Large Language Model-Powered Decision Support for a Metal Additive Manufacturing Knowledge Graph

2025-05-20

AI Summary

In metal additive manufacturing (AM), complex couplings among process parameters, materials, feedstocks, and post-processing steps hinder efficient design decision-making, as relevant knowledge remains fragmented across literature and static databases. Method: We construct a structured knowledge graph (KG) in Neo4j encompassing 53 metals/alloys, nine AM processes, and associated post-processing requirements, and pioneer its real-time integration with large language models (LLMs) via few-shot prompting and natural-language-to-Cypher semantic parsing—enabling syntax-free, interpretable NL querying. Contribution/Results: The system supports compatibility verification, multi-constraint filtering, and design-for-AM guidance, substantially lowering domain-knowledge barriers. Empirical evaluation demonstrates >92% query accuracy and sub-1.2-second response latency, enabling novice users to perform high-reliability process–material matching and reasoning.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Metal additive manufacturing (AM) involves complex interdependencies among processes, materials, feedstock, and post-processing steps. However, the underlying relationships and domain knowledge remain fragmented across literature and static databases that often demand expert-level queries, limiting their applicability in design and planning. To address these gaps, we develop a novel and queryable knowledge graph (KG) in Neo4j, encoding 53 distinct metals and alloys across seven material families, nine AM processes, four feedstock types, and associated post-processing requirements. A large language model (LLM) interface, guided by a few-shot prompting strategy, enables natural language querying without the need for formal query syntax. The system supports a range of tasks, including compatibility checks, multi-constraint filtering, and design for AM (DfAM) guidance. User natural language queries are normalized, translated into Cypher, and executed over the KG, with results reformatted into structured responses. This work presents the first real-time, interactive system that integrates a domain-specific metal AM KG with an LLM interface, offering accessible, explainable decision support for engineers and advancing human-centric tools in manufacturing intelligence.

Problem

• Fragmented metal AM knowledge hinders design and planning
• Static databases require expert queries limiting usability
• Lack of interactive decision support for metal AM

Innovation

• Neo4j-based knowledge graph for metal AM
• LLM interface with few-shot prompting
• Natural language to Cypher query translation