Artur gives a webinar on generative AI for Chemical Process Engineering in IChemE

Artur gives a webinar on generative AI for Chemical Process Engineering In IChemE

You can find the video here:

It is envisioned that generative artificial intelligence (AI) will have a huge impact on chemical process engineering. Generative AI has gained immense traction across diverse sectors, exemplified by remarkable achievements such as ChatGPT’s language generation and GitHub Copilot’s code generation. Generative AI also holds immense potential to reshape chemical process engineering by offering advanced data handling, modeling and decision-support capabilities, ultimately driving innovation and efficiency in the industry. However, there are only limited applications in chemical engineering so far. Promising applications are proposed for generative AI in process engineering including autocompletion of flowsheets, autocorrection of engineering documents, P&ID generation and AI-assisted HAZOPs.

​It is felt there is a need to conduct research and development in three main areas to ultimately develop useful generative AI tools in our domain: data, information representation, and model architectures including mechanistic information.

Key publications

• Vogel, G., Balhorn, L. S., & Schweidtmann, A. M. (2022). Learning from flowsheets: A generative transformer model for autocompletion of flowsheets. arXiv preprint arXiv:2208.00859.
• Vogel, G., Balhorn, L. S., Hirtreiter, E., & Schweidtmann, A. M. (2022). SFILES 2.0: An extended text-based flowsheet representation. arXiv preprint arXiv:2208.00778.