摘要
机械设备一旦出现故障,若不能及时发现和处理,将直接影响生产效率和质量。基于上述背景,以制浆造纸设备为研究对象,提出一种基于大数据的远程故障监测方法。在制浆造纸设备上布设振动传感器,采集设备工作时的振动大数据,并通过远程通信设备将振动数据传输到远程监测站当中。在远程监测站,对振动数据实施去噪。基于预处理好的振动数据,提取振动数据的时域特征和频域特征,以提取的特征为输入,通过深层神经网络识别故障,实现故障监测。结果表明:与基于温度的监测方法,基于油样分析的监测方法以及基于超声波的监测方法相比,所研究方法应用下,监测结果与实际情况一致,说明所研究的监测方法准确性较高。
Once the mechanical equipment fails,if it cannot be found and handled in time,it will directly affect the production efficiency and quality.Based on the above background,taking pulp and paper equipment as the research object,a remote fault monitoring method based on big data is proposed.A vibration sensor is arranged on the pulp and paper equipment to collect the vibration big data of the equipment,and the vibration data is transmitted to the remote monitoring station through the remote communication equipment.At the remote monitoring station,the vibration data is denoised.Based on the pre-processed vibration data,the time-domain and frequency-domain features of the vibration data are extracted.Taking the extracted features as the input,the fault is identified through deep neural network to realize fault monitoring.The results show that compared with the monitoring methods based on temperature,oil sample analysis and ultrasonic,the monitoring results are consistent with the actual situation,indicating that the monitoring method is more accurate.
作者
滕振宇
TENG Zhenyu(Guangxi Modern Ploytechnic College,Hechi 547000,China)
出处
《造纸科学与技术》
2022年第2期50-54,共5页
Paper Science & Technology
基金
广西高校中青年教师科研基础能力提升项目(2020KY45012)。
关键词
大数据
制浆造纸设备
故障特征
深层神经网络
故障监测
big data
pulp and papermaking equipment
fault characteristics
deep neural network
fault monitoring
