基于深度学习的煤矿机电设备状态监测方法
Methods of Electromechanical Equipment Status Monitoring in Coal Mines Based on Deep Learning
齐广平 1张振平 1侯祥芳1
作者信息
- 1. 兖矿能源集团股份有限公司济宁三号煤矿 山东济宁 272169
- 折叠
摘要
为降低煤矿机电设备检测的漏警率,提出了基于深度学习的煤矿机电设备状态监测方法.以分布函数表示样本分布,建立模糊分类集,获取煤矿机电设备状态信息,利用深度学习提取状态监测的特征向量集合,进而拟合设备状态信息,实现分组式监测.实验结果证明,研究的漏警率在0.2%以内,且多数漏警率的数值为 0,可及时、准确地预警异常状态.
Abstract
In order to reduce the false dismissal rate of electromechanical equipment detection in coal mines,a method for electromechanical equipment status monitoring in coal mines based on deep learning is proposed.It ob-tains the information of electromechanical equipment status in coal mines,uses deep learning to extract the feature vector set of electromechanical equipment status monitoring in coal mines,fits the information of equipment status,carries out the group-based monitoring of electromechanical equipment status in coal mines,so as to achieve elec-tromechanical equipment status monitoring in coal mines.Experimental results demonstrate that the false dismissal rate of this method is within 0.2%,and most of them have a value of 0,which can timely and accurately alert abnor-mal states.
关键词
深度学习/煤矿机电设备/状态监测方法/漏警率Key words
Deep learning/Mechanical and electrical equipment in coal mines/Condition monitoring method/False dismissal rate引用本文复制引用
出版年
2024
NETL
NSTL
万方数据