面向物理集成迭代建模的领域特定 ReAct:以燃气轮机气路分析的 LLM 智能体为例
Domain-specific ReAct for physics-integrated iterative modeling: A case study of LLM agents for gas path analysis of gas turbines
AI总结:
本文研究可调用工具的 LLM 在燃气轮机气路分析中的应用,提出双智能体工具调用流程,发现接近千亿参数模型经微调和提示设计可满足专业需求。
摘要:
本研究探讨了具有可调用工具的大型语言模型(LLMs)在能源与动力工程领域的应用,重点关注燃气轮机的气路分析。我们开发了一个双智能体工具调用流程,以整合专家知识、预定义工具和 LLM 推理。我们评估了多种 LLM,包括 LLama3、Qwen1.5 和 GPT。较小的模型在工具使用和参数提取方面存在困难,而较大的模型表现出良好的能力。所有模型在面对复杂的多组件问题时都遇到了挑战。基于测试结果,我们推断,参数规模接近 1000 亿的 LLM 通过微调和先进的提示设计可以满足专业场景需求。持续的发展有望提高其准确性和有效性,为更强大的 AI 驱动解决方案铺平道路。
英文摘要:
This study explores the application of large language models (LLMs) with callable tools in energy and power engineering domain, focusing on gas path analysis of gas turbines. We developed a dual-agent tool-calling process to integrate expert knowledge, predefined tools, and LLM reasoning. We evaluated various LLMs, including LLama3, Qwen1.5 and GPT. Smaller models struggled with tool usage and parameter extraction, while larger models demonstrated favorable capabilities. All models faced challenges with complex, multi-component problems. Based on the test results, we infer that LLMs with nearly 100 billion parameters could meet professional scenario requirements with fine-tuning and advanced prompt design. Continued development are likely to enhance their accuracy and effectiveness, paving the way for more robust AI-driven solutions.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。