental correlations on convective heat transfer coefficient have been developed in enclosures. Convective heat transfer in a cavity is classified as natural, forced, and mixed convection on the basis of the driving forces (buoyant or mechanical). In recent years, there has been an increasing interest in the mixed convection, particularly in cooled ceiling – displacement ventilation indoor applications. It seems this interest is tending to increase while contamination of viruses and energy saving are growing as health and environmental concerns worldwide. Hence, the reasons behind the interest in mixed convection applications have been investigated along the paper. This comparative study seeks to explain the progress of convective heat transfer at indoor applications by reviewing mostly experimental correlation studies in time. The mixed convection has not been widely studied experimentally in indoor applications in comparison to natural and forced convection. Therefore, this study is devoted to indicate this gap in the literature on this issue and it includes all convection types with a wide and up-to-date review, descriptions, explanations, and comparisons, as well. Moreover, almost all empirical correlations on the topic are given in tables in detail. It can be concluded that general correlations for mixed convection applications is needed. Correlations related to radiant floor cooling applications are nearly non-existent. Additionally, more experimental studies are required for various split air conditioner cases. These gaps in the literature are unveiled and comparison of applications with various convection types have been made as a first comparative study in the literature.