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 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.
We are looking for a candidate who meets the following requirements :
Preferably you finished a master’s in Systems and Control, Mechanical Engineering, (Applied) Physics, (Applied) Mathematics, Information Technologies, or Electrical Engineering.
Conditions of employment
We offer :
well-known because of many high-tech industries and start-ups. A place to be for talented scientists!