Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing
Xiaopei Liang, Hanxin Chen, Lei Wang, Shaoyi Li, Zhigang Wang, Zhaohui Shi, Xiangying Sheng · 2025
Read Fault feature extraction for centrifugal pump impellers via EMD and cyclic bispectral slicing by Xiaopei Liang, Hanxin Chen, Lei Wang, Shaoyi Li, Zhigang Wang, Zhaohui Shi, Xiangying Sheng (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12753833.txt.
Description
Liang and six co-authors built a way to pull fault signs from pump vibration in twenty twenty-five. Early faults in centrifugal pump impellers give off vibration that is not straight-line and not bell-shaped. The signal is unsteady too, yet it repeats in cycles, so faults hide in noise. Pulling clean fault signs out is the choke point for early warning.
Their chain first runs empirical mode decomposition. It adapts on its own and splits the signal into simpler swinging waves. A cyclic bispectral slice cleans a noisy wave using higher-order stats. It pins down the modulation rate that marks the fault, with slice settings tuned. Fed to three classifiers, the signs scored about eighty-six, ninety-two, and ninety-six percent. That clearly beat single-sign methods. The authors report fault parts split apart more cleanly and hold up better against noise.
Catalog record
| CREATOR | Xiaopei Liang, Hanxin Chen, Lei Wang, Shaoyi Li, Zhigang Wang, Zhaohui Shi, Xiangying Sheng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |