Machine learned aero-thermodynamic engine inlet condition synthesis

    公开(公告)号:US12180892B2

    公开(公告)日:2024-12-31

    申请号:US16265319

    申请日:2019-02-01

    Abstract: A system for neural network compensated aero-thermodynamic gas turbine engine parameter/inlet condition synthesis. The system includes an aero-thermodynamic engine model configured to produce a real-time model-based estimate of engine parameters, a machine learning model configured to generate model correction errors indicating the difference between the real-time model-based estimate of engine parameters and sensed values of the engine parameters, and a comparator configured to produce residuals indicating a difference between the real-time model-based estimate of engine parameters and the sensed values of the engine parameters. The system also includes an inlet condition estimator configured to iteratively adjust an estimate of inlet conditions based on the residuals and adaptive control laws configured to produce engine control parameters for control of gas turbine engine actuators based on the inlet conditions.

    Adaptive model predictive control for hybrid electric propulsion

    公开(公告)号:US12140083B2

    公开(公告)日:2024-11-12

    申请号:US18153487

    申请日:2023-01-12

    Abstract: A hybrid electric propulsion system includes a gas turbine engine having at least one compressor section and at least one turbine section operably coupled to a shaft. The hybrid electric propulsion system includes an electric motor configured to augment rotational power of the shaft of the gas turbine engine. A controller is operable to determine hybrid electric propulsion system parameters based on a composite system model and sensor data, determine a prediction based on the hybrid electric propulsion system parameters and the composite system model, determine a model predictive control optimization for a plurality of hybrid electric system control effectors based on the prediction using a plurality of reduced-order partitions of the composite system model, and actuate the hybrid electric system control effectors based on the model predictive control optimization.

Patent Agency Ranking