Fault feature extraction method of pump data sample under strong impact and strong noise environment. (14th June 2023)

• Record Type: Journal Article
• Authors: Liu, Changming; Wu, Zhuang; Huang, Yuewen; Mao, Wei
• Is Part Of: International journal of service and computing oriented manufacturing. Volume 4:Number 2(2023)
• Page Start: 104
• Page End: 114
• Publication Date: 2023-06-14
• Subjects: pump -- condition monitoring -- fault diagnosis -- fault feature extraction -- resonance frequency band -- maximum correlation kurtosis deconvolution method; Computer integrated manufacturing systems -- Periodicals; Manufacturing industries -- Information technology -- Periodicals; Manufacturing industries -- Computer networks -- Periodicals; Service-oriented architecture (Computer science) -- Periodicals; 670.285
• Languages: English
• ISSNs: 2045-175X

Abstract

The condition monitoring and fault diagnosis of pump stations are essential to ensure the normal operation of pump stations. This work monitors the vibration, swing, pressure pulsation, noise, speed of the pump unit in the steady and transient operation process and diagnoses the equipment state to judge the safety and health of the unit. The fault feature extraction method suitable for the environment of strong impact and strong noise is studied. The frequency band segmentation, accuracy chart to determine the resonance frequency band and the maximum correlation kurtosis deconvolution method are used to enhance the fault feature. Finally, the data measured are sampled and selected, and the kurtosis of the system software is measured the skewness and other indicators are compared with the indicators of handheld analysis and measurement data. The total accuracy rate of data collected by the system software reaches 98.22%.