Doctoral fellow

Last application date
Dec 31, 2022 00:00
Department
TW08 - Department of Electromechanical, Systems and Metal Engineering
Contract
Limited duration
Degree
M.Sc. in (electro-)mechanical engineering or related engineering fields such as control & automation.
Occupancy rate
100%
Vacancy type
Research staff

Job description

Short job description
We are seeking a highly motivated and talented PhD researcher in the field of physics-informed modelling for the control design of real-world industrial machines. Our goal is to combine data-driven and physics-based modelling techniques within a generalized probabilistic machine learning framework to bring value to the control design and real-time tuning of industrial machines, mechatronic systems and processes.
You will work on a cutting-edge project that pursues first-time-right control design of real-world industrial machines by leaning on virtual experiments. You are responsible for the development of new modeling techniques that extract predictive models from data, accelerate learning using informed physical priors, and allow for real-time updating so to minimize the reality gap at all times. Your techniques will be incorporated into a larger framework that supports operators and experts with the machine commissioning and real-time tuning of industrial machines and processes.
You have a Master's degree in a relevant field, such as (electro-)mechanical engineering, control and automation, computer science, physics, or engineering in general. Ideally candidates have experience in data-driven as well as physics-based modelling techniques and will be able to demonstrate a strong understanding of these concepts before starting this position.
If you are passionate about conducting cutting-edge research in the field of physics-informed modelling for real-world machines, we encourage you to apply for this exciting opportunity.
Detailed job description
You will work on the REXPEK project, short for ‘Reproducing EXPErt Knowledge’. The project resides in the virtual commissioning paradigm where (near) first-time-right commissioning of machines is pursued by means of model-based design approaches. The key idea is to determine optimal machine settings through virtual experiments. For this concept to work, the reality gap between the virtual and physical experiments needs to be minimized. Furthermore, this reduction needs to come with a minimal number of attempts that need to be chosen carefully so that they yield as much information as possible. The project takes a unique angle to this problem by taking into account the human as a valuable resource both as a knowledge base, a performance sensor or critique as well as a discriminator between what could be good or bad settings. The project has the overall aim to research new methodologies to assist operators with machine commissioning and real-time tuning; and this way accelerate and enable developments within the Industry 5.0 paradigm.
Your specific research challenge lies in the development of hybrid modelling methods that combine physics-based expert models with historical and on-site data whilst striving towards real-time model evaluation and model improvement. You will pursue a probabilistic modelling approach taking into account unobservable context variables and will work towards iterative sampling schemes to identify actual context probabilities on the basis of physical experiments. In the past years our research group has accumulated critical expertise and laboratory infrastructure to support this PhD.
In this role, you will be responsible for

  • conducting research into physics-informed modelling techniques for the control design
  • developing new methods for combining probabilistic machine learning with physics-based modelling
  • presenting your research at conferences and in journals
  • cooperating with researchers active within the research group and outside

Job profile

Your profile

We look for a highly motivated and talented individual with at least some background in (probabilistic) machine learning, physics based modelling and numerical simulation of mechatronic applications. You are quick-witted, have an appetite for the theoretical and are keen on applying and/or improving your programming skills.

  • You hold a M.Sc. in (electro-)mechanical engineering or related engineering fields such as control & automation.
  • You have proven experience with the control, modelling and simulation of (electro-)mechanical, mechatronic & robotic systems.
  • You have proven experience in Python.
  • You have experience in or understanding of artificial intelligence and (probabilistic) machine learning methods.
  • You have a team player mindset, a strong personality and work in a result-oriented manner.
  • You are creative and willing to work in a multidisciplinary context.
  • You are proficient in oral and written English and have strong communication skills.
  • You are willing to extend your network and able to talk on technical matters.

How to apply

Send your CV, containing 1 or more references and a motivation letter to dr. Tom Lefebvre (Tom.Lefebvre@ugent.be) and professor Guillaume Crevecoeur (Guillaume.Crevecoeur@UGent.be) including ‘PHYSICS-INFORMED MODELLING PHD’ in the email subject before Saturday 31/12/2022. If you pass the pre-selection, you will receive further instructions on the selection process and will be invited for an online job interview.