Fault Feature Expression Method for Hydroelectric Units Based on Multi-Agent

A multi-agent fault feature extraction method based on hydroelectric units is proposed to solve the problem of significant fault feature extraction of vibration signals in hydroelectric units. A multi-agent method is proposed, and multiple EMD techniques are used to adaptively decompose the original signal into a series of components with different time scales. Then, the IMF spectral features are analyzed and selected based on the mutual information (MI) method in the frequency domain, achieving selective information fusion of multi-source and multi-scale spectral features. The effectiveness of this method is verified through simulation based on actual operating data