Estimation of sludge volume index (SVI) using bright field activated sludge images

Abstract

Image processing and analysis is a potential tool for monitoring of activated sludge wastewater treatment plant. One of the important parameters to track the performance of activated sludge plant is sludge volume index (SVI). In this paper, image analysis based modeling is used to estimate the sludge volume index. Bright field microscopic images of activated sludge were segmented by integrating four algorithms to skim any possible failures of any of them. The morphological parameters for activated sludge flocs have been extracted from the segmented images. Seven classes were identified for image analysis parameters with respect to range of equivalent diameter of activated sludge flocs. The process resulted into 134 image analysis parameters and seven classes. The feature selection is done by two procedures: correlation method and stepwise linear regression. The stepwise linear regression is automated process which selected 6 parameters with adjusted correlation of 95.1%. The results showed that image analysis based modeling with as small as six parameters can be used to predict the sludge volume index. Finally, three out of seven classes are identified which can contribute to the estimation of SVI.