Development of physics inspired neural networks for condition monitoring of gearboxes

The proposed research track runs at the KU Leuven Mecha(tro)nic System Dynamics (LMSD) division which currently counts more than 100 researchers and is part of the Department of Mechanical Engineering, a vibrant environment of more than 300 researchers (www.mech.kuleuven.be). Doctoral training is provided in the framework of the Leuven Arenberg Doctoral School (https://set.kuleuven.be/phd). LMSD has a longstanding history and internationally highly recognized expertise in the fields of condition monitoring, numerical modeling, engineering dynamics, automotive engineering, vibro-acoustic analysis, identification and robust optimal control of (non-) linear systems, active control and lightweight structure design and analysis. It is also recognized for its yearly Modal Analysis (ISMA) and Acoustics (ISAAC) courses and for organizing the biennial ISMA Noise and Vibration Engineering Conference (www.isma-isaac.be). The research group has a long track record of combining excellent fundamental academic research with industrially relevant applications, leading to dissemination in both highly ranked academic journals as well as on industrial fora. Furthermore, the group contributes to the Flanders Make@KU Leuven Motion Products University Core Lab of Flanders Make. Flanders Make (https://www.flandersmake.be/en) is the strategic research centre for the manufacturing industry in Flanders, stimulating open innovation through excellent research. The research group’s international research flavour is illustrated amongst others by the large portfolio of research projects (https://www.mech.kuleuven.be/en/mod/Projects) which includes regional, national and international funded activities through which the group cooperates with leading mechatronic and machine & vehicle-building companies in Flanders and throughout Europe. More information on the research group can be found on the website: https://www.mech.kuleuven.be/en/research/mod/about and our Linked.In page: https://www.linkedin.com/showcase/noise-&-vibration-research-group/. The PhD will be supervised by Prof. Konstantinos Gryllias.
Website unit

Project
——————
Measuring directly temperatures at critical points of interest is difficult or rather expensive for many industrial machines making accurate monitoring of local temperatures challenging. Often, only a few measurement points are available close to the point of interest (e.g. the junction temperature in power electronics modules) or even impossible to obtain (e.g. temperature at the gear flanks or in the bearing contact of gearboxes). These temperatures however strongly correlate to the performance and degradation rate of the component under consideration.
Therefore in the frames of the Flanders Make SBO project DTF-PINN, PINN (physics inspired neural networks) based virtual sensors for thermal applications will be developed, that are computationally lightweight compared to their physics based counterparts. Physics inspired neural networks have the ability to accurately capture thermal phenomena that are governed by PDEs, while having the potential to run significantly faster than their physics based (FE, FV, LP, …) counterparts. By incorporating physical laws and boundary conditions, the PINN architecture has the ability to learn from fewer and sparser data compared to regular “data hungry” black box Machine Learning techniques.
The focus of this PhD track will be on the development of Physics Inspired Neural Network architectures for the monitoring of gearboxes. In gearboxes, the temperature of the oil, bearings and gear flanks correlate to the operational efficiency, durability and system degradation. In practice a single thermo-couple on the gearbox and/or in the oil is used as an indirect measurement and diagnostic indicator. In the frames of this PhD track, these indirect measurements will be leveraged to estimate local temperatures at key locations to get a better assessment of efficiency, durability and the current condition of the gearbox. The PhD student will develop a condition monitoring framework based on the PINNs and will apply and validate it at gearbox setups. The experimental part of the thesis will include installation of sensors on dedicated test rigs and realization of measurements during acceleration life tests of gearboxes.

Profile
——————
If you recognize yourself in the story below, then you have the profile that fits the project and the research group.
– I have a master degree in engineering, physics, computer science or mathematics and performed above average in comparison to my peers.
– I am proficient in written and spoken English.
– I have a genuine interest in combining sensing techniques, signal processing, machine learning, first principle models and measurement approaches into an innovative toolchain for condition monitoring of gearboxes and I have experience with (at least) some of these topics.
– I have interest in measurements and set up development
– I have good programming skills in Matlab and/or in Python.
– As a PhD researcher of the KU Leuven Mecha(tro)nic System Dynamics (LMSD) division I perform research in a structured and scientifically sound manner. I read technical papers, understand the nuances between different theories and implement and improve methodologies myself.
– Based on interactions and discussions with my supervisors and the colleagues in my team, I set up and update a plan of approach for the upcoming 1 to 3 months to work towards my research goals. I work with a sufficient degree of independence to follow my plan and achieve the goals. I indicate timely when deviations of the plan are required, if goals cannot be met or if I want to discuss intermediate results or issues.
– In frequent reporting, varying between weekly to monthly, I show the results that I have obtained and I give a well-founded interpretation of those results. I iterate on my work and my approach based on the feedback of my supervisors which steer the direction of my research.
– I value being part of a large research group which is well connected to the machine and transportation industry and I am eager to learn how academic research can be linked to industrial innovation roadmaps.
– During my PhD I want to grow towards following up the project that I am involved in and representing the research group on project meetings or conferences. I see these events as an occasion to disseminate my work to an audience of international experts and research colleagues, and to learn about the larger context of my research and the research project.

Offer
——————
– A remuneration package competitive with industry standards in Belgium, a country with a high quality of life and excellent health care system.
– An opportunity to pursue a PhD in Mechanical Engineering, typically a 4 year trajectory, in a stimulating and ambitious research environment.
– Ample occasions to develop yourself in a scientific and/or an industrial direction. Besides opportunities offered by the research group, further doctoral training for PhD candidates is provided in the framework of the KU Leuven Arenberg Doctoral School (https://set.kuleuven.be/phd), known for its strong focus on both future scientists and scientifically trained professionals who will valorise their doctoral expertise and competences in a non-academic context. More information on the training opportunities can be found on the following link: https://set.kuleuven.be/phd/dopl/whytraining.
– A stay in a vibrant environment in the hearth of Europe. The university is located in Leuven, a town of approximately 100000 inhabitants, located close to Brussels (25km), and 20 minutes by train from Brussels International Airport. This strategic positioning and the strong presence of the university, international research centers, and industry, lead to a safe town with high quality of life, welcome to non-Dutch speaking people and with ample opportunities for social and sport activities. The mixture of cultures and research fields are some of the ingredients making the university of Leuven the most innovative university in Europe (KU Leuven is the Most Innovative University of Europe – Faculty of Arts). Further information can be found on the website of the university: https://www.kuleuven.be/english/living

Interested?
——————
To apply for this position, please follow the application tool and enclose:
1. Full CV – mandatory
2. Motivation letter – mandatory
3. Full list of credits and grades of both BSc and MSc degrees (as well as their transcription to English if possible) – mandatory (when you haven’t finished your degree yet, just provide us with the partial list of already available credits and grades)
4. Proof of English proficiency (TOEFL, IELTS, …) – if available
5. Two reference letters – if available
6. An English version of MSc thesis, or of a recent publication or assignment – if available
For more information please contact Prof. dr. ir. Konstantinos Gryllias, tel.: +32 16 32 30 00, mail: [email protected].
KU Leuven strives for an inclusive, respectful and socially safe environment. We embrace diversity among individuals and groups as an asset. Open dialogue and differences in perspective are essential for an ambitious research and educational environment. In our commitment to equal opportunity, we recognize the consequences of historical inequalities. We do not accept any form of discrimination based on, but not limited to, gender identity and expression, sexual orientation, age, ethnic or national background, skin colour, religious and philosophical diversity, neurodivergence, employment disability, health, or socioeconomic status. For questions about accessibility or support offered, we are happy to assist you at this email address.