Title: Fault feature extraction method of pump data sample under strong impact and strong noise environment

Authors: Changming Liu; Zhuang Wu; Yuewen Huang; Wei Mao

Addresses: Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China ' Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, China; Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan, Hubei 430081, China ' Changjiang River Scientific Research Institute, Wuhan, Hubei 430019, China ' Hubei Qixing Group, Suizhou, Hubei 441399, China

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%.

Keywords: pump; condition monitoring; fault diagnosis; fault feature extraction; resonance frequency band; maximum correlation kurtosis deconvolution method.

DOI: 10.1504/IJSCOM.2023.131564

International Journal of Service and Computing Oriented Manufacturing, 2023 Vol.4 No.2, pp.104 - 114

Received: 15 Feb 2023
Accepted: 03 Mar 2023
Published online: 19 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article