A State Space Modeling Method for Aero-Engine Based on AFOS-ELM

State space models (SSMs) are important for multi-variable performance analysis and controller design of aero-engines. In order to solve the problems traditional state modeling methods that rely on component-level (CLMs) cannot be carried out in real time, an aero-engine method based adaptive forgetting factor online sequential extreme learning machine (AFOS-ELM) is proposed this paper. The structure (ELM) determined according form model, inverse-free ELM algorithm used automatically select appropriate number hidden nodes improve efficiency offline initialization. focus current operation enhanced by renewed factor, which reduces impact history deviated data output improves accuracy model. Then, analytical equation model at each sampling time obtained using partial derivative method. simulation results engine test show real-time established paper can meet needs control system requirement.