Fuzzy model predictive control for small-scale biomass combustion furnaces

This work presents a fuzzy model predictive controller for small-scale grate furnaces based on a newly derived biomass combustion model. Several local linear controllers are designed for a selected number of operating points utilizing a gap metric. The resulting local predictive controllers are merged with membership functions to form a global nonlinear fuzzy control structure. The presented framework intends to improve the transient and steady state operation by applying an optimal control strategy with state estimation and to cover the entire operating range of the furnace. The open loop results of the introduced combustion model are parameterized and cross-validated with measured data from a test furnace. In order to find suitable parameters for the grey-box model, a local sensitivity analysis is conducted to contribute to an efficient parameter estimation process. Closed loop simulation results of the fuzzy model predictive controller, a linear model predictive controller and a PI control algorithm are presented and compared. Based on the performance of the proposed fuzzy controller, its application, advantages and disadvantages are discussed. Additionally, the impact of the different controllers on the formation of carbon monoxide is investigated based on estimation models from literature. The simulation results show that the fuzzy model predictive controller performs best in the considered categories.