Automated Validation of Textual Constraints Against AutomationML via LLMs and SHACL

2025-06-12

AI Summary

In AutomationML (AML) engineering practice, modeling guidelines rely on informal textual constraints, hindering automated validation. To address this, we propose a semi-automatic formalization method integrating large language models (LLMs) with semantic technologies. First, AML models are mapped to OWL ontologies using RML/SPARQL. Second, LLMs translate natural-language rules into executable SHACL constraints—marking the first application of LLMs to SHACL generation without requiring user expertise in ontologies or formal methods. Finally, automated compliance checking and natural-language explanations are provided. Evaluated on a real-world AML recommendation case, our approach enables end-to-end, interpretable verification of complex rules. Preliminary results confirm high accuracy and practical utility, significantly improving the efficiency and traceability of industrial model specification formalization.

Technology Category

• Knowledge Representation and Reasoning: Description Logics
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

AutomationML (AML) enables standardized data exchange in engineering, yet existing recommendations for proper AML modeling are typically formulated as informal and textual constraints. These constraints cannot be validated automatically within AML itself. This work-in-progress paper introduces a pipeline to formalize and verify such constraints. First, AML models are mapped to OWL ontologies via RML and SPARQL. In addition, a Large Language Model translates textual rules into SHACL constraints, which are then validated against the previously generated AML ontology. Finally, SHACL validation results are automatically interpreted in natural language. The approach is demonstrated on a sample AML recommendation. Results show that even complex modeling rules can be semi-automatically checked -- without requiring users to understand formal methods or ontology technologies.

Problem

• Automating validation of informal textual constraints in AutomationML
• Translating textual rules into SHACL constraints using LLMs
• Enabling constraint checking without formal methods expertise

Innovation

• Map AML models to OWL via RML and SPARQL
• Translate textual rules to SHACL using LLM
• Automatically interpret SHACL results naturally