Adaptive neuro-fuzzy modeling of transient heat transfer in circular duct air flow

✍ Scribed by Abdulsamet Hasiloglu; Mehmet Yilmaz; Omer Comakli; İsmail Ekmekci

• Publisher: Elsevier Science
• Year: 2004
• Tongue: French
• Weight: 475 KB
• Volume: 43
• Category: Article
• ISSN: 1290-0729
• DOI: 10.1016/j.ijthermalsci.2004.01.010

✦ Synopsis

The aim of this study is to demonstrate the usefulness of an adaptive neuro-fuzzy inference system (ANFIS) for the prediction of transient heat transfer. An ANFIS has been applied for the transient heat transfer in thermally and simultaneously developing circular duct flow, subjected to a sinusoidally varying inlet temperature. The experiments covered Reynolds numbers in the 2528 Re 4265 range and inlet heat input in the 0.01 β 0.96 Hz frequency range. The accuracy of predictions and the adaptability of the ANFIS were examined, and good predictions were achieved for the temperature amplitudes of the transient heat transfer in thermally and simultaneously developing circular duct flow. The results show that the neuro-fuzzy can be used for modeling transient heat transfer in ducts. The results obtained with the ANFIS are also compared to those of a multiple linear regression and a neural network with a multi-layered feed-forward backpropagation algorithm.