@misc {pub5945,
	title = {AI-supported Evolutionary Design Optimization for Engineering Applications},
	author = {Stefan Menzel},
	year = {2024},
	month = {November},
	abstract = {Machine learning and data science successfully contribute to system design and optimisation from a variety of perspectives and on different granularity levels in industrial applications. Among them are aspects like revealing hidden information from data to increase optimisation efficiency, learning surrogate models of costly simulation data for fast optimisation runtime, transferring knowledge between tasks, or exploring deep learning architectures for shape generation. As a result, humans acquire a deeper understanding of the application problem, process parameter adaptations to save resources, and explore the search space to find innovative solutions. These are important aspects when it comes to design optimisation in the automotive industry. Here, e.g., we search for optimal geometries for aerodynamic efficiency, apply system optimisation for generating design concepts including human preferences, or use geometric deep learning to build efficient shape representations for design optimisation. With the current advances in processing large data sets for generative AI systems and text-to-X models, we can explore new ways of design optimisation and interfacing by tackling research questions such as assessing the potentials of integrating generative models for engineering applications, as well as improving cooperation between humans and computers for informed decision-making.},
	publisher = {HRI-EU},
	booktitle = {Invited Talk Hochschule Aalen}
}