Thrust Estimation, Control, and Evaluation for Turbofan Engines

Given that thrust is the most core parameter of turbofan engines but cannot be measured, and that engines are subject to performance degradation, disturbances, or even failure, this paper presents a direct thrust control (DTC) system based on an onboard model and robust control. To overcome the limitations of the unscented Kalman filter (UKF) in terms of accuracy and convergence speed, the Levenberg-Marquardt (L-M) algorithm is employed to optimize the measurement update process, thereby establishing a superior onboard model for turbofan engines. Then, to address the real-time issue, the LSTM network is trained to approximate the nonlinear engine model used for the Kalman observer, substantially accelerating the computational efficiency. Finally, based on this onboard model, an H∞ gain-scheduled controller is designed for the DTC system. The comparative results of numerical simulations and hardware experiments on the Xavier embedded controller substantiate the feasibility, superiority, and real-time performance of our approaches, thus suggesting the potential for practical engineering.