Free Vortex Turbulent Swirling Flow Reconstruction Using a Neural Network

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 LDV measurements provide only limited discrete information at given points; especially, for the cases of complex flows such as free vortex 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 artificial neural networks are suitable for the prediction of free vortex turbulent swirling flow characteristics in a model dump combustor. These techniques are proposed for optimum designs of dump combustors and ramjet engines.

Predictions of Turbulence Intensity in a Combustor Model Using Neural Network Analysis

Predictions of turbulence intensity and continuous evolution of fluid flow characteristics in a combustor model are useful and essential for better and optimum design of gas turbine combustors. Many experimental techniques such as Laser Doppler Velocimetry (LDV) 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 flow, usual numerical interpolating schemes appear to be unsuitable. Neural Network Analysis (ANN) is proposed and the results are presented in this paper and are compared with the experimental data used for training purposes. This pilot study showed that artificial neural network is an appropriate method for predicting swirl flow characteristics in a model of a dump combustor. These techniques are proposed for better designs and optimization of dump combustors.