PhD position on Characterizing input composition by statistical learning
Last modification : Wednesday, August 17, 2022
At the Department of Computer Science of KU Leuven, the Numerical Analysis and
Applied Mathematics research unit NUMA works on numerical methods, algorithms
and software for simulation and data analysis, with applications in many
fields in science and engineering. The research in NUMA focuses, amongst
others, on simulation, optimization, data science, uncertainty quantification
and high performance computing. The present industrial linked PhD position,
which will be carried out in close contact with ArcelorMittal Belgium, fits in
a 4-year project funded by the Horizon Europe Framework Program.
In the steel production process, two important ingredients are combined: pig
iron (or crude iron) and scrap (recycled metal materials). Depending on
the scrap quality, which is determined by the concentration of impurities such
as sulfur, the amount of scrap going into a single production batch can be
adjusted. By better characterization of scrap input impurities it is possible
to reduce CO2 emissions by using less pig iron.
The aim of this PhD position is to develop methods and algorithms to model the
distributional properties of sulfur and other impurities in the different
scrap piles, based on available measurements which are present in the current
steel production process. For this, you will be in close contact with
modelling specialists from ArcelorMittal Belgium. You will apply a number of
state-of-the-art methods and algorithms and determine which method is the most
suitable to track the interesting properties of the scrap piles and include
ways to manage their uncertainties. This will involve Markov Chain Monte Carlo
and Gaussian process techniques, whose efficiency will depend on the quality
and the features of the data. Validation of the methods can be performed by
effective measurements on the scrap piles.
A second part of the work is centered around time dependence of the stochastic
model. Since scrap piles are dynamic and their properties change over time, it
is necessary that the stochastic distributions of the impurities in the scrap
piles can be adjusted over time. An additional difficulty with time dependent
modelling is the difference in rate at which scrap piles change and the rate
at which information from the production process flows back through the
You have a Masters degree in Mathematics, Applied Mathematics, Computer
Science, Engineering or Physics.
You have experience in programming and a general interest in the
development of numerical methods and their application in engineering.
Excellent proficiency in English is required, both oral and written.
We offer a full-time position as a doctoral researcher for four years.
You will receive a salary or a monthly tax-free grant. In addition, health
insurance and social security will be covered.
You will work in a supportive multi-disciplinary research team of
engineers and scientists with backgrounds in scientific computing,
computer science, mathematical engineering and data science.
You will from the start have the opportunity (and are encouraged) to be
actively involved in an industrial environment by partly working on-site
at ArcelorMittal Belgium.
You will build up research and innovation skills that are essential for a
future career in research and development, both in industry and academia.
For more information please contact Prof. dr. ir. Dirk Nuyens, tel.: +32 16 37
35 59, mail: email@example.com or Mr. Ward Melis, tel.: +32 16 32 06 16,
KU Leuven seeks to foster an environment where all talents can flourish,
regardless of gender, age, cultural background, nationality or impairments. If
you have any questions relating to accessibility or support, please contact us