海上油气田机泵机械密封泄漏信号检测方法设计  

Leakage Signal Detection Method Designed for Mechanical Seals of Pumps in Offshore Oil and Gas Fields

在线阅读下载全文

作  者:鞠文杰[1] JU Wen-jie(China Offshore Oil Engineering Co.,Ltd.)

机构地区:[1]海洋石油工程股份有限公司

出  处:《化工自动化及仪表》2024年第3期417-421,共5页Control and Instruments in Chemical Industry

摘  要:为避免出现大型海上油气田开采事故,保证机泵机械密封装置正常运行,提出针对海上油气田机泵机械密封的泄漏信号检测方法。利用小波包分解细化海上油气田机泵机械密封振动信号高频部分,运用希尔伯特变换重构信号,归一化处理信号矢量提取机械装置异常信号,使用匹配追踪法去除信号噪声。计算油体流动规律,通过音波评估信号波动范围,以温度与压力为前提,将高斯函数作为分类核函数,采用支持向量机构建泄漏信号检测判断函数,完成机械密封泄漏信号检测。实验结果表明:所提方法信号降噪能力较强,在保证机械密封泄漏检测准确性的同时,检测耗时最短,有效提高了海上油气田开采效率,可带来可观的经济收益。For purpose of avoiding the accident in ffshore large-scale oil gas fields and ensuring normal operation of mechanical seal devices for pumps,a leakage signal detection method for the mechanical seal leak-age of pumps was proposed.In which,having wavelet packet decomposition used to refine high-frequency part of the mechanical seal's vibration signals of the pump in the offshore oil gas field,the Hilbert transform used to reconstruct signals,and the signal vector normalized to extract any abnormal signal of the mechanical device,as well as the matching tracing method adopted to de-noise the signals.In addition,the oil flow law was calculated and through making use of sound wave,the signal fluctuation range was evaluated and both temperature and pressure were taken as the premise,including having the Gaussian function used as the classification kernel function,and the support vector machine used to build leakage signal detection judgment function so as to complete mechanical seal leakage signal detection.The experimental results show that,the proposed method has strong signal noise reduction ability,and the detection time becomes the shortest while ensuring the accuracy of mechanical seal leakage detection,which effectively improves the exploitation efficiency of offshore oil gas fields and can bring about considerable economic benefits.

关 键 词:海上油气田 机泵机械 密封泄漏智能检测 信号提取 支持向量机 

分 类 号:TH17[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