US 11,694,101 B1Granted

Predictive sensor system for aircraft engines with graphical user interface

AssigneeAmerican Airlines, Inc.

InventorsNing Xu, Jose Antonio Ramirez-Hernandez, Steven James Oakley, Mei Zhang, Ou Bai, Supreet Reddy Mandala

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system according to which a network of physical sensors are configured to detect and track the performance of aircraft engines. The physical sensors are placed in specific locations to detect an exhaust gas temperature, vibration, speed, oil pressure, and fuel flow for each aircraft engine. The performance of each aircraft engine is then viewed in combination with oil consumption associated with that aircraft engine and the routine maintenance program associated with that aircraft engine to route the aircraft and move the aircraft, in accordance with the routing, to a specific location. The sensors efficiently track the performance and physical condition of the engines. Moreover, a listing of identified “at-risk” engines is displayed on a screen of a GUI in a manner that allows for easy navigation and display. Data point(s) that triggered the identification of each “at-risk” engine are easily accessible and viewable.

Claims30

Dependent claims

A method of creating a listing of components using sensors, wherein each component in the listing of components is within a first plurality of components and is predicted to be removed from service due to an unplanned maintenance event, the method comprising:

collecting component performance data, for each component in the first plurality of components, from one or more sensors associated with the first plurality of components;
collecting component performance data, for each component in a second plurality of components, from one or more sensors associated with the second plurality of components;
training a module in a first stage using a training data set,
wherein the training data set comprises:
the component performance data for each component in the second plurality of components collected from the one or more sensors associated with the second plurality of components;
operational data regarding maintenance for each component in the second plurality of components;
and
a listing of removed components each of which was removed from service due to an unplanned maintenance event, wherein each component in the listing of removed components is within the second plurality of components;
wherein training the module in the first stage comprises using one or more machine learning models to generate one or more listings of predicted components based on:
the component performance data for each component in the second plurality of components collected from the one or more sensors associated with the second plurality of components;
and
the operational data regarding maintenance for each component in the second plurality of components;
and
wherein each of the predicted components is predicted to be removed from service due to an unplanned maintenance event;
accessing component data,
wherein the component data comprises:
the component performance data for each component in the first plurality of components collected from the one or more sensors associated with the first plurality of components;
and
operational data regarding maintenance for each component in the first plurality of components;
and
creating, using the trained module and the accessed component data, the listing of components within the first plurality of components, each component in the listing of components being predicted to have an unplanned maintenance event.

18 more elements

A system adapted to create a listing of components using sensors, wherein each component in the listing of components is within a first plurality of components and is predicted to be removed from service due to an unplanned maintenance event, the system comprising:

one or more sensors associated with the first plurality of components;
one or more sensors associated with a second plurality of components;
and
a non-transitory computer readable medium having stored thereon a plurality of instructions, wherein the instructions are executed with at least one processor so that the following steps are executed:
collecting component performance data, for each component in the first plurality of components, from the one or more sensors associated with the first plurality of components;
collecting component performance data, for each component in the second plurality of components, from the one or more sensors associated with the second plurality of components;
training a module in a first stage using a training data set,
wherein the training data set comprises:
the component performance data for each component in the second plurality of components collected from the one or more sensors associated with the second plurality of components;
operational data regarding maintenance for each component in the second plurality of components;
and
a listing of removed components each of which was removed from service due to an unplanned maintenance event, wherein each component in the listing of removed components is within the second plurality of components;
wherein training the module in the first stage comprises using one or more machine learning models to generate one or more listings of predicted components based on:
the component performance data for each component in the second plurality of components collected from the one or more sensors associated with the second plurality of components;
and
the operational data regarding maintenance for each component in the second plurality of components;
and
wherein each of the predicted components is predicted to be removed from service due to an unplanned maintenance event;
accessing component data,
wherein the component data comprises:
the component performance data for each component in the first plurality of components collected from the sensors associated with the first plurality of components;
and
operational data regarding maintenance for each component in the first plurality of components;
and
creating, using the trained module and the accessed component data, the listing of components within the first plurality of components, each component in the listing of components being predicted to have an unplanned maintenance event.

22 more elements

determining a training data set comprising:
component performance data for each component in a second plurality of components collected from one or more sensors associated with the second plurality of components;
operational data regarding maintenance for each component in the second plurality of components;
and
a listing of removed components within the second plurality of components that were removed from service due to an unplanned maintenance event;
training a module in a first stage using one or more machine learning models to generate one or more listings of predicted components that are predicted to be removed from service due to an unplanned maintenance event based on the training data set;
accessing component data comprising:
component performance data for each component in the first plurality of components collected from one or more sensors associated with the first plurality of components;
and
operational data regarding maintenance for each component in the first plurality of components;
and
creating, using the trained module and the accessed component data, the listing of components within the first plurality of components predicted to have an unplanned maintenance event.

9 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/811,965Filed 12 Jul 2022 · continuation
Priority: 20 Nov 2018
Granted: 4 Jul 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification23 codes

G06N 5/04
Computing arrangements using knowledge-based models: inference or reasoning models
G07C 5/0841
Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working,…
G06N 20/00
Machine learning
G06N 20/20
Machine learning: ensemble learning