Health evaluation of axial piston pumps based on density weighted support vector data description

Axial piston pump is the power source of hydraulic systems and its health evaluation is crucial for the condition monitoring of hydraulic systems. Previous studies focused on the fault diagnosis of axial piston pumps but paid little attention to their health evaluation. In addition, labeled faulty samples are often insufficient for training supervised fault diagnosis models in practical applications. Therefore, this work aims to develop a health evaluation model for axial piston pumps, which only requires normal samples for model training. The proposed method uses density weighted support vector data description (SVDD) to determine the normal baseline level of an axial piston pump and then constructs a dimensionless health index to score the pump's health condition. A test bench was built to collect pressure and vibration signals of an actual axial piston pump at different health levels. Results show that the proposed method can effectively evaluate the pump's health condition through the quantifiable health index.