Aerial vehicle engine health prediction

Patent metadata

Field	Value
Publication number	US-2018102000-A1
Application number	US-201615289266-A
Country	US
Kind code	A1
Filing date	Oct 10, 2016
Priority date	Oct 10, 2016
Publication date	Apr 12, 2018
Grant date	—

Abstract

Systems and methods for navigating an unmanned aerial vehicle are provided. One example aspect of the present disclosure is directed to a method for modeling engine health. The method includes receiving, by one or more processors, engine data. The method includes receiving, by the one or more processors, flight test data. The method includes generating, by the one or more processors, one or more coefficients for a power assistance check (PAC) based on the engine ATP data and the received flight test data using a machine learning technique. The method includes transmitting, by the one or more processors, the one or more coefficients for the PAC to a vehicle, wherein the vehicle uses the one or more coefficients in the PAC to predict engine health.

First claim

What is claimed is:

1 . A method for modeling engine health comprising:
receiving, by one or more processors, engine data; receiving, by the one or more processors, flight test data; generating, by the one or more processors, one or more coefficients for a power assistance check (PAC) based on the engine data and the received flight test data using a computer automated training process; and transmitting, by the one or more processors, the one or more coefficients for the PAC to a vehicle, wherein the vehicle uses the one or more coefficients in the PAC to predict engine health.

2 . The method of claim 1 , further comprising:
receiving, by the one or more processors, additional flight test data; updating, by the one or more processors, the one or more coefficients based on the additional flight test data; and transmitting, by the one or more processors, the one or more updated coefficients to the vehicle, wherein the vehicle uses the one or more updated coefficients in the PAC.

3 . The method of claim 1 , wherein the computer automated training process is implemented at least in part by a Bayesian hybrid model.

4 . The method of claim 1 , wherein the computer automated training process is implemented at least in part by a neural network.

5 . The method of claim 1 , wherein the flight test data is specific to an engine.

6 . The method of claim 1 , wherein the flight test data is specific to the vehicle.

7 . The method of claim 1 , wherein the PAC correlates one or more parameters to a temperature margin.

8 . The method of claim 1 , wherein the flight test data is associated with an aggregation of a plurality of vehicles.

9 . The method of claim 1 , wherein the one or more processors are in a cloud computing environment.

10 . The method of claim 1 , wherein the vehicle is a helicopter.

11 . A system for modeling engine health comprising:
a memory device; and one or more processors configured to:
receive engine acceptance test procedure (ATP) data;
receive flight test data;
generate one or more coefficients for a power assistance check (PAC) based on the engine ATP data and the received flight test data using a machine learning technique; and
transmit the one or more coefficients for the PAC to a vehicle, wherein the vehicle uses the one or more coefficients in the PAC to predict engine health.

12 . The system of claim 11 , the one or more processors further configured to:
receive additional flight test data; recalculate the one or more coefficients based on the additional flight test data; and transmit the one or more recalculated coefficients to the vehicle, wherein the vehicle uses the one or more recalculated coefficients in the PAC.

13 . The system of claim 11 , wherein the machine learning technique is implemented at least in part by a Bayesian hybrid model.

14 . The system of claim 11 , wherein the machine learning technique is implemented at least in part by a neural network.

15 . The system of claim 11 , wherein the flight test data is specific to a fleet.

16 . The system of claim 11 , wherein the flight test data is associated with an aggregation of a plurality of vehicles.

17 . An aerial vehicle comprising:
a memory device; and one or more processors configured to:
accumulate flight test data during a flight;
transmit the flight test data to a cloud computing environment, wherein the cloud computing environment is configured to generate one or more coefficients for a power assistance check (PAC) based on the received flight test data using a machine learning technique;
receive the one or more coefficients; and
predict engine health based on the one or more coefficients in the PAC.

18 . The aerial vehicle of claim 17 , wherein the aerial vehicle is a helicopter.

19 . The aerial vehicle of claim 17 , wherein the flight test data is specific to an engine.

20 . The aerial vehicle of claim 17 , wherein the flight test data relates to all engines on the vehicle.

Assignees

• Gen Electric

Inventors

• Vala Ayin Mokri
• Hannula Scott Victor

Classifications

• G06F18/24155

  Bayesian classification · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06N3/09

  Supervised learning · CPC title

• G07C5/0808 Primary

  Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005) · CPC title