Identification of coal mill model parameters using genetic algorithm

Master of Philosophy in Computer Science 2014-2015 INT Elizabeth Sherly

Coal mill is a necessary part of the thermal power plant. They are now obliged to vary their output in response to changing electricity scenario. Now a days the demand of electricity is increasing but the conventional methods like hydroelectric power generation facing numerous difficulties. Therefore the urgency of the power plant is towering; these have impacted the coal mill and thermal power plant operation safety and reliability. This thesis is a study of dynamic responses of thermal power plants through mathematical modeling, identification, and simulation. Genetic Algorithm is chosen in this work as it is a stable algorithm for parameter identification, real-time and on-line implementation. The raw data used in modeling can be obtained without any extensive mill tests. The simulation results show a satisfactory agreement between the model response and measured value. The model is verified using on-site measurement data and on-line test. The mill-related features that affect milling performance include coal properties mainly calorific value, grind ability, abrasiveness, moisture content, mill types (low-speed mill, medium-speed mill, high-speed mill), pulverized coal distribution system that is presence of bifurcations and trifurcations, and control strategy, etc. We have tried to estimate the unknown parameter that affect the coal milling process at steady state condition implemented using Genetic Algorithm based on plant measurement data