Clean Coal Technology using Inventive Materials for Monitoring SO2 Emissions in Smart Power Plants.

The main objective of this work is to provide a hazard free environment for power generation in thermal power plants. Estimation of Sulphur Dioxide (SO2) emissions from flame images in thermal and gas turbine power plants is of great importance in the domain of image processing. The primary objective in detection, recognition and understanding of combustion conditions offers a feed forward control action for minimizing flue gas emissions. In this work, soft sensors using feed forward neural network trained with Back Propagation Algorithm (BPA) and Particle Swarm Optimization (PSO) are used for flame image classification. The solution includes the Internet of Things (IoT) where the intelligent sensors are connected to the embedded computing system to monitor the fluctuation of parameters relating to the flame colour. The first step is to define a feature vector for each flame image including 8 feature elements, which are the brightness of flame, the area of the high temperature flame, the brightness of high temperature flame, the rate of area of the high temperature flame, the flame centroid and Linear Binary pattern (LBP) respectively. The quality of the captured images is enhanced using curvelet transform. The concept of object (flame feature) recognition and classification (BPA and PSO) of the flame image is carried out to measure the SO2 emissions from the flame colour. A PC based online setup for flame monitoring to detect SO2 emissions in thermal and gas turbine power plants at the furnace level is proposed here. The effectiveness of the system is inferred from the specificity and sensitivity of the soft sensor. [ABSTRACT FROM AUTHOR]