【目的】随着全球对可再生能源的依赖增加，风力发电作为其中的重要组成部分，正受到越来越多的关注。人工智能技术的快速发展，特别是大语言模型（large language models，LLM）的崛起，为风力发电领域带来了新的机遇和挑战。【方法】本文概述了风力发电的重要性以及人工智能对其发展的推动作用，并详细介绍了LLM的原理和发展现状。综述了LLM在风电领域的典型应用，包括智能问答系统和自动文档生成等文本信息处理应用，通过生成技术报告和诊断报告，提升信息管理效率。【结果】在数据分析与预测方面，LLM 支持风力发电量预测、电力系统运行优化等，显著提高决策的精准性与实时性。在设备运维中，LLM结合图像识别技术，实现风电设备故障的智能检测与诊断，有效降低运维成本。展望了LLM在未来风电系统中的发展前景，重点包括加强数据安全和质量管理，提升模型的可解释性和可靠性，以及优化硬件算力以满足大规模模型的计算需求。【结论】本研究为大语言模型在风力发电领域的应用提供支撑。 

[Objective] As the global reliance on renewable energy increases, wind power generation, as an important part of it, is receiving more and more attention. The rapid development of artificial intelligence technology, especially the rise of large language models (LLM), has brought new opportunities and challenges to the field of wind power generation. [Methods] This paper outlines the importance of wind power generation and the role of artificial intelligence in promoting its development, and introduces the principle and development status of LLM in detail. Typical applications of LLM in the field of wind power are overviewed, including textual information processing applications such as intelligent Q&A system and automatic document generation, which enhance the efficiency of information management by generating technical reports and diagnostic reports. [Results] In data analysis and prediction, LLM supports wind power generation forecasting and power system operation optimisation, which significantly improves the accuracy and real-time decision-making. In equipment operation and maintenance, LLM combines image recognition technology to achieve intelligent detection and diagnosis of wind power equipment faults, effectively reducing operation and maintenance costs. Prospects for the development of LLM in future wind power systems are outlined, with emphasis on strengthening data security and quality management, improving the interpretability and reliability of the model, and optimising the hardware arithmetic to meet the computational demands of large-scale models. [Conclusion] Provide support for the application of large language models in wind power generation.