Generative AI for mechanical engineering design and optimization

This Collection supports and amplifies research related to SDG 9 and SDG 12.

The concept of artificial intelligence (AI) as a creative design tool might once have been controversial. But in recent years, generative AI tools have rapidly advanced and are now offering new modes of working and advancing human-AI interaction to explore solution spaces and discover, create and optimise designs.

In this collection we aim to publish exciting advances in the capability of generative AI methods and their application directions within a broad mechanical engineering scope. We are using an inclusive definition of mechanical engineering which can include materials, manufacturing, structural, aerospace and interdisciplinary research. Overarching goals include structural integrity and safety, material and energy efficiency, manufacturability and cost-effectiveness, functionality and performance advances, compliance and regulatory requirements. These goals amplify research related to the United Nations Sustainable Development Goals (SDGs), notably SDG 9 (Industry, Innovation, and Infrastructure) and SDG 12 (Responsible Consumption and Production). Specific research directions might include, but are not limited to, generative  or data-driven design, design automation, topology and structure optimization, additive manufacturing, shape and form generation.

We are happy to consider all AI approaches, including multi-modal generative models, physics-informed AI, explainable AI for design, inverse modeling, diffusion models with or without guidance, Large Language Models or Vision Language Models, Transformer-based auto-regressive models and Representation Learning Models amongst others. For researchers working with proprietary large language models such as GPT we highly recommend reproduction of findings with open-source models (such as LLAMA) where all details (models, prompts, scripts etc) can be shared to ensure fair benchmarking with the literature in future works.