Cavitation state identification of centrifugal pump based on CEEMD-DRSN

• Published in: Nuclear engineering and technology Vol. 55; no. 4; pp. 1507 - 1517
• Main Authors: Dai, Cui, Hu, Siyuan, Zhang, Yuhang, Chen, Zeyu, Dong, Liang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2023; Elsevier; 한국원자력학회
• Subjects: Centrifugal pump; Complementary Ensemble Empirical Mode Decomposition; Deep Residual Shrinkage Network; Identification of cavitation; 원자력공학; Centrifugal pump; Deep Residual Shrinkage Network; Identification of cavitation; Complementary Ensemble Empirical Mode Decomposition
• ISSN: 1738-5733; 2234-358X
• DOI: 10.1016/j.net.2023.01.009

Centrifugal pumps are a crucial part of nuclear power plants, and their dependable and safe operation is crucial to the security of the entire facility. Cavitation will cause the centrifugal pump to violently vibration with the large number of vacuoles generated, which not only affect the hydraulic performance of the centrifugal pump but also cause structural damage to the impeller, seriously affecting the operational safety of nuclear power plants. A closed cavitation test bench of a centrifugal pump is constructed, and a method for precisely identifying the cavitation state is proposed based on Complementary Ensemble Empirical Mode Decomposition (CEEMD) and Deep Residual Shrinkage Network (DRSN). First, we compared the cavitation sensitivity of pressure fluctuation, vibration, and liquid-borne noise and decomposed the liquid-borne noise by CEEMD to capture cavitation characteristics. The decomposition results are sent into a 12-layer deep residual shrinkage network (DRSN) for cavitation identification training. The results demonstrate that the liquid-borne noise signal is the most cavitation-sensitive signal, and the accuracy of CEEMD-DRSN to identify cavitation at different stages of centrifugal pumps arrives at 94.61%