An Improvement Method Based on Similarity Theory for Equilibrium Manifold Expansion Model

Data-driven model has been employed as a powerful tool for identification of complex industrial systems with nonlinear dynamics, such as gas turbines (GT). In this study, a methodology based on data and prior knowledge fusion was developed to improve the equilibrium manifold expansion model to be a multi-input-multi-output (MIMO) model for offline system identification of a two-spool gas turbine. The methodology is evaluated through a case study involving data that are generated by general gas turbine simulation. Simulations show good precision of the proposed model in capturing the nonlinear behavior of the gas turbine.