PaA – Partnership Area

Project

PaA-5

AI Based Simulation of Transient Physical Systems – From Benchmarks to Hybrid Solutions

Project Heads

Martin Eigel, Hanno Gottschalk, Alexander Klawonn

Project Members

Onur Tanil Doganay

Project Duration

01.01.2024 − 31.12.2025

Located at

TU Berlin

Description

AI tools have entered the application area of industrial physics-based simulations, but there is still little knowledge on the actual strengths and weaknesses of the different methods. We develop a systematic benchmark of various recent AI techniques with
regard to their industrial applicability and develop hybrids that combine their respective strengths.

Toward this end, we apply three different AI techniques to two reference problems that sufficiently capture the difficulties and complexities of applications from the industry partner Siemens Energy. The two reference problems are explained in detail below. As for the three AI techniques to benchmark we investigate

• Physics-Informed Neural Networks (PINNs) since they have become a widely popular technique to solve complex partial differential equations (PDEs),
• Graph Neural Networks (GNNs) which take the approach of learning physical behavior on a local scale (the communication
  between nodes across edges) and generalize to the global problem setting at hand,
• and Generative AI, where we consider Generative Adversarial Networks (GANs).

For this project we aim to successfully tackle the two reference problems with each of the three AI techniques and benchmark their performances. Furthermore, with these insights we intend to develop hybrid approaches, i.e., combinations of the three techniques.

Reference Problems

There are two problems in this project, which serve as a reference to evaluate the performance of the different methods. We refer to them as reference problems. Both of them describe heat transfer phenomena which, in general, are encountered in many different technical applications where systems or components are heating up during operation.

The applications we have in mind here are assets of the electrical grid, such as high-power switch gears or transformers. In these kinds of components, one major heat source is the electrical current’s power loss in the conductors, which might have a cross sectional diameter of up to ten centimeters or more. Different cooling mechanisms are utilized to keep the system’s temperature below the respective design limits. One of the central contributors in this context is convection, a mechanism which is often difficult to simulate in complex settings (especially in its evolution over time) due to being a fluid-solid interaction. The two reference problems we consider are therefore both describing primarily convection phenomena. The first reference problem (A) focuses on natural convection around conductors in air while the second reference problem (B) describes a setting where conductors are actively cooled by an oil flow, i.e., forced convection.

The general reasoning behind the two chosen problems was to include the physical phenomena which make their simulation challenging while keeping the problem complexity as low as possible, to avoid high costs for training data generation as well as effort for data handling. This is also the reason why both problems are defined in 2D instead of 3D.

Problem A – Natural Convection

This first problem describes two conductors in air with gravity (g) acting downwards, see the figure below. The two aluminum conductors are positioned vertically aligned with some distance between them, so that a convective air stream from the conductor below will meet the conductor above and influence its temperature. A respective heat source is defined on both conductors, so that they will heat up with time. The two conductors are enclosed in a box which has a fixed ambient temperature at its boundary, allowing the generated heat from the conductors to leave the domain. Consequently, the system cannot increase its average temperature indefinitely but will converge to a stationary state. However, due to turbulence there will still be small flow field fluctuations in this quasi-static converged state. Note the authors are aware that turbulence is a 3D-phenomenon while the considered problem is only in 2D. But even if physically not fully accurate, the chaotic behavior is also encountered in a 2D setup.

Problems like this are encountered for example in high-power, gas-insulated switch gears. Here, not two but three conductors (three-phase current) are enclosed in a metal hull containing an insulating gas (i.e., pressurized air).

Problem B – Forced Convection

The second problem describes a solid copper block which heats up over time and is actively cooled by an oil flow, see the figure below. The copper block is fully immersed into the oil so that all the heat energy generated here will be transferred to the oil which will carry it across the domain boundary at the outlet. Due to the adiabatic walls, this is the only way how the heat energy can leave the domain. The fresh oil at the inlet has a fixed temperature, so that, over time, a stationary state will be reached.

This problem resembles the situation in an oil-cooled high-power transformer. Instead of a copper block, one would find multiple smaller copper blocks (actually, these are not solid blocks but many copper wires which are the transformer windings) insulated by paper.

Project Webpages

Related Publications

Related Picture