⚡ PowerPulse · 电力+LLM 前沿周报
2026-08-08 ~ 2026-08-14 第33周
PowerPulse Weekly · Issue #33

前沿周报

电力系统 × 大语言模型
本周新论文
0篇
arXiv + OpenAlex 严格审查
总库
0篇
累计入库 · 浏览总库 →

本周新论文

arXiv + IEEE/Elsevier · 智能体(GLM)严格审查 1
1
期刊 · Journal of Dynamic Data Developing 电网运维 · 水电厂 2026 · ★★☆ 0.60
针对水电厂工作票安全措施人工编写效率低、易出错的问题,构建"工作内容—安全措施"知识图谱捕获历史关联,并建立安全规程向量数据库;LLM 在检索增强下自动生成符合规程的安全措施,兼顾准确率与合规性。本期 60 篇候选中唯一同时满足"真用 LLM + 解决电力问题"的论文,其余 59 篇已被智能体逐篇排除(详见总库)。
To address the low efficiency and error-prone nature of manually formulating safety measures in hydropower plant work tickets, as well as the difficulty of existing methods in balancing accuracy and compliance, this paper proposes a safety measure generation method integrating a knowledge graph (KG) and large language models (LLMs). A work ticket KG is constructed to capture historical associations between work contents and safety measures, while a safety regulation vector database is established…