计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (22): 258-264.DOI: 10.3778/j.issn.1002-8331.1708-0021

• 工程与应用 • 上一篇    下一篇

基于大数据的辅机设备振动噪声监测分析平台

刘肃平,谭志平   

  1. 广东科技学院 计算机系,广东 东莞 523083
  • 出版日期:2018-11-15 发布日期:2018-11-13

Vibration and noise monitoring and analysis platform of auxiliary equipment based on big data

LIU Suping, TAN Zhiping   

  1. Department of Computer Science, Guangdong University of Science & Technology, Dongguan, Guangdong 523083, China
  • Online:2018-11-15 Published:2018-11-13

摘要: 分析了对辅机设备进行状态监测和分析研究的必要性,创新地将大数据技术应用于该领域,解决了该研究领域中的关键技术难题,设计并实现了一个辅机设备振动噪声大数据监测分析研究平台。平台采用流式数据实时分析技术和实时批处理技术相结合的方式,采用Storm+Hadoop大数据处理架构。一方面,利用Storm以流计算的方式,对噪音、振动、电流、电压、谐波等海量原始数据进行快速计算和处理,并将处理后的数据传输至实时监测中心;另一方面,采用批计算技术,将海量原始数据存储到基于Hadoop的分布式文件系统中,建立大数据库,再采用基于MapReduce的大数据分析技术对海量数据进行数据挖掘和建模。该平台的研究不仅实现了对辅机设备的运行管理的监测和分析,还可以作为辅机设备振动噪声大数据建模和研究的基础。

关键词: 辅机设备, 大数据技术, 数据挖掘, 振动噪声

Abstract: This paper analyzes the necessity of condition monitoring and analysis of auxiliary equipment, and innovates the application of big data technology in this field. It solves the key technical problems in the research field, designs and realizes the vibration and noise monitoring and analysis platform of auxiliary equipment. The platform combines streaming data real-time analysis technology and real-time batch technology, uses Storm+Hadoop big data processing architecture. On the one hand, Storm is used to calculate and process the mass of raw data such as noise, vibration, current, voltage, harmonics and so on, and the processed data are transmitted to the real-time monitoring center. On the other hand, using batch computing technology, the mass of raw data are stored in Hadoop-based distributed file system, the large databases are established, and then the big data analysis technology based on MapReduce is used for massive data mining and modeling. The research on the platform not only realizes the monitoring and analysis of the operation and management of the auxiliary equipment, but also can be used as the basis for the modeling and research of the large vibration and noise data of auxiliary equipment.

Key words: auxiliary equipment, big data technology, data mining, vibration and noise