摘要
电力运维安全是备受社会关注的课题。为了避免因运维人员的操作失误而产生严重后果,提出了一种基于长短期记忆网络LSTM(Long Short Term Memory)的、面向电力运维作业的动作识别方法,该方法涵盖了从数据采集、数据处理到分类识别的整个过程,可对人员工作过程中的操作行为进行识别和监督。基于新构建的电力运维作业数据集将方法中用到的深度学习算法LSTM与传统机器学习算法KNN进行仿真对比实验,结果表明,LSTM的表现更佳,在时间窗口为120帧时,LSTM的准确率达到91.32%,比KNN高出约2个百分点。
The security of power operation and maintenance has always been a subject of great social concern. In order to avoid serious consequences caused by the fault of staffs, a motion recognition method for power operation and maintenance jobs based on LSTM(Long Short-Term Memory) is proposed, which covers the whole process from data collection, data processing to motion classification and recognition, then it can recognise and supervise the behavior of staffs who are at work. In addition, a simulation experiment is conducted between the deep learning algorithm LSTM and the traditional machine learning algorithm KNN based on the newly constructed data set of power operation and maintenance jobs. The results show that LSTM achieves better performance than KNN. When the time window is 120 frames, the accuracy based on LSTM reaches 91.32%, which is about 2 percentage points higher than KNN.
作者
刘培贞
贾玉祥
夏时洪
Liu Peizhen;Jia Yuxiang;Xia Shihong(School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China;1nstitute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;Collaborative Innovation Center of IoT Industrialization and Intelligent Production,Minjiang University,Fuzhou 350108,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2019年第12期2837-2844,共8页
Journal of System Simulation
基金
国家自然科学基金(61402419)
闽江学院物联网产业化与智能生产协同创新中心开放基金(IIC1707)
关键词
电力运维安全
LSTM
动作识别方法
仿真实验
power operation and maintenance security
LSTM
motion recognition method
simulation experiment