Application of Neural Network Technique to Combustion Spray Dynamics Analysis

This paper presents results from several analytical and empirical combustion process investigations using data mining tools and techniques. An artificial neural network was used to analyze the performance of data in phase Doppler anemometry (PDA) and particle image velocimetry (PIV) which can measure droplet size and velocity in combustion spray. The dataset used for the analysis was obtained from measurements in a practical combustion burner. The preliminary results are discussed, and improvements to the neural network architecture are suggested. The inclusion of additional input variables and modified data pre-processing improved the results of the classification process, providing a higher level of accuracy and narrower ranges of classified droplet sizes.

[1]  Christopher R. Westphal,et al.  Data Mining Solutions: Methods and Tools for Solving Real-World Problems , 1998 .

[2]  Yuji Ikeda,et al.  Size-Classified Droplet Dynamics and its Slip Velocity Variation of Air-Assist Injector Spray , 1997 .

[3]  G. D. Roy,et al.  Propulsion Combustion: Fuels to Emissions , 1999 .

[4]  Guo-Wei Wei,et al.  A new algorithm for solving some mechanical problems , 2001 .

[5]  Michael J. A. Berry,et al.  Data mining techniques - for marketing, sales, and customer support , 1997, Wiley computer publishing.

[6]  Ryoji Homma,et al.  Combustion process optimization by genetic algorithms: Reduction of NO2 emission via optimal postflame process , 2000 .

[7]  Michael J. A. Berry,et al.  Mastering Data Mining: The Art and Science of Customer Relationship Management , 1999 .

[8]  A. Vogel,et al.  Modern Optical Techniques in Fluid Mechanics , 1984 .

[9]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[10]  Robert Groth,et al.  Data Mining: Building Competitive Advantage , 1999 .

[11]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[12]  Haojiang Wu,et al.  Intelligent identification system of flow regime of oil–gas–water multiphase flow , 2001 .

[13]  Thomas S. Huang,et al.  Extracting 3D Vortices in Turbulent Fluid Flow , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  M. G. Allen,et al.  An imaging neural network combustion control system for utility boiler applications , 1993 .

[15]  Yuji Ikeda,et al.  Multi-intensity-layer particle-image velocimetry for spray measurement , 2000 .

[16]  Norberto Fueyo,et al.  Modelling the Temporal Evolution of a Reduced Combustion Chemical System With an Artificial Neural Network , 1998 .

[17]  Yoshikazu Nakajima,et al.  Acquisition of Symbolic Description from Flow Fields: A New Approach Based on a Fluid Model , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  R. Adrian.  Particle-Imaging Techniques for Experimental Fluid Mechanics , 1991 .