PhD Physics-Based Learning for Engineering Systems

PhD - EAISI DAMOCLES: Deep Learning with Physics-Based Constraints for the Identification of Engineering Systems

Department(s)

Electrical Engineering

Reference number

V36.5102

The modeling of complex engineering systems is highly challenging. Physics-based models require a cautious application of constitutive assumptions, whereas data-based models require vast amounts of data. The research project “DAMOCLES: Data-Augmented Modeling Of Constitutive Laws for Engineering Systems”, of which this PhD position is a part, targets a breakthrough in the constitutive modeling of such systems in different physical domains by developing a unified multi-tool framework that combines the favorable characteristics of physics-based and data-based approaches. DAMOCLES is an inter-departmental project part of the Eindhoven Artificial Intelligence Institute (EAISI) Exploratory Multidisciplinary AI Research Program (EMDAIR).

The DAMOCLES project is divided into three interlinked sub-projects of which one project is advertised here. The other two DAMOCLES sub-projects are: Identification of constitutive laws with data-driven evolutionary algorithms and Robust Bayesian Uncertainty Quantification.

This open PhD position aims to – starting from a data-driven modeling point of view – learn constitutive laws in a multi-physics setting using an ANN-based Hamiltonian model learning framework. This will be realized by merging state-of-the-art machine learning approaches with system and control methods and physical system insight.

Hamiltonian Neural Networks (HNNs) have been introduced as a physics-informed learning framework. Physical information is included by representing the system dynamics through their Hamiltonian equivalent, which automatically imposes conservation of energy and results in much better generalization properties of the learned model. During this project, the PhD candidate will develop identification methods and theory for system identification using HNNs, broaden the applicability of the HNN modelling framework to a wider range of systems, and realize tools and methods to provide a physical interpretation of the resulting HNN models in terms of the underlying constitutive relations of the data-generating system under consideration.

To accomplish the objectives of the DAMOCLES project, a strong cooperation with the PhD candidates and researchers in the other sub-projects is required. In particular, the results obtained in this PhD project will be evaluated and analyzed on a selected set of overarching benchmark applications.

Tasks

• Study the literature of modeling, machine learning, and nonlinear system identification.
• Development of interpretable, physics-driven, data-driven nonlinear modeling approaches using Hamiltonian Neural Networks.
• Stochastic analysis of consistency and convergence of the results and empirical validation of the techniques on complex physical fluid dynamics/electrical/mechatronic systems.
• Exploration of the steps of the identification cycle for the developed methods from experiment design to verification of model completion (validation).
• Dissemination of the results of your research in international and peer-reviewed journals and conferences.
• Writing a successful dissertation based on the developed research and defending it.
• Assume educational tasks like the supervision of Master students and internships.
• Successful integration in the Eindhoven Artificial Intelligence for Systems Institute.

We are looking for a candidate who meets the following requirements:

• You are a talented and enthusiastic young researcher.
• You have experience with or a strong background in systems and control, mathematics, statistics, and signal processing. Preferably you finished a master’s in Systems and Control, Mechanical Engineering, (Applied) Physics, (Applied) Mathematics, Information Technologies, or Electrical Engineering.
• You have good programming skills and experience (Python is an asset).
• You have good communicative skills, and the attitude to partake successfully in the work of a research team.
• You are creative and ambitious, hard-working, and persistent.
• You have good command of the English language (knowledge of Dutch is not required).

We offer:

• Challenging job in a highly motivated team at a dynamic and ambitious university and a stimulating internationally renowned research environment.
• You will be part of a highly profiled multidisciplinary collaboration where expertise of a variety of disciplines comes together.
• Full-time temporary appointment for 4 years.
• A gross monthly salary and benefits in accordance with the Collective Labor Agreement for Dutch Universities.
• Additionally, an annual holiday allowance of 8% of the yearly salary, plus a year-end allowance of 8.3% of the annual salary.
• An extensive package of fringe benefits (e.g. excellent technical infrastructure).
• Family-friendly initiatives are in place, such as an international spouse program, and excellent on-campus children day care and sports facilities.
• The TU/e offers opportunities for personal development. We do this by offering every PhD candidate a series of courses that are part of the PROOF program as an excellent addition to your scientific education.
• Should you come from abroad and comply with certain conditions, you can make use of the so-called ‘30% facility’, which permits you not to pay tax on 30% of your salary.

The TU/e is located in one of the smartest regions of the world and part of the European technology hotspot ‘Brainport Eindhoven’; well-known because of many high-tech industries and start-ups. A place to be for talented scientists!

More information about the project can be obtained through the project’s supervisory team:

For information about terms of employment, click here  or contact HRServices.flux[at]tue.nl

Please visit www.tue.nl/jobs  to find out more about working at TU/e!

Application

We invite you to submit a complete application by using the 'apply now'-button on this page. The application should include:

• a cover letter (stating personal goal and research interests connecting to one or more of the topics defined above), max 1 page;
• a complete Curriculum Vitae (including contact details of 2 references and a list of publications, if any), max. 2 pages;
• transcripts of BSc and MSc degrees,

All documents should be provided in pdf format. We do not respond to applications that are sent to us in a different way.

We look forward to your application and will screen it as soon as we have received it. Screening will continue until the position has been filled. Promising candidates will be contacted by email.

Please keep in mind you can upload only 5 documents up to 2 MB each. If necessary please combine files.

Both national and international applications to this advertisement are appreciated.