Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models

2026-06-30

AI Summary

Manually authoring causal logic specifications—such as interlock conditions and cause-effect matrices—is inefficient and prone to inconsistencies, failing to meet the demands of modern process safety. This work proposes the first semantic-AI framework that integrates a modular, ontology-aligned knowledge graph with a constrained large language model to enable end-to-end automatic generation of verifiable safety specifications from a unified semantic representation. By leveraging ontology-based modeling, prompt constraints, SWRL rule generation, and machine-interpretable semantic representations, the approach successfully produces causally coherent, diagnostically explicit, and machine-verifiable specifications in a modular plant case study. The method substantially reduces manual intervention while significantly enhancing the automation and reliability of safety specification generation.

Abstract

Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C&E) 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&E 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.

Problem

• cause-and-effect specification
• engineering specifications
• manual documentation
• inconsistency
• process safety

Innovation

• knowledge graph
• large language model
• cause-and-effect matrix
• semantic AI
• SWRL