Power grid fault diagnosis is a critical task for ensuring the reliability and stability of electrical infrastructure. Traditional diagnostic systems often struggle with the complexity and variability of power grid data. This paper proposes a novel approach that leverages Large Language Models (LLMs), specifically ChatGPT and GPT-4, combined with advanced prompt engineering to enhance fault diagnosis accuracy and explainability. We designed comprehensive, context-aware prompts to guide the LLMs in interpreting complex data and providing detailed, actionable insights. Our method was evaluated against baseline techniques, including standard prompting, Chain-of-Thought (CoT), and Tree-of-Thought (ToT) methods, using a newly constructed dataset comprising real-time sensor data, historical fault records, and component descriptions. Experimental results demonstrate significant improvements in diagnostic accuracy, explainability quality, response coherence, and contextual understanding, underscoring the effectiveness of our approach. These findings suggest that prompt-engineered LLMs offer a promising solution for robust and reliable power grid fault diagnosis.

翻译：电网故障诊断是确保电力基础设施可靠性与稳定性的关键任务。传统诊断系统常因电网数据的复杂性和多变性而面临挑战。本文提出一种创新方法，利用大语言模型（特别是ChatGPT与GPT-4）结合先进的提示工程技术，以提升故障诊断的准确性与可解释性。我们设计了全面且具有上下文感知能力的提示，引导大语言模型解析复杂数据并提供详细、可操作的洞察。该方法在包含实时传感器数据、历史故障记录及元件描述的新建数据集上，与基线技术（包括标准提示、思维链及思维树方法）进行了对比评估。实验结果表明，该方法在诊断准确率、可解释性质量、响应连贯性及上下文理解方面均有显著提升，印证了本方法的有效性。这些发现表明，经过提示工程优化的大语言模型为构建稳健可靠的电网故障诊断系统提供了可行方案。