Integrated machine learning and probabilistic degradation approach for vessel electric motor prognostics

Abstract

In the transition towards more sustainable ships, electric motors (EM) are being used in ship propulsion systems to reduce emissions and increase efficiency. The safe operation of ships is crucial, and prognostics and health management applications have emerged as effective solutions to transit towards monitored reliable systems. In this context, this paper presents a probabilistic EM prognostics model integrating data-driven operational models and physics-informed degradation models. Firstly, motor torque and winding temperature are estimated through connected machine learning models, which are based on operational and meteorological data. Operational and meteorological variables drive the EM degradation model and enable the analysis of EM degradation under different operational and environmental conditions. Subsequently, EM remaining useful life (RUL) is predicted within a probabilistic Monte-Carlo approach combining the thermal-stress model along with the associated uncertainties. The methodology is tested on a real case study of the OV Ryvingen vessel, with collected data during voyages along the Norwegian coast. Results confirm the validity of the designed RUL model showing that, under normal operation conditions, the degradation is mild, and the temperature measurement errors are important for RUL estimation.