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.