| Autor: |
Bhalake, Suhas, Kale, Arati, Pawar, Prajwal, Salunkhe, Gayatri, Zade, Nishant |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| DOI: |
10.5281/zenodo.8024767 |
| Popis: |
This research article describes a statistical analysis of heat transfer by developing an artificial neural network-based machine learning model. Automotive heat removal levels are of high importance for maximizing fuel consumption. Current radiator designs are constrained by air-side impedance, and a large front field must meet the cooling requirements. There is enormous demand for powerful engines in smaller hood areas has caused a lack of heat dissipation in the vehicle radiators. As a prediction, exceptional radiators are modest enough to understand coolness and demonstrate great sensitivity to cooling capacity. Enhancement of heat transfer coefficient continues to be an important research area in various fields of engineering ranging from microelectronics to high powered automobiles. The initial effort in the present research study is to enhance the heat transfer coefficient in a vehicle radiator using nanofluids with high thermal conductivity. The world’s most abundant element ‘Carbon’ astoundingly exists in various structures and one such form is tube commonly known as Carbon Nanotubes (CNTs). Heat transfer enhancement in water and coolant-based systems with different concentrations of nano particles (carbon nanotubes) have been investigated from an engineering system perspective. One such system considered is a “SUZUKI (800CC) - CAR RADIATOR”, cooling circuit using different nanofluids to replace the conventional engine coolant. In the present study, the effect of nano-fluid heat transfer to enhance in water and coolant-based systems with multi walled carbon nanotubes has been investigated. The improvement of heat transfer when compared to water, coolant (water + ethylene glycol 60:40) and water with MWCNTS and coolant with MWCNTS has been studied. It has been observed that there is an enhancement of heat transfer up to 30% when coolant and CNTS are used as a cooling medium. An artificial neural network model is used for regression analysis to predict the heat transfer in terms of Nusselt number and thermohydraulic efficiency, and the results showed high prediction accuracies. The artificial neural network model is robust and precise and can be used by thermal system design engineers for predicting output variables. Two different models are trained based on the features of experimental data, which provide an estimation of experimental output based on user-defined input parameters. The models are evaluated to have an accuracy of 97.00% on unknown test data. These models will help the researchers working in heat transfer enhancement-based experiments to understand and predict the output. As a result, the time and cost of the experiments will reduce. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
