ABSTRACT
Proportional–integral–derivative (PID)-based control systems are widely applied in the electrical power generation industry; however, for highly complex combustion problems, such as slagging and fouling, conventional PID controllers have limitations. It is very difficult to use PID controllers to control combustion processes and prevent slagging and fouling because data regarding slagging and fouling are very difficult to measure, and a PID controller cannot work on a control system in which sufficient output parameters are not available. Slagging and fouling badly influence boiler-combustion efficiency [3, 11], so it is significant to solve the problems for coal-fired power plants with high-slagging trends in the combustion process. This chapter proposes a novel control method of integrating online learning with computational fluid dynamics (CFD) to control the temperature in a generic combustion process, and discussion comparing the method with a PID controller is included.
