In-flight stabilization of an aircraft

Patent metadata

Field	Value
Publication number	US-12054239-B2
Application number	US-202117404809-A
Country	US
Kind code	B2
Filing date	Aug 17, 2021
Priority date	Oct 9, 2019
Publication date	Aug 6, 2024
Grant date	Aug 6, 2024

Abstract

A system for in-flight stabilization including a plurality if flight components mechanically coupled to an aircraft. The system further comprises a sensor mechanically coupled to the aircraft, wherein the sensor is configured to detect a failure datum of the flight component. The system comprises a vehicle controller communicatively connected to the sensor and is configured to receive the failure datum of a flight component of the aircraft from the sensor, generate a mitigating response to be performed by at least a flight component of the plurality of flight components, and initiate the at least a flight component of the plurality of flight components. Initiating the flight component of the plurality of flight components further includes performing the mitigating response.

First claim

What is claimed is:

1. A system for in-flight stabilization, the system comprising:
a plurality of flight components mechanically coupled to an aircraft;
a sensor mechanically coupled to the aircraft, wherein the sensor is configured to:
detect a failure event associated with the aircraft; and
generate a failure datum based on the failure event, wherein the failure datum contains a component classifier representing a flight component of the plurality of flight components that is affected by the failure event and a component descriptor representing an extent of progression of the failure event;

a pilot interface device mechanically coupled to the aircraft, wherein the pilot interface device is configured to:
present a mitigating response representing an adjustment in a flight path of the aircraft;
receive a user selection of the mitigating response; and
generate a response confirmation datum based on the user selection; and

a vehicle controller communicatively connected to the sensor, the vehicle controller configured to:
receive the failure datum from the sensor;
receive the response confirmation datum from the pilot interface device;
generate the mitigating response based on the component classifier and the component descriptor; and
based on receiving the failure datum and the response confirmation datum, cause the plurality of flight components to adjust the flight path based on the mitigating response.

2. The system of claim 1 , wherein the aircraft further comprises an electric aircraft.

3. The system of claim 1 , wherein the plurality of flight components includes a propulsor.

4. The system of claim 1 , wherein the vehicle controller is further communicatively coupled to each flight component of the plurality of flight components and the flight component.

5. The system of claim 1 , wherein the vehicle controller further comprises a reconfigurable hardware platform.

6. The system of claim 1 , wherein the pilot interface device is further configured to display the mitigating response to be performed by at least one of the plurality of flight components.

7. The system of claim 1 , wherein the vehicle controller further configured to:
receive heuristic training data from a database correlating the failure datum to at least one heuristic element from a plurality of heuristic elements; and
generate, using a supervised machine-learning process, a heuristic model that receives the failure datum as an input and produces an output containing the at least one heuristic element.

8. The system of claim 1 , wherein the vehicle controller is further configured to generate the mitigating response by:
receiving a plurality of heuristic elements; and
generating the mitigating response based on the plurality of heuristic elements.

9. The system of claim 8 , wherein generating the mitigating response based on the plurality of heuristic elements is further configured to:
generate a loss function based on the failure datum and the plurality of heuristic elements;
minimize the loss function; and
select at least one of the plurality of heuristic elements based on the loss function.

10. The system of claim 1 , wherein the vehicle controller is further configured to:
store the failure datum in a heuristic database;
store a plurality of heuristic elements in the heuristic database; and
store the mitigating response in the heuristic database.

11. The system of claim 1 , wherein performing the mitigating response further comprises:
pulsing a torque associated with one or more rotors of the aircraft to increase an average torque while minimizing a net thrust;
utilizing a pusher rotor to stabilize the aircraft;
utilizing one or more flight surfaces associated with the aircraft in a non-coordinated way; and
altering a flight path of the aircraft.

12. A method for in-flight stabilization, the method comprising:
detecting, by a sensor, a failure event associated with an aircraft;
generating, by a sensor and based on the failure event, a failure datum, wherein the failure datum contains a component classifier representing a component of a plurality of flight components of the aircraft that is affected by the failure event and a component descriptor representing an extent of progression of the failure event;
presenting, by a pilot interface device, a mitigating response, wherein the mitigating response represents an adjustment in a flight path of the aircraft;
receiving, by the pilot interface device, a user selection of the mitigating response;
generating, by the pilot interface device, a response confirmation datum based on the user selection;
receiving, by a vehicle controller, the failure datum;
receiving, by the vehicle controller, the response confirmation datum from the pilot interface device;
generating, by the vehicle controller, the mitigating response based on the component classifier and the component descriptor with the adjustment; and
based on receiving the failure datum and the response confirmation datum, causing a plurality of flight components of the aircraft to adjust the flight path based on the mitigating response.

13. The method of claim 12 , wherein the aircraft further comprises an electric aircraft.

14. The method of claim 12 , wherein the plurality of flight components includes a propulsor.

15. The method of claim 12 , further comprising displaying, at the pilot interface device, the mitigating response to be performed by the plurality of flight components.

16. The method of claim 12 , wherein generating the mitigating response further comprises:
receiving heuristic training data from a database correlating a failure datum to at least one heuristic element from a plurality of heuristic elements; and
generating, using a supervised machine-learning process, a heuristic model that receives the failure datum as an input and produces an output containing the at least one heuristic element.

17. The method of claim 12 , wherein generating a mitigating response to be performed by a flight component of the plurality of flight components further comprises:
receiving a plurality of heuristic elements; and
generating the mitigating response based on the plurality of heuristic elements.

18. The method of claim 17 , wherein generating the mitigating response as a function of the plurality of heuristic elements further comprises:
generating a loss function based on the failure datum and the plurality of heuristic elements;
minimizing the loss function; and
selecting at least one of the plurality of heuristic elements based on the loss function.

19. The method of claim 12 , wherein generating the mitigating response further comprises:
storing the failure datum in a heuristic database;
storing a plurality of heuristic elements in the heuristic database; and
storing the mitigating response in the heuristic database.

20. The method of claim 12 , wherein performing the mitigating response further comprises:
pulsing a torque associated with one or more rotors of the aircraft to increase an average torque while minimizing a net thrust;
utilizing a pusher rotor to stabilize the aircraft;
utilizing one or more flight surfaces associated with the aircraft in a non-coordinated way; and
altering a flight path of the aircraft.

Assignees

• Beta Air Llc

Inventors

• Clark Kyle B

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• B64D27/34

  All-electric aircraft · CPC title

• B64D27/31

  within, or attached to, wings · CPC title

• B64C13/16 Primary

  actuated automatically, e.g. responsive to gust detectors · CPC title