基于频谱分析的油田注水柱塞泵故障诊断  

Fault diagnosis of oil field water injection plunger pump based on spectrum analysis

作　　者：齐光峰[1] 孙东[1] 郑炜博 邹林[1] 宋长山[1] 刘心颖 李云飞 QI Guangfeng;SUN Dong;ZHEN Weibo;ZOU Lin;SONG Changshan;LIU Xinying;LI Yunfei(Shengli Oilfield Technical Testing Center,Dongying 257000,China;Shengli Oilfield Testing and Evaluation Research Co.,Ltd.,Dongying 257000,China)

机构地区：[1]胜利油田技术检测中心,山东东营257000 [2]胜利油田检测评价研究有限公司,山东东营257000

出　　处：《流体机械》2023年第3期84-90,98,共8页Fluid Machinery

摘　　要：针对传统注水柱塞泵故障诊断高度依赖经验,实时处理能力不足,准确率低的问题,提出了一种柱塞泵频域信号在线诊断方法。采集了柱塞泵正常和16种故障状态下的振动信号,采用傅里叶变换进行分析,通过建立故障模型库,在线获取振动信号并进行故障特征提取,通过多次连续时间与模型库的均方根误差进行故障诊断,同时对故障中传感器贡献率进行排序并使传感器降维减少计算量。研究结果表明:采用该方法对轴向柱塞泵故障进行诊断,准确率从66.7%提高到80%以上,计算量降低为原来的26.7%。For the problems of high dependence on experience,insufficient real-time processing ability and low accuracy of traditional fault diagnosis of water injection plunger pump,an online diagnosis method of frequency domain signal of plunger pump was proposed.The vibration signals of the plunger pump under normal and 16 fault conditions were collected and analyzed by using Fourier transform.By establishing a fault model library,the vibration signals were obtained online and the fault characteristics were extracted.Fault diagnosis was conducted through multiple continuous times and the root mean square error of the model library.At the same time,the sensor contribution rate was ranked to reduce the sensor dimensions and reduce the calculation amount.The results show that the accuracy of the method is improved from 66.7%to more than 80%,and the calculation amount is reduced to 26.7%of the original calculation amount.

关 键 词：柱塞泵 频谱分析 特征提取 故障诊断 

分 类 号：TH00[机械工程]