项目介绍

2025年4月10日

Job description

Short job description

• We are seeking a highly motivated and talented PhD researcher in the field of system identification and control engineering for mechanical/mechatronic systems. You will work on a strategic research project funded by the Flanders Make. In this project we want to research and develop a transformer-based framework that couples with physics-based models to handle multiscale, multirate and multimodal data in mechatronics. This paves the way to extract actionable insights, i.e. underlying mechanisms that are active within the mechatronic system and its interaction with environment, for improved monitoring and realizing high product quality. From the drawbacks residing in classical physics-based models and data-driven models we want to develop hybrid transformer models that can find both short- and long-term time dependencies without overfitting and requiring large amounts of data. The methodologies will be developed and validated on complex real-world mechatronic systems.
• This research will be in collaboration with senior researchers within the research group and will be done together with researchers affiliated to Flanders Make.
• You have a Master’s degree in a relevant field, such as control and automation, mechanical engineering, robotics, electromechanical or mechatronics engineering. Ideally candidates have experience in system identification, theoretical and numerical system modeling techniques, control engineering; as well as notions on real-world mechatronic, robotic, mechanical systems, 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 transformer-based models using physics priors to interpret multiscale, multirate and multimodal data, we encourage you to apply for this exciting opportunity.

Detailed job description

• You will work on a strategic research project funded by the Flanders Make.
• Your task will be to start from in-house hybrid physics-based data-driven models and explore extensions with attention layers. Meanwhile you will investigate the suitability of transformers without physics on industrial datasets based on in-house wind turbine, motors, winding machine lab setups. You will investigate different types of attention-layers, by looking at cross-attention and couple physics priors on different levels in transformer models. You will research strategies on including physics and enhance active learning as well as aim at reducing catastrophic forgetting. You will research how to uncover uncertainties that are hidden to sensors and not included in physics priors within your transformer-based hybrid physics-based modeling techniques. You will benchmark your new system identification and modeling tools on real-world data, i.e. wind turbine, motors, winding machine lab setups; with respect to its ability to handle multiscale, multirate and multimodal data.
• In the past years our research group has accumulated critical expertise and laboratory infrastructure to support this PhD.
• You will be responsible for
  • conducting research into physics-informed transformer-based modeling techniques for real-world mechatronic applications
  • developing new methods for coupling physics priors to transformers that can interpret multiscale, multirate and multimodal data
  • seeking for industrial and societal impact and adoption of your methodologies
  • presenting your research at conferences and in journals
  • cooperating with researchers active within the research group and outside

Job profile

• We look for a highly motivated and talented individual with at least some background in control and electromechanical engineering, having knowledge in real-world mechatronic applications and has system identification and modeling experience. You are quick-witted, have an appetite for the theoretical and experimental, and willing to apply and/or improve your programming skills.
• You hold a M.Sc. in mechanical engineering or related engineering fields such as control & automation, robotics.
• You have proven experience with modelling and system identification of mechatronic systems.
• You have proven experience in Python and/or MATLAB.
• You have experience in or understanding of physics-based modelling and data-driven modelling
• You have experience in mechatronic hardware and software.
• 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.

WHAT WE CAN OFFER YOU

• We offer a full-time position as a doctoral fellow, consisting of an initial period of 12 months, which – after a positive evaluation, will be extended to a total maximum of 48 months.
• Your contract will start on 09/01/2025 at the earliest.
• The fellowship amount is 100% of the net salary of an AAP member in equal family circumstances. The individual fellowship amount is determined by Team Personnel Administration based on family status and seniority. A grant that meets the conditions and criteria of the regulations for doctoral fellowships is considered free of personal income tax. Click here for more information about our salary scales
• All Ghent University staff members enjoy a number of benefits, such as a wide range of training and education opportunities, 36 days of holiday leave (on an annual basis for a full-time job) supplemented by annual fixed bridge days, bicycle allowance and eco vouchers. Click here for a complete overview of all the staff benefits.
• Access to state-of-the-art tools and facilities, a network of Flemish companies active in the manufacturing industry, and the possibility to collaborate with other research groups.
• The time to apply and improve your knowledge and skills on state-of-the-art in machine learning, (probabilistic) modelling, system identification and numerical optimization.

How to apply

Send your CV containing one or more references, copy of your diploma (if already in your possession) and a motivation letter to Annelies.Coene@UGent.be including ‘TRANSFORMER PHD’ in the email subject before Monday 19/05/2025.

We do not accept late applications.

For more information about this vacancy, please contact Annelies Coene, +32(0)9/264.79.18)