Knowledge graphs

Knowledge graphs link engineering data in a meaningful, machine-readable way. We build knowledge graphs from chemical engineering literature and from engineering diagrams, and use them as a foundation for AI applications.

Challenge

Chemical engineering knowledge is spread over heterogeneous and mostly unstructured sources: scientific articles, simulation files, engineering diagrams, and reports. AI methods, and large language models in particular, need this information in a structured and linked form to give reliable answers.

Our approach

This line of work builds on earlier research on chemical data intelligence and on machine learning in chemical engineering, which started during Artur M. Schweidtmann's time at the University of Cambridge and RWTH Aachen University. We develop data processing pipelines that transform unstructured data into structured, linked data:

  • The Chemical Engineering Knowledge Graph (ChemEngKG) mines literature data and stores the results in a knowledge graph (software).
  • Smart P&IDs as knowledge graphs. Using the DEXPI standard and our library pyDEXPI, P&IDs are represented as knowledge graphs that large language models can query, as in ChatP&ID.
  • FAIR research data. In 2023, Artur M. Schweidtmann was a visiting professor at Leibniz Universität Hannover with the Open Research Knowledge Graph (ORKG) team of Prof. Sören Auer, working on semantic web technologies and FAIR research data.

Key publications

  • Alimin, A. A., & Schweidtmann, A. M. (2026). GraphRAG for engineering diagrams: ChatP&ID enables LLM interaction with P&IDs. AIChE Journal, 72, e70540. doi:10.1002/aic.70540
  • Goldstein, D. P., Schulze Balhorn, L., Alimin, A. A., & Schweidtmann, A. M. (2025). pyDEXPI: A Python framework for piping and instrumentation diagrams (P&IDs) using the DEXPI information model. Systems and Control Transactions (Proceedings of ESCAPE 35). doi:10.69997/sct.139043
  • Weber, J. M., Guo, Z., Zhang, C., Schweidtmann, A. M., & Lapkin, A. A. (2021). Chemical data intelligence for sustainable chemistry. Chemical Society Reviews, 50(21), 12013–12036. doi:10.1039/D1CS00477H · Details
  • Schweidtmann, A. M., Esche, E., Fischer, A., Kloft, M., Repke, J.-U., Sager, S., & Mitsos, A. (2021). Machine learning in chemical engineering: A perspective. Chemie Ingenieur Technik, 93(12), 2029–2039. doi:10.1002/cite.202100083 · Details
← All projects