Method and system for monitoring operations of landing gears of aircraft

1 . A method for providing an operational state of a monitored landing gear of an aircraft, the method being performed by a system comprising electronic circuitry, the method comprising:

obtaining, in real-time, captured signals representative of an actual position of the monitored landing gear;

transforming the captured signals in a descriptor vector using Principal Components Analysis;

injecting the descriptor vector in a machine learning-based model trained and configured to transform descriptor vectors into equivalent operational states of landing gears, the equivalent operational states consisting of up-locked, up-unlocked, in-transit, down-unlocked, and down-locked;

providing an operational state of the monitored landing gear to avionics of the aircraft, the operational state identified as one of the equivalent operational states;

displaying the operational state of the landing gear for further analysis by the avionics; and

modifying, via the avionics, control surfaces of the aircraft responsive to the operational state of the landing gear.

2 . The method according to claim 1 , wherein the captured signals are captured images.

3 . The method according to claim 1 , wherein the images are captured by at least one video camera located in the aircraft in a vicinity of the monitored landing gear in such a way so as to capture the images of the monitored landing gear regardless of the operational state of the monitored landing gear.

4 . The method according to claim 1 , wherein, before the obtaining, the method comprises initializing the machine learning-based model by a computer system by:

obtaining a set of reference signals representative of candidate operational states of landing gears;

generating, in an un-supervised mode, a codebook of using Principal Components Analysis on the set of reference signals, the codebook gathering descriptor vectors obtained from the set of reference signals using Principal Components Analysis; and,

building the machine learning-based model, in a supervised mode, for labelling descriptor vectors with information representative of a corresponding operational state of landing gears.

5 . The method according to claim 4 , wherein the set of reference signals is a set of reference images comprising a plurality of images of each candidate operational state, captured with different lighting conditions, with different background interference, or both.

6 . A non-transitory storage medium storing a computer program comprising instructions which, when executed by a processor, perform the method according to claim 1 .

7 . A system for providing an operational state of a monitored landing gear of an aircraft, the system comprising:

at least one capturing device to capture signals of the monitored landing gear; and

electronic circuitry configured to:

obtain, in real-time, the captured signals representative of an actual position of the monitored landing gear from the at least one capturing device;

transform the captured signals in a descriptor vector using Principal Components Analysis;

inject the descriptor vector in a machine learning-based model trained and configured to transform descriptor vectors into equivalent operational states of landing gears, the equivalent operational states consisting of up-locked, up-unlocked, in-transit, down-unlocked, and down-locked;

provide an operational state of the monitored landing gear to avionics of the aircraft, the operational state identified as one of the equivalent operational states;

display the operational state of the landing gear for further analysis by the avionics; and

modify, via the avionics, control surfaces of the aircraft responsive to the operational state of the landing gear.

8 . An aircraft comprising:

at least one landing gear; and,

the system according to claim 7 .