Phd Marie Curie Moira - Leuven, België - Siemens Mobility

Siemens Mobility

Geverifieerd bedrijf

Leuven, België

2 weken geleden

Geplaatst door:

Sophie Dubois

beBee Recruiter

Beschrijving

Job ID:

Company:

Siemens Industry Software NV
Organization:
Digital Industries
Job Family:
Internal Services
Experience Level:
Student (Not Yet Graduated)
Full Time / Part Time:
Fulltime
Remote vs Office:
Hybrid (Remote/Office)
Contract Type:
Fixed Term
Marie Curie Early Stage Researcher
MOIRA
Automatic Multi-Sensor Validation MethodsSiemens Digital Industries Software (DISW), headquartered in Leuven, Belgium, has an open position for an earlystage researcher (ESR) in frame of the European Training Network on Monitoring Large-Scale Complex Systems ("MOIRA"), funded by the European Commission through the H2020 "Marie Skłodowska-Curie Innovative Training Networks" (ITN) program.
The objective of the MOIRA project is to develop the next generation of knowledge discovery methodologies, algorithms and technologies, so enabling datadriven, plantwide fleet monitoring, with the focus on realtime diagnostics and prognostics. This objective will be achieved by having a collaborative network of ESRs hosted by top European universities, research institutes, windturbine and plant operators, OEMs and industrial partners with an expertise in mechanical engineering, computer science, signal processing, vibrations, inverse problems, operations maintenance, data analytics and networks.

The ESR connected to this vacancy will become part of the research team of the SISW TEST division and will collaborate closely with the SISW staff as well as other international visiting researchers and students.

Moreover, the ESR will also have the opportunity to enroll as PhD student in the doctoral school of academic partner KU Leuven (KUL).

ESR Project Description:

The ESR will research methods that enable the automatic detection of "incorrect" sensor data.

Sensors are exposed to tough operating conditions in many industrial environments (e.g., excavation machines driving on off-road tracks, gantry cranes in steel mills, etc.).

Therefore, a common problem is the occurrence of "measurement anomalies", i.e., where part of the data is incorrect in the sense that there are some deviations from what was intended to be measured.

Examples of measurement anomalies with particular shapes are dropouts, offsets, drifts and spikes, but the measurement anomaly can also be a more subtle problem with the data.

A sophisticated automatic sensor validation method is thus highly sought after.

The ESR will investigate machine-learning methods that are trained to recognize incorrect sensor data.

A systematic approach will be followed:

in the first stage, a supervised learning technique will be embraced, whereby it is assumed that an historical dataset with fully labelled examples is available.

As this assumption might not prove to be practically realizable in many cases, an unsupervised anomaly-detection approach will be investigated in the second stage.

Such an approach does not require labelled data, but is typically more difficult to implement effectively compared to a supervised approach.

An exciting third alternative that will be investigated is a semi-supervised approach, where a small labelled dataset (e.g., acquired from expert user feedback) is available in addition to the larger unlabelled dataset.

Besides the detailed investigation outlined above (supervised - unsupervised - semi-supervised), a particular focus point will be to use the fact that there will be multiple sensors, i.e., there is a certain redundancy in the measurement setup so that some sensors will be measuring related quantities.

While measurement anomalies are non-physical events that occur at random times (so that they will likely not be observed in multiple sensor channels), real physical events likely affect multiple (closely located) sensors.

A comparison between sensor pairs (e.g., linear or nonlinear correlation analysis) could thus be exploited so to better detect the measurement anomalies (for example, to distinguish an incorrect measurement spike from a true physical shock event in the data).

The remuneration is generous and will be in line with the EC rules for Marie Curie grant holders.

It consists of a salary augmented by a mobility allowance, resulting in a net monthly salary of about Euro depending on family status.

Supervisors and main contacts:

Siemens Digital Industries Software:
dr. Bram Cornelis (research manager)

KUL:
prof. Konstantinos Gryllias

Applicants must have
a MSc degree or equivalent in mechanical/mechatronic engineering or related field.

They must have:

Excellent qualification in engineering fields such as mechanics, electronics, physics and mathematics;
Very strong curiosity about machine learning;
Experience with scientific computing and highlevel programming languages such as Matlab or Python.
Affinity with the scientific research methodology;
Capability to work independently and in a team;
Proficient in spoken and written