Prognostic failure detection system

Patent metadata

Field	Value
Publication number	US-9944404-B1
Application number	US-201514666144-A
Country	US
Kind code	B1
Filing date	Mar 23, 2015
Priority date	Mar 23, 2015
Publication date	Apr 17, 2018
Grant date	Apr 17, 2018

Abstract

A prognostic failure detection system may be implemented for an unmanned aerial vehicle(s) (UAV). A prognostic failure detection system may include a process of predicting failure conditions that may affect an UAV physical system or structure before they occur. By predicting failure conditions before they occur, the prognostic system allows maintenance centers to perform corrective actions in a timely and cost-effective manner. The prognostic system is intended to monitor and support the functionality of several physical systems and physical structures associated with an UAV. A physical system includes, but is not limited to, the electrical system, power system including the power supply, motor and propeller assemblies including motor controllers, navigation system, and flight controller system.

First claim

What is claimed is:

1. A computer implement method comprising:
receiving sensor data from a plurality of sensors associated with an unmanned aerial vehicle (UAV), wherein the receiving occurs during an in-progress phase of a flight cycle of the UAV;
determining that the sensor data indicates a likelihood of a failure condition occurring on a physical structure or a physical system of the UAV during the in-progress phase of the flight cycle, wherein determining the sensor data indicates the likelihood of the failure condition further comprises comparing at least the sensor data to trend data, and wherein the trend data includes historical sensor data from at least one of the UAV, a second UAV, or a fleet of UAVs during normal operating conditions;
determining a failure condition classification based at least in part on the sensor data, the failure condition classification selected from a predetermined set of failure condition classifications that includes at least a flight non-critical classification, a flight critical non-priority classification, and a flight critical priority classification, wherein:
the flight non-critical classification indicates that the UAV can sustain continued flight without damage to an affected physical structure or an affected physical system,
the flight critical non-priority classification indicates that the UAV can sustain continued flight with predetermined performance restrictions without damage to an affected physical structure or an affected physical system, and
the flight critical priority classification indicates that the UAV cannot sustain continued flight without damage to an affected physical structure or an affected physical system;

determining a corrective action during the in-progress phase of the flight cycle based at least on the failure condition classification;
causing a modification to an operational characteristic that is associated with the flight cycle of the UAV based at least in part on the corrective action;
determining a plurality of ground tests to conduct on the UAV at a completion phase of the flight cycle based at least in part on the sensor data;
prioritizing a subset of ground tests from the plurality of ground tests based at least in part on the failure condition classification and on-ground time constraints associated with the UAV; and
transmitting a signal to an operations center, the signal modifying a maintenance plan by scheduling the prioritized subset of ground tests associated with the UAV.

2. The computer-implemented method of claim 1 , wherein causing the modification to the operational characteristic includes causing the UAV to operate in a reduced performance mode, wherein the reduced performance mode further includes at least one of restricting an altitude gain per time interval to a predetermined altitude gain per time interval during a climb phase of flight or restricting a cruise speed to a predetermined cruise speed during a cruise phase of flight, the predetermined altitude gain per time interval and the predetermined cruise speed based at least in part on the corrective action.

3. The computer-implemented method of claim 1 , wherein the corrective action includes causing the UAV to deposit inventory at a predetermined location before reaching a planned delivery location associated with the inventory.

4. The computer-implemented method of claim 1 , wherein the failure condition is the flight critical priority classification, and wherein the corrective action comprises causing the UAV to perform an emergency landing at a geographic location that is proximate to a current location of the UAV.

5. The computer-implemented method of claim 1 , wherein the corrective action corresponding to the flight critical non-priority classification includes:
inspecting the physical structure or the physical system at reduced time intervals until maintenance is performed; and
reducing allowable cruise altitude or reducing allowable cruise speed.

6. The computer-implemented method of claim 1 , wherein the sensor data comprises strain gauge sensor data and the method further comprising:
determining an in-flight vibration frequency of the physical structure based at least in part on the strain gauge sensor data; and
wherein the determining the likelihood of the failure condition occurring on the physical structure is based at least in part on a comparison of the in-flight vibration frequency and a vibration frequency threshold.

7. The computer-implemented method of claim 6 , wherein trend data includes the historical trend of operational vibration frequencies that correspond to the physical structure of the UAV, and wherein the vibration frequency threshold is based at least in part on the trend data.

8. The computer-implemented method of claim 1 , wherein the plurality of sensors includes at least an accelerometer, a gyroscope, a proximity sensor, a digital camera, a global position system (GPS) sensor, a temperature sensor, a moisture sensor, a voltage sensor, a current sensor or a strain gauge.

9. The computer-implemented method of claim 1 , wherein the physical system includes at least one of an electrical system, a power system, a navigation system, a flight controller system, an inertial measurement unit, or a motor-propeller assembly.

10. A unmanned aerial vehicle (UAV) comprising:
an airframe;
physical systems coupled to the airframe, the physical systems comprising at least a propulsion system to provide thrust, a control system to control at least the propulsion system, and a power system to power at least the control system and the propulsion system;
a plurality of sensors distributed throughout the airframe and the physical systems, the plurality of sensors configured to monitor at least the operation of the airframe and the physical systems; and
a diagnostic controller to process sensor data associated with the plurality of sensors, the diagnostic controller performing acts comprising:
receive sensor data from a plurality of sensors during an in-progress phase of a flight cycle of the UAV;
determine that the sensor data indicates a probability of a failure condition occurring on the airframe or at least one of the physical systems;
determine a failure condition classification based at least in part on the sensor data, the failure condition classification selected from a predetermined set of failure condition classifications that includes at least one of a flight non-critical classification, a flight critical non-priority classification, and a flight critical priority classification;
determine a corrective action during the in-progress phase of the flight cycle based at least on the failure condition classification;
cause a modification to an operational characteristic that is associated with the flight cycle of the UAV based at least in part on the corrective action;
determine a plurality of ground tests to conduct on the UAV at a completion phase of the flight cycle based at least in part on the sensor data;
prioritize a subset of ground tests from the plurality of ground tests based at least in part on the failure condition classification and on-ground time constraints associated with the UAV; and
transmit a signal to an operations center, the signal modifying a maintenance plan by scheduling the prioritized subset of ground tests associated with the UAV.

11. The UAV of claim 10 , wherein the corrective action includes causing the UAV to deposit inventory at a predetermined location before reaching a planned delivery location associated with the inventory.

12. The UAV of claim 10 , wherein the corrective action includes causing the UAV to reduce altitude gain per time interval to

Assignees

• Amazon Tech Inc

Inventors

• Gentry Nicholas Kristofer

Classifications

• B64F5/60

  Testing or inspecting aircraft components or systems · CPC title

• G07C5/0808

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

• G01M17/00

  Testing of vehicles (testing fluid tightness G01M3/00; testing elastic properties of bodies or chassis, e.g. torsion-testing, G01M5/00; testing alignment of vehicle headlight devices G01M11/06; testing of engines G01M15/00) · CPC title

• G07C5/008

  communicating information to a remotely located station (transmission systems for measured values G08C) · CPC title

• G07C5/0841

  Registering performance data (recording measured values G01D; information storage G11B) · CPC title