Combustion efficiency optimization by adjusting the amount of excess air

Abstract

Boiler combustion process in thermal power plants is important from both economic and environmental aspects. Boiler combustion system is a complex multi-input and multi-output plant with strong nonlinear and large time-delay. So adjusting the main controllable parameters based on model is difficult. power plant Distributed Control System (DCS) collect and save the boiler's run-time data by numerous sensors. This large volume of data contains information of the boiler that can be analyzed with data-mining algorithms in order to optimize the combustion process. In this paper, a complete resolution strategy for combustion optimization based on fuzzy data mining is proposed and A virtual testing procedure is developed to validate the results produced by the optimization method.