Research on Vibration Feature Extraction of Drilling Pump based on Time Domain Joint Statistical Parameters
-
摘要: 开展机械设备振动信号时域统计参数信息挖掘的研究,为检测、诊断设备故障,预测设备的工作状态服务,是一项很有意义的工作。以钻井泵为研究对象,对振动信号进行基元分段处理,统计基元分段后振动信号的时域参数;采用一种新的框架-时域参数联合统计分布,在时域参数联合坐标系下详细考察振动信号时域统计参数的分布特征与量化规律。研究表明,在不同工况下时域参数散点的分布具有很强的规律性与空间区域特征,能够在时域波形信号、参数分布特征和分布区域,以及设备故障之间建立很好的对应关系。Abstract: Research on mining combined time domain statistical parameter information from vibration signal is a very meaningful work for machinery detection, fault diagnosis and state prediction service. In this paper, drilling pump's vibration signal is segmented by BOU(Basic operation unit) processing, then time domain parameters of such vibration signal's segmentation has been calculated. These time domain parameters are investigated carefully with using a new framework-statistical distribution of combined time domain parameters. Studies have shown that the distribution of time domain parameter scatters has strong regularity and spatial feature under different working conditions. A good corresponding relationship between the vibration signal, combined parameter distribution characteristics, regional distribution, and equipment malfunction has been established. It can also provide a geat convenience for the fault detection of drilling pump.
-
Key words:
- vibration /
- time domain analysis /
- feature extraction /
- fault detection
-
[1] 吕苗荣,刘志成,裴峻峰,等.面向故障诊断的钻井泵动力学系统仿真分析[J].系统仿真学报,2014,26(7):1598-1606 Lv M R, Liu Z C, Pei J F, et al. Fault-oriented simulation study of drilling pump dynamic system and its application[J]. Journal of System Simulation, 2014,26(7):1598-1606 (in Chinese) [2] 张键.机械故障诊断技术[M].北京:机械工业出版社,2008:13-20 Zhang J. Mechanical fault diagnosis technology[M]. Beijing: Machinery Industry Press, 2008:13-20 (in Chinese) [3] 李鹤,杨铎,闻邦椿,等.大型压缩机管道系统振动现场测试与故障分析[J].振动、测试与诊断,2007,27(1):1-4 Li H, Yang D, Wen B C, et al. Vibration measurement and fault analysis of large scale compressor-pipeline system[J]. Journal of Vibration Measurement & Diagnosis, 2007,27(1):1-4 (in Chinese) [4] 罗红梅.3NB-1300C钻井泵故障诊断及寿命预测[D].山东青岛:中国石油大学(华东),2007 Luo H M. The fault diagnosis and life prediction of type 3NB-1300C drilling pump[D]. Shandong Qingdao: China University of Petroleum (Huadong), 2007 (in Chinese) [5] 钱济国.机械故障的时域参数诊断法[J].煤矿机械,2006,27(9):192-193 Qian J G. Diagnosis of machinery fault by time-domain parameters[J]. Coal Mine Machinery, 2006,27(9):192-193 (in Chinese) [6] 曹兴.时域参数指标在轴承故障诊断中的应用[J].科技资讯,2010,(24):35 Cao X. Application of time domain parameter index in bearing fault diagnosis[J]. Science & Technology Information, 2010,(24):35 (in Chinese) [7] 吕苗荣,周琳,王丽,等.石油工程准周期性振动信号的新处理方法[J].石油钻探技术,2009,37(5):89-92 Lü M R, Zhou L, Wang L, et al. A new method of quasi-periodic signal processing in petroleum engineering[J]. Petroleum Drilling Techniques, 2009,37(5):89-92 (in Chinese) [8] 王茜,吕苗荣,刘亚军,等.钻井泵振动信号分离与特征提取的研究[J].石油机械,2010,38(3):54-56 Wang Q, Lv M R, Liu Y J, et al. Study on separation and feature extraction of vibration signal of drilling pump[J]. China Petroleum Machinery, 2010,38(3):54-56 (in Chinese) [9] 刘锡军,何继善,周后志.一种提高时域参数识别精度的新方法[J].机械强度,2007,29(6):877-880 Liu X J, He J S, Zhou H Z. Wavelet packet analysis based filtering technique for improving time domain identification of physical parameters[J]. Journal of Mechanical Strength, 2007,29(6):877-880 (in Chinese) [10] Azami H, Sanei S. Automatic signal segmentation based on singular spectrum analysis and imperialist competitive algorithm[C]//Proceedings of the 2012 2nd International Conference on Computer and Knowledge Engineering. Mashhad, Iran: IEEE, 2012:121-126 [11] Elston G R, Bell J M. Pseudospectral time-domain modeling of non-Rayleigh reverberation: synthesis and statistical analysis of a sidescan sonar image of sand ripples[J]. IEEE Journal of Oceanic Engineering, 2004,29(2):317-329 [12] Lv M R, Li M, Chen Z Q, et al. Foundation and application of fluid end's vibration model for drilling reciprocation pump[J]. Advanced Materials Research, 2011,337:575-583 [13] 吕苗荣,陈志强.检测识别钻井泵冲击振动信号的新方法[J].长江大学学报(自然科学版),2010,7(2):58-61 Lv M R, Chen Z Q. A new method for detecting shock vibration signal of drilling pump[J]. Journal of Yangtze University (Natural Science Edition), 2010,7(2):58-61 (in Chinese) [14] Kaewkongka T, Au Y H J, Rakowski R, et al. Continuous wavelet transform and neural network for condition monitoring of rotodynamic machinery[C]//Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Budapest, Hungary: IEEE, 2001:1962-1966
点击查看大图
计量
- 文章访问数: 215
- HTML全文浏览量: 37
- PDF下载量: 10
- 被引次数: 0