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.

本研究探讨了在能源和电力工程领域中使用大型语言模型（LLMs）与可调用工具进行研究，并重点关注燃气轮机的燃气通道分析。我们开发了双代理工具调用过程，以整合专家知识、预定义工具和 LLM 推理。我们评估了包括 LLama3、Qwen1.5 和 GPT 在内的各种 LLMs。较小的模型在工具使用和参数提取方面存在困难，而较大的模型展示了较好的能力。所有模型都面临着复杂、多组分问题的挑战。基于测试结果，我们推测具有近 1000 亿参数的 LLMs 可以通过精调和先进的提示设计满足专业场景需求。持续的发展可能提高其准确性和效果，为更强大的基于人工智能的解决方案铺平道路。

物理集成迭代建模的领域专用反应：燃气涡轮气道分析中 LLM 代理的案例研究

Domain-specific ReAct for physics-integrated iterative modeling: A case  study of LLM agents for gas path analysis of gas turbines

The main objective of this paper is to investigate the feasibility of
employing Physics-Informed Neural Networks (PINNs) techniques, in particular
KolmogorovArnold Networks (KANs), for facilitating Electromagnetic Interference
(EMI) simulations. It introduces some common EM problem formulations and how
they can be solved using AI-driven solutions instead of lengthy and complex
full-wave numerical simulations. This research may open new horizons for green
EMI simulation workflows with less energy consumption and feasible
computational capacity.

利用物理信息神经网络（PINNs）技术，特别是科尔莫戈洛夫 - 阿诺德网络（KANs），探索在电磁干扰（EMI）仿真中应用的可行性，通过使用人工智能驱动的解决方案来替代冗长复杂的全波数值模拟，为低能耗和可行的计算能力的绿色 EMI 仿真工作流开辟了新的可能性。