A multi-fault diagnostic method based on acceleration signal for a hydraulic axial piston pump

Abstract

In any industrial application the maintenance of systems and components is an important task to guarantee a proper functioning of the plants and maximize their uptime. During the last decades the trend is to move from a time-based maintenance to a condition-based maintenance, where the inspections are performed only when they are effectively required. This paper presents a solution based on vibration signal to identify the health state of a variable displacement axial-piston pump which is one of the main components of a hydraulic system. The proposed methodology follows a data-driven approach including data acquisition and feature extraction. Data acquisition phase was carried out on a laboratory test rig with the pump in healthy and faulty conditions for different operating points, each different faulty condition was achieved by introducing one or more damaged components inside the pump. The vibration signals were acquired and exploited to extract features, the extracted features were subsequently used to train a classification algorithm for faults identification. Results showed the capability of the proposed classification algorithm of identify each faulty condition occurred in the system even in the presence of simultaneous faults. In future works, the diagnostic algorithm will be implemented onboard to validate its effectiveness for the online identification of the typical incipient faults in axial-piston pumps.