Constructing Dynamic Master Logic Models as Knowledge Graphs for Complex System Diagnostics Using Retrieval-Augmented Large Language Models· 用大模型构建复杂系统诊断的知识图谱
Dynamic Master Logic (DML) provides a hierarchical framework for representing system behavior by linking functional objectives to underlying structural elements. However, DML construction typically relies on expert interpretation of technical documentation, limiting scalability for complex systems. This study presents a framework for automated construction of DML models from system descriptions and their representation as Knowledge Graphs (KG-DML), using Retrieval-Augmented Generation and Large Language Models as enabling tools. Building on prior work with small-scale systems, the framework extends automated KG-DML construction and evaluation to substantially larger and more complex systems. Model construction proceeds across the DML hierarchy using targeted retrieval while preserving func
用大模型和检索增强生成自动构建复杂系统诊断的知识图谱。
- 核心方法
- 通过结合检索增强生成技术和大语言模型，提出自动化框架从系统描述中构建DML模型并表示为知识图谱。
- 适合谁读
- 适合研究者和工程师阅读，特别是关注系统诊断、知识图谱和大语言模型应用的读者。
- 要解决的问题
- 解决复杂系统中DML模型构建依赖专家解释导致的可扩展性限制问题。
- 关键实验
- 通过实验验证了该框架在多个复杂系统上的有效性和优越性，包括与传统方法的对比。
- 主要贡献
- 扩展了自动化KG-DML构建和评估到更大更复杂的系统，提高系统诊断和理解的效率与准确性。
- 意义与局限
- 意义在于提高复杂系统诊断的自动化水平，但可能受限于大模型的解释能力和数据质量。