Diagnosis of multiple independent and coexisting mechanical and hydraulic faults in centrifugal pumps using support vector machine based algorithms
No Thumbnail Available
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Reliable detection and isolation of centrifugal pump (CP) faults is a challenging and important task in the modern industries. Hence, this study proposes, machine learning based multi-fault detection of CPs driven by induction motor. The intelligent fault detection methodology is developed based on the multi-class support vector machine (SVM). The mechanical and hydraulic faults in CPs are mutually dependent and therefore may exist concurrently. Hence, in the present research, an assortment of various flow instabilities like, the suction flow blockages, discharge flow blockages, pseudo re-circulation and dry runs are considered coexisting with mechanical faults, like the impeller cracks and pitted cover plate faults. In addition, the suction and discharge CP blockages are considered with five levels of varying severity. A total of thirty-three faults are considered on the CP. In order to generate relevant fault signatures of CP faults, vibration signals in three orthogonal directions and current signals of all three phases have been acquired for a wide range of operating conditions (i.e., the speed) in time domain using an experimental test rig.
Description
Supervisor: Rajiv Tiwari
Keywords
MECHANICAL ENGINEERING