Asset Details
Do you wish to reserve the book?
Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing
Do you wish to request the book?
Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing
2025
Overview
The vibration signal of early centrifugal pump impeller faults is a nonlinear, non-Gaussian, non-steady-state signal with inherent periodicity. These characteristics complicate the accurate extraction of fault features. This study aims to explore a novel feature extraction method for centrifugal pump impeller fault vibration signals. This method leverages the adaptive characteristics of empirical mode decomposition (EMD) for multi-scale decomposition of the original vibration signal and separation of each intrinsic mode function (IMF). The cyclic bispectrum secondary slicing technique is introduced to perform high-order statistical purification of the noisy IMF, and the modulation frequency characterizing the fault is accurately isolated through optimized slicing parameters. In the analysis of actual centrifugal pump impeller vibration signals, this method effectively enhances the separability and anti-noise robustness of the modulation component. Furthermore, the extracted features are input into SVM, XGBoost, and 1D-CNN classification models, with test accuracies of 85.7%, 92.1%, and 95.7%, respectively, significantly outperforming the single-feature method.
Publisher
Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
