{"ID":5438875,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T13:00:35.913618206Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31614","arxiv_id":"2606.31614","title":"Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models","abstract":"Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C\u0026E) matrices remain central to process control and safety, yet their creation is still predominantly manual, document-driven, and prone to inconsistency. This paper presents a semantic-AI framework that automates the generation of C\u0026E logic by combining a knowledge graph (KG) with a constrained large language model (LLM) layer. The KG builds on an established modular alignment ontology to represent process structure, operating modes, faults, symptoms, causes, and mitigation actions in a machine-interpretable form. The LLM then transforms this information into operator-ready safety narratives and Semantic Web Rule Language (SWRL) rules under strict ontology and vocabulary constraints, grounding the generated artifacts in the underlying semantic model. The workflow is demonstrated on a modular process plant, showing how engineering semantics, diagnostic relations, and machine-verifiable specifications can be generated from a unified knowledge representation with reduced manual effort.","short_abstract":"Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C\u0026E) matrices remain central to process control and safety, yet their creation is still predominantly manual, document-driven, and prone to inconsistency. This paper presents a semantic-AI framework that automates the gen...","url_abs":"https://arxiv.org/abs/2606.31614","url_pdf":"https://arxiv.org/pdf/2606.31614v1","authors":"[\"Javal Vyas\",\"Milapji Singh Gill\",\"Mehmet Mercangöz\"]","published":"2026-06-30T13:03:46Z","proceeding":"eess.SY","tasks":"[\"eess.SY\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}