Image processing for flame monitoring in power station boilers

Abstract

The quality of combustion in power station boiler plays an important role in minimizing the flue gas emissions. In this research work, various intelligent schemes are proposed to infer the flue gas emissions by monitoring the flame colour at the furnace of the boiler. Limited work is reported in the literature regarding the flue gas emissions. Different schemes or algorithms have been developed by various researchers to infer the flue gas emissions like CO, CO2, and SOx etc. As a part of the present research work, integrated intelligent schemes are proposed to infer combustion quality as well as flue gas emissions based on the colour of the furnace flame. The work attempted involves capturing the flame video using an infrared camera. The flame video is then split up into the frames for further analysis. The Cannon video splitter is used for progressive extraction of the flame images from the video. The various features like average intensity, orientation, area of the high temperature flame, centroid, standard deviation, median, mode etc., were extracted. The conventional classification and clustering techniques include the Euclidean distance classifier (L2 norm classifier) Bayesian classifier and K-means clustering. The major contribution of this research work is to develop an indigenous online intelligent scheme for inferring the process parameters and gas emissions in the centralized control room directly from the combustion chamber of a boiler. Hence this method offers an economical intelligent feed forward scheme to minimize the flue gas emissions based on the colour of the furnace flame. Moreover in the existing setup, measurements of various flue gases are inferred from the samples that are collected periodically or by using gas analyzers (expensive and difficult to maintain). The proposed algorithm can be integrated with the Distributed Control System (DCS) that is used for automation of the power plant. The inferred parameters can be displayed in the centralized control room a (cost effective solution). newline