全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于关联及多阶拟合的螺杆泵故障诊断
Fault Diagnosis of Screw Pump Based on Correlation and Multi-Order Fitting

DOI: 10.12677/HJDM.2020.102012, PP. 118-128

Keywords: Apriori算法,K-Means聚类,最小二乘法,多阶拟合,故障诊断
Apriori Algorithm
, K-Means, Least Squares, Multi-Order Fitting, Fault Diagnosis

Full-Text   Cite this paper   Add to My Lib

Abstract:

螺杆泵在不同中心频率下的振动加速度偏离正常范围会导致螺杆泵产生异常振动,因此,螺杆泵在出厂前需要设置不同测点检测其振动加速度。为此,本文基于螺杆泵在正常工作下不同测点的振动加速度应用Apriori算法得到螺杆泵不同测点间振动加速度并无显著性差异且呈强正相关的结论;然后应用多阶拟合法建立螺杆泵中心频率和振动加速度的函数关系式,以正常运行参数所对应的系数向量作为模板,计算出待诊断设备的测点运行参数所构造的系数向量与模板之间的系数距离,并应用统计方法设计适当的阈值与之作比较,当且仅当系数距离大于阈值时,将待诊断样本判定为故障。经实际应用,本文方法能够及时发现螺杆泵的异常振动,从而达到故障诊断的目的。
The vibration acceleration of the screw pump at different center frequencies deviates from the normal range, which will cause abnormal vibration of the screw pump. Therefore, the screw pump needs to set different measurement points to detect its vibration acceleration before leaving the factory. For this reason, based on the vibration acceleration of different measurement points of the screw pump under normal operation, this paper applies the Apriori algorithm to obtain the conclu-sion that there is no significant difference in vibration acceleration between different measure-ment points of the screw pump and that there is a strong positive correlation. The multi-order fit-ting method is used to establish the functional relationship between the center frequency and the vibration acceleration of the screw pump. The coefficient vector corresponding to the normal op-erating parameters is used as a template, and calculate the coefficient distance between the coeffi-cient vector constructed by the operating parameters of the measurement points of the equipment to be diagnosed and the template, then apply statistical methods to design an appropriate thresh-old to compare with it, and determine the sample to be diagnosed as a fault if and only if the coeffi-cient distance is bigger than the threshold. After practical application, the method in this paper can find the abnormal vibration of the screw pump in time, so as to achieve the purpose of fault diagno-sis.

References

[1]  贾昀昭. 三螺杆泵性能评估及故障诊断研究[D]: [硕士学位论文]. 哈尔滨: 哈尔滨工业大学, 2017.
[2]  Zaher, A., McArthur, S. and Infield, D. (2009) Online Wind Turbine Fault Detection through Automated SCADA Data Analysis. Wind Energy, 12, 574-593.
https://doi.org/10.1002/we.319
[3]  Zhang, S., Ye, F., Wang, B. and Habetler, T.G. (2019) Semi-Supervised Learning of Bearing Anomaly Detection via Deep Variational Autoencoders. arXiv:1912.01096 [cs. LG].
[4]  Guggilam, S., Zaidi, S.M.A., Chandola, V. and Patra, A.K. (2019) Integrated Clustering and Anomaly Detection (INCAD) for Streaming Data (Revised). In: Lecture Notes in Computer Science, Volume 11539, Springer, Berlin.
https://doi.org/10.1007/978-3-030-22747-0_4
[5]  Han, J., et al. (2006) Data Mining: Concepts and Tech-niques. Margan Kaufmann, San Francisco, CA, 157-164.
[6]  Syakur, M.A., Syakur, M.A., Khotimah, B.K., et al. (2018) Integration K-Means Clustering Method and Elbow Method for Identification of The Best Customer Profile Cluster. IOP Conference Series: Materials Science and Engineering, 336, Article ID: 012017.
https://doi.org/10.1088/1757-899X/336/1/012017
[7]  张良均, 等. Python数据分析与挖掘实战[M]. 北京: 机械工业出版社, 2016: 113-114
[8]  茆诗松. 概率论与数理统计教程[M]. 北京: 高等教育出版社, 2004.
[9]  何春雄, 龙卫江, 朱锋峰. 概率论与数理统计[M]. 北京: 高等教育出版社, 2012: 7.
[10]  李萍, 王茂才, 林琳, 等. 最小二乘多项式拟合算法在管理高消耗医用低值耗材中的应用[J]. 中国卫生经济, 2019, 38(11): 72-75.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133