Performance Degradation Analysis of Axial Piston Pumps Based on Self-Organizing Map

Abstract

Axial piston pumps are key components in hydraulic systems, and their real-time performance degradation analysis has received more and more attention in engineering practice. This paper proposes a degradation trajectory method based on self-organizing map (SOM), which is used to analyze the performance degradation of axial piston pumps. Firstly, a selfadaptive Morlet wavelet filter is applied to process the vibration signals of axial piston pumps, and time-domain metrics of filtered signal is used as eigenvectors which can reflect the performance degradation degree. Then data from typical status are used to train SOM, and trajectory on the output layer of SOM is used to represent the real-time performance of degradation degree. Lastly, the performance degradation experiment of axial piston pumps was carried out and the results showed that the proposed method can describe performance degradation process of axial piston pumps effectively.