Internship 2020 – Anomaly detection in time series for flight tests (m/f)

Job description

Airbus Operations SAS

Airbus is a global leader in aeronautics, space and related services. In 2018 it generated revenues of € 64 billion and employed a workforce of around 134,000. Airbus offers the most comprehensive range of passenger airliners. Airbus is also a European leader providing tanker, combat, transport and mission aircraft, as well as one of the world's leading space companies. In helicopters, Airbus provides the most efficient civil and military rotorcraft solutions worldwide.

Our people work with passion and determination to make the world a more connected, safer and smarter place. Taking pride in our work, we draw on each other's expertise and experience to achieve excellence. Our diversity and teamwork culture propel us to accomplish the extraordinary - on the ground, in the sky and in space.

Job Description

What if YOU starts your journey with US!

As part of a school curriculum in initial training , you are looking for a mandatory internship or integrated into a gap year that will allow you to validate your studies. The internship duration is 4 to 6 months maximum.

We offer you to work in a world-leading company which is at the heart of a digital transformation, at the cutting edge of research and innovation.

We are looking for a Machine Learning and Statistics Specialist (m/f) who will be joining us at Airbus site in Toulouse Saint-Martin.

This internship is to be filled from February 2020 (the dates are subject to a certain flexibility)

You will be joining the Data Processing team in the Flight and Integration tests department of AIRBUS. This 50 passionate people are in charge to define, configure, collect, process and distribute tests data for all the stakeholders in relation to development and production activities (lab and flight tests).   

A way to represent time series data conveniently is to use the functional data framework where a time series is represented by a linear combination of (time-dependent) basis functions.

A multivariate time series can be processed as a trajectory, for instance a bivariate time series can be seen as curve in a two-dimensional space from which geometrical features can be extracted to train an anomaly detection model. It has already showed promising results in some cases and requires improvement.

The abnormality is usually rarer than the success and detecting an abnormal observation (an abnormal flight test) in a data set can be viewed as the statistical problem of outlier, or “anomaly”, detection. This problem can be solved by using the statistical notion of functional depth which is specific to functional data. A depth provides an outlier score on each time series and thus eases the detection. Unfortunately, when there are multiple classes of outliers in the data set, the state-of-the-art functional depths fail.

·  Tasks and Responsibilities :

The applicant will have to combine ideas from trajectory considerations of the time series with ideas from functional depths to improve the detection and the interpretability of abnormal flight tests (i.e outliers).

Based on already proposed and experimented new methods on such kind of data, the application will set up further development and experiments on this basis.

Relevant algorithms will be added into an Airbus anomaly detection Python-library. The internship will be supervised by a third year PhD student and a data scientist.

·  Required skills :

You are preparing a master degree in applied mathematics or software engineering and you obtain following competences:

·  Good programming skills in Python, numpy + scipy. R is a plus
·  Ability to understand concept from applied mathematics, statistics, machine learning
·  Knowledge in outlier detection algorithms in time-series or functional data is a plus
·  Appeal for aircraft industry and practical problems
·  Team playEr considering that having fun is of prime importance

·  Soft skills:

·  Rigorous, curious and autonomous
·  Good interpersonal and communication skills
·  Able to integrate into a team and be a flexible team player
·  Good organizational skills
·  Able to analyse and synthesize information

Depending on the specifics of the offer, you may have to travel to another locations.

If your profile catches our attention, you will be invited to perform a video interview during which you will have a few minutes to tell us about your background, motivations and your professional project. Afterwards, your application could be proposed to the managers for further review.

If the prospect of joining our innovative Group motivates you do not hesitate and apply online on our website www.airbus.com/careers !

This job requires an awareness of any potential compliance risks and a commitment to act with integrity, as the foundation for the Company’s success, reputation and sustainable growth.

By submitting your CV or application you are consenting to Airbus using and storing information about you for monitoring purposes relating to your application or future employment. This information will only be used by Airbus.
Airbus is committed to achieving workforce diversity and creating an inclusive working environment. We welcome all applications irrespective of social and cultural background, age, gender, disability, sexual orientation or religious belief.