Search

This paper investigates the use of Large Language Models (LLMs) in engineering complex systems, demonstrating how they can support designers on detail design phases. Two aerospace cases, a system architecture definition and a CAD model generation activities are studied. The research reveals LLMs' challenges and opportunities to support designers, and future research areas to further improve their application in engineering tasks. It emphasizes the new paradigm of LLMs support compared to traditional Machine Learning techniques, as they can successfully perform tasks with just a few examples. [ABSTRACT FROM AUTHOR]

Despite the recognized importance of datasets in data-driven design approaches, their extensive study remains limited. We review the current landscape of design datasets and highlight the ongoing need for larger and more comprehensive datasets. Three categories of challenges in dataset development are identified. Analyses show critical dataset gaps in design process where future studies can be directed. Synthetic and end-to-end datasets are suggested as two less explored avenues. The recent application of Generative Pretrained Transformers (GPT) shows their potential in addressing these needs. [ABSTRACT FROM AUTHOR]

Introducing new technologies in low-income contexts have potential for positive social impact, and such efforts are made by humanitarian engineering non-governmental organisations (NGOs). The impact can increase if a systemic sustainability perspective is considered in the design process. Sustainability criteria are identified using a literature study combined with an empirical study together with a Swedish NGO. These criteria are synthesized into a simplified Sustainability Fingerprint tool which is evaluated and deemed to be useful when introducing new technologies in low-income contexts. [ABSTRACT FROM AUTHOR]

As the world deals with climate change, it is crucial that new products are designed to be more sustainable. Product design strategies which conform to the Circular Economy principles have recently gained attention, which promote sustainability and resource efficiency. However, such strategies require careful consideration of uncertainties and the ways to mitigate them, e.g. by using margins. The pursuit of circularity can inadvertently lead to overdesign as designers strive to mitigate elevated risks, thereby making a product less sustainable. In this paper, we explore this balance. [ABSTRACT FROM AUTHOR]

Software implementations of traditional engineering design methods can potentially enrich the original methods. A study was conducted to better understand how concept generation can be facilitated using software. Participants of the study were asked to generate concepts using either specialized software, or by using traditional means, for applying function-means modeling and morphological matrices. A concept concretization metric was used to evaluate the results, which indicated that there are both positive and negative aspects of performing concept generation using specialized software. [ABSTRACT FROM AUTHOR]