Intelligent Human-Machine Partnership for Manufacturing: Enhancing Warehouse Planning through Simulation-Driven Knowledge Graphs and LLM Collaboration
🤖 AI Summary
To address insufficient human–machine collaboration in manufacturing planning and the difficulty of translating simulation insights into actionable knowledge for human decision-makers, this paper proposes a simulation-driven collaborative intelligence system. The method introduces a novel “dynamic knowledge graph construction + dual-loop LLM agent reasoning” mechanism: (1) it automatically constructs a semantically enriched knowledge graph from simulation data; and (2) it deploys an LLM-based agent that performs iterative reasoning, natural-language query generation, and traceable verification—enabling planners to interact via natural language and obtain interpretable, auditable operational insights. Evaluation shows the system achieves 99.8% accuracy in bottleneck identification and supports cross-process root-cause tracing. It significantly reduces cognitive load, enhances expert decision-making efficiency and analytical depth, and—critically—preserves human-centered analytical modeling and decision authority.
Application Category
📝 Abstract
Manufacturing planners face complex operational challenges that require seamless collaboration between human expertise and intelligent systems to achieve optimal performance in modern production environments. Traditional approaches to analyzing simulation-based manufacturing data often create barriers between human decision-makers and critical operational insights, limiting effective partnership in manufacturing planning. Our framework establishes a collaborative intelligence system integrating Knowledge Graphs and Large Language Model-based agents to bridge this gap, empowering manufacturing professionals through natural language interfaces for complex operational analysis. The system transforms simulation data into semantically rich representations, enabling planners to interact naturally with operational insights without specialized expertise. A collaborative LLM agent works alongside human decision-makers, employing iterative reasoning that mirrors human analytical thinking while generating precise queries for knowledge extraction and providing transparent validation. This partnership approach to manufacturing bottleneck identification, validated through operational scenarios, demonstrates enhanced performance while maintaining human oversight and decision authority. For operational inquiries, the system achieves near-perfect accuracy through natural language interaction. For investigative scenarios requiring collaborative analysis, we demonstrate the framework's effectiveness in supporting human experts to uncover interconnected operational issues that enhance understanding and decision-making. This work advances collaborative manufacturing by creating intuitive methods for actionable insights, reducing cognitive load while amplifying human analytical capabilities in evolving manufacturing ecosystems.
Problem
Research questions and friction points this paper is trying to address.
Bridging human-system gaps in manufacturing planning
Transforming simulation data into accessible operational insights
Enhancing collaborative bottleneck identification with AI reasoning
Innovation
Methods, ideas, or system contributions that make the work stand out.
Integrates Knowledge Graphs with LLM agents for manufacturing analysis
Transforms simulation data into semantic representations for natural interaction
Enables collaborative bottleneck identification through iterative reasoning
🔎 Similar Papers
No similar papers found.
