IEEE - Aerospace and Electronic Systems - June 2021 - 59

Credit: Image licensed by Ingram Publishing
Specifically, this article describes a data mining environment
(see Figure 1) to help an expert to establish and
to modify over the time the sequence of ground tests and
to understand the influence of every fault test (incidence)
on the A400M ground testing time. (Note that in this article,
several figures omit data (such as the names of the stations,
user codes, test codes, or the codes of the aircraft)
due to a confidentiality agreement between Airbus DS and
the University of Seville.)
A400M AIRCRAFT'STESTDATA
For the data mining process, a dump of the simulation
database, as well as files extracted from the folder tree of
the test system, were used as the data source. The test system
includes a data integration system [7] that provides
transparent access to a collection of data stored in multiple,
autonomous, and heterogeneous data sources. The
data related to simulations condense all the information
recorded prior to the real-world test of the airplane. The
data used for the folder tree include both the recorded files
with the results of various tests in the past and the source
code of tests executed on those aircraft. A preliminary
data exploration was programmed with the IBM SPSS
Modeler 18 tool. This tool is a software application for
data mining and text analytics developed by IBM and
used to perform analytic tasks. It has a visual interface
that allows users to leverage statistical and data mining
algorithms. The aim of the data mining process was to
analyze the data source in order to manage the following.
The test sequence (the relative location of each test
in the full test sequence).
The classification of the test (i.e., incidence, warning,
or success).
The timing of the test (the start and end dates of a
successful test).
The influence of external factors on the test (the aircraft
code, the type of test, the technological area,
the number of signals defined for the test, the test
length or the number of sections of the test, the station
and workstation, the concurrence or the number
of executions of other tests in parallel, and the identifier
of the user who executed the test).
It is necessary to remember that Airbus DS considers
two types of incidences [8]: abortive incidences (incidences
that imply the failure of the test) and nonabortive incidences
or warnings (incidences that do not imply the
mandatory termination of the test and, therefore, the operator
may continue with the execution of the test).
In the first phase of the work, several tasks were develFigure
1.
Data mining environment for aircraft test management.
JUNE 2021
oped: first, all the available information was processed for
each test execution extracted from the simulation environment
and, second, the preparation of this data was performed.
To this end, the set of tables from the database of
Airbus DS as well as the historic files of the tests were
used. A historic file is a log file generated during the execution
of a test that records information on acquisition
data and relevant events (such as the information of an
incidence that occurred during execution). For the
described environment, the information from the simulation
data for eight aircraft has been used. Only the fully
completed tests have been included in the sample. The
IEEE A&E SYSTEMS MAGAZINE
57
IEEE - Aerospace and Electronic Systems - June 2021

Table of Contents for the Digital Edition of IEEE - Aerospace and Electronic Systems - June 2021
