Computing environment system for monitoring aircraft engines

1 . A computing environment system for monitoring aircraft engines, said system being connected to a cluster of servers, wherein said system comprises:

processing circuitry configured to

receive user codes deployed in the server cluster and including specifications of input and output data, said user codes specifying the calculation of a set of indicators representing the health state of an aircraft engine for deployment on a fleet of aircraft engines, the user codes include specifications of input data to be processed in parallel and output data comprising context and health indicators, said user codes being described in at least two different languages chosen from parallel languages of the Spark type as well as business languages of the Scala, Python, or R type,

extract, by an application programming interface (API), said indicators by deploying parallel calculations in the server cluster on temporal flight data from the fleet of aircraft engines and stored in a database distributed over said cluster of servers, such that the API is configured to (i) encapsulate the user codes to cause the user codes to operate identically in different data domains and (ii) automatically deploy the user codes a distributed manner over said cluster of servers,

use said indicators to construct, without supervision, from said indicators, a monitoring model representative of the indicators by implementing predetermined learning functions, wherein the indicators are filtered and ranked on a map, and the monitoring model maps the indicators relative to states of the engines independently of the context, to rank the engines according to similar behaviours, and

display a visual representation of the monitoring model,

wherein the temporal flight data is continuous operating data of the engine from sensors and computers associated with the aircraft engines as well as continuous data from aircraft, said temporal flight data being stored in a system of files distributed over said cluster of servers, and

the processing circuitry is configured to form the temporal vectors by aggregating said temporal flight data on new incoming data flight by flight without requiring processing of a data line of the temporal flight data per step of time.

2 . The system according to claim 1 , wherein the processing circuitry implements a sequencing mechanism configured to implement any recurrences in the extraction of the indicators.

3 . The system according to claim 1 , wherein said indicators include health indicators and corresponding context indicators and wherein the processing circuitry implements is configured to standardise said health indicators according to the corresponding context indicators by implementing regression techniques.

4 . The system according to claim 1 , wherein the indicators extracted by the processing circuitry are stored in a data structure deployed over the cluster of servers.

5 . The system according to claim 1 , wherein the processing circuitry is configured to transform the vector format of the indicators into a matrix format adapted to the application of learning functions.

6 . The system according to claim 1 , wherein the predetermined learning functions include learning algorithms from the following algorithms: Kohonen self-adapting mapping algorithms, anomaly detection algorithms, trend detection and tracking algorithms, algorithms for analysing the operation of a piece of equipment or of a specific system of aircraft engine, event anticipation or prognostic algorithms.

7 . A method for monitoring aircraft engines, said method comprising the following steps:

receiving user codes deployed in the server cluster and including specifications of input and output data, said user codes specifying the calculation of a set of indicators representing the health state of an aircraft engine for deployment on a fleet of aircraft engines, the user codes include specifications of input data to be processed in parallel and output data comprising context and health indicators, said user codes being described in at least two different languages chosen from parallel languages of the Spark type as well as business languages of the Scala, Python, or R type,

extracting, by an application programming interface (API), said indicators by deploying parallel calculations in the server cluster on temporal flight data from the fleet of aircraft engines and stored in a database distributed over a cluster of servers, such that the API is configured to (i) encapsulate the user codes to cause the user codes to operate identically in different data domains and (ii) automatically deploy the user codes a distributed manner over said cluster of servers,

using said indicators to construct, without supervision, from said indicators a monitoring model representative of the indicators by implementing predetermined learning functions, wherein the indicators are filtered and ranked on a map, and the monitoring model maps the indicators relative to states of the engines independently of the context, to rank the engines according to similar behaviours, and

displaying a visual representation of the monitoring model,

wherein the temporal flight data is continuous operating data of the engine from sensors and computers associated with the aircraft engines as well as continuous data from aircraft, said temporal flight data being stored in a system of files distributed over said cluster of servers, and

the method includes forming the temporal vectors by aggregating said temporal flight data on new incoming data flight by flight without requiring processing of a data line of the temporal flight data per step of time.

8 . A non-transitory computer readable medium that stores a computer program comprising code instructions for the implementation of the method for monitoring according to claim 7 when said code instructions are executed on the computing environment system.