摘要
Experimental data of the continuous evolution of fluid flow characteristics in a dump combustor is very useful and essential for better and optimum designs of gas turbine combustors and ramjet engines. Unfortunately, experimental techniques such as 2D and/or 3D LDV （Laser Doppler Velocimetry） measurements provide only limited discrete information at given points; especially, for the cases of complex flows such as dump combustor swirling flows. For this type of flows, usual numerical interpolating schemes appear to be unsuitable. Recently, neural networks have emerged as viable means of expanding a finite data set of experimental measurements to enhance better understanding of a particular complex phenomenon. This study showed that generalized feed forward network is suitable for the prediction of turbulent swirling flow characteristics in a model dump combustor. These techniques are proposed for optimum designs of dump combustors and ramjet engines.
