摘要
由于现有设备监控方法的监控传输时延较大、监控灵敏度低,文章研究了基于多源数据融合的工控网络设备运行状态可视化监控方法。通过布置传感器,可以提取工控网络设备的多源特征信息并将其整合为数据集样本,再采用模糊处理的方式消除误差数据,从而获得可靠的设备运行数据。在对运行状态数据进行降维处理后,采用BP神经网络监测设备的运行状态,同时设置状态上限值。在自学习的状态下,对比运行状态数据与上限值以完成在线监控。实验结果表明,应用该方法后,监控时延最高仅为1260ms,且时延变化曲线波动较小;当信息传输距离增加时,该方法的信噪比始终保持在75dB以上,具有较高的监控灵敏度。
Due to the large monitoring transmission delay and low monitoring sensitivity of existing equipment monitoring methods,this article studies a visual monitoring method for the operational status of industrial control network equipment based on multi-source data fusion.By arranging sensors,multi-source feature information of industrial control network equipment can be extracted,integrated into a dataset sample,and then fuzzy processing is used to eliminate error data,thereby obtaining reliable equipment operation data.After reducing the dimensionality of the operating status data,a BP neural network is used to monitor the equipment's operating status and set the upper limit value of the status.In a self-learning state,compare the running state data with the upper limit value to complete online monitoring.The experimental results show that after applying this method,the maximum monitoring delay is only 1260 ms,and the fluctuation of the delay change curve is relatively small.When the distance of information transmission increases,the signal-to-noise ratio of this method always remains above 75 dB,and it has high monitoring sensitivity.
作者
宋俊述
SONG Junshu(Shengli Oilfield Branch of China Petroleum and Chemical Corporation,Dongying,Shandong 257100,China)
出处
《计算机应用文摘》
2024年第13期129-131,134,共4页
Chinese Journal of Computer Application
关键词
多源数据融合
网络设备
运行状态监控
BP神经网络
multi-source data fusion
network equipment
operation status monitoring
BP neural network
