METHOD AND SYSTEM ABOARD AN AIRCRAFT FOR GENERATING AN ANOMALY REPORT

• US 20160107765A1
• Filed: 10/19/2015
• Published: 04/21/2016
• Est. Priority Date: 10/20/2014
• Status: Active Grant

• Current Assignee: Airbus Operations (European Aeronautic Defence and Space Company EADS NV)
• Original Assignee: Airbus Operations (European Aeronautic Defence and Space Company EADS NV)
• Inventors: DANI, Mohamed-Cherif, SILVEIRA FREIXO, Cassiano
• Granted Patent: US 9,796,481 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B64D 2045/0065 Black boxes, devices automatically broadcasting distress signals
• CPC Class Codes: B64D 2045/0085 Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
• CPC Class Codes: B64D 45/00 Aircraft indicators or protectors not otherwise provided for camouflage F41H3/00
• CPC Class Codes: G05B 23/0251 Abstraction hierarchy, e.g. "complex systems", i.e. system is divided in subsystems, subsystems are monitored and results are combined to decide on status of whole system
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B

Abstract

A method and system for generating an alert report on board an aircraft, comprising an on-board acquiring module configured to acquire data relating to the aircraft, the data originating from sensors and/or equipment installed in the aircraft. An on-board processing module is configured to detect possible anomalies by automatically partitioning the data into a set of homogeneous groups, each anomaly being revealed by a corresponding datum belonging to no homogeneous group. An on-board alert-emitting module is configured to emit an alert report on each detection of an anomaly. An on-board transmitting module is configured to transmit the alert report to the ground and in real-time.

Claims

1. A system for generating an alert report on board an aircraft, the system comprising:

an on-board acquiring module configured to acquire data relating to the aircraft, the data originating from sensors and/or equipment installed in the aircraft;

an on-board processing module configured to detect possible anomalies by automatically partitioning the data into a set of homogeneous groups, each anomaly being revealed by a corresponding datum belonging to no homogeneous group;

an on-board alert-emitting module configured to emit an alert report on each detection of an anomaly; and

an on-board transmitting module configured to transmit the alert report to the ground and in real-time.

2. The system as claimed in claim 1, comprising:

an on-board buffer memory configured to buffer the data acquired by the acquiring module; and

an on-board smoothing module configured to smooth the buffered data before they are processed by the processing module.

3. The system as claimed in claim 1, wherein the processing module is configured to automatically partition the data using an unsupervised learning technique.

4. The system as claimed in claim 1, wherein the processing module is configured to automatically partition the data using a semi-supervised learning technique by comparing the data to abnormal learning data recorded in an on-board knowledge database.

5. The system as claimed in claim 4, wherein the system comprises:

an acquiring unit configured to acquire learning data relating to at least one aircraft;

a smoothing unit configured to smooth the learning data, thus forming smoothed learning data;

a processing unit configured to automatically partition the smoothed learning data using an unsupervised learning technique generating a first class of normal learning data and a second class of abnormal learning data; and

a recording unit configured to record the abnormal learning data in a knowledge database corresponding to the on-board knowledge database.

6. The system as claimed in claim 5, wherein the acquiring unit is configured to acquire the learning data from a first data source comprising ACMC recordings of a set of aircraft and of various flights and/or other data sources comprising manual requests, electronic logbooks and maintenance reports of the set of aircrafts.

7. An aircraft comprising a generating system as claimed in claim 1.

8. A method for generating an alert report on board an aircraft, comprising:

acquiring data relating to the aircraft originating from sensors and/or equipment installed in the aircraft;

detecting possible anomalies by automatically partitioning the data into a set of homogeneous groups, each anomaly being revealed by a corresponding datum belonging to no homogeneous group;

emitting an alert report on each detection of an anomaly; and

transmitting the alert report to the ground and in real-time.

9. The method as claimed in claim 8, wherein the data is partitioned using a semi-supervised learning technique by comparing the data to abnormal learning data recorded in a knowledge database installed on board the aircraft.

10. The method as claimed in claim 9, wherein the knowledge database is constructed on the ground by:

acquiring learning data relating to at least one aircraft;

smoothing the learning data, thus forming smoothed learning data;

automatically partitioning the smoothed learning data using an unsupervised learning technique generating a first class of normal learning data and a second class of abnormal learning data;

recording the abnormal learning data in the knowledge database; and

installing the knowledge database on board the aircraft.

11. The method as claimed in claim 10, comprising periodically updating the knowledge database.