A bumpless transfer fault tolerant control method for aero-engine under actuator fault is disclosed. For an aero-engine actuator fault, by adopting an undesired oscillation problem produced by an active fault tolerant control method based on a virtual actuator, in order to solve the shortage of the existing control method, a bumpless transfer active fault tolerant control design method for the aero-engine actuator fault is provided, which can guarantee that a control system of the reconfigured aero-engine not only has the same state and output as an original fault-free system without changing the structure and parameters of a controller, to achieve a desired control objective, and that a reconfigured system has a smooth transient state, that is, output parameters such as rotational speed, temperature and pressure do not produce the undesired transient characteristics such as overshoot or oscillation.

Methods and systems for determining an engine temperature for a gas turbine engine are provided. An estimated combustor temperature is determined based on at least one operating condition of the gas turbine engine and an estimated vane mass flow. A corrected vane mass flow is determined based on the estimated combustor temperature, the estimated vane mass flow, and a combustor pressure. The corrected vane mass flow is compared to a reference vane mass flow to obtain the mass flow correction factor. When a condition associated with the mass flow correction factor is not satisfied, the estimated combustor temperature is adjusted based on the mass flow correction factor to produce an adjusted combustor temperature; and the mass flow correction factor is updated based on the adjusted combustor temperature. When the condition associated with the mass flow correction factor is satisfied, the estimated combustor temperature is assigned as the engine temperature.

A system for determining and/or controlling motor thrust and engine thrust in a parallel hybrid aircraft. One or more sensors may be configured to monitor one or more flight parameters to generate sensor information. User input including one or more pilot estimates may be received. The sensor information may be obtained. A performance thrust ratio may be calculated based on the user input, the sensor information, an aerodynamic model, a propeller model, and a battery model. The performance thrust ratio may be used to control the motor thrust and engine thrust to improve utilization of electric energy throughout a flight. A first thrust setting for the motor and/or a second thrust setting for the engine may be determined based on the performance thrust ratio.

A system for determining and/or controlling motor thrust and engine thrust in a parallel hybrid aircraft. One or more sensors may be configured to monitor one or more flight parameters to generate sensor information. User input including one or more pilot estimates may be received. The sensor information may be obtained. A performance thrust ratio may be calculated based on the user input, the sensor information, an aerodynamic model, a propeller model, and a battery model. The performance thrust ratio may be used to control the motor thrust and engine thrust to improve utilization of electric energy throughout a flight. A first thrust setting for the motor and/or a second thrust setting for the engine may be determined based on the performance thrust ratio.

An engine includes a fan section including a plurality of fan blade assemblies. A fan blade assembly includes a midspan shroud separating an inner portion and an outer portion of the fan blade assembly. An outer pitch of the outer portion is variable with respect to an inner pitch of the inner portion.

An engine includes a fan section including a plurality of fan blade assemblies. A fan blade assembly includes a midspan shroud separating an inner portion and an outer portion of the fan blade assembly. An outer pitch of the outer portion is variable with respect to an inner pitch of the inner portion.

A gas turbine engine includes a fan comprising fan blades. In a forward mode of operation the fan blades have a forward pitch and generate forward thrust, and in a reverse mode of operation the fan blades have a reverse pitch and generate reverse thrust. A fan drive shaft drives the fan and an electric machine is connected to the fan drive shaft. In a reverse mode of operation, the electric machine operates as a motor to convert stored electric energy into rotation of the fan drive shaft.

A gas turbine engine includes a fan comprising fan blades. In a forward mode of operation the fan blades have a forward pitch and generate forward thrust, and in a reverse mode of operation the fan blades have a reverse pitch and generate reverse thrust. A fan drive shaft drives the fan and an electric machine is connected to the fan drive shaft. In a reverse mode of operation, the electric machine operates as a motor to convert stored electric energy into rotation of the fan drive shaft.

The propulsion system have a load change detecting unit detecting a load change and an operating point control unit controlling power operating points defined using a torque T and a rotation number Ne. The operating point control unit calculates target power operating points 44 and 54 corresponding to the load after change for first power operating points 41 and 51 that are current power operating points in a case in which a change in the load is detected by the load change detecting unit. By changing the fuel flow in a range not exceeding a predetermined fuel line, the operating point control unit moves the power operating points from first power operating points 41 and 51 to second power operating points 42 and 52, third power operating points 43 and 53, and target power operating points 44 and 54 in order.

This disclosure relates to method and system for training of deep learning based time-series models based on self-supervised learning. The problem of missing data is taken care of by introducing missing-ness masks. The deep learning model for univariate and multivariate time series data is trained with the distorted input data using the self-supervised learning to reconstruct the masked input data. Herein, the one or more distortion techniques include quantization, insertion, deletion, and combination of the one or more such distortion techniques with random subsequence shuffling. Different distortion techniques in the form of reconstruction of masked input data are provided to solve. The deep learning model performs these different distortion techniques, which force the deep learning model to learn better features. It is to be noted that the system uses a lot of unlabeled data available cheaply as compared to the label or annotated data which is very hard to get.