IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
US-0945449
(2010-11-12)
|
등록번호 |
US-8768556
(2014-07-01)
|
우선권정보 |
IL-191438 (2008-05-14); IL-198691 (2009-05-11) |
발명자
/ 주소 |
- Ben-Arie, Gershon
- Segall, Ilana
- Dotan, Asi
|
출원인 / 주소 |
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
3 인용 특허 :
7 |
초록
▼
An apparatus defines a protection envelope in an aircraft, including a processor and at least one sensor, each sensor being coupled with the processor, the processor executing at least one neural network based algorithm. The at least one sensor monitors flight parameters of the aircraft thereby gene
An apparatus defines a protection envelope in an aircraft, including a processor and at least one sensor, each sensor being coupled with the processor, the processor executing at least one neural network based algorithm. The at least one sensor monitors flight parameters of the aircraft thereby generating monitored flight parameters. The processor divides the performance envelope of the aircraft into predefined flight regimes, wherein for each predefined flight regime, the processor defines and stores a suitable protection envelope. The processor determines an estimated flight regime of the aircraft using the neural network based algorithm based on the monitored flight parameters. The processor selects a respective suitable protection envelope for the aircraft based on the estimated flight regime.
대표청구항
▼
1. Apparatus for defining a protection envelope in an aircraft, comprising: a processor, for executing at least one neural network based algorithm; andat least one sensor, each said at least one sensor coupled with said processor, for monitoring a plurality of flight parameters of said aircraft, the
1. Apparatus for defining a protection envelope in an aircraft, comprising: a processor, for executing at least one neural network based algorithm; andat least one sensor, each said at least one sensor coupled with said processor, for monitoring a plurality of flight parameters of said aircraft, thereby generating a plurality of monitored flight parameters, wherein said plurality of monitored flight parameters excludes a speed of said aircraft;wherein said processor divides the performance envelope of said aircraft into predefined flight regimes,wherein for each said predefined flight regime, said processor defines and stores a suitable protection envelope,wherein said processor determines an estimated flight regime of said aircraft using said at least one neural network based algorithm based on said plurality of monitored flight parameters, andwherein said processor selects a respective suitable protection envelope for said aircraft based on said estimated flight regime. 2. The apparatus according to claim 1, said apparatus coupled with a forward looking terrain avoidance (FLTA) system. 3. The apparatus according to claim 1, wherein each said predefined flight regime relates to a predefined interval of speed. 4. The apparatus according to claim 1, wherein said apparatus is operational when said aircraft attains a minimum speed. 5. The apparatus according to claim 1, wherein said plurality of flight parameters comprises a mandatory set of flight parameters and an optional set of flight parameters, said mandatory set of flight parameters and said optional set of flight parameters being determined by the type of said aircraft. 6. The apparatus according to claim 1, wherein said processor modifies at least one dimension of said respective suitable protection envelope for said aircraft based on a subset of said plurality of monitored flight parameters. 7. The apparatus according to claim 6, wherein said subset of said plurality of flight parameters comprises at least one of: a vertical speed;a weight;an altitude;said estimated flight regime;a type of aircraft; anda make of aircraft. 8. Method for defining a protection envelope in an aircraft, the method comprising the procedures of: monitoring a plurality of flight parameters of said aircraft, excluding a speed of said aircraft;dividing the protection envelope of said aircraft into predefined flight regimes;for each predefined flight regime, defining and storing a suitable protection envelope;calibrating a neural network based algorithm to map said monitored plurality of flight parameters to said suitable protection envelope for said aircraft based on an estimated flight regime;determining said estimated flight regime for said aircraft based on said monitored plurality of flight parameters using said calibrated neural network based algorithm; andselecting said suitable protection envelope for said aircraft based on said estimated flight regime. 9. The method according to claim 8, further comprising the procedure of modifying at least one dimension of said selected suitable protection envelope based on a subset of said plurality of monitored flight parameters. 10. The method according to claim 9, further comprising the procedure of modifying at least one dimension of said selected suitable protection envelope based on at least one of: a vertical speed;a weight;an altitude;said estimated flight regime;a type of aircraft; anda make of aircraft. 11. The method according to claim 8, further comprising the procedure of collecting data for a particular type of said aircraft, said data substantially representing said plurality of flight parameters. 12. The method according to claim 11, wherein said collected data is collected from a 6 degree of freedom (DOF) simulation of said particular type of said aircraft. 13. The method according to claim 11, wherein said collected data is collected from an actual flight of said particular type of said aircraft. 14. The method according to claim 8, wherein said neural network based algorithm is a backpropagation algorithm. 15. The method according to claim 8, further comprising the procedures of: generating a plurality of flight parameter test cases; andtesting the performance of said calibrated neural network based algorithm. 16. The method according to claim 8, wherein said neural network based algorithm comprises a neural architecture comprising an input layer, at least one hidden layer and an output layer. 17. The method according to claim 8, wherein said procedure of calibrating said neural network based algorithm comprises the sub-procedures of: generating a plurality of flight parameter validation cases; anddefining a stopping rule.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.