| description abstract | In much of the public literature on pinfin heat transfer, the Nusselt number is presented as a function of Reynolds number using a powerlaw correlation. Powerlaw correlations typically have an accuracy of 20% while the experimental uncertainty of such measurements is typically between 5% and 10%. Additionally, the use of powerlaw correlations may require many sets of empirical constants to fully characterize heat transfer for different geometrical arrangements. In the present work, artificial neural networks were used to predict heat transfer as a function of streamwise spacing, spanwise spacing, pinfin height, Reynolds number, and row position. When predicting experimental heat transfer data, the neural network was able to predict 73% of arrayaveraged heat transfer data to within 10% accuracy while published powerlaw correlations predicted 48% of the data to within 10% accuracy. Similarly, the neural network predicted 81% of rowaveraged data to within 10% accuracy while 52% of the data was predicted to within 10% accuracy using powerlaw correlations. The present work shows that firstorder heat transfer predictions may be simplified by using a single neural network model rather than combining or interpolating between powerlaw correlations. Furthermore, the neural network may be expanded to include additional pinfin features of interest such as fillets, duct rotation, pin shape, pin inclination angle, and more making neural networks expandable and adaptable models for predicting pinfin heat transfer. | |
