Research on Blind Source Separation of Vibration Signal of Single-channel Converter Transformer Based on CEEMDAN-KPCA
Xiaohui Zhu, Zhuangzhuang Zhang, Dong Wang, Wu Xibo, Dalei Dong, Zhang Li · 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) · 2022
The safe and stable operation of the converter transformer is of great significance to the power system. The vibration signal on the surface of the converter transformer tank can well reflect its internal operating state. However, the vibration signals of the core and winding of the converter transformer are highly correlated, and there is a phenomenon of frequency aliasing. This paper proposes a blind source separation algorithm for the vibration signal of a single-channel converter transformer based on CEEMDAN-KPCA. The reliability of the algorithm is verified by means of simulation signal separation, actual converter transformer measurement signal analysis and unoptimized algorithm separation effect comparison, which is of great significance to converter transformer fault monitoring.