Neural network system whose training is based on a combination of model and flight information for estimation of aircraft air data
US-2020309810-A1 · Oct 1, 2020 · US
US11287283B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11287283-B2 |
| Application number | US-201815980991-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 16, 2018 |
| Priority date | May 23, 2017 |
| Publication date | Mar 29, 2022 |
| Grant date | Mar 29, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A device for monitoring and estimating parameters relating to the flight of an aircraft includes an estimation module 4 for determining an estimation of the values of the parameters relating to the flight of the aircraft and for generating residues, a detection module for determining the statuses associated with each of said sensors C 1 , C 2 , . . . , CN and with a parameter P 1 corresponding to the weight of the aircraft, a transmission module for transmitting the statuses associated with each of said sensors C 1 , C 2 , . . . , CN to a user device and, on the next iteration, to the estimation module.
Opening claim text (preview).
The invention claimed is: 1. A method for monitoring and estimating: parameters relating to a flight of an aircraft (AC); statuses of sensors (C 1 , C 2 , . . . , CN), the statuses being representative of an operation of said sensors (C 1 , C 2 , . . . , CN); and a status of a parameter (P 1 ) corresponding to a current weight of the aircraft (AC), the status being representative of a validity of said parameter, the method comprising: an initialization step (E 1 ), implemented by an initialization module, including initializing the statuses of sensors (C 1 , C 2 , . . . , CN) configured to determine flight parameters of the aircraft (AC) and the status of the parameter (P 1 ) corresponding to the current weight of the aircraft (AC) and initializing parameters used in an implementation of a monitoring and estimation device; the method further comprising the following steps, implemented iteratively: an estimation step (E 2 ), implemented by an estimation module, including determining an estimation of values of the parameters relating to the flight of the aircraft (AC) and an estimation of an error of said weight, from: measurements of the parameters relating to the flight supplied by the sensors (C 1 , C 2 , . . . , CN); parameters relating to the flight initialized in the initialization step (E 1 ) or estimated on the preceding iteration of the estimation step (E 2 ); and statuses associated with each of said sensors (C 1 , C 2 , . . . , CN), the estimation step (E 2 ) further comprising generating residues (r i ) which are functions of the measured and estimated values of the parameters relating to the flight and of innovation terms; a first transmission step (E 3 ), implemented by a first transmission module, including: transmitting to a user device and to a detection module a signal representative of the estimation of the values of the parameters relating to the flight of the aircraft (AC) and of the estimation of the error of the current weight parameter, determined in the estimation step (E 2 ), sending to said detection module a signal representative of the residues generated in the estimation step (E 2 ); a detection step (E 4 ), implemented by a detection module, including determining different statuses associated with each of said sensors (C 1 , C 2 , . . . , CN) and with the parameter (P 1 ) corresponding to the current weight of the aircraft (AC), from: the estimation of the values of the residues (r i ) determined in the estimation step (E 2 ); the estimation of the values of the parameters relating to the flight of the aircraft (AC) determined in the estimation step (E 2 ); the measurements of the parameters relating to the flight supplied by the sensors (C 1 , C 2 , . . . , CN); the estimation of the error of the current weight parameter (P 1 ) determined in the estimation step (E 2 ); and the statuses determined on the preceding iteration of the detection step (E 4 ) or initialized in the initialization step (E 1 ); and a second transmission step (E 5 ), implemented by a second transmission module, including transmitting to the user device and, on the next iteration, to the estimation module the different statuses associated with each of said sensors (C 1 , C 2 , . . . , CN) and the status associated with said parameter (P 1 ) corresponding to the current weight, wherein the estimation step (E 2 ) comprises the following substeps: an adaptation substep (E 21 ), implemented by an adaptation submodule, including determining a variance and/or a validity Boolean associated with each of the measurements of the parameters relating to the flight supplied by the sensors (C 1 , C 2 , . . . , CN) and of the setting parameters associated with the estimation algorithm used in an estimation substep (E 22 ), from: said measurements of the parameters relating to the flight, and the statuses associated with each of said sensors (C 1 , C 2 , . . . , CN); the adaptation substep (E 21 ) further comprising correcting the current weight from a weight error estimated on the preceding iteration or initialized in the initialization step (E 1 ), and from a status associated with the parameter (P 1 ) corresponding to the weight; an estimation substep (E 22 ), implemented by an estimation submodule, including determining the estimation of the values of the parameters relating to the flight and an estimation of the error of said weight, from: the measurements of the parameters relating to the flight supplied by said sensors (C 1 , C 2 , . . . , CN); the parameters relating to the flight estimated on the preceding iteration or initialized in the initialization step (E 1 ); and the variance and/or the validity Boolean of each of the measurements of the parameters relating to the flight and of the setting parameters determined in the adaptation substep (E 21 ), the estimation substep (E 22 ) further comprising generating the residues from the estimated and measured parameters relating to the flight and from the innovation terms, and wherein the estimation substep (E 22 ) corresponds to an extended Kalman filter associated with a state vector (X), an observation vector (Y) and an auxiliary measurement vector (Z), the auxiliary measurement vector (Z) having for expression: Z = ( i H m , δ q i m , δ sp i m , ψ m , φ m , θ m , n X 1 m , m , conf , V g x 0 m , V g y 0 m , V g z 0 m
electric · CPC title
Combined instruments indicating more than one navigational value, e.g. for aircraft; Combined measuring devices for measuring two or more variables of movement, e.g. distance, speed or acceleration · CPC title
based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title
Flight directors (indicating arrangements specially adapted for rotary gyroscopes G01C19/32) · CPC title
specially adapted for use in aircraft · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.