Data-driven dynamic prediction of interrelated heat and electric outputs of microturbines

This paper proposes a simplified microturbine (MT) model which allows for dynamic heat and power output prediction. Considering the time-scale difference of various dynamic processes occuring within MTs, the electromechanical subsystem is treated as a fast quasi-linear system while the thermo-mechanical subsystem is treated as a slow process with high nonlinearity. A subspace model identification method is utilized to capture dominant dynamics and predict outputs of the electromechanical subsystem. For the thermo-mechanical process, a fast recursive algorithm assisted radial basis function model is employed to handle the strong nonlinear characteristics. Experimental tests on a Capstone C30 MT show that the proposed modeling method can well capture the system dynamics and produce a good model to predict the interrelated heat and electricity outputs.