Prediction of post-dryout heat transfer in vertical annular channels using artificial neural network method

Experimental investigations on post-dryout heat transfer in 10×8.1, 10×7 and 0×6mm annular test sections have been carried out under low-pressure and low mass flow rate conditions. An Artificial Neural Network (ANN) was trained successfully based on the experimental data for predicting the average post-dryout Nusselt number. Based on the ANN, the effects of gap size, pressure, steam Reynolds number, Re_g, inlet quality, x, Prandtl number, (Pr_g)_w, and the ratio of heat flux of inner-tube to that of outer-tube, q_iq_o, on post-dryout heat transfer were analyzed, respectively. In present study, Nusselt number in annular channels with big gap size is larger than that in annular channels with small gap size. Nusselt number increases significantly in \.5mm and 2.0mm annular channels while it is almost constant in 0.95mm annular channel with increasing pressure or q₁q₀,. Nusselt number increases with Re _g in case of 0.95mm and 1.5mm gap sizes. However, Nusselt number in 2.0mm annular channel firstly increases and then decreases with increasing Re_g. Nusselt number decreases with increasing inlet quality under all three annular channels condition. Nusselt number decreases significantly with increasing (Pr_g)_w when (Pr_g)_w is less than 1.5. The changes of Nusselt number in \.5mm or 2.0mm annular channels are larger than that in 0.95mm annular channel.