大型机组润滑安全在线监控与智能预警系统研究  

Research on On-line Monitoring and Intelligent Early Warning System for Lubrication Safety of Large Units

作　　者：张杰 冯伟 宋雷 刘明磊 李桂青[3] ZHANG Jie;FENG Wei;SONG Lei;LIU Minglei;LI Guiqing(Sinopec Zhongyuan Oilfield Puguang Branch,Dazhou Sichuan 635000,China;Guangzhou Mechanical Engineering Research Institute Co.,Ltd.,Guangzhou Guangdong 510700,China;Natural Gas Production and Marketing Plant of Zhongyuan Oilfield Branch,Puyang Henan 457001,China)

机构地区：[1]中国石油化工股份有限公司中原油田普光分公司,四川达州635000 [2]广州机械科学研究院有限公司,广东广州510700 [3]中原油田分公司天然气产销厂,河南濮阳457001

出　　处：《润滑与密封》2022年第4期170-175,共6页Lubrication Engineering

基　　金：中国石油化工股份有限公司科技开发项目(319022-12);国机集团重大科技专项(SINOMAST-ZDZX-2017-01-05);广东省科技计划项目(2020B1212070022);开发区国际科技合作项目(2018GH12)。

摘　　要：石化行业中的大型机组实时润滑数据是设备在线监测、智能诊断和预警的关键信息。为实现石化行业大型机组润滑状态的在线监测、智能诊断和预警,融合传感技术、网络通信、大数据和故障诊断技术,设计基于机电液一体化的油液在线安全监控与智能预警系统;应用多传感器采集的润滑油温度、水分、黏度、介电常数和污染度等实时数据,实现润滑系统的在线监测、智能诊断和预警,并构建了远程分布式在线监测系统;专家诊断系统根据自回归滑动平均模型,结合设备状态和润滑油性能指标退化机制建立润滑油劣化模型,推导润滑油性能退化直至失效前的剩余寿命,实现预测设备润滑磨损状态的功能。实际工程应用表明,该系统的预测结果和离线检测结果趋势一致,表明该系统能准确预警润滑系统潜在的故障风险,为制定设备维护计划提供科学依据。The real-time lubrication data of large units in the petrochemical industry is the key information for online equipment monitoring, intelligent diagnosis and early warning.In order to realize on-line monitoring, intelligent diagnosis and early warning of lubrication status of large units in petrochemical industry, an oil on-line safety monitoring and intelligent early warning system based on the integration of mechatronics and hydraulics was designed by integrating sensor technology, network communication, big data and fault diagnosis technology.Using the real-time data such as lubricating oil temperature, moisture, viscosity, dielectric constant and pollution level collected by multi-sensors, the on-line monitoring, intelligent diagnosis and early warning of the lubrication system were realized, and a distributed remote on-line monitoring system was constructed.The expert diagnosis system establishes a lubricant deterioration model based on the autoregressive moving average model, combined with the equipment status and the deterioration mechanism of lubricant performance indicators, and derives the remaining life before the lubricant performance degradation until failure, and realizes the function of predicting the lubricant wear status of the equipment.The practical engineering application shows that the prediction results of the system are consistent with the off-line detection results, which shows that the system can accurately warn the potential failure risk of the lubrication system and provide a scientific basis for making equipment maintenance plan.

关 键 词：大型机组 专家诊断系统 润滑油劣化模型 磨损状态预测 

分 类 号：TH117.2[机械工程—机械设计及理论] TP212[自动化与计算机技术—检测技术与自动化装置]