Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models

The increasing complexity of smart manufacturing environments demands interfaces that can translate high-level human intents into machine-executable actions. This paper presents a unified framework that integrates instruction-tuned Large Language Model (LLM) with ontology-aligned Knowledge Graphs (KGs) to enable intent-driven interaction in Manufacturing-as-a-Service (MaaS) ecosystems. We fine-tune Mistral-7B-Instruct-V0.2 on a domain-specific dataset, enabling the translation of natural language intents into structured JSON requirement models. These models are semantically mapped to a Neo4j-based KG grounded in the ISA-95 standard, ensuring operational alignment with manufacturing processes, resources, and constraints. Our experimental results demonstrate significant performance gains over zero-shot and 3-shot inference baselines using the pre-trained Mistral-7B-Instruct-v0.2 model without fine-tuning, achieving 89.33% exact match accuracy and 97.27% overall accuracy. This work lays the foundation for scalable, and adaptive human-machine collaboration in smart manufacturing, with promising implications for real-time applications.