期刊文献+

基于多源数据的电力作业人员实时行为安全预警 被引量:1

Real-time Behavioral Safety Warning for Power Operators Based on Multi-source Data
下载PDF
导出
摘要 为了在电网建设过程中,减少安全事故的发生及保障电力作业人员安全,提出一种基于三维残差卷积神经网络(R3D)模型的决策融合的行为识别模型。首先,将采集的视频数据集进行数据清洗和增强;然后,用多个角度采集的数据集分别训练对应的R3D模型;进一步地,将多个R3D模型进行决策级融合;最后,通过构建云平台,将电力作业人员可能存在的违规行为或危险行为进行实时预警。实验结果表明,该模型具有识别精度高、参数量少等优点,表明本文提出的行为安全预警方法能够快速准确地做出预警,为电网建设提供安全保障。 In order to reduce the occurrence of safety accidents and ensure the safety of power operators in the process of power grid construction,a behavior recognition model based on decision fusion of three dimensional residual convolutional neural net-work(R3D)models is proposed.First,the captured video dataset is subjected to data cleaning and enhancement;then,the cor-responding R3D models are trained with the datasets collected from multiple angles;further,the multiple R3D models are fused at the decision level;finally,the possible violations or dangerous behaviors of power operators are warned in real-time by build-ing a cloud platform.The experimental results show that the model has the advantages of high recognition accuracy and a low number of parameters,which proves that the behavior safety early warning method proposed in this paper can make early warning quickly and accurately and provide a safety guarantee for power grid construction.
作者 张楠 李温静 刘彩 谢可 马世乾 肖钧浩 邹枫 ZHANG Nan;LI Wen-jing;LIU Cai;XIE Ke;MA Shi-qian;XIAO Jun-hao;ZOU Feng(State Grid Information and Communication Industry Group Co.,Ltd.,Beijing 102211,China;State Grid Tianjin Electric Power Company,Tianjin 300010,China)
出处 《计算机与现代化》 2023年第10期84-91,共8页 Computer and Modernization
基金 国家重点研发计划项目(2020YFB0905900) 国家电网有限公司总部科技项目(SGTJDK00DWJS2100223)。
关键词 电力施工 不安全行为 R3D模型 云平台 预警系统 决策融合 多源数据 power construction unsafe behavior R3D model cloud platform early warning system decision fusion multi-source data
  • 相关文献

参考文献17

二级参考文献125

共引文献190

同被引文献18

引证文献1

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部