Paper Conference

Proceedings of eSim 2010: 6th Conference of IBPSA-Canada

     

PREDICTION OF LOCAL HEAT TRANSFER IN A VERTICAL CAVITY USING ARTIFICIAL NEURAL NETWORK

M. Ebrahim Poulad, D. Naylor, A. S. Fung

Abstract: A time-averaging technique was developed to measure the unsteady and turbulent free convection heat transfer in tall vertical enclosure using a Mach-Zehnder interferometer. The method used a combination of digital high speed camera and an interferometer to obtain the time-averaged heat transfer rates in the cavity. The measured values were used to train an Artificial Neural Network (ANN) algorithm to predict the local heat transfer. The time-averaged local Nusselt number is needed to study local phenomena, e.g. condensation in windows (Wright, 1998); (Abodahab & Muneer, Feb. 1998). Optical heat transfer measurements were made in a differentially heated vertical cavity with isothermal walls. The cavity widths (distance between the plates) were W = 12.7, 32.3, 40, and 56.2mm. The corresponding Rayleigh numbers were about 3x10 3 , 5x10 4 , 1x10 5 , 2.7x10 5 , respectively, and the enclosure aspect ratio (H/W) ranged from A=18 to 76. The fluid was air and the temperature differential was about 15 K for all measurements. Alyuda NeuroIntelligence 2.2 (577) software (Alyuda Research Inc., 2003) is used to generate solutions for the time-averaged local Nusselt number in the cavity based on the experimental data. Here, feed-forward architecture and trained by Levenberg-Marquardt (LM) algorithm is adopted. The ANN is designed to suit the present system which has 4 to 13 inputs and 1 output. The network predictions are found to be in a good agreement with the experimental observed value of local Nusselt number.
Pages: 193 - 200
Paper:
esim2010_7A2_193_200