华电技术 ›› 2019, Vol. 41 ›› Issue (11): 40-45.

• 专题综述 • 上一篇    下一篇

"云+端"大数据驱动的预见性电厂设备维护

  

  1. 1.中国华电集团有限公司山东分公司,济南〓2500142.北方工业大学大规模流数据集成与分析技术北京市重点实验室,北京〓100144

  • 出版日期:2019-11-25 发布日期:2019-12-18

Predictive maintenance of power plant equipment driven by cloud+clientbig data

  1. 1.Shandong Company, China Huadian Corporation Limited, Jinan 250014, China2.Beijing Key Laboratory on Integration and Analysis of Largescale Stream Data, North China University of Technology,Beijing 100144, China)

  • Online:2019-11-25 Published:2019-12-18

摘要:

电厂设备可靠性的维护和保障对发电集团具有重要意义。提出预见性电厂设备维护系统架构,在前端实现设备的数据采集、本地实时处理和计算,在云端实现数据的汇集、存储、批处理及实时处理和分析。分析了该系统的基于HBase的云端数据库设计及写入、海量感知数据的并行化处理以及预见性维护等关键技术。该架构既节约了前端资源,又可以发挥电厂海量感知数据的潜在价值,通过基于海量感知数据的故障预测,实现基于运行实际状态的电厂设备的及时维护,便于决策和维护人员及时制定防范措施、防止和控制可能的故障出现,保障电厂运行可靠和稳定。

关键词:

font-size: 10.5pt, mso-spacerun: 'yes', mso-font-kerning: 1.0000pt">预见性维护, 大数据, -端融合, 故障诊断, 设备维护

Abstract:

Guarantee for the stability of power plant equipment is very important for power generation enterprises. An architecture of a predictive maintenance system for power plant equipment is proposed,which can collect, process and computing data on the client side,and aggregate, store, batch process and realtime process  data on the cloud side. The key technologies of writing, parallel processing of massive sensor data,  and predictive maintenance for the system based on HBase cloud database were analyzed.The  architecture not only saved frontend resources, but also showed the potential value of the massive sensor data. Through predicting fault based on massive sensor data, the  maintenance on the equipment could be done timely according to actual situations, which helped personnel in decisionmaking and making countermeasures in advance.Preventing and controlling the potential fault will ensure the reliability and stability of power plants.

Key words:

font-size: 10.5pt, mso-spacerun: 'yes'