一种基于热力预测系统的大型往复压缩机故障诊断方法  

Fault Diagnosis Method for Large Reciprocating Compressor Based on Thermodynamic Prediction System

在线阅读下载全文

作  者:杨毅帆 祝钟青 张戟 陈青松 吴伟烽[1] YANG Yi-fan;ZHU Zhong-qing;ZHANG Ji;CHEN Qing-song;WU Wei-feng(School of Energy and Power Engineering,Xi′an Jiaotong University,Xi′an 710049,China;Sinopec-SK(Wuhan)Petrochemical Co.,Ltd.,Wuhan 430082,China)

机构地区:[1]西安交通大学能源与动力工程学院,陕西西安710049 [2]中韩(武汉)石油化工有限公司,湖北武汉430082

出  处:《压缩机技术》2023年第5期1-6,30,共7页Compressor Technology

摘  要:大型往复压缩机是石油化工、天然气压缩等行业中不可或缺的关键设备,由于其具有运动部件多、工作条件恶劣和易损件多的特点,意外故障的发生率较高。传统的状态监测系统不具备故障诊断功能,通过状态参数设置预警范围,提出报警,仍然依靠工程经验对机组故障进行判断,准确度欠佳。以往复式压缩机的多个状态参数作为故障诊断指标,采用无故障数据训练GA-BP模型,完成了热力预测系统的搭建,得到了安全阈值的范围,在此基础上通过理论分析提出了不同级数压缩机的故障诊断逻辑表,最后结合故障模拟实验验证了本方法的可靠性。采用本文提出的方法,可在现有状态监测系统的基础上实施压缩机故障诊断,无需添加新的硬件。Large reciprocating compressor is the indispensable key equipment in petrochemical,natural gas compression andother industries.Due to its characteristics of many moving parts,poor working conditions and many vulnerableparts,the accident rate is high.Traditional fault diagnosis methods only set the warning range for a singleparameter,and rely on fault data,so the accuracy is poor.In this paper,multiple state parameters of reciprocatingcompressor were taken as fault diagnosis indexes,and the GA-BP model was trained with non-fault data tocomplete the construction of thermal prediction system,by which the range of safety threshold was obtained.Onthis basis,the fault diagnosis logic table of different compressor stages was proposed through theoreticalanalysis.Finally,the reliability of this method was verified by fault simulation experiments.By adopting the methodproposed in this paper,compressor fault diagnosis can be implemented on the basis of existing conditionmonitoring systems without the need for adding new hardware.

关 键 词:往复压缩机 故障诊断 热力预测系统 故障模拟实验 

分 类 号:TH457[机械工程—机械制造及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象