Method And Apparatus For Probabilistic Alerting Of Aircraft Unstabilized Approaches Using Big Data

• US 20170301247A1
• Filed: 04/19/2017
• Published: 10/19/2017
• Est. Priority Date: 04/19/2016
• Status: Active Grant

• Current Assignee: George Mason University
• Original Assignee: George Mason University
• Inventors: Sherry, Lance, Shortle, John, Wang, Zhenming
• Granted Patent: US 10,643,480 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/043 based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G08G 5/0021 located in the aircraft
• CPC Class Codes: G08G 5/0091 for monitoring atmospheric conditions radar or analogous systems specially adapted for meteorological use G01S13/95; meteorology G01W
• CPC Class Codes: G08G 5/025 Navigation or guidance aids radar or analogous systems specially adapted for landing purposes G01S13/913

Abstract

Traditional approaches to predicting aircraft trajectories using kinematic models cannot work due to the complexity of the approach maneuver including flaps/slats, landing gear, ATC vectors, winds, and other traffic. The methods and systems disclosed can utilize Big Data Analytics (e.g., massive amounts of data of flights on each approach) to nowcast the approach stability given the state of the flight prior to the 1000′/500′ check points.

Claims

1. A method, comprising:

generating a predictive model for unstable approach based on a plurality of historical aircraft performances;

generating, based on the predictive model, a current state of an aircraft, and at least one current wind condition, a projected state of the aircraft; and

determining a projected unstable approach by determining that the projected state of the aircraft satisfies one or more unstable approach conditions.

2. The method of claim 1, further comprising displaying, in response to determining that the projected state of the aircraft satisfies one or more unstable approach conditions, an indication of the projected unstable approach.

3. The method of claim 1, wherein the current wind condition comprises one or more of:

a crosswind speed, a crosswind speed magnitude, a headwind, or a gust.

4. The method of claim 1, wherein the current state of the aircraft comprises one or more of:

a current lateral deviation absolute value, a current vertical deviation absolute value, a current average airspeed deviation from a baseline average airspeed, or a current average rate of descent deviation from a baseline rate of descent, wherein the baseline average airspeed or the baseline rate of descent correspond to a weight class of the aircraft.

5. The method of claim 1, wherein the plurality of historical aircraft performances comprise one or more of an airspeed at a predefined distance from a runway, an altitude at the predefined distance from the runway, an angle difference between a course and a centerline at the predefined distance from the runway, or a distance from a deceleration point to a current position.

6. The method of claim 1, wherein determining the projected state of the aircraft comprises determining one or more conditional probabilities.

7. The method of claim 1, wherein determining the projected state of the aircraft comprises applying a supervised learning approach.

8. The method of claim 1, wherein applying the supervised learning approach comprises applying a logistic regression.

16. The method of claim 1, wherein the at least one computing device is configured to apply the supervised learning approach by applying a logistic regression.

9. A system, comprising:

at least one computing device configured to at least;

generate a predictive model for unstable approach based on a plurality of historical aircraft performances;

generate, based on the predictive model, a current state of an aircraft, and at least one current wind condition, a projected state of the aircraft; and

determine a projected unstable approach by determining that the projected state of the aircraft satisfies one or more unstable approach conditions.

10. The system of claim 9, wherein the at least one computing device is further configured to display, in response to determining that the projected state of the aircraft satisfies one or more unstable approach conditions, an indication of the projected unstable approach.

11. The system of claim 9, wherein the current wind condition comprises one or more of:

a crosswind speed, a crosswind speed magnitude, a headwind, or a gust.

12. The system of claim 9, wherein the current state of the aircraft comprises one or more of:

a current lateral deviation absolute value, a current vertical deviation absolute value, a current average airspeed deviation from a baseline average airspeed, or a current average rate of descent deviation from a baseline rate of descent, wherein the baseline average airspeed or the baseline rate of descent correspond to a weight class of the aircraft.

13. The system of claim 9, wherein the plurality of historical aircraft performances comprise one or more of an airspeed at a predefined distance from a runway, an altitude at the predefined distance from the runway, an angle difference between a course and a centerline at the predefined distance from the runway, or a distance from a deceleration point to a current position.

14. The system of claim 9, wherein the at least one computing device is configured to determine the projected state of the aircraft by determining one or more conditional probabilities.

15. The system of claim 9, wherein the at least one computing device is configured to determine the projected state of the aircraft by applying a supervised learning approach.

17. A non-transitory computer-readable medium have encoded thereon instructions that, when executed by at least one computing device, cause the at least one computing device to at least:

generate a predictive model for unstable approach based on a plurality of historical aircraft performances;

generate, based on the predictive model, a current state of an aircraft, and at least one current wind condition, a projected state of the aircraft; and

determine a projected unstable approach by determining that the projected state of the aircraft satisfies one or more unstable approach conditions.

18. The non-transitory computer-readable medium of claim 17, wherein the current wind condition comprises one or more of:

a crosswind speed, a crosswind speed magnitude, a headwind, or a gust.

19. The non-transitory computer-readable medium of claim 17, wherein the current state of the aircraft comprises one or more of:

a current lateral deviation absolute value, a current vertical deviation absolute value, a current average airspeed deviation from a baseline average airspeed, or a current average rate of descent deviation from a baseline rate of descent, wherein the baseline average airspeed or the baseline rate of descent correspond to a weight class of the aircraft.

20. The non-transitory computer-readable medium of claim 17, wherein the plurality of historical aircraft performances comprise one or more of an airspeed at a predefined distance from a runway, an altitude at the predefined distance from the runway, an angle difference between a course and a centerline at the predefined distance from the runway, or a distance from a deceleration point to a current position.